Continuous speech recognition using hidden Markov models
- 1 July 1990
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE ASSP Magazine
- Vol. 7 (3) , 26-41
- https://doi.org/10.1109/53.54527
Abstract
The use of hidden Markov models (HMMs) in continuous speech recognition is reviewed. Markov models are presented as a generalization of their predecessor technology, dynamic programming. A unified view is offered in which both linguistic decoding and acoustic matching are integrated into a single, optimal network search framework. Advances in recognition architectures are discussed. The fundamentals of Viterbi beam search, the dominant search algorithm used today in speed recognition, are presented. Approaches to estimating the probabilities associated with an HMM model are examined. The HMM-supervised training paradigm is examined. Several examples of successful HMM-based speech recognition systems are reviewed.Keywords
This publication has 46 references indexed in Scilit:
- Integration of acoustic information in a large vocabulary word recognizerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Experiments with the Tangora 20,000 word speech recognizerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Acoustic Markov models used in the Tangora speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- On the use of bandpass liftering in speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- Frame-specific statistical features for speaker independent speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1986
- Comparative study of several distortion measures for speech recognitionSpeech Communication, 1985
- Vector quantization in speech codingProceedings of the IEEE, 1985
- Maximum likelihood estimation for multivariate observations of Markov sourcesIEEE Transactions on Information Theory, 1982
- An Algorithm for Vector Quantizer DesignIEEE Transactions on Communications, 1980
- A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov ChainsThe Annals of Mathematical Statistics, 1970