Phoneme classification using Markov models
- 24 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 11, 2759-2762
- https://doi.org/10.1109/icassp.1986.1168555
Abstract
An approach for supporting large vocabulary in speech recognition is to use broad phonetic classes to reduce the search to a subset of the dictionary. In this paper, we investigate the problem of defining an optimal classification for a given speech decoder, so that these broad phonetic classes are recognized as accurately as possible from the speech signal. More precisely, given Hidden Markov Models of phonemes, we define a similarity measure of the phonetic machines, and use a standard classification algorithm to find the optimal classification. Three measures are proposed, and compared with manual classifications.Keywords
This publication has 4 references indexed in Scilit:
- Application of allophonic and lexical constraints in continuous digit recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Properties of large lexicons: Implications for advanced isolated word recognition systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A coarse phonetic knowledge source for template independent large vocabulary word recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A Maximum Likelihood Approach to Continuous Speech RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1983