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 (wsj1) and LM (turtle) 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

--- (Edited on 7/29/2008 9:42 am [GMT-0500] by DrewKing) ---

--- (Edited on 7/29/2008 9:51 am [GMT-0500] by DrewKing) ---

> 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 >

This certainly means your feature extraction is wrong. You need to review your changes and compare feature files with desktop version of the recognizer. 

>  I need to know what Sampling rate to use,

 Most probably you need 8 kHz.

> Sorry for too many questions. I just wanted to bring everything to the table

 This forum is for sure not a good place to ask about pocketsphinx. David doesn't read it for example. Use #cmusphinx irc channel or mail to cmusphinx-sdmeet mailing list on sourceforge.

--- (Edited on 7/29/2008 3:25 pm [GMT-0500] by nsh) ---

Problem solved.

Please read my post: http://sourceforge.net/forum/message.php?msg_id=5154975 
 
Drew

--- (Edited on 8/9/2008 10:27 am [GMT-0500] by DrewKing) ---