Applying hidden Markov models to recognition of nonverbal speech
- 6 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Experimental results of the application of a hidden-Markov-model-based isolated-word recognition procedure to nonverbal speech are presented. Effects of different model structures on the accuracy of recognition are discussed.Keywords
This publication has 5 references indexed in Scilit:
- Structural methods in automatic speech recognitionProceedings of the IEEE, 1985
- Vector quantization in speech codingProceedings of the IEEE, 1985
- On the Application of Vector Quantization and Hidden Markov Models to Speaker-Independent, Isolated Word RecognitionBell System Technical Journal, 1983
- Speaker-independent isolated word recognition for a moderate size(54 word)vocabularyIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979
- A microcomputer-based control and communication system for the severely disabledACM SIGCAPH Computers and the Physically Handicapped, 1978