TDNN labeling for a HMM recognizer

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. >