Speech Recognition Engines

Julius 4.0 released
User: kmaclean
Date: 12/26/2007 3:33 pm
Views: 7959
Rating: 46

Julius 4.0 is now available from the Julius Dev site - from the release notes:

What's new in Julius-4.0
The Julius rev.4.0 is a full major version up, a re-innovation of the
decoder as a flexible speech recognition engine.  The internal
structures are re-organized and modularized thoroughly, which results
in the librarization of core engine, enhancement and unification of
language model, realization of multi-decoding with hot plugging
feature.  The major features are listed below:
 - Engine core becomes separate C library with simple API
 - Can handle various LM, thus Julius and Julian are integrated
 - Multi-decoding with multiple models
 - Support to add and remove models while running the decoder
 - Support N-gram longer than 4 (N now unlimited)
 - User-defined LM function
 - Confusion network output
 - GMM-based and decoder-based VAD
 - New tools added, new functions added
 - Memory efficiency is improved
Julius-4.0 ensures the compatibility with Julius-3.x for its usage and
Jconf configuration, so that one can easily migrate to Julius-4.
The decoding performance of Julius-4.0 is still kept as the same as
the latest release (Julius-3.5.3) for now.

Many thanks to Ralf Herzog for picking this up and posting on his blog.


--- (Edited on 12/26/2007 4:33 pm [GMT-0500] by kmaclean) ---

Re: Julius 4.0 released
User: kmaclean
Date: 1/22/2008 3:44 pm
Views: 415
Rating: 43

Julius Main site now updated with Julius 4.0:

Documentation links: 

Code Links: 



--- (Edited on 1/22/2008 4:45 pm [GMT-0500] by kmaclean) ---

Re: Julius 4.0.1 released
User: kmaclean
Date: 3/12/2008 2:40 pm
Views: 1149
Rating: 36

From the Julius Announcements Forum page:

Julius rev.4.0.1 has been released today.
This release incorpolates bug fixes from 4.0 that has been reported so far.

http://sourceforge.jp/projects/julius/f ... 9930#29930

For Linux users, it should be noted that the default audio API
has been changed from OSS to ALSA. You can still use
the old OSS interface by giving "--with-mictype=oss" for
configure script at compilation time.

Have fun!


From the release notes:

4.0.1 (2008.3.12)
New features:
    - ALSA now become default on Linux instead of OSS.
  Module mode
      grammar name as arguments in addition to grammar ID number.
    - new command "GRAMINFO" to get list of current grammars.
Fixed bugs:
    - ALSA codes updated to work on 1.x drivers.
    - segfault with "-48".
    - segfault on MFCC input with zero frames with "-spsegment".
    - CMN not working on spsegment/GMM-VAD/decoder-VAD with microphone input.
  Acoustic model
    - Error when no short-pause model defined in multi-path mode.
    - incorrect 2-gram prob on 1st pass with backward N-gram only.
    - incorrect 1-gram prob for unknown words.
    - fail to read some ARPA files with no back-off compaction.
    - read failure or segfault on big N-gram with over 24bit entries.
    - redundant index for back-off weights in some case. 
  Word recognition
    - incorrect N-best output with "-output N" on word recognition.
    - "make install" fails on cygwin.
  Source code
    - Static variables in functions that are not meant to be static
      are made local.
    - Global variables in search are moved to StackDecode.

--- (Edited on 3/12/2008 3:40 pm [GMT-0400] by kmaclean) ---

--- (Edited on 3/12/2008 3:41 pm [GMT-0400] by kmaclean) ---

Re: Julius 4.0.1 released
User: xffmqjx
Date: 10/3/2013 12:26 pm
Views: 1776
Rating: 5

Hi kmaclean,

thanks for the nice information~

one question I would like to ask is: whether the user can use Confusion Network library/binary independently for other search purposes with proper inputs, e.g. from HTK enginer?




--- (Edited on 10/3/2013 12:26 pm [GMT-0500] by xffmqjx) ---