http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/help-julius-doesnt-recognize-anything-and-give-warning Hello! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/help-julius-doesnt-recognize-anything-and-give-warning Mon, 30 Jan 2012 20:28:49 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-linx-installation Hello all , http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-linx-installation Sat, 14 Jan 2012 05:22:08 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/simple-question please how to make testref.mlf file ? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/simple-question Sat, 07 Jan 2012 07:01:28 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/please-help-me HERest -C config -I phones0.mlf -t 250.0 150.0 1000.0 -S train.scp -H hmm0/macros -H hmm0/hmmdefs -M hmm1 monophones0 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/please-help-me Tue, 03 Jan 2012 06:13:55 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/herest--errors-2 Hello all , http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/herest--errors-2 Tue, 27 Dec 2011 06:36:54 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/herest Hello all , http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/herest Mon, 26 Dec 2011 03:37:35 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-hinit-error I was just using htk to make a model for signal data being converted http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-hinit-error Wed, 21 Dec 2011 05:11:02 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/hcopy-error- Hello all , http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/hcopy-error- Tue, 20 Dec 2011 05:24:59 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/incorporating-high-order-n-grams-for-recognition-with-htk Hi everyone. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/incorporating-high-order-n-grams-for-recognition-with-htk Sun, 20 Nov 2011 09:06:56 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-extract-plp-feature-from-htk Dear all. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-extract-plp-feature-from-htk Tue, 15 Nov 2011 08:30:56 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/about-quantize--dhmm I've to use HTK 3.3 for Speaker Identification in my project. I've used MFCC & HMM function, It's work However, I want to use vector quantize but I don't have any tutorial. I don't know about config file for Hquant or prototype HMM modelling for dicrete HMM. I would like more tutorial. Thank you very much. Tom http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/about-quantize--dhmm Sun, 06 Nov 2011 09:20:36 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-to-sphinx3-acoustic-models-conversion I’ve used htk2s3conv to convert my models from HTK to SPHINX. The http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-to-sphinx3-acoustic-models-conversion Thu, 27 Oct 2011 06:13:49 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-n-gram Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-n-gram Sun, 16 Oct 2011 05:31:08 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/error-cmd_ln.c-line-868-unknown-argument--debug Before post it, i've made a search, and i found similars errors but no good reply. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/error-cmd_ln.c-line-868-unknown-argument--debug Sun, 25 Sep 2011 21:25:37 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/iatros-speech-recognizer Just came across the iATROS speech decoder (GPLv3) - seems like it is similar to Julius in that it needs HTK for acoustic model creation. From their website: http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/iatros-speech-recognizer Thu, 08 Sep 2011 13:53:45 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-matching-every-word Hello, I would like to ask how to restrict Julius to try to match every noise to my dictionary (my.voca)? Each time I say something (even in czech language), Julius simply outputs CALL HELLO or TEST or something. When I actually say the phrase CALL HELLO or CALL OPERA, Julius detects this correctly, with scoring 1.0 1.0 1.0. But the wrong phrase is often 1.0 as well or 1.0 0.8 1.0. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-matching-every-word Fri, 02 Sep 2011 05:03:49 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/query-regarding-usage-of-hbuild hai all, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/query-regarding-usage-of-hbuild Sat, 20 Aug 2011 04:03:56 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/model-probability-in-htk Hi! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/model-probability-in-htk Wed, 03 Aug 2011 09:24:48 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/mllrmap-adaptation Hi, i would combine the MLLR with MAP algorithm for adaptation purpose. I have already seen in HTK book's that it is possible. It must just change the outgoing MLLR mean with the incomming MAP mean. but i can't find how to do it. can any one help me. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/mllrmap-adaptation Mon, 18 Jul 2011 10:25:15 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech-recognition-with-timing-info Hello guys, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech-recognition-with-timing-info Fri, 08 Jul 2011 19:26:05 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/untitled2 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/untitled2 Wed, 22 Jun 2011 11:42:59 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-calculate-roc-by-htk Dear all. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-calculate-roc-by-htk Sun, 19 Jun 2011 04:18:04 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/can-htk-setup-on-windows7 can HTK setup on windows7? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/can-htk-setup-on-windows7 Mon, 13 Jun 2011 19:08:25 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-use-option--w-in-hresults-htk Dear all http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-use-option--w-in-hresults-htk Wed, 08 Jun 2011 00:42:47 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-4.2-and-mic-input After using Julius for what seems like years, I had to install the latest version after a system upgrade and all of a sudden my bluetooth USB devices would not work with Julius. Imagine, you have everything set up as before (including '-input mic') and <please speak> stares you in the face and does not move as you speak into the mike. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-4.2-and-mic-input Thu, 26 May 2011 14:42:51 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/multiple-streams-with-user-defined-features Hi everybody, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/multiple-streams-with-user-defined-features Wed, 25 May 2011 06:26:03 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/untitled4 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/untitled4 Thu, 19 May 2011 03:26:09 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/problem-with-data-base i establish recognition system based in mffcc isolated word(i followed HTK 3.4 tutorial part 3 untill step 11 ). I perform the whole recognition without get error. But when itry to test the recognition system, I only get 18% of recognition rate. I think that i didn't make a good choice of training data then my question is how arranging the data base for recognition and test step. I used a clean Aurora data base(with nohead data). My config file is as follow: TRAGETKIND=MFCCC_0_D_A http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/problem-with-data-base Thu, 12 May 2011 12:26:03 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/untitled3 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/untitled3 Sun, 01 May 2011 00:36:43 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/hcompv-reports-different-results I tried http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/hcompv-reports-different-results Wed, 13 Apr 2011 07:54:51 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-use-hresults-htk Dear all http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-use-hresults-htk Wed, 30 Mar 2011 03:12:00 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/new-to-htk Hello everyone, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/new-to-htk Sat, 26 Mar 2011 07:50:16 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sinhala-speech-recognition-system-for-voice-dialing hi all, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sinhala-speech-recognition-system-for-voice-dialing Tue, 22 Mar 2011 23:20:20 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-training--julius-decoding Hi all, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-training--julius-decoding Tue, 15 Mar 2011 08:23:41 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/is-possible-to-create-speech-recognizer--on-phonetic-based-by-htk Dear all http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/is-possible-to-create-speech-recognizer--on-phonetic-based-by-htk Sat, 05 Mar 2011 05:40:44 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/alignment-with-hvite Hi all! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/alignment-with-hvite Wed, 02 Mar 2011 05:41:19 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/is-it-a-bug-savelabs-in-hcopy.c I have two wave files (16k, 16bit, raw) http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/is-it-a-bug-savelabs-in-hcopy.c Wed, 16 Feb 2011 05:06:18 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/maximum-a-posteriori-estimation-using-htk Can anyone pls tell me how to do MAP using HTK? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/maximum-a-posteriori-estimation-using-htk Thu, 03 Feb 2011 21:42:44 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/mllr-using-htk HERest -C config -S mllr_list -H monophone_work/hmms/proto_1s_10mi -u a -z mllrop.tmf -K xforms mllr1 -J classes -h ’*/%%%%%%_*.mfc’ monophone_work/lists/alpha0.5_list http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/mllr-using-htk Thu, 03 Feb 2011 21:25:09 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/making-two-different-acoustic-models-performance-comparable Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/making-two-different-acoustic-models-performance-comparable Thu, 13 Jan 2011 01:26:55 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-hcopy-error-when-trying-to-convert-.wav-or-.htk-to-.mfcc Hello, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-hcopy-error-when-trying-to-convert-.wav-or-.htk-to-.mfcc Sat, 18 Dec 2010 16:27:02 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-files-from-java-problem Hi! I am making a Java application that uses HTK recognition. I need Java to create feature files in HTK format from certain data that the program handles. So, I need from Java to create new files and add data to them. I have a MatLab function that does this I want: function escribeHTK(file,d,fp,tc) fid = fopen(file,'w','b'); [nf,nv] = size(d); fwrite(fid,nf,'long'); % write frame count fwrite(fid,round(fp*1.E7),'long'); % write frame period (in 100 ns units) nby = nv * 4; fwrite(fid,nby,'short'); % write byte count fwrite(fid,tc,'short'); % write type code fwrite(fid,d.','float'); % write data array fclose(fid); But I need to do that in Java. The function above generates a file whose data format is IEEE754 floating-point big-endian. Then, the function adds a header and append the features, where every variable has its own precission. I have tried to deploy the function above in Java defining every variable correspondingly (short, long...) and after, writing in an output stream the header and features using the method "floatToIntBits" from "Float" class. This did not work because HTk does not recognize the resulting files (as if the file does not have the correct format). I do not want to use MatLab Builder JA so, what can I do? Anybody knows how can I deploy it? Thanks a lot. Regards. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-files-from-java-problem Fri, 17 Dec 2010 17:49:18 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-convert-mfcc-to-mfcc-by-hcopy Dear all. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-convert-mfcc-to-mfcc-by-hcopy Wed, 08 Dec 2010 01:44:52 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-do-the-phoneme-segmentation-with-sphinxsomeone-help-me-i-will-appreciate-it http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-do-the-phoneme-segmentation-with-sphinxsomeone-help-me-i-will-appreciate-it Tue, 07 Dec 2010 07:38:17 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/phoneme-segmentation Is there anyone who can tell me that what tools does HTS use to finish phoneme segmentation ? Sphinx? or any other tools ? I want to know the answer.If someone knows,please tell me !Any hints will be appreciated! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/phoneme-segmentation Tue, 07 Dec 2010 07:35:14 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-use-word-networks-to-increase-correct- Hi all, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-use-word-networks-to-increase-correct- Sun, 28 Nov 2010 11:02:50 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-use-user-parameter-kind-in-hcopy In HCopy, user can define sample kind by config in config file which use in HCopy. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-use-user-parameter-kind-in-hcopy Mon, 15 Nov 2010 00:34:45 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/problem-with-hslab-htk Hi all, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/problem-with-hslab-htk Sat, 13 Nov 2010 10:18:57 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/help-me-2_____________htk thank you very much Kamclean , I used Hcompv and I found the following results http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/help-me-2_____________htk Fri, 05 Nov 2010 17:35:15 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/adding-words-to-.voca-file---is-there-a-limit All, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/adding-words-to-.voca-file---is-there-a-limit Wed, 03 Nov 2010 19:43:42 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/help-me-.............htk hello Mr.Kmacean I will like help me solve my problem. I http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/help-me-.............htk Wed, 03 Nov 2010 10:22:11 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/possible-to-recognizably-use-large-word-as-a-single-phoneme-in-julius Hello, I was following the tutorial as listed at http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/possible-to-recognizably-use-large-word-as-a-single-phoneme-in-julius Sun, 24 Oct 2010 15:55:26 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/engine-for-dictation Hi! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/engine-for-dictation Sun, 17 Oct 2010 18:50:25 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/unable-to-run-hcompv hi.. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/unable-to-run-hcompv Sat, 16 Oct 2010 16:00:27 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/problem-while-installing-julius.. Hello! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/problem-while-installing-julius.. Sat, 16 Oct 2010 06:43:51 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/number-recognition Hello http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/number-recognition Fri, 15 Oct 2010 07:28:51 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/user-defined-features-for-htk Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/user-defined-features-for-htk Thu, 14 Oct 2010 05:57:54 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-using-external-coefficients-vectors-problem Hi! I'm trying to develop a recognition system pitch-based. So, I need to use external coefficients vectors proceeding from a pitch detector that I've programmed. I use a MatLab function to make a .htk file format where I append pitch coefficients to the head. If I use "HList -h -S train.scp", for example, I obtain for one .htk file: http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-using-external-coefficients-vectors-problem Tue, 12 Oct 2010 13:40:13 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/very-new-to-vox--voice-commands- Hi http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/very-new-to-vox--voice-commands- Sun, 10 Oct 2010 04:27:17 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/break-an-mfcc-file-into-time-segments-for-training-script Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/break-an-mfcc-file-into-time-segments-for-training-script Tue, 05 Oct 2010 09:42:09 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/spontaneous-speech Currently, I am using Julius for my speech recognition project. I have been able to use Julius recognizer, but the result was quite good for http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/spontaneous-speech Tue, 05 Oct 2010 08:35:14 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/multiple-recognizer Hi All, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/multiple-recognizer Tue, 05 Oct 2010 08:21:32 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/tiesr-embedded-speech-reocognizer-library-now-under-the-lgpl-v2.1-license From the TIesr website: http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/tiesr-embedded-speech-reocognizer-library-now-under-the-lgpl-v2.1-license Sat, 11 Sep 2010 23:28:16 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/tools how can we create a tool like HCopy in htk if we want to input the coeeficients through rasta or some oter code. pls do reply... http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/tools Tue, 31 Aug 2010 11:00:00 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech-recognition2 How can we input coefficients from outside. I mean i neet to use my own plp code instead of mfcc-your inbuilt code.pls help me out.I have to submit my project. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech-recognition2 Tue, 31 Aug 2010 10:09:08 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/unable-to-install-htk hi... http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/unable-to-install-htk Fri, 20 Aug 2010 23:55:48 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/jsapi-interfaces Hi, I am working in a project that want to make a JSAPI compilant speech reconition engine, if possible Julius engine. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/jsapi-interfaces Tue, 10 Aug 2010 09:05:03 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/audio-segmentation-problem Dear All, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/audio-segmentation-problem Thu, 12 Aug 2010 06:57:28 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/pocketsphinx-building-problem-with-vs2008-for-wmobile Hi, I was trying to build pocketsphinx0.6 for windows Mobile(5 or 6) with VS2008. I chose the 'batch build' all to compile sphinxbase,win32 succeed , but there came some problems when Mobile 5.0: http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/pocketsphinx-building-problem-with-vs2008-for-wmobile Mon, 09 Aug 2010 23:38:21 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how if recout.mlf does not match ref.mlf file or contains more words that we expected? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how Sat, 07 Aug 2010 13:51:15 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/configure-julius-for-lcsr I have downoad Julius 4.1.5 and tried to use it to do dictation. The sample comes with a grammar while I am looking for using ngram language model. I create my lm using the tool mkbingram from a 3gram arpa format. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/configure-julius-for-lcsr Thu, 05 Aug 2010 15:23:08 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/hvite-force-aligment Hello all, I am trying to adapt the HMMs and i am in the phase of realigning the training data. I am running the: -->HVite -A -D -T 1 -l '*' -o SWT -b SENT-END -C http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/hvite-force-aligment Fri, 23 Jul 2010 16:44:50 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/pocketsphinx-on-embedded-platforms Nickolay has written an article on Hack A Day showing you how to add Pocketsphinx to an embedded system (like the Nokia N800) and includes examples in C and Python. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/pocketsphinx-on-embedded-platforms Sun, 11 Jul 2010 10:06:24 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-adaptation hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-adaptation Mon, 05 Jul 2010 08:13:24 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/understanding-languague-model-file I already use Language Model Tookits from CMU http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/understanding-languague-model-file Sun, 04 Jul 2010 23:06:57 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/is-it-possible-to-get-the-timed-output Hi all, I 'm a beginner with julius. By dragon NS and sphinx4 it is possible to return the timed result like this: "test(0,41 0,55) result(1,45 1,98)" the number in brackets is the time stamp of the result word. i think it should also be possible by julius but have not found the right option in the .jconf file. Can anybody help me? Thanks in advance. Ian http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/is-it-possible-to-get-the-timed-output Wed, 16 Jun 2010 17:21:44 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-generate-pdf-sequence-from-realigned-model http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-generate-pdf-sequence-from-realigned-model Mon, 14 Jun 2010 00:50:49 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-site-not-working-properly Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-site-not-working-properly Fri, 04 Jun 2010 09:22:09 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-on-osx-10.6 Sorry to cross-post this, but the English section of the Julius site is pretty quiet. I'm trying to run Julius on OSX 10.6 and the mic is handing data off to libjulius, but it looks like this: http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-on-osx-10.6 Thu, 03 Jun 2010 20:44:32 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-deploy-poketsphinx-on-windows-mobile I have already deploy Pocketsphinx on Ubuntu and Windows 32 , but I can convert from Windows 32 to Win Mobile in Visual Studio because of many errors of libraries . http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-deploy-poketsphinx-on-windows-mobile Tue, 01 Jun 2010 22:50:40 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/hresult-does-that-mean-its-all-right I got this output after I do the "HResult" command: ------------------------ http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/hresult-does-that-mean-its-all-right Mon, 31 May 2010 15:35:47 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/convert-acoustic-model-from-sphinx-into-julius Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/convert-acoustic-model-from-sphinx-into-julius Wed, 26 May 2010 07:29:51 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinxtrain-runall.pl-error hello t friends !!!!!!!!! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinxtrain-runall.pl-error Tue, 18 May 2010 07:06:38 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/help-me-pleasehtk-toolkit Unfortunately, I do not metrizable much English, but I have a big problem on programming using HTK, precisely because the command Hrest after having run this statement, an error appeared, the vFloors is illegible, although that it is the result of the command Hcompv. I would like to help me find: where is the problem. thank you very much. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/help-me-pleasehtk-toolkit Mon, 17 May 2010 06:44:16 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-make-grammar-model-in-htk-for-using-with-hvite I have trained HMMs using HTK. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-make-grammar-model-in-htk-for-using-with-hvite Wed, 12 May 2010 02:02:32 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/output-julius-result-to-text-editor Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/output-julius-result-to-text-editor Thu, 06 May 2010 21:39:42 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/problem-by-julius-using-keithvs-wsj-acoustic-model Hello everyone, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/problem-by-julius-using-keithvs-wsj-acoustic-model Wed, 05 May 2010 11:17:02 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/vocalkit-objective-c-shim-for-speech-recognition Hey Folks, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/vocalkit-objective-c-shim-for-speech-recognition Tue, 04 May 2010 14:49:16 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/modify-julius-code http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/modify-julius-code Sun, 02 May 2010 03:09:46 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/problem-using-hcopy-loading-config http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/problem-using-hcopy-loading-config Tue, 13 Apr 2010 12:25:38 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/adapting-the-hmms Hi everyone, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/adapting-the-hmms Thu, 08 Apr 2010 15:47:31 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/hhed-step-10 Hi i go this error when i tried using the below command http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/hhed-step-10 Sun, 04 Apr 2010 10:34:25 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/regarding-the-sphinx4-an4-regression-tests-in-correct-hypothesis Hi to all, i am veeresh,i ran regression tests for an4 data with http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/regarding-the-sphinx4-an4-regression-tests-in-correct-hypothesis Wed, 31 Mar 2010 04:14:42 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/corrupted-htk-binary-file hi all I'm recognizing visual speech recognition based on htk, i http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/corrupted-htk-binary-file Sat, 27 Mar 2010 10:21:48 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/step-7-help-hcompv Hi everyone. i manage to reach step 7 however i could not proceed because of this error. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/step-7-help-hcompv Sat, 27 Mar 2010 04:04:28 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/creating-a-config-file-for-htk Hi everyone i am new to htk and the unix enviroment. in step 5 for hcopy i am required to create a config file. How do i create this file . Thanks :) http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/creating-a-config-file-for-htk Thu, 25 Mar 2010 10:16:33 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-control-julius-execution the Julius recognizer keeps outputting the words even i am not speaking. how can i control the Julius execution, so that Julius will only output the result when i am speaking? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-control-julius-execution Tue, 09 Mar 2010 10:08:24 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-final-output-result-in-tamil Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-final-output-result-in-tamil Thu, 04 Mar 2010 07:04:11 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/installing-julian All, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/installing-julian Fri, 26 Feb 2010 19:47:30 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-compv-hcopy-mfcc-problem I am new to HTK and am trying to work through a tutorial. I am getting hung up on initializing the HMMs. HCopy seems to work and makes my .mfc file. But HCompV returns errors: http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-compv-hcopy-mfcc-problem Thu, 25 Feb 2010 13:45:17 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/word-confusion-matrix hi all, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/word-confusion-matrix Sun, 21 Feb 2010 23:36:06 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-with-baby-monitors I'm trying to use a baby monitor receiver connected to the input on my sound card on a linux server in the garage and the transmitter in my room upstairs as a 'room mic'. The mic is so sensitive it even picks up the ticking of my wall clock. I have even set the receiver to the lowest volume for julius. I am having some problems as you can imagine, Julius thinks everything is input: http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-with-baby-monitors Fri, 12 Feb 2010 18:22:28 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/can-nists-sclite-be-used-on-windows I'm trying to install NIST's Speech Recognition Scoring Toolkit (SCTK) on Windows 7, but all the make files are set up for linux so I'm getting several errors. Are there versions of this toolkit put together as a MS Visual Studio solution? Or is there another way I can get the makefile working in windows? Any help would be appreciated. Thanks! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/can-nists-sclite-be-used-on-windows Mon, 08 Feb 2010 13:24:09 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/lms-run-on-julius Hi, I have generated arpa format 3-gram LM by CMU SLM Toolkit. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/lms-run-on-julius Thu, 04 Feb 2010 02:53:53 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-wont-ignore-me Even when I say something that is not even remotely defined in its dictionary, it interprets it as something that is and echos back the first thing it has. How do I get it to ignore utterances that are not listed? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-wont-ignore-me Wed, 03 Feb 2010 23:59:39 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-output-to-txt-file-or-c-program hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-output-to-txt-file-or-c-program Thu, 21 Jan 2010 20:29:57 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech-reconition-plugin-for-firefox hi, please someone help me to create a speech recognition plugin to the firefox. im doing this as my research project. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech-reconition-plugin-for-firefox Sun, 17 Jan 2010 23:54:31 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/cmu-sphinx-4-in-the-cloud infinear.com uses an open source stack which includes Asterisk (PSTN interface), the java Sphinx-4 speech decoder, and a http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/cmu-sphinx-4-in-the-cloud Sat, 16 Jan 2010 14:00:56 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/voxforge-acoustic-models-w/-sphinx-4 Hi All, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/voxforge-acoustic-models-w/-sphinx-4 Fri, 08 Jan 2010 08:51:48 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/use-voxforges-sphinx-acoustic-model-with-sphinx4 Hi, I've executed the demos of Sphinx4 successfully. Now I'm trying to make my own application but the acoustic models in the demos have a very small vocabulary. I would like to use the acoustic model of VoxForge, but I don't know how to configure the application to use it. The acoustic models of the Sphinx4 demos are JAR files and the files in that JAR are not the same as the ones in the TAR of de acoustic model from VoxForge. Thank you http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/use-voxforges-sphinx-acoustic-model-with-sphinx4 Mon, 28 Dec 2009 18:58:36 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/reading-input-from-wavfiles-in-sphinx4 Hello. I m trying to read from an wavfile. Basically the wavfile is supposed to contain digits as well as words. I need to extract only digits from this file. First i tried the same program with microphone..it was working fine(with 20% accuracy), but now as i m trying to provide input from wavfile it returns me NULL. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/reading-input-from-wavfiles-in-sphinx4 Mon, 28 Dec 2009 00:50:11 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/use-of-forced-alignment-for-mllr-adaptation-with-htk Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/use-of-forced-alignment-for-mllr-adaptation-with-htk Tue, 22 Dec 2009 08:06:07 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/using-your-graphics-card-for-improved-speech-recognition-and-acoustic-model-training This paper: Implementing Parallel Speech Decoding in HTK Toolkit by Exploiting Manycore GPU and SIMD Technology discusses parallel speech decoding using HTK using the NVIDIA CUDA platform. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/using-your-graphics-card-for-improved-speech-recognition-and-acoustic-model-training Fri, 18 Dec 2009 12:36:45 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-introduce-in-htk-a-new-form-of-parameterization Hello, I am working on speaker recognition. I have implemented a new form of parameterization called HFCC using MATLAB. However, I have to test my system using the toolkit HTK. I have been trying to learn using HTK Book and other tutorials about how to introduce in HTK a new parameterization (no default predefined in HTK) but it has been impossible. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-introduce-in-htk-a-new-form-of-parameterization Mon, 30 Nov 2009 14:32:38 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-take-advantage-of-the-multiple-cpus-in-pc--windows-to-train-the-acoustic-model-in-sphinx Dear all, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-take-advantage-of-the-multiple-cpus-in-pc--windows-to-train-the-acoustic-model-in-sphinx Wed, 25 Nov 2009 17:40:09 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/what-is-the-best-linux-based-speech-recognition-engine-that-is-speaker-independant Hi There, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/what-is-the-best-linux-based-speech-recognition-engine-that-is-speaker-independant Sun, 22 Nov 2009 22:41:00 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/create-phoneme-recogniser-using-voxforge-models-and-htk Is it possible to create a phoneme recognizer with HTK using the VoxForge Acoustic models? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/create-phoneme-recogniser-using-voxforge-models-and-htk Tue, 17 Nov 2009 06:44:09 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/restrcited-language-model-for-speech-improvement Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/restrcited-language-model-for-speech-improvement Mon, 16 Nov 2009 05:15:10 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/phoneme-level-confusion-matrix can we obtain a phoneme level confusion matrix using htk. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/phoneme-level-confusion-matrix Wed, 11 Nov 2009 04:07:20 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/voice-filtering hi, please someone tell me how to find about voice filtering methods and how to use them to speech recognition using HTK or sphinx http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/voice-filtering Sun, 08 Nov 2009 21:38:53 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/recognizing-homophones Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/recognizing-homophones Thu, 22 Oct 2009 03:54:09 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-compile-julius-in-visual-studio http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-compile-julius-in-visual-studio Mon, 19 Oct 2009 00:02:18 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-obtain-mfcc-parameters http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-obtain-mfcc-parameters Sun, 18 Oct 2009 22:47:50 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/asterisk-intergration-with-sphinx hi http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/asterisk-intergration-with-sphinx Sat, 17 Oct 2009 18:01:42 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/jsapi-pocketsphinx-mobile-phone---newbie Hello :-)! I need to create application for mobile phone which communicates with the user (it requires speech recognition) and creates some data based on this talk. Then it should send this file to server. I've just read jsapi guide and I thought about using this jsapi but there are some problems (my language is not so popular so it may be unsupported, I don't see any info about creating acoustic model for new languages and I don't see any way to specify order of sounds in the words based on informations from this jsapi guide). I've got two ideas how to do it: 1) MIDlet which involves jsapi and then sends data with the use of httpconnection POST to TomCat server (I have already developed some code) 2) mobile phone with Symbian which involves PocketSphinx (I guess maybe I should abandon that first idea and learn from beginning how to create programs for Symbian) In general I've spent much time on reading about speech recognition (you can simply look for my topics in the internet by typing "johnyjj2 speech" on google to see results of my research) and I still don't have anything and it pisses me off. Can you tell me which way (1) or (2) would be better, please? And suggest any materials connected with (2) if this one would be better choice, please (preferably code of applications which use it, I didn't see in pocketsphinx-0.5.1.zip any examples which would help me in my project)? I would be very grateful for any help from you :-) Greetings :-)! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/jsapi-pocketsphinx-mobile-phone---newbie Tue, 13 Oct 2009 04:30:58 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/juliuss-behavior-understanding Hello, My requirement is to identify selected 20 words from any speaker and ignore all other speech data. I recorded those 20 words from different (currently 10 speakers). I have single wav file per speaker and each wav file contains those 20 words, which I need to identify. e.g. Speaker1.wav  WORD1 WORD2 WORD3 … WORD20 Speaker2.wav WORD1 WORD2 WORD3 … WORD20 . . . Speaker10.wav -> WORD1 WORD2 WORD3 … WORD20 I trained Julius using these files. But Julius’s accuracy was not good. Here accuracy means accuracy to identify trained 20 words from different speakers. So I divided recorded wav file in such a way that each wav file contains single word only. e.g. Speaker1_1.wav  WORD1 Speaker1_2.wav  WORD2 Speaker1_3.wav  WORD3 . . Speaker1_20.wav  WORD20 Speaker2_1.wav  WORD1 Speaker2_2.wav  WORD2 . . . Speaker10_20.wav  WORD20 I trained Julius using these new files. Julius’s accuracy is improved in this case. Again accuracy means accuracy to identify trained 20 words from different speakers. If the spoken word is not present in trained 20 words, Julius still returns one of the word from 20 words with some cmscore (confidence score) value. I noticed that this score value is not accurate to reject unknown words. To handle such scenario, I have decided to add more words in my dictionary file (currently my dictionary file contains only 20 words). I have downloaded required training data from voxforge site (approx. 2000 wav files of different speakers) and trained Julius with them and also with my current data (which contains training for my 20 words). But when I ran Julius using new training model, I got following warning message regarding hypothesis stack. WARNING: 00 _default: hypothesis stack exhausted, terminate search now I searched Julius forum for this problem. Please refer following Julius forum for more information regarding this problem. http://julius.sourceforge.jp/forum/viewtopic.php?f=6&t=42 I tried all those things but still I am getting this warning message. Again I trained Julius again with those downloaded data (this time only 600 wav files) and my current data (which contains training for my 20 words). Julius started without above warning message, but with the worst accuracy. Also I noticed one more thing. When my training dictionary has multiple pronunciations for same WORD, accuracy of the Julius decreases. Can anyone help me, what should I do next? Anyone passed through such scenario? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/juliuss-behavior-understanding Mon, 12 Oct 2009 23:39:38 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/asterisk-intergration-with-asterisk hi i am trying to intergrate asterisk with sphinx on ubuntu 8.04, i have been following http://scribblej.com/svn/ tutorial my problem the tutorial does not how to create the grammar files,it has everything but i don't know how to put everything together,like how to get the lm and hmm is not described though it is mentioned that it is required. can somebody help me on how to put things togethere and get the server working? so far i have downloaded the server.tar.tgz but when i run it i get lots of errors,i don't even know where to get the files it is requesting,this is some of the errors,your help will be greately appreciated astsphinx.c:10:20: error: cmd_ln.h: No such file or directory astsphinx.c:11:26: error: pocketsphinx.h: No such file or directory astsphinx.c:12:25: error: ngram_model.h: No such file or directory astsphinx.c: In function ‘testserver’: astsphinx.c:39: error: ‘cmd_ln_t’ undeclared (first use in this function) astsphinx.c:39: error: (Each undeclared identifier is reported only once astsphinx.c:39: error: for each function it appears in.) http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/asterisk-intergration-with-asterisk Sun, 27 Sep 2009 19:47:52 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-much-training-required-for-julius Hello, I want to train julius for 20 words only. 1) How much training is sufficient, if I want to generate speaker independent model? 2) How can I train julius for noisy environment? 3) How to specify filler words in grammer file? 4) Is there any way to reject unknown words? 5) How can I generate N-gram file? 6) How can I use -mapunk option available in release 4.1.2 of julius? 7) Which julius options help me to improve accuracy? 8) How can I generate GMM definition file required for -gmm option? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-much-training-required-for-julius Mon, 21 Sep 2009 01:29:06 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/pocketsphinx_continuos-not-found hi http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/pocketsphinx_continuos-not-found Sun, 20 Sep 2009 15:04:57 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech-enabled-games-using-mits--wami-toolkit Here is a proof of concept app (http://www.voxforge.org/testApp.html) using the WAMI toolkit to create a game to collect speech. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech-enabled-games-using-mits--wami-toolkit Wed, 16 Sep 2009 22:49:44 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/ignore-words-in-speech Hello, I have installed julius 4.1.2 and trained it with required words. Julius is working properly if trained words are given in input. But it is given false result, when different words are given in input. For e.g. I have trained julius with ONE, TWO, THREE. Julius is working fine if I gave any of these words in any sequence. But when I gave FOUR , which is not present in training database, still it detects them as ONE . How can I ignore other words in speech? As per manual "GMM will be used for input rejection". How can I generate required "-gmm hmmdefs_file" file for it. Is there any otherway to ignore input speech? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/ignore-words-in-speech Wed, 16 Sep 2009 05:33:09 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk/julius-with-language-model-quickstart Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk/julius-with-language-model-quickstart Mon, 14 Sep 2009 05:02:57 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/running-sphinx3-on-windows Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/running-sphinx3-on-windows Thu, 10 Sep 2009 04:23:24 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/which-one-sphinx-isip-julius-htk I'm thinking of trying VoxForge on this dinosaur desktop http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/which-one-sphinx-isip-julius-htk Tue, 08 Sep 2009 13:44:46 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk---processfile-analysis Hi. Has anyone analyzed the internal working of ProcessFile() function in the HVite code (HTK)? Can you please give brief me about it? Or how you went on with analyzing it? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk---processfile-analysis Thu, 03 Sep 2009 04:12:01 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/.mfc-files Hi.......My question is that i extract some part of .mfc files which i change to a simple .txt file. In short lets say that a wave file has 300 frames and i want to get the one from 100 to 120. so i use cepview and then append it to a .txt file. Now i want this .txt file to be converted into the binary format which can be recognized by Sphinx......Any clue from any one on how to do it. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/.mfc-files Thu, 27 Aug 2009 01:54:42 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/poor-accuracy-with-pocketsphinx Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/poor-accuracy-with-pocketsphinx Wed, 19 Aug 2009 00:50:00 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speaker-adaptation-with-htk-.. Hi everybody, I would like to evaluate speaker adaptation on a digits corpus in German. I have trained using HTK, a monophone system on another german corpus which work quite well in term of accuracy on the digits corpus. But I have problems in making the adaptation process (MLLR) to run on this corpus ... So I have multiple questions: - In the doc and examples, most of the examples for speaker adaptation given are with triphones models ... I suppose that adapting context independent monophone acoustic models is also possible ? - If yes, here are the steps that have been followed (following htk doc): http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speaker-adaptation-with-htk-.. Thu, 13 Aug 2009 02:38:12 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3_livedecode Hi I want to do livedecodeing. when I run sphnx3_livedecode I got this. Usage: livedecode config_file In sphinx4 we have demo programs for testing. I tried to run sphinx3_livedecode, but it asks for input 'config_file'. How can I construct it or find it ? Could anyone give me a demo example to test Sphinx3 Thank u http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3_livedecode Sat, 01 Aug 2009 23:17:40 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-4-in-action---transcribing-bruce-sterlings-reboot-11-closing-talk The Laurian Gridinoc's blog has an interesting entry documenting how the author tried to use the Replay tool to transcribe a presentation by Bruce Sterling. Replay uses the sphinx 4 open source speech recognition engine for speech-to-text. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-4-in-action---transcribing-bruce-sterlings-reboot-11-closing-talk Wed, 29 Jul 2009 09:51:29 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-create-xxx_test.fileids-and-xxx_test.transcription http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-create-xxx_test.fileids-and-xxx_test.transcription Mon, 27 Jul 2009 01:01:26 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/cannot-access-sample.dict Hello all, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/cannot-access-sample.dict Sat, 25 Jul 2009 20:30:54 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-config-for-short-utterances-like-single-letters What jconf parameters would be best for recognizing short utterances like single letters? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-config-for-short-utterances-like-single-letters Thu, 23 Jul 2009 14:38:58 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/new-to-htk-and-need-help2 Hello, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/new-to-htk-and-need-help2 Wed, 22 Jul 2009 09:48:30 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/new-to-htk-and-need-help Hello, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/new-to-htk-and-need-help Wed, 22 Jul 2009 09:48:20 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/improve-the-accuracy-of-the-htk-recognition Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/improve-the-accuracy-of-the-htk-recognition Mon, 13 Jul 2009 00:20:09 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/unsupervised-speaker-adaptation Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/unsupervised-speaker-adaptation Mon, 06 Jul 2009 07:47:41 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/inaccurate-recognition-with-sphinx-using-voxforge-en I loaded voxforge-en 1.1 and 1.2 acoustic models into Sphinx, but I'm not getting very accurate results. It is better than the an4 tutorial am, but still not great. How can I improve accuracy? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/inaccurate-recognition-with-sphinx-using-voxforge-en Sun, 05 Jul 2009 20:06:23 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/adapt-model http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/adapt-model Thu, 02 Jul 2009 03:14:51 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/limiting-the-match-threshold-with-julius Hey, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/limiting-the-match-threshold-with-julius Fri, 19 Jun 2009 15:36:10 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx_fe I following the Adapting the default acoustic model documentation. so I record 20 wav files with my voice and I also create transcription file, listoffiles. an4.txt and an4.dic taken from an4 database. my question is how to generate mfcs feature files. I think it is same as preliminary training by using SphinxTrain and perl scripts. OR some other else plz tell me. And sphinx_fe tool also not understand. sphinx_fe tool is generate a set of acoustic model feature file for raw audio recordings ,but where this tool run.clear directory stucture is not their. I follows directory structure as follows adapt/an4.txt /an4.dic /an4_train.fileids /an4_train.transcription /an4_01.wav . . . /an4_20.wav /bw /mllr_solve bw and mllr_solve files taken from SphinxTrain/bin/release. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx_fe Thu, 18 Jun 2009 22:00:03 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-4.1.2 Hey, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-4.1.2 Thu, 18 Jun 2009 06:47:11 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3 Tue, 16 Jun 2009 08:07:45 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/segmentation-fault-with-sphinx3-init_gau Hello, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/segmentation-fault-with-sphinx3-init_gau Fri, 12 Jun 2009 06:29:24 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/errors-in-traing-sphinx3 hai when iam traing the http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/errors-in-traing-sphinx3 Tue, 09 Jun 2009 05:44:10 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech1 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech1 Mon, 08 Jun 2009 20:44:26 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/converting-.wav-to-.mfc-using-hcopy-in-htk hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/converting-.wav-to-.mfc-using-hcopy-in-htk Mon, 08 Jun 2009 07:49:10 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech Sun, 07 Jun 2009 00:32:48 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3.x-hypotheses Can I get Top N=5 hypotheses decoded with sphinx3.x? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3.x-hypotheses Wed, 03 Jun 2009 20:53:08 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/real-time-recognition-using-sphinx3.x Please share your valuable knowledge regarding live mode recognition using sphinx3.x . myself trying to use livepretend option but not getting success. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/real-time-recognition-using-sphinx3.x Wed, 03 Jun 2009 08:16:39 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-4-environment-setup I recently tried to integrate sphinx into eclipse but there are still errors and warnings. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-4-environment-setup Tue, 02 Jun 2009 21:22:44 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/lm3g2dmp http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/lm3g2dmp Sat, 30 May 2009 01:46:20 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech-recognition http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech-recognition Sat, 30 May 2009 00:06:16 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius---time-taken-to-recognise-commands Hello. I have installed Julius on my Ubuntu Jaunty system from the repos, and followed some information found here and in the examples readme, but I'm having some problems. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius---time-taken-to-recognise-commands Tue, 26 May 2009 09:16:44 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speaker-adaptation http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speaker-adaptation Mon, 25 May 2009 06:49:45 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-decoder-problem when I use julius to decoder, occur to error! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-decoder-problem Fri, 22 May 2009 09:01:24 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/regarding-recognition Hi Ken, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/regarding-recognition Tue, 12 May 2009 00:58:38 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-create-databases-for-speech-recognition http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-create-databases-for-speech-recognition Fri, 08 May 2009 04:38:28 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/for-noisy-input i Ken, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/for-noisy-input Mon, 27 Apr 2009 05:11:48 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/my-solution-for-the-error-2226 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/my-solution-for-the-error-2226 Tue, 21 Apr 2009 12:21:01 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/reading-rawfile-as-switch Hi Kmaclean, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/reading-rawfile-as-switch Tue, 07 Apr 2009 06:37:49 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/step-6-error-5021 hi there, can anyone help me with this problem. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/step-6-error-5021 Mon, 06 Apr 2009 08:35:18 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/warning-strip-sample-0-1217-is-invalid-stripped Hi Kmaclean, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/warning-strip-sample-0-1217-is-invalid-stripped Wed, 25 Mar 2009 07:47:54 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-3.4.1-is-released Amazing news really. The new features include: http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-3.4.1-is-released Tue, 17 Mar 2009 16:35:36 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/strange-overall-likelihood-per-frame-with-sphinxtrain Hi, I am using SphinxTrain and sphinx3. I followed the Robust Group tutorial for the databases rm1 and an4 an it worked fine for both of them. Now I am trying to train and test another database (Aurora2 - containing only digits). I've got feature vectors computed from HTK and I converted them to the format used by Sphinx (13 components per vector in big-endian and a 4-byte int header containing the number of datapoints). I am quite sure, that this conversion is working properly, because I get reasonable output with cepview. As it is a small vocabulary, I don't use phonems but simply the hole word in the dictionary: EIGHT EIGHT FIVE FIVE FOUR FOUR NINE NINE OH OH ONE ONE SEVEN SEVEN SIX SIX THREE THREE TWO TWO ZERO ZERO The training with SphinxTrain is working, but it produces strange results. After the last iteration in MODULE: 50 Training Context dependent models there is a Current Overall Likelihood Per Frame = -116.562247763689. Is this a reasonable value? Compared to the Likelihoods from "an1", it looks quite strange to me. In addition to that I don't get any decoding results with sphinx3 (probably because the training already failed?), i.e. for every test file only "sil" is recognized. Does anybody have any hint to me? Thank you, Brina http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/strange-overall-likelihood-per-frame-with-sphinxtrain Tue, 03 Mar 2009 03:51:20 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinxtrain-error-with-slave.pl Hi all, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinxtrain-error-with-slave.pl Sat, 28 Feb 2009 22:30:01 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/running-pocketsphinx-from-java Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/running-pocketsphinx-from-java Mon, 16 Feb 2009 12:53:51 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-4-new-release After 4½ years, there's a new release of Sphinx-4 available (1.0-beta2). http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-4-new-release Sun, 08 Feb 2009 11:23:37 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-isolated-word Hi All, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-isolated-word Fri, 06 Feb 2009 23:01:45 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/bad-accuracy-in-sphinx-3-preliminary-decode http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/bad-accuracy-in-sphinx-3-preliminary-decode Fri, 06 Feb 2009 12:56:11 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3-problem Hi, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3-problem Wed, 04 Feb 2009 22:49:23 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech-recoginion-sphinx3 Hi http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/speech-recoginion-sphinx3 Thu, 22 Jan 2009 03:06:12 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3-accuracy I'm using sphinx3 [latest from svn] on windows vista using visual studio 2008. Everything is compiling and working correctly, however I'm getting TERRIBLE accuracy. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3-accuracy Mon, 19 Jan 2009 18:01:32 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/if-the-score-of-recognation-can-be-negatif hello http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/if-the-score-of-recognation-can-be-negatif Wed, 14 Jan 2009 13:50:21 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/voxforge-tutorial-step-6---herest---cannot-open-source-file-dx Hi Ken, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/voxforge-tutorial-step-6---herest---cannot-open-source-file-dx Wed, 14 Jan 2009 10:05:55 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/untitled Hi kmaclean, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/untitled Tue, 13 Jan 2009 00:07:30 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/final-state-not-reached I'm facing a problem when i'm running baum welch algorithm in sphinx train as final state not reached. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/final-state-not-reached Mon, 12 Jan 2009 04:05:50 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/an-overview---help Hi All, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/an-overview---help Fri, 02 Jan 2009 03:00:17 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3-with-windows I had trained my corpus with SphinxTrain in windows!But when I decode it I got a error:"sphinx_deocde.exe:Cannot found sphinxbase.dll,...." http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3-with-windows Tue, 16 Dec 2008 03:16:01 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/comparing-sphinx-ibms-via-voice-philips-speech-sdk-microsoft-win-xp-dragon-naturally-speaking Here is a study by the National Research Council of Canada entitled: http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/comparing-sphinx-ibms-via-voice-philips-speech-sdk-microsoft-win-xp-dragon-naturally-speaking Wed, 10 Dec 2008 13:33:21 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3-features Can I use PLP features with sphinx3? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3-features Tue, 09 Dec 2008 01:08:43 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-open-source-voice-recognition-compare-to-google-one Is it possible to get simular results with VoxForge/Julius? Or possibly CMU Sphinx? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-open-source-voice-recognition-compare-to-google-one Mon, 08 Dec 2008 12:14:59 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/is-it-possible-to-have-the-probability-of-a-model-compared-to-all-the-other-models-withe-the-tool-hvite- Is it possible to have the probability of a model compared to all the other models withe the tool "Hvite" For example http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/is-it-possible-to-have-the-probability-of-a-model-compared-to-all-the-other-models-withe-the-tool-hvite- Sat, 08 Nov 2008 13:37:24 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-idea Now ,I want to modify the "-ceplen 13" to any number what I want,do you think the Sphinx will complete? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-idea Tue, 04 Nov 2008 06:21:34 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/evaluation-of-julius-output-hresults Hi !! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/evaluation-of-julius-output-hresults Mon, 20 Oct 2008 16:18:28 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-and-julius--different-recognition-score Hi all, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-and-julius--different-recognition-score Fri, 19 Sep 2008 05:34:16 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/problem-with-hcompv---htk Hello everyone, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/problem-with-hcompv---htk Sat, 13 Sep 2008 16:58:44 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/hvite-silence-detection Hi Under windows XP i have successfully tested the HVIte(live) to automatically detect the silence after the word spoken word, and then end the recording session prininting the detected word to the command prompt. This is easy achieved by specifiying the following commands in the config file USESILDET = T MEASURESIL = F OUTSILWARN = T SILENERGY = 55.0 However when i try the same in linux it doens't work. The HVite just stays at READT[] > and nothin happens! does anyone no a way to correct this problem? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/hvite-silence-detection Wed, 27 Aug 2008 01:48:41 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-train-wav-files-in-sphinx4 hi all, I want the procedure for training the wav files so that it will increse the recognition accuracy or any other way to increse the accuracy thanks... http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-to-train-wav-files-in-sphinx4 Thu, 21 Aug 2008 06:56:22 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/cmuslm-_arpa I made a.arpa with CMUSLM2.0,and context cues with <s></s> Why <s></s> are predicted in my a.arpa file ,If there is not <s></s> in my a.vocab file then the result will be b.vocab,what i should do ? This is my file: a.text <s> OPEN BROWSER </s> <s> NEW E-MAIL </s> <s> FORWARD </s> <s> BACKWARD </s> <s> NEXT WINDOW </s> <s> LAST WINDOW </s> <s> OPEN MUSIC PLAYER </s> a.vocab ## Vocab generated by v2 of the CMU-Cambridge Statistcal ## Language Modeling toolkit. ## ## Includes 13 words ## </s> <s> BACKWARD BROWSER E-MAIL FORWARD LAST MUSIC NEW NEXT OPEN PLAYER WINDOW a. arpa ############################################################################# ## Copyright (c) 1996, Carnegie Mellon University, Cambridge University, ## Ronald Rosenfeld and Philip Clarkson ## Version 3, Copyright (c) 2006, Carnegie Mellon University ## Contributors includes Wen Xu, Ananlada Chotimongkol, ## David Huggins-Daines, Arthur Chan and Alan Black ############################################################################# ============================================================================= =============== This file was produced by the CMU-Cambridge =============== =============== Statistical Language Modeling Toolkit =============== ============================================================================= This is a 3-gram language model, based on a vocabulary of 13 words, which begins "</s>", "<s>", "BACKWARD"... This is an OPEN-vocabulary model (type 1) (OOVs were mapped to UNK, which is treated as any other vocabulary word) Witten Bell discounting was applied. This file is in the ARPA-standard format introduced by Doug Paul. p(wd3|wd1,wd2)= if(trigram exists) p_3(wd1,wd2,wd3) else if(bigram w1,w2 exists) bo_wt_2(w1,w2)*p(wd3|wd2) else p(wd3|w2) p(wd2|wd1)= if(bigram exists) p_2(wd1,wd2) else bo_wt_1(wd1)*p_1(wd2) All probs and back-off weights (bo_wt) are given in log10 form. Data formats: Beginning of data mark: \data\ ngram 1=nr # number of 1-grams ngram 2=nr # number of 2-grams ngram 3=nr # number of 3-grams \1-grams: p_1 wd_1 bo_wt_1 \2-grams: p_2 wd_1 wd_2 bo_wt_2 \3-grams: p_3 wd_1 wd_2 wd_3 end of data mark: \end\ \data\ ngram 1=14 ngram 2=18 ngram 3=24 \1-grams: -1.1461 <UNK> 0.0000 -98.8037 </s> -0.8451 -98.8037 <s> -0.0348 -1.1461 BACKWARD -0.3010 -1.1461 BROWSER -0.3010 -1.1461 E-MAIL -0.3010 -1.1461 FORWARD -0.3010 -1.1461 LAST -0.2341 -1.1461 MUSIC -0.2688 -1.1461 NEW -0.2688 -1.1461 NEXT -0.2341 -0.8451 OPEN -0.2341 -1.1461 PLAYER 0.0000 -0.8451 WINDOW -0.4771 \2-grams: -0.0669 </s> <s> 0.0348 -1.1139 <s> BACKWARD 0.0000 -1.1139 <s> FORWARD 0.0000 -1.1139 <s> LAST 0.0000 -1.1139 <s> NEW 0.0000 -1.1139 <s> NEXT 0.0000 -0.8129 <s> OPEN 0.0000 -0.3010 BACKWARD </s> 0.5441 -0.3010 BROWSER </s> 0.5441 -0.3010 E-MAIL </s> 0.5441 -0.3010 FORWARD </s> 0.5441 -0.3010 LAST WINDOW 0.1761 -0.3010 MUSIC PLAYER -0.3010 -0.3010 NEW E-MAIL 0.0000 -0.3010 NEXT WINDOW 0.1761 -0.6021 OPEN BROWSER 0.0000 -0.6021 OPEN MUSIC 0.0000 -0.1761 WINDOW </s> 0.3680 \3-grams: -1.0792 </s> <s> BACKWARD -1.0792 </s> <s> FORWARD -1.0792 </s> <s> LAST -1.0792 </s> <s> NEW -1.0792 </s> <s> NEXT -1.0792 </s> <s> OPEN -0.3010 <s> BACKWARD </s> -0.3010 <s> FORWARD </s> -0.3010 <s> LAST WINDOW -0.3010 <s> NEW E-MAIL -0.3010 <s> NEXT WINDOW -0.6021 <s> OPEN BROWSER -0.6021 <s> OPEN MUSIC -0.3010 BACKWARD </s> <s> -0.3010 BROWSER </s> <s> -0.3010 E-MAIL </s> <s> -0.3010 FORWARD </s> <s> -0.3010 LAST WINDOW </s> -0.3010 MUSIC PLAYER </s> -0.3010 NEW E-MAIL </s> -0.3010 NEXT WINDOW </s> -0.3010 OPEN BROWSER </s> -0.3010 OPEN MUSIC PLAYER -0.1761 WINDOW </s> <s> \end\ b.arpa ... \1-grams: -0.2840 <UNK> 0.2382 -1.4491 BACKWARD 0.3188 -1.4491 BROWSER 0.3188 -1.4491 E-MAIL 0.3188 -1.4491 FORWARD 0.3188 -1.4491 LAST 0.0362 -1.4491 MUSIC 0.0157 -1.4491 NEW 0.0157 -1.4491 NEXT 0.0362 -1.0969 OPEN 0.0320 -1.4491 PLAYER 0.0000 -1.0969 WINDOW -0.2833 \2-grams: -0.3358 <UNK> <UNK> 0.0726 -99.9990 <UNK> BACKWARD 0.0000 -99.9990 <UNK> FORWARD 0.0000 -99.9990 <UNK> LAST 0.0000 -99.9990 <UNK> NEW 0.0000 -99.9990 <UNK> NEXT 0.0000 -0.8129 <UNK> OPEN 0.0000 -99.9990 BACKWARD <UNK> 0.2688 -99.9990 BROWSER <UNK> 0.2688 -99.9990 E-MAIL <UNK> 0.2688 -99.9990 FORWARD <UNK> 0.2688 -99.9990 LAST WINDOW 0.6021 -99.9990 MUSIC PLAYER 0.3188 -99.9990 NEW E-MAIL 0.0000 -99.9990 NEXT WINDOW 0.6021 -99.9990 OPEN BROWSER 0.0000 -99.9990 OPEN MUSIC 0.0000 -0.1249 WINDOW <UNK> -0.2083 \3-grams: -99.9990 <UNK> <UNK> BACKWARD -99.9990 <UNK> <UNK> FORWARD -99.9990 <UNK> <UNK> LAST -99.9990 <UNK> <UNK> NEW -99.9990 <UNK> <UNK> NEXT -99.9990 <UNK> <UNK> OPEN -99.9990 <UNK> BACKWARD <UNK> -99.9990 <UNK> FORWARD <UNK> -99.9990 <UNK> LAST WINDOW -99.9990 <UNK> NEW E-MAIL -99.9990 <UNK> NEXT WINDOW -99.9990 <UNK> OPEN BROWSER -99.9990 <UNK> OPEN MUSIC -99.9990 BACKWARD <UNK> <UNK> -99.9990 BROWSER <UNK> <UNK> -99.9990 E-MAIL <UNK> <UNK> -99.9990 FORWARD <UNK> <UNK> -99.9990 LAST WINDOW <UNK> -99.9990 MUSIC PLAYER <UNK> -99.9990 NEW E-MAIL <UNK> -99.9990 NEXT WINDOW <UNK> -99.9990 OPEN BROWSER <UNK> -99.9990 OPEN MUSIC PLAYER -0.1761 WINDOW <UNK> <UNK> \end\ http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/cmuslm-_arpa Tue, 19 Aug 2008 07:21:16 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/pocketsphinx-0_5-running-on-wince-windows I have got pocketsphinx 0.5 running on Windows Mobile 5.0. However, I'm getting only one 'hypothesis' no matter how long I speak into the PDA. Infact, I'm only getting the words -"THE", "SAY", "TURN" and "EIGHT" although I didn't mention any of these during the 'utterance_loop'. BTW, -I am using the code from continuous.c - Sampling rate 16000 - HMM and LM which come with version 0.5 I noticed that the number of recognised words in my PDA is way smaller than when I run in pocketsphinx_continuous.exe in cmd. Here is the output (if this is not too much info): INFO: ..\..\src\libsphinxbase\feat\cmn_prior.c(122): cmn_prior_update: from < 266240.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 > INFO: ..\..\src\libsphinxbase\feat\cmn_prior.c(140): cmn_prior_update: to < 48.43 -5.48 -1.47 -2.56 -1.41 -3.03 -0.77 -1.19 0.16 -0.49 1.40 0.51 0.90 > INFO: ..\..\..\src\libpocketsphinx\ngram_search_fwdtree.c(1471): 403 words recognized (7/fr) INFO: ..\..\..\src\libpocketsphinx\ngram_search_fwdtree.c(1473): 49502 senones evaluated (812/fr) INFO: ..\..\..\src\libpocketsphinx\ngram_search_fwdtree.c(1475): 15112 channels searched (247/fr), 3819 1st, 4734 last INFO: ..\..\..\src\libpocketsphinx\ngram_search_fwdtree.c(1479): 697 words for which last channels evaluated (11/fr) INFO: ..\..\..\src\libpocketsphinx\ngram_search_fwdtree.c(1482): 1508 candidate words for entering last phone (24/fr) INFO: ..\..\..\src\libpocketsphinx\ngram_search_fwdflat.c(829): 296 words recognized (5/fr) INFO: ..\..\..\src\libpocketsphinx\ngram_search_fwdflat.c(831): 9212 senones evaluated (151/fr) INFO: ..\..\..\src\libpocketsphinx\ngram_search_fwdflat.c(833): 3519 channels searched (57/fr) INFO: ..\..\..\src\libpocketsphinx\ngram_search_fwdflat.c(835): 454 words searched (7/fr) INFO: ..\..\..\src\libpocketsphinx\ngram_search_fwdflat.c(837): 87 word transitions (1/fr) WARNING: "..\..\..\src\libpocketsphinx\ngram_search.c", line 965: </s> not found in last frame, using EIGHT instead INFO: ..\..\..\src\libpocketsphinx\ngram_search.c(1007): lattice start node <s>.0 end node EIGHT.3 I have been debugging the code using my PDA for some time now and can't figure out why I am not getting good recognition. I need some one to advise how to proceed from here. I need to know what Sampling rate to use, do I need to create a new LM based on the PDA, why I'm I getting only one word printed out everytime? Sorry for too many questions. I just wanted to bring everything to the table. Many thanks http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/pocketsphinx-0_5-running-on-wince-windows Tue, 29 Jul 2008 09:42:56 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/comparing-htk-and-sphinx David Huggins-Daines (PocketSphinx developer) has an article in his wiki comparing Sphinx 3.0 and HTK speech recognition engines. From the article: http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/comparing-htk-and-sphinx Tue, 22 Jul 2008 13:43:23 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-3-forward-backward-error Phase 3: Forward-Backward http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-3-forward-backward-error Mon, 21 Jul 2008 21:34:42 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/generating-phoneme-confusion-matrix-by-hresults-of-htk Hi all, I have to generate the phoneme (or word) confusion matrix by HResults of HTK. I have tried but it wasn't work. Does anyone has experience of doing this? Thanks for your help. Do Cong Thanh http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/generating-phoneme-confusion-matrix-by-hresults-of-htk Fri, 18 Jul 2008 06:13:08 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/any-interest-in-a-jack-interface-to-julius I have written an interface that connects Jack audio input into the Julius SRE. I was wondering if there was any community interest, I still need to do some code cleanup before I would release is(done by the end of the month), but it works right now and I think it is handy. So, anyone interested in playing with Jack and Julius? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/any-interest-in-a-jack-interface-to-julius Tue, 15 Jul 2008 09:28:39 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-can-we-get-the-phoneme-in-speech-recognition rks_mfs http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-can-we-get-the-phoneme-in-speech-recognition Wed, 18 Jun 2008 11:13:20 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/detailed-how-to-cross-compiling-for-sharp-zaurus HI http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/detailed-how-to-cross-compiling-for-sharp-zaurus Sat, 17 May 2008 00:43:50 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/cmu-slm-doubt Hi, I am trying to create my own laguage model and I have a doubt about the context file. I read at the web site that it is a file containing a list of words within the vocabulary which will serve as context cues. What is the format of the file? Does it have to contain the word's pronunciation or just the word? Thanks http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/cmu-slm-doubt Wed, 14 May 2008 09:40:24 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/what-do-i-have-to-do I'm using julius 3.5.2 quickstart. Everything seems to work. There is a line <<< please speak >>> and I have to read the sentences loudly again and again. How long to I have to speak? I want julius to understand what I say and not what he wants me to say. thank you, Jan http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/what-do-i-have-to-do Sat, 10 May 2008 06:37:05 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sp16-buffer Hi, Can any one suggest me how to read the data for the recognition purpose from the SP16 BUFFER. Through JACK data is read to this buffer and then I intiated the recognition engine but I am not able to figure out how to do the recognition process by reading the data from the buffer. Thanks, Siri. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sp16-buffer Wed, 23 Apr 2008 13:30:29 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/doubt-about-train-and-key-training-issues Hi, I am trying to begin my own exercise with sphinx3. I have already given a name to it with the perl scripts_pl/copy_setup.pl -task mgf command. I reran the Sphinxtrain setup without problems: ./configure make perl scripts_pl/setup_tutorial.pl mgf cd ../mgf perl scripts_pl/make_feats.pl -ctl etc/an4_train.fileids perl scripts_pl/RunAll.pl Then, I reran the decoder setup: ./configure --prefix=`pwd`/build --with-sphinxbase=`pwd`/../sphinxbase make && make install perl scripts/setup_tutorial.pl mgf I got the following message: Building task mgf Task not previously defined. User has to provide language model and supporting variables The tutorial says I have to copy the configuration files located under etc, to the new setup. I am not understanding well because I looked the etc/ directory of my new task and it already has the same files as the an4/etc. What haven't I understood? Thanks http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/doubt-about-train-and-key-training-issues Fri, 18 Apr 2008 08:48:29 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/-i-am-not-conquering-install-the-pocket-sphinx I am not conquering install the pocket sphinx, in any way after make a download from: http://sourceforge.net/project/showfiles.php?group_id=1904&package_id=199612 , I extracted the files, opened the configure and autogen files but after this I did not finish the instalation, the instal program says to open the make program I opened and compiled but so many trobles occured. I´d like some help. Atenciously. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/-i-am-not-conquering-install-the-pocket-sphinx Wed, 16 Apr 2008 13:50:26 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julian-errors-with-voxforge-sample I'm getting the following back when I run Julian from the quickstart: [localhost]$ ./julian -C julian.jconf include config: julian.jconf ###### check configurations ###### build up system Reading in HMM definition...(ascii)...Warning: initial state has more than one arc Warning: more than one arc to end state Warning: HMM "sp" has unsupported arc. SERIOUS WARNING: Transition arc has been modified as below SERIOUS WARNING: This may cause unintended recognition result 0.000000e+00 0.000000e+00 1.000000e+00 0.000000e+00 1.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 limit check passed defined HMMs: 4382 logical names: 6075 in HMMList base phones: 44 used in logical done Making pseudo bi/mono-phone for IW-triphone...1026 added as logical...done Reading in dictionary... 23 words...done ERROR: head sil word "<s>" not exist in voca Terminated Not sure what's up but sample.voca has % NS_B <s> sil % NS_E </s> sil and sample.dict has 0 [<s>] sil 1 [</s>] sil do I need to edit something by hand in the other grammar/ files? thanks, josh http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julian-errors-with-voxforge-sample Sat, 05 Apr 2008 00:00:59 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/doubt-about-sphinx3-installation Hi, I am new at sphinx and I have been experiencing some trouble to install it. I am using Linux version 2.6.18-4-686 (Debian 2.6.18.dfsg.1-12), gcc 4.1.2, perl 5.8.8 and the nightly.tar.gz versions of an4, Sphinxtrain, sphinxbase and sphinx3. I have been following the tutorial of http://www.speech.cs.cmu.edu/sphinx/tutorial.html page. Everything is okay until I try to perform a preliminary decode using the following command: perl scripts_pl/decode/slave.pl Does anyone knows how to solve the following error: MODULE: DECODE Decoding using models previously trained Decoding 130 segments starting at 0 (part 1 of 1) 0% Can't open /home/margarita/tutorial/an4/result/an4-1-1.match SENTENCE ERROR: 100.000% (130/130) I looked up into the an4/result directory and I found an4.align and an4.match What can I do? Thanks http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/doubt-about-sphinx3-installation Tue, 01 Apr 2008 18:06:37 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-tiny From the Simile site: http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-tiny Fri, 28 Mar 2008 21:40:28 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-again-and-again Hello, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx-again-and-again Mon, 17 Mar 2008 04:54:24 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/strange-error-from-the-libraries-of-julius I am developing an interface for JULIUS and JACK(an audio server). But when I am compiling a code I am getting errors from the libraries. I have written cmake inorder to compile the libraries from JACK and JULIUS. I have manually set the path for JULIUS libraries. This is the following error I am getting http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/strange-error-from-the-libraries-of-julius Thu, 13 Mar 2008 14:50:09 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3-07-mysterious-error Hello, I am trying sphinx3-07. I installed sphinxbase et sphinx3 sucessfully. My proble; is that when I run for instance sphinx-simple or others exectuable, I always get the same error. /usr/local/bin/sphinx3_livedecode: error while loading shared libraries: libs3decoder.so.0: cannot open shared object file: No such file or directory Meanwhile I know that this library exist, in the file /usr/local/lib So why didn't he suceed to open it ?? I try with sudo and doesn't change a think. So I guess this library is at the wrong place what should I do to make it work ? I used the ./configure by default Thx http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinx3-07-mysterious-error Mon, 10 Mar 2008 11:47:35 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/howto-use-pocketsphinx Hi everybody, I know that this topic should be in the CMU sphinx forum, but I enjoye this one so. Well, my problem is. On the pocketSphinxs web page http://www.speech.cs.cmu.edu/pocketsphinx/ it is well explain how to compile and to install the sources. But main problem, I don't find any examples or demos of the Sphinxpocket .!! and I know that they are somewhere !! So does someone point me on the good website. DOes it exist for LInux only executable with demo and a file for explaining howto use the sooftware ?? THx a lot regards http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/howto-use-pocketsphinx Thu, 06 Mar 2008 04:19:52 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/error-compiling-julius-4_0-under-fedora-6 error occur when i was compiling julius 4 ,the massages are someting like: /usr/bin/install -c -d /root/julius-4.0//bin /usr/bin/install -c generate-ngram /root/julius-4.0//bin /usr/bin/install -c -d /root/julius-4.0//man/man1 /usr/bin/install -c -m 644 generate-ngram.man /root/julius-4.0//man/man1/generate-ngram.1 /usr/bin/install: cannot stat “generate-ngram.man”: no such file or filefolder make[1]: *** [install.man] error 1 make[1]: Leaving directory `/root/julius-4.0/generate-ngram' make: *** [install] error 2 my compile instructions are: ./configure --prefix=/root/julius4.0 make make all and the above error infos occured in "make all" step Does anybody know why? TIA http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/error-compiling-julius-4_0-under-fedora-6 Fri, 29 Feb 2008 08:38:07 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-and-alsa-strange-behavior Hi, Does anybodu have experiences about using alsa sound card driver with julius (v4.0 and 3.5.3)? I've used julius 4.0 (and before julian) with my internal soundcard without any problem and I've discovered a strange behavior recently when trying to use an external usb soundcard alsa complient : I compile and configure julius with the --with-mictype=alsa option and I get the right message at the end of configure saying "mic device API : alsa (Advanced Linux Sound architecture)". But when I launch julius using -input mic option I get this jlog message : "STAT : ###### initialize input device" "Stat : adin_oss : device name = /dev/dsp" [...] which means oss is used instead of alsa, because this log message can only comes from the adin_mic_linux_oss.c file. I've tried to understand where is the problem in the configure/make script of julius, but I've not been able to see it. Any idea? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-and-alsa-strange-behavior Mon, 21 Jan 2008 09:28:37 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-v4_0--isolated-word-reco--phone-silb-not-found Hi all, http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-v4_0--isolated-word-reco--phone-silb-not-found Mon, 14 Jan 2008 11:06:19 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/help-needed-for-julius Hi Can anyone help me with this problem?I have installed Julius on my LINUX machine. After downloading the acoustic model from the voxforge site I tried to test it using a microphone. When I am speaking after the prompt <<Please Speak>> no response is coming out. I have adjusted the microphone input level using the mixer and also adjusted the speech detection level.Everything is fine with other methods like MFCC files and rawfiles. Thanks, Siri. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/help-needed-for-julius Tue, 08 Jan 2008 23:05:29 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-4_0-released Julius 4.0 is now available from the Julius Dev site - from the release notes: What's new in Julius-4.0 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-4_0-released Wed, 26 Dec 2007 15:33:02 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/disfluency-speech-corpus Howdy Folks, I am looking for a Speech Data that contains disfluencies, such as filled pauses, sentence restarts and so on. I am wondering if there is any data like this available on VoxForge? And if not, if you could point me in the right direction that would be great. Cheers, Adam http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/disfluency-speech-corpus Mon, 03 Dec 2007 06:25:17 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/compiling-julian-source-under-windows-xp Hello Is there any instruction on how to compile Julian under Win XP and what tools are required to perform it? I was unable to find compiling instruction. When I compiled HTK there was step by step tutorial on how to do it, is there one for Julian? Thank you for any help. Best regards Marcin Fedyna http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/compiling-julian-source-under-windows-xp Sun, 25 Nov 2007 07:28:58 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/handhled/smartphone-asr Hi all, I know that my question can be a bit out of line in this forum, but I would like to do an isolated word speaker in/dependent recognition system with a quite small vocabulary on a Windows mobile/CE system. Does anyone know which engine can I use? I think PocketSphinx is the more suitable but I do not know if it is supported on these Windows versions. What about HTK?? Thanks, best regards!! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/handhled/smartphone-asr Wed, 14 Nov 2007 06:42:23 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sautrela-speech-recognition-framework Sautrela is a Java based, highly modular and pluggable open source framework http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sautrela-speech-recognition-framework Mon, 29 Oct 2007 20:28:04 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/about-julian-recognition-output Hi, I finished the whole training job. But when I run Julian, here come the problems, it can only recognition two words, just like "dial one", it ignore almost all the words that I speak. I try so many times, but the result is all the same. And I download the tutorial of VoxForge, where I can also try the Julian, but the problem is the same. Why is that? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/about-julian-recognition-output Fri, 05 Oct 2007 01:32:02 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/word-error-rate-with-julian HI, I use julian to try my own acoustic model create following the VoxForge Tutorial Step, but always I have a very high WER, why? If I try the Linux QuickStart I have a smaller WER. For my test I use over than 100 audio file, downloaded from VoxForge, to train the model, and the same sample.grammar and sample.voca of Quickstart. Someone has good result with his own acoustic model? Tks Manuel http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/word-error-rate-with-julian Tue, 11 Sep 2007 06:25:58 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinxtrain-is-missing-file-/util/utils_pl Hi, I'm trying to install Sphinx 3 When I start PERL script decode/slave.pl, it gives me an error, because it can't find /SphinxTrain/script_pl/util/utils.pl script_pl has no /util folder. I can only find one download location for SphinxTrain: http://cmusphinx.sourceforge.net/html/download.php#SphinxTrain This doesn't contain a /script_pl/util/ folder. Please can someone help? Maybe could you send me a .zip of the /util folder? Many thanks, Sam SunFish7@GMail.com PS Is there a better place for posting such a query? PPS I'm not the only one to get this problem - half way down this page, some guy gets the same problem: http://www.voxforge.org/home/forums/message-boards/other-languages/italian-language?pn=2 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/sphinxtrain-is-missing-file-/util/utils_pl Mon, 10 Sep 2007 19:57:53 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/comparing-open-source-speech-recognition-engines Here is an email thread I had with Anna: Hello Ken, My name is Anna and I'm a Spanish computer sciences student. I'm http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/comparing-open-source-speech-recognition-engines Tue, 28 Aug 2007 09:44:34 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/looking-for-an-engine-to-extract-voice-from-videos http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/looking-for-an-engine-to-extract-voice-from-videos Wed, 13 Jun 2007 08:43:02 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius_--hmm-lexicon-treesegmentation-fault-error Hi folks? I tried to create an acoustic modell with HTK and wanted to test it on Julius. Here is my jconf file ( rest is same with the sample jconf file in the How to document of the Voxforge site ) -h ../phone_m/hmmtied # copied from hmm15 folder -hlist ../phone_m/tiedlist -v ../lang_m/dict -forcedict And here is the output from julius: ... ... z-eh+n z-eh+sp z-er+sp z-i:+k z-i:+sp z-j+o: z-l+er z-o:+sp z-y:+d z-y:+s z-y:+t ////////////////////// errors are ignored 1028 words...done Reading in word n-gram...1-gram.....2-gram.......3-gram..indexing...done Mapping dictonary words to n-gram entries...done Building HMM lexicon treeSegmentation fault: 11 (core dumped) Does anybody know what is wrong with my Acoustic modell ? What does "treeSegmentation fault" error mean ? if I try -h option with the "hmmdefs" file which is created in "hmm12" folder (triphone) julius gives me following error: ------------------------------- Reading in HMM definition...(ascii)...Warning: initial state has more than one arc Warning: more than one arc to end state Warning: HMM "sp" has unsupported arc. SERIOUS WARNING: Transition arc has been modified as below SERIOUS WARNING: This may cause unintended recognition result 0.000000e+00 0.000000e+00 1.000000e+00 0.000000e+00 9.999999e-01 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 limit check passed defined HMMs: 2668 Error: HMMList: line 2: physical HMM "C" not found .... .... Error: HMMList: line 2631: physical HMM "Y" not found Error: HMMList: line 2661: physical HMM "er" not found HMMList "../phone_m/tiedlist" read error Terminated ----------------------- How can i fix these "arc" errors and physical HMM "XX" not found errors ? If you need, I can give you more detailed information of my training steps and outputs. Any suggestion would be appreciated. Thanks in advance. Nagi http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius_--hmm-lexicon-treesegmentation-fault-error Mon, 11 Jun 2007 03:20:33 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/acoustic-model-htk Hi guys, I'm willing to use HTK to create a large vocabulary recognizer. I've already managed to make it work with sphinx4 using HUB4 or WSJ acoustic model. These one are freely available. I was wondering wether it exists free acoustic model for HTK as well? I didn't find any. I guess we are forced to train our own. But it just take too much time. I hope you'll be able to enlight me. Thank you all for reading ;) regards http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/acoustic-model-htk Thu, 10 May 2007 14:01:40 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-error-2126 Hello. I am using the HTK 3 and I'm having an error I have not been able to solve: the error code is +2126, what, in htkbook is defined as: +2126 No path through segment The Viterbi segmentation failed to find a path through model with this data. Check that data is not corrupt and that a valid path exists through the model. What does "corrupt" mean? Can anybody help me? I need the results of that "corrupt" files.... Thanks in advance http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/htk-error-2126 Fri, 27 Apr 2007 04:59:57 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/comparaison-of-the-different-recognition-device Hi guys, I'm willing to create a speech recognition device. Of course i'm only looking at the open source project, but I don't exactely know which one to use yet. I already know that the 4 mains one are: Sphinx, ISIP, HTK, and Julius.. But wich one should I choose knowing that I need to create a continuous speech recognizer, in english. I would really like to have your opinion. Best regards http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/comparaison-of-the-different-recognition-device Fri, 06 Apr 2007 05:43:22 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/recognition-engine-wishlist As I've been researching the subject of speech recognition and toying with the existing open source engines available (mainly CMU Sphinx2 and Julius/Julian), I've been making a mental list of ways to improve the engines themselves. DISCLAIMER: I've never written a recognition engine personally, so I'm hardly an expert on the subject. All I have to draw on is nature and existing documents detailing how speech recognition works. Here are a few things I've thought up, none of which are particularly novel, and none of which I have the slightest idea how to translate into code. I'm a programmer, but I don't deal with audio much, so this is new territory for me. 1.) Codec agnostic The human ear/brain doesn't care whether speech is encoded as 8 bit 8 khz or 32 bit 60 khz. Neither should our speech recognition engines. I know why they do care currently. And I don't have a clue how to make them not care (some sort of abstraction/inference system, most likely). But I think it needs to happen. And I don't think training an engine separately for each individual codec is an efficient way to do it. 2.) Background noise filtering We need some way to deal with background noise. It could be a simple algorithmic filter or something more intelligent. I'm not even sure if it belongs in the engine itself (probably not). But it needs to be somewhere in the pipeline or the technology becomes much less useful. 3.) Multiple speaker identification and separation. Again, I'm not sure if this belongs in the recognition engine itself or if it should be a separate filter that runs before the engine to clean up the input data, but I think it would be excellent to have. In particular, it could be used to identify the speaker and "lock on" to his voice patterns, filtering out everything in the background. This is an advanced form of #2 above. Please feel free to comment on the above and/or offer your own improvements. Who knows, maybe one of us will end up coding some of this functionality in the future. Thanks! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/recognition-engine-wishlist Tue, 03 Apr 2007 13:22:47 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/engine-comparison Hello, You all obviously know a lot more about these engines than me. However, I'll try to sum up what I've discovered through research and testing here. Hopefully everyone will add to my findings and correct my misconceptions. In particular, I'm interested in comparing Julius and Sphinx2 (perhaps pocketsphinx as a stand in. I don't think they're all that different.) I haven't had much luck with sphinx3, and sphinx4 is basically sphinx3 re-written in Java. And HTK is more of a toolkit than an ASR, right? I think most english speaking people have more experience with sphinx because it comes with english language models and acoustic models. Julius comes with Japanese models. I've got a Japanese for Dummies book that I read from time to time, but overall I suck at Japanese, so I'm sticking with English. Gentoo linux has a sphinx ebuild, and I believe I've seen RPMs for Fedora Core 5. Linux distribution penetration is still quite low for sphinx. Julius, however, while not having an english language or acoustic model (apart from those provided by this site) comes with a win32 build, which is a great advantage to the masses not running linux. I haven't seen any julius RPMs or ebuilds, but they do have a linux binary on the website. I personally run win32 and linux, so I've had fun playing with both sphinx and julius, but I've only used julius on win32 because I don't enjoy compiling code under win32. I'll compile and test julius on linux shortly. Julius also has grammar based recognition (Julian.exe), which this project uses extensively. Julius also has dictation capabilities (Julius.exe), but I haven't seen english language models (n-gram files, etc) so I haven't been able to test it out. I think sphinx is similar. I think sphinx ships with a limited grammar and has the capability for dictation with an expanded grammar. So far I've had much better recognition accuracy (worked really well, actually) with julian + voxforge on win32 than with sphinx + default AM/LM on linux. But my win32 machine is much faster than my linux machine and I bought a new headset mic before doing the win32 test so I'll have to repeat my test on linux with the new mic and test julius on my linux machine to be sure. What I don't know is how the two systems compare under the hood. Does julius have functionality that sphinx lacks? What about the other way around? Thanks! http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/engine-comparison Sun, 01 Apr 2007 01:06:44 -0500 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/does-any-one-has-htk-3_4-executable-files hiiii, i try to build the HTK 3.4 new tools for windows, but i can't i asked my friend Mr. Google, but he didn't answer me.. i'm asking you now if any one have these files already built to use in windows please tell me or send me an email k_sr_p@yahoo.com .... best regards Khalid k_sr_p@yahoo.com http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/does-any-one-has-htk-3_4-executable-files Tue, 06 Mar 2007 06:06:54 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-speech-recognition-works There is a good article on the Howstuffworks.com site that describes How Speech Recognition Works. Ken http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/how-speech-recognition-works Tue, 30 Jan 2007 20:30:12 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/compiling-htk-in-windows Hi. I tried to build HTK tools by nmake /f htk_htktools_nt.mkf all as shown in http://htk.eng.cam.ac.uk/docs/inst-win.shtml. But everytime I got the error message "expected ':' or '=' seperator". Does anybody know how to fix this problem? http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/compiling-htk-in-windows Fri, 26 Jan 2007 16:16:41 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/new-julius-web-site See link to new Julius Web Site. http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/new-julius-web-site Wed, 17 Jan 2007 12:49:10 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-3_5_3-released From LEE Akinobu (Julius maintainer): We have just released Julius-3.5.3 in the Japanese site (sorry http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/julius-3_5_3-released Tue, 02 Jan 2007 21:24:08 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/intel-audio-visual-speech-recognition Another possible use of the VoxForge Acoustic Models: From the Intel Audio-Visual Speech Recognition site: http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/intel-audio-visual-speech-recognition Wed, 10 Jan 2007 09:16:57 -0600 http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/evaldictator Just got wind of a new Sphinx4-based Speech Recognition Engine (Java), targeted http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/evaldictator Thu, 12 Oct 2006 09:49:27 -0500