зеркало из https://github.com/mozilla/kaldi.git
fd2eb8819c
Update arpa2fst invocations in individual egs/*/local scripts |
||
---|---|---|
.. | ||
s5 | ||
README.txt |
README.txt
This recipe is JHU's submission to the ASpIRE challenge. It uses Fisher-English corpus for training the acoustic and language models. It uses impulse responses and noises from RWCP, AIR and Reverb2014 databases to create multi-condition data