Corrective tuning by applying LVQ for continuous density and semi-continuous Markov models
暂无分享,去创建一个
[1] Mikko Kurimo,et al. Using LVQ to enhance semi-continuous hidden Markov models for phonemes , 1993, EUROSPEECH.
[2] Mikko Kurimo,et al. Application of self-organizing maps and LVQ in training continuous density hidden Markov models for phonemes , 1992, ICSLP.
[3] Mikko Kurimo,et al. Status Report Of The Finnish Phonetic Typewriter Project , 1991 .
[4] Jerome R. Bellegarda,et al. Tied mixture continuous parameter modeling for speech recognition , 1990, IEEE Trans. Acoust. Speech Signal Process..
[5] Shigeru Katagiri,et al. GPD training of dynamic programming-based speech recognizers , 1992 .
[6] Teuvo Kohonen,et al. The self-organizing map , 1990 .
[7] Lalit R. Bahl,et al. A new algorithm for the estimation of hidden Markov model parameters , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.
[8] Biing-Hwang Juang,et al. New discriminative training algorithms based on the generalized probabilistic descent method , 1991, Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop.
[9] Kunio Nakajima,et al. An optimal discriminative training method for continuous mixture density HMMs , 1990, ICSLP.