The following schema describes how to train the speaker identification module with speakers.
[SpkIdTrainWav] 0 = a <- wav(MONO, input) 1 = f <- frontend(_,a) 2 = nf <- normalizer(BLOCK, f) 3 = output <- audiotemplateTrain(STREAM, nf)
0 |
The wav module processes the mono audio data. |
1 |
The frontend module converts audio data (a ) into front-end frame data. |
2 |
The normalizer module normalizes frame data from 1 (f ). |
3 |
The audiotemplatetrain module uses audio feature data from 2 (nf ) to train a new speaker classifier, which is saved as an audio template file. |
|