Modelling asynchrony in automatic speech recognition using loosely coupled hidden Markov models

Cognitive Science

Volumn 26, Issue 3, 2002, Pages 283-301

  Nock, H J ^a   Young, S J ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Automatic speech recognition; Loosely coupled hidden Markov models; Pronunciation modeling; Variation approximation

Indexed keywords

EID: 0036081023     PISSN: 03640213     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0364-0213(02)00071-X     Document Type: Article

References (44)

1. Phonological structures for speech recognition
2. The ISOLET spoken letter database
3. The computational complexity of probabilistic inference using Bayesian belief networks
4. Maximum likelihood from incomplete data via the EM algorithm
5. Structural design of a hidden Markov model based speech recognizer using multi-valued phonetic features: Comparison with segmental speech units
6. Dynamic pronunciation models for automatic speech recognition
7. An automatic speech recognition system using neural networks and linear dynamic models to recover and model articulatory traces
8. Factorial hidden Markov models
9. Some statistical issues in the comparison of speech recognition algorithms
10. Phonological theory: The essential readings
11. Insights into spoken language gleaned from phonetic transcription of the Switchboard corpus
12. Word recognition from tiered phonological models
13. An introduction to Bayesian networks
14. An introduction to variational methods for graphical models
15. Word-level phonetic variation in large speech corpora
16. Detection of phonological features in continuous speech using neural networks
17. Syllable-level desynchronization of phonetic features for speech recognition
18. Robust speech recognition using articulatory information
19. Robust speech recognition using articulatory information
20. Factorial HMMs for acoustic modelling
21. A multi-band approach to automatic speech recognition
22. Critique: The potential role of speech production models in automatic speech recognition
23. A view of the EM algorithm that justifies incremental and other variants
24. Techniques for modelling phonological processes in automatic speech recognition
25. Incorporating linguistic theories of pronunciation variation into speech recognition models
26. Hidden-articulator Markov models: Performance improvements and robustness to noise
27. Stochastic pronunciation modelling from hand-labelled phonetic corpora
28. The potential role of speech production models in automatic speech recognition
29. Progress towards speech models that model speech
30. Pronunciation modelling for conversational speech recognition
31. Pronunciation modelling by sharing Gaussian densities across phonetic models
32. Mixed memory Markov models
33. Speech recognition using phonetically-featured syllables
34. From acoustic cues to segments, features and words
35. Data-driven model construction for continuous speech recognition using overlapping articulatory features
36. Modelling asynchrony in speech using elementary single-signal decomposition
37. Error bounds for convolutional codes and an asymmetrically optimum decoding algorithm
38. Effect of speaking style on LVCSR performance
39. The development of the 1994 HTK large vocabulary speech recognition system
40. Speech recognition with dynamic Bayesian networks