Duration modeling in large vocabulary speech recognition
暂无分享,去创建一个
[1] Stephen E. Levinson,et al. Continuously variable duration hidden Markov models for automatic speech recognition , 1986 .
[2] Chris Barry,et al. Robust smoothing methods for discrete hidden Markov models , 1989, International Conference on Acoustics, Speech, and Signal Processing,.
[3] M. Adda-Decker,et al. Experiments on stress-dependent phone modelling for continuous speech recognition , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.
[4] Francis Kubala,et al. New uses for the N-Best sentence hypotheses within the BYBLOS speech recognition system , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.
[5] R. Moore,et al. Explicit modelling of state occupancy in hidden Markov models for automatic speech recognition , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.
[6] Janet M. Baker,et al. The Design for the Wall Street Journal-based CSR Corpus , 1992, HLT.
[7] Philip C. Woodland,et al. Using relative duration in large vocabulary speech recognition , 1993, EUROSPEECH.