Discriminative training for speech recognition is compensating for statistical dependence in the HMM framework - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Dan Gillick, Steven Wegmann, Larry Gillick. Discriminative training for speech recognition is compensating for statistical dependence in the HMM framework. In 2012 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2012, Kyoto, Japan, March 25-30, 2012. pages 4745-4748, IEEE, 2012. [doi]

This author has not been identified. Look up 'Dan Gillick' in GoogleThis author has not been identified. Look up 'Steven Wegmann' in GoogleThis author has not been identified. Look up 'Larry Gillick' in Google

runs on WebDSL