Hi I've trained an italian phone model with about 3000 utterances, the recognition is good if I do a batch recognition using the files used in the train (6% not well recognized), but It's bad (~50% wrong) changing audio set (microphone, audio board...,etc...). Do you know a way to adapt the phone model to your hardware (ex. doing an audio setup and some little training words) ?
thanks
andrea.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi I've trained an italian phone model with about 3000 utterances, the recognition is good if I do a batch recognition using the files used in the train (6% not well recognized), but It's bad (~50% wrong) changing audio set (microphone, audio board...,etc...). Do you know a way to adapt the phone model to your hardware (ex. doing an audio setup and some little training words) ?
thanks
andrea.