Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
ATREUS: a comparative study of continuous speech recognition systems at ATR
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Hi-index | 0.00 |
This paper describes a speaker adaptation technique using a segment-based neural-mapping applied to continuous speech recognition. The adaptation neural network has a time shifted sub-connection architecture to maintain the temporal structure in the acoustic segment and to decrease the amount of speech data for training. The effectiveness of this network has been reported for phoneme recognition. In this paper, this speaker adaptation network is combined with a TDNNLR continuous speech recognizer, and is evaluated in word and phrase recognition experiments with several speakers. The results of 500-word recognition experiments show that the recognition rate by segment-based adaptation is 92.2%, 28.8% higher than the rate without adaptation. The results of 278 phrase recognition experiments show that the recognition rate by segmentbased adaptation is 57.4%,27.7% higher than the rate without adaptation.