Continuous speech recognition using linked predictive neural networks
Authors:
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 61-64 vol.1
Abstract
The authors present a large vocabulary, continuous speech recognition system based on linked predictive neural networks (LPNNs). The system uses neural networks as predictors of speech frames, yielding distortion measures which can be used by the one-stage DTW algorithm to perform continuous speech recognition. The system currently achieves 95%, 58%, and 39% word accuracy on tasks with perplexity 7, 111, and 402, respectively, outperforming several simple HMMs that have been tested. It was also found that the accuracy and speed of the LPNN can be slightly improved by the judicious use of hidden control inputs. The strengths and weaknesses of the predictive approach are discussed.Keywords
This publication has 3 references indexed in Scilit:
- Links between Markov models and multilayer perceptronsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Phoneme recognition using time-delay neural networksIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- The use of a one-stage dynamic programming algorithm for connected word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984