kaldi/egs/aspire
Daniel Povey fd2eb8819c Merge pull request #681 from kkm000/arpa-invoke-egs
Update arpa2fst invocations in individual egs/*/local scripts
2016-04-13 14:19:24 -07:00
..
s5 Merge pull request #681 from kkm000/arpa-invoke-egs 2016-04-13 14:19:24 -07:00
README.txt trunk: JHU submission to ASpIRE far-field recognition challenge. Joint work with Daniel Povey and Guoguo Chen. Best result on dev is 29% WER. Includes minor changes to steps/nnet2/scripts. 2015-04-04 17:21:46 +00:00

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