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-ichi | 1 | 74 | 9.96 |
Takao Watanabe | 2 | 107 | 14.18 |