A robust compensation strategy for extraneous acoustic variations in spontaneous speech recognition

IEEE Transactions on Speech and Audio Processing

Volumn 10, Issue 1, 2002, Pages 9-17

  Jiang, Hui ^a,b,c   Deng, Li ^a,b,d  

^a IEEE   (United States)

^b UNIVERSITY OF WATERLOO   (Canada)

^c NOKIA RESEARCH CENTER   (United States)

^d MICROSOFT RESEARCH   (United States)

Author keywords

Bayesian predictive classification (BPC); Extraneous variation; Generic (or compact) model; Prior PDF; Speaker adaptive training (SAT)

Indexed keywords

BAYESIAN PREDICTIVE CLASSIFICATION; EXTRANEOUS VARIATION; GENERIC MODEL; PARAMETER TRANSFORMATIONS; SPEAKER ADAPTIVE TRAINING;

AUDIO ACOUSTICS; ERROR COMPENSATION; LEARNING ALGORITHMS; MARKOV PROCESSES; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; PARAMETER ESTIMATION; PROBABILITY DENSITY FUNCTION; ROBUSTNESS (CONTROL SYSTEMS);

CONTINUOUS SPEECH RECOGNITION;

EID: 0036124301     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.979381     Document Type: Article

References (20)

1. A compact model for speaker-adaptive training
2. Pronunciation modeling for conversational speech recognition: A status report from WS97
3. A statistical coarticulatory model for the hidden vocal-tract-resonance dynamics
4. Cluster adaptive training for speech recognition
5. Cluster adaptive training of hidden Markov models
6. Bayesian adaptive learning of the parameters of hidden Markov model for speech recognition
7. Irrelevant variability normalization in learning structure from data: A case study on decision-tree based HMM state tying
8. Robust speech recognition based on adaptive classification and decision strategies
9. Robust speech recognition based on Bayesian prediction approach
10. Improving Viterbi Bayesian predictive classification via sequential Bayesian leaning in robust speech recognition
11. A minimax search algorithm for CDHMM based robust continuous speech recognition
12. Hierarchical stochastic feature matching for robust speech recognition
13. Integrated bias removal techniques for robust speech recognition
14. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models
15. Fabricating conversational speech data with acoustic models: A program to examine model-data mismatch
16. Signal bias removal by maximum likelihood estimation for robust telephone speech recognition
17. A maximum-likelihood approach to stochastic matching for robust speech recognition
18. Tree-based state tying for high accuracy acoustic modeling