Hierarchical stochastic feature matching for robust speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2001, Pages 217-220

  Jiang, H ^a   Soong, F ^a   Lee, C H ^a  

^a LUCENT TECHNOLOGIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

HIERARCHICAL STOCHASTIC FEATURE MATCHING; MAXIMUM A POSTERIOR;

ALGORITHMS; DATABASE SYSTEMS; DECODING; MAXIMUM LIKELIHOOD ESTIMATION; PATTERN MATCHING;

SPEECH RECOGNITION;

EID: 0034848766     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. On-line adaptive learning of the continuous density hidden Markov model based on approximate recursive bayes estimate
2. On stochastic feature and model compensation approaches to robust speech recognition
3. Maximum likelihood linear regression for speaker adaptation of the parameters of continuous density hidden Markov models
4. A maximum-likelihood approach to stochastic matching for robust speech recognition
5. Structural MAP speaker adaptation using hierarchical priors