sphinx2-demo does not recognize my words .. all i get is:
[initializing]
[silence] [audio]
- the mic is working fine (i was able to record my voice using GNOME's sound recorder and play it back ok)
- using on-board audio VIA AC97 with the OSS driver
- i even passed models/lm/turtle to the script and had the same problem
- i tried both the tar ball and the tree ... same problem
- got no errors compiling
any suggestions will be greatly appreciated.
also, the FAQ mentioned the following bit .. could this be my problem? if so can someone please point me to some URL, documentation, anything that might lead me to how i can achieve this.
FAQ #8 "Change the code that sends the audio to be processed to use every third sample, and pass the buffer as usual. You can effectively subsample the 48k to 16k by taking every third sample."
Thank you.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Anonymous
-
2003-05-12
The FAQ that you cited has to do with signal data that has been sampled at 48 kHz instead of the 16 kHz that Sphinx is expecting; it's a quick-and-dirty way (not the best from a theoretical point of view) for converting such signals to the 16 kHz sample rate. This would be applicable only if your a/d were sampling at 48 rather than 16 kHz, which seems unlikely, IMO. Look at the audio files that you have sampled with GNOME and check that they are 16 kHz.
cheers,
jerry
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Anonymous
-
2003-05-12
The FAQ that you cited has to do with signal data that has been sampled at 48 kHz instead of the 16 kHz that Sphinx is expecting; it's a quick-and-dirty way (not the best from a theoretical point of view) for converting such signals to the 16 kHz sample rate. This would be applicable only if your a/d were sampling at 48 rather than 16 kHz, which seems unlikely, IMO. Look at the audio files that you have sampled with GNOME and check that they are 16 kHz.
cheers,
jerry
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello all,
sphinx2-demo does not recognize my words .. all i get is:
[initializing]
[silence] [audio]
- the mic is working fine (i was able to record my voice using GNOME's sound recorder and play it back ok)
- using on-board audio VIA AC97 with the OSS driver
- i even passed models/lm/turtle to the script and had the same problem
- i tried both the tar ball and the tree ... same problem
- got no errors compiling
any suggestions will be greatly appreciated.
also, the FAQ mentioned the following bit .. could this be my problem? if so can someone please point me to some URL, documentation, anything that might lead me to how i can achieve this.
FAQ #8 "Change the code that sends the audio to be processed to use every third sample, and pass the buffer as usual. You can effectively subsample the 48k to 16k by taking every third sample."
Thank you.
The FAQ that you cited has to do with signal data that has been sampled at 48 kHz instead of the 16 kHz that Sphinx is expecting; it's a quick-and-dirty way (not the best from a theoretical point of view) for converting such signals to the 16 kHz sample rate. This would be applicable only if your a/d were sampling at 48 rather than 16 kHz, which seems unlikely, IMO. Look at the audio files that you have sampled with GNOME and check that they are 16 kHz.
cheers,
jerry
The FAQ that you cited has to do with signal data that has been sampled at 48 kHz instead of the 16 kHz that Sphinx is expecting; it's a quick-and-dirty way (not the best from a theoretical point of view) for converting such signals to the 16 kHz sample rate. This would be applicable only if your a/d were sampling at 48 rather than 16 kHz, which seems unlikely, IMO. Look at the audio files that you have sampled with GNOME and check that they are 16 kHz.
cheers,
jerry
I have a VIA-based board, but I'm using ALSA drivers rather than OSS. You might try that if you're still having problems with this.
(BTW, sphinx2-continuous which sphinx2-demo calls uses the OSS *interface* by default. This shouldn't be an issue either way, however.)