Neural networks for statistical inference: Generalizations with applications to speech recognition
Authors:
- N. MorganNMN. Morgan
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 242-247 vol.1
Abstract
The basic principles of the hybrid HMM/MLP (hidden Markov model/multilayer perceptron) approach are reviewed and extended to triphone models. It is also shown how the statistical interpretation of the MLP output values can act upon the development of other algorithms and help them understand their behavior, which is the case with the a priori probabilities and the radial basis function networks. The advantages of a speech recognition system incorporating both MLPs and HMMs are the best discrimination and the ability to incorporate multiple sources of evidence (features, temporal context) without restrictive assumptions of distributions or statistical independence.<>Keywords
This publication has 6 references indexed in Scilit:
- Context-Dependent Phonetic Hidden Markov Models for Speaker-Independent Continuous Speech Recognition1992
- On the interaction between true source, training, and testing language models1991
- Links between Markov models and multilayer perceptronsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Networks for approximation and learningProceedings of the IEEE, 1990
- Semi-continuous hidden Markov models for speech signalsComputer Speech & Language, 1989
- Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern RecognitionIEEE Transactions on Electronic Computers, 1965