Fuzzy partition models and their incremental training for continuous speech recognition.
Yoshinaga Kato, Masahide Sugiyama · Journal of the Acoustical Society of Japan (E) · 1992
This paper describes the application of Fuzzy Partition Models (FPMs) and their in cremental training to continuous speech recognition.FPMs are neural networks with multiple input-output units.Since the outputs are non-negative and their sum is one, they can be regarded as the probabilities of recognizing input speech phonemes.Auto matic incremental training is developed using the Viterbi alignment to adapt FPMs to continuous speech.The FPMs are retrained automatically by using speech data seg mented by the Viterbi alignment.We combined FPMs with an LR parser (FPM-LR) and carried out experiments in continuous speech recognition.The recognition rate of the FPM-LR was higher than that of a Time-Delay Neural Network-LR (TDNN-LR).Automatic incremental training was more effective with FPMs than with TDNNs.