Paper Info
Title
Speaker-independent word recognition using a neural prediction model
Abstract
A speech recognition model called the neural prediction model (NPM) is proposed. The model uses a sequence of multilayer perceptrons (MLPs) as a separate nonlinear predictor for each class. It is designed to represent temporal structures of speech patterns as recognition cues. In particular, temporal correlation in successive feature vectors of a speech pattern is represented in the mappings formed as MLP input-output relations. Temporal distortion of speech is efficiently normalized by a dynamic-programming technique. Recognition and training algorithms are presented based on the combination of dynamic-programming and back-propagation techniques. Evaluation experiments were conducted using ten-digit vocabulary samples uttered by 107 speakers. A 99.8% recognition accuracy was obtained. This suggests that the model is effective for speaker-independent speech recognition
Year
DOI
Venue
1990
10.1109/ICASSP.1990.115744
Readings in speech recognition
Keywords
DocType
ISSN
dynamic programming,neural nets,speech recognition,MLP input-output relations,back-propagation,dynamic-programming,multilayer perceptrons,neural prediction model,nonlinear predictor,recognition accuracy,recognition cues,speaker independent word recognition,speaker-independent speech recognition,speech patterns,speech recognition model,successive feature vectors,temporal correlation,temporal distortion,temporal structures,ten-digit vocabulary samples,training algorithms
Conference
1520-6149
ISBN
Citations 
PageRank 
1-55860-124-4
48
5.11
References 
Authors
4
2
Name
Order
Citations
PageRank
Iso, Ken-ichi1749.96
Takao Watanabe210714.18