http://www.voxforge.org/home/dev/acousticmodels/linux/test/htk--julius/htk/comments http://www.voxforge.org/home/dev/acousticmodels/linux/test/htk--julius/htk/comments/how-to-do-the-recognition-by-phonem--withe-htk In this tutorial you are doing the recognition by words. Is it is possible with the same stages to do the recognition by phoneme, of course we change the grammar and the dictionary I tried to do that but the result (recout.mlf) was only the phoneme "sil" for each sentence in test file. Is the problem that each sentence is begins and finished by a "sil" !! And the rate of recognition was 2% !!!! http://www.voxforge.org/home/dev/acousticmodels/linux/test/htk--julius/htk/comments/how-to-do-the-recognition-by-phonem--withe-htk Sun, 21 Sep 2008 05:27:46 -0500 http://www.voxforge.org/home/dev/acousticmodels/linux/test/htk--julius/htk/comments/julius-performance I went through the steps to test the tutorial but found that the performance of Julius was considerably inferior to what was posted here. I have not been able to get above %50 word error rate. In particular, the recognizer seems to have lots of difficulty in identifying a long stream of digits. It is only able to recognize the first few digits. My guess is that the settings in the Julian.jconf file might need changing. Any suggestions? http://www.voxforge.org/home/dev/acousticmodels/linux/test/htk--julius/htk/comments/julius-performance Fri, 08 Aug 2008 20:28:47 -0500