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]
Abstract is missing.