Speaker adaptation based on Markov modeling of speakers in speaker-independent speech recognition
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 845-848 vol.2
- https://doi.org/10.1109/icassp.1991.150470
Abstract
A speaker adaptation method for HMM (hidden Markov model) based speaker-independent speech recognition without supervising is presented. This method reduces the confusion between models, which is caused by training using large-size training data, by controlling the influences of the training samples used in HMM training by considering the similarity of speaker individuality. A Markov model and a hidden Markov model are used to represent an input speaker's individuality. These models are compared through their entropy and /b, d, g, m, n, N/ recognition task. The results show that a hidden Markov model is more suitable than a Markov model.Keywords
This publication has 6 references indexed in Scilit:
- Construction of a large-scale Japanese speech database and its management systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Large-vocabulary speaker-independent continuous speech recognition using HMMPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Sub-word unit talker verification using hidden Markov modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Variable parameter speaker verification system based on hidden Markov modelingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Speaker adaptation for large vocabulary speech recognition systems using speaker Markov modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- On the Application of Vector Quantization and Hidden Markov Models to Speaker-Independent, Isolated Word RecognitionBell System Technical Journal, 1983