I have a large data base which is recoded in stereo, 16KHz and 16bit and saved as mswav
But when I make feats, it occured a problem with wave2feat:
INFO: ........\src\programs\wave2feat\wave2feat.c(786): Reading MS Wav file D
:/Sphinx/tutorial/test/wav/app/film001.wav:
INFO: ........\src\programs\wave2feat\wave2feat.c(787): 16 bit PCM data,
2 channels 41912 samples
INFO: ........\src\programs\wave2feat\wave2feat.c(788): Sampled at 16000
ERROR: "........\src\programs\wave2feat\wave2feat.c", line 883: unknown input
file format
ERROR: "........\src\programs\wave2feat\wave2feat.c", line 201: error reading
speech data
FATAL_ERROR: "........\src\programs\wave2feat\wave2feat.c", line 90: error co
nverting files...exiting
and I set trian.cfg as follows:
Audio waveform and feature file information
$CFG_WAVFILES_DIR = "$CFG_BASE_DIR/wav";
$CFG_WAVFILE_EXTENSION = 'wav';
$CFG_WAVFILE_TYPE = 'mswav'; # one of nist, mswav, raw
I'm not sure but I think it's the problem with "2 channel" wav.
how can I solve it?
THX
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I have a large data base which is recoded in stereo, 16KHz and 16bit and saved as mswav
But when I make feats, it occured a problem with wave2feat:
INFO: ........\src\programs\wave2feat\wave2feat.c(786): Reading MS Wav file D
:/Sphinx/tutorial/test/wav/app/film001.wav:
INFO: ........\src\programs\wave2feat\wave2feat.c(787): 16 bit PCM data,
2 channels 41912 samples
INFO: ........\src\programs\wave2feat\wave2feat.c(788): Sampled at 16000
ERROR: "........\src\programs\wave2feat\wave2feat.c", line 883: unknown input
file format
ERROR: "........\src\programs\wave2feat\wave2feat.c", line 201: error reading
speech data
FATAL_ERROR: "........\src\programs\wave2feat\wave2feat.c", line 90: error co
nverting files...exiting
and I set trian.cfg as follows:
Audio waveform and feature file information
$CFG_WAVFILES_DIR = "$CFG_BASE_DIR/wav";
$CFG_WAVFILE_EXTENSION = 'wav';
$CFG_WAVFILE_TYPE = 'mswav'; # one of nist, mswav, raw
I'm not sure but I think it's the problem with "2 channel" wav.
how can I solve it?
THX
> how can I solve it?
You can convert stereo audio to mono. In a batch script you could use sox:
http://sox.sourceforge.net/