Yes you have to make sure you use the one that comes with Pocketsphinx and not the 7.x one you download from the website. They aren't compatible last I checked. /b On Jul 10, 2009, at 9:12 AM, Peter P GMX wrote:

Hello Helmut,

I looked at these dic files. Their content (look at all the qq's) is quite different from the dic files supplied with freeswitch pocketsphinx. As I remember the CMU dict file format has changed in April 2008.

Best regards Peter

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Hi Peter, hmmm well, I had the same idea and I tested it! Buuuuut ... you have to make sure that the english grammar/acousticModel is able to cover all german noises. E.g. I tried to detect "Burke", "Jan" and "Gerd". I was able to map Burke successfully in default.dic. Otherwise I had to say "Böhrki" ... I did the same with "Jan" - but when I tried to detect Jan I always got Gerd (with and witout mapping ind default.dic) ... Quite strange and not really usable for (german) customers. But some typical software magic happened on my way: During my tests I had somehow a configuration using the voxforge files which was working within FS. But I can't reproduce it. I configured serveral files at the same time and used for reloading "reloadxml" and "reload mod_pocketsphinx" instead of rebooting FS. When it worked, FS was able to detect "Burke", "Jan" and "Gerd" correctly without modifying the dictionary... Is there any manual about pocketsphinx and its config files, which can explain how PS is working in more detail? Currently I walk with a flashlight in the dark ... regards Helmut On 10.07.2009 16:24, Peter P GMX wrote:

Hello Helmut,

I looked at these dic files. Their content (look at all the qq's) is quite different from the dic files supplied with freeswitch pocketsphinx. As I remember the CMU dict file format has changed in April 2008. Maybe there is a converter somewhere?

I was thinking of just enhancing the current dict file for some german words I need, but did not test it so far. This should be possible without modifying the underlying grammar. http://en.wikipedia.org/wiki/CMU_Pronouncing_Dictionary I would love to hear when you have had any progress on this.

Best regards Peter -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (MingW32)

iD8DBQFKWugP4tZeNddg3dwRAhjkAKConTWen4bq5BxSg23F6keZeY2CIACffAks yyOVZOkROr8tfUNGMv4t9o8= =lC+W -----END PGP SIGNATURE-----

Helmut, Your hard work is appreciated. Like Brian said, we'd all be interested in knowing more. Please feel free to put this on the wiki or see me off list and we'll discuss further how to document it for the good of the FS community. Thanks! -MC On Fri, Jul 31, 2009 at 6:18 AM, Helmut Kuper <helmut.kuper@ewetel.de>wrote:

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1

Hello,

I spent a few days working on my problem. I played around with voxforge's data, read some of the train docs of CMU, and debugged the sphinxbase, pocketsphinx and mod_pocketsphinx.

Results: - -I found a way to use the voxforge data as training data for creation of a german language corpus.

- -I enabled the logging of pocketsphinx to stderr (Dirty, but easy way to see what went wrong when FS loads grammar, mdef, etc and simply stopped. Very helpful!

- -I had to add a "dictcase" parameter to pocketsphinx.conf.xml resp mod_pocketsphinx.c to allow case sensitive dictionaries (like the german dictionary from voxforge).

FS starts up with german language model and detects the words as expected. But it's not so reliable as I want to ... I guess this is caused by the very small amount of training audio data. I used 4000 of 19000 audio files provided by voxforge due to the reason that voyforge's training fileid-list contains only 4000 files ... I have to create new fileid-list and transcription-lists containing all audio I have downloaded from voxforge.

Quite complex the whole thing ...

regards helmut

On 10.07.2009 14:53, Helmut Kuper wrote:

...

Hi,

I try to change pocketsphinx's grammar from default (english) to german. I found this archive (http://www.repository.voxforge1.org/downloads/de/Trunk/AcousticModels/), which contains similar files like those which can be found in grammar/model/communicator directory.

Unfortunately FS crashed without writing a core file nor logfile enries as soon as as pizza demo trys to detect speech.

Any Ideas? Maybe someone has already working grammar/model files for german language?

regards helmut

-----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (MingW32)

iD8DBQFKcu8z4tZeNddg3dwRAiVKAKCJdAvZyYXLClWp+kQO4MhsPVzbSQCgoX/T 7NosCujHwpkCXHzxkEY/N3M= =6Bu8 -----END PGP SIGNATURE-----

_______________________________________________ FreeSWITCH-users mailing list FreeSWITCH-users@lists.freeswitch.org http://lists.freeswitch.org/mailman/listinfo/freeswitch-users UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users http://www.freeswitch.org

On Wed, Aug 5, 2009 at 9:56 AM, Helmut Kuper <helmut.kuper@ewetel.de> wrote:

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1

Hi Michael,

today I put my documentation on FS wiki describing the steps to get a 8kHz sample rate acoustic model basing on voxforge's data for german language. It's not complete, yet.

You can found it here: http://wiki.freeswitch.org/wiki/Mod_pocketsphinx

regards Helmut

Thanks! I'd like to ask the community members who are interested in ASR and PocketSphinx to please review Helmut's page and add to it as well as offer feedback. -MC