Sir, I have trained acoustic models using 6800 utterance it includes both words and sentences of around 4.3 hrs of speech. The results obtained from the decoder is very not even 15% I am getting. Pocket sphinx currently I am using. Is there anything I need to change so that decoder results might improve. Thanks in advance.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Sir, I have trained acoustic models using 6800 utterance it includes both words and sentences of around 4.3 hrs of speech. The results obtained from the decoder is very not even 15% I am getting. Pocket sphinx currently I am using. Is there anything I need to change so that decoder results might improve. Thanks in advance.