A hierarchical Bayesian model for continuous speech recognition

Pattern Recognition Letters

Volumn 23, Issue 7, 2002, Pages 773-781

  Mouria Beji, Fériel ^a,b  

^a UNIVERSITY OF MANOUBA   (Tunisia)

^b LORIA   (France)

Author keywords

Bayesian; Gibbs distribution; Hierarchical; Markov random field; Speech recognition; Time series

Indexed keywords

ACOUSTICS; IMAGE SEGMENTATION; PROBABILITY DISTRIBUTIONS; VECTORS;

PHONEME DURATIONS;

SPEECH RECOGNITION;

PATTERN RECOGNITION;

EID: 0036566979     PISSN: 01678655     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-8655(01)00154-4     Document Type: Article

References (22)

1. On the statistical analysis of dirty pictures
2. Bayes empirical Bayes
3. Variable duration models for speech
4. Sampling based approach to calculating marginal densities
5. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images
6. Statistical trajectory models for phonetic recognition
7. Continuous speech recognition based on high plausibility regions
8. The 1994 Abbot hybrid connectionist-HMM large-vocabulary recognition system
9. A model for segmentation and analysis of noisy images
10. Continuously variable duration hidden Markov models for automatic speech recognition
11. Probabilistic solution of ill-posed problems in computational vision
12. Neural networks for statistical recognition of continuous speech
13. Segmental phoneme recognition using Markov random fields
14. From HMM to segment models: A unified view of stochastic modeling for speech recognition
15. Stochastic segment model for phoneme-based continuous speech recognition
16. Connectionist probability estimators in HMM speech recognition
17. The calculation of posterior distribution by data augmentation
18. Automatic labeling of prosodic patterns