Voice Training

Voice Training Checklist

Speech lab students: please see the voice training checklist to make sure everything is in place before running voice training.

Running the Training

Once all the data is in place, run this from the top-level voice directory:

perl scripts/Training.pl scripts/Config.pm > train.log 2> err.log

This typically takes a while and is best run under a screen session. If you want to have it email you when done so you don't have to keep checking on it, you can run it like this using the mail command:

( perl scripts/Training.pl scripts/Config.pm > train.log 2> err.log ; echo "email content" | mail -s "email subject" your@email.address )

If the training fails before it is finished, you can see how far it got:

grep "Start " train.log

These steps match the ones at the end of scripts/Config.pm, so once you debug the problem, you can pick up the voice training from where it left off, rather than starting over from the beginning, by switching off the steps that already completed successfully in scripts/Config.pm by switching their 1s to 0s.

You will know the voice has trained successfully when there are .wav files in the gen/qst001/ver1/hts_engine/ directory.

Voice Output

Test synthesis utterances can be found under gen/qst001/ver1. hts_engine contains utterances synthesized using HTS-engine, and 1mix, 2mix, and stc contain synthesis using either SPTK or STRAIGHT.

The different speech waveform generation methods are as follows (from this thread):

Errors and Solutions