I used WavFile demo and changed it to convert wav file to english words by using WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz.Model acoustic model. I used an inauguration speech of President Obama as an example wav file. I added the words in his speech to digits.gram file. But, program is detecting only couple of words in a One minute speech. Can anyone suggest how to increase the accuracy of this program.
Thanks,
Gurucharan
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
> Can anyone suggest how to increase the accuracy of this program.
Learn how to use sphinx4 and the accuracy will magically increase. Try to read this forum first, its full of questions like yours. It also has several links on examples of proper usage which you could follow.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
I used WavFile demo and changed it to convert wav file to english words by using WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz.Model acoustic model. I used an inauguration speech of President Obama as an example wav file. I added the words in his speech to digits.gram file. But, program is detecting only couple of words in a One minute speech. Can anyone suggest how to increase the accuracy of this program.
Thanks,
Gurucharan
> Can anyone suggest how to increase the accuracy of this program.
Learn how to use sphinx4 and the accuracy will magically increase. Try to read this forum first, its full of questions like yours. It also has several links on examples of proper usage which you could follow.