TDNN labeling for a HMM recognizer
暂无分享,去创建一个
A system which combines the good short-time classification properties of the time delay neural network (TDNN) with the good integration and overall recognition capabilities of hidden Markov models (HMMs) is proposed for a speaker-independent speech recognizer. The standard vector quantization is replaced by a TDNN labeler giving phonelike labels. In order to avoid hand segmentation for the training of the TDNN, a separate HMM and a Viterbi alignment derived from it are used. This gives a coarse phonetic segmentation of the training data.<<ETX>>
[1] Frank K. Soong,et al. High performance connected digit recognition using hidden Markov models , 1989, IEEE Trans. Acoust. Speech Signal Process..
[2] J R Cohen,et al. Application of an auditory model to speech recognition. , 1989, The Journal of the Acoustical Society of America.
[3] Geoffrey E. Hinton,et al. Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..
[4] Kai-Fu Lee. On large-vocabulary speaker-independent continuous speech recognition , 1988, Speech Commun..