Multi-stream speech recognition based on Dempster-Shafer combination rule

Speech Communication

Volumn 52, Issue 3, 2010, Pages 213-222

  Valente, Fabio ^a  

^a IDIAP RESEARCH INSTITUTE   (Switzerland)

Author keywords

Inverse entropy combination; Multi Layer Perceptron; Multi stream speech recognition; TANDEM features

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; BAYESIAN FRAMEWORKS; COMBINATION RULES; COMBINED FEATURES; DEMPSTER-SHAFER; DEMPSTER-SHAFER COMBINATION RULES; HUMAN SPEECH; LARGE VOCABULARY SPEECH RECOGNITION; MULTI LAYER PERCEPTRON; MULTI-STREAM; MULTI-STREAM SPEECH RECOGNITION; OTHER APPLICATIONS; SPEECH RECOGNITION SYSTEMS; SPEECH SIGNALS; TANDEM FEATURES;

DIELECTRIC RELAXATION; ENTROPY; HYDRAULICS;

SPEECH RECOGNITION;

EID: 73649085443     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2009.10.002     Document Type: Article

References (25)

1. Allen J.B. Articulation and Intelligibility (2005), Morgan and Claypool
2. Bourlard, H., Dupont, S., 1996. A new asr approach based on independent processing and re-combination of partial frequency bands. In: Proc. ICSLP 96.
3. Bourlard H., and Morgan N. Connectionist Speech Recognition - A Hybrid Approach (1994), Kluwer Academic Publishers
4. Fletcher H. Speech and Hearing in Communication (1953), Krieger, New York
5. Galina L.R. Combining the results of several neural network classifiers. Neural Networks 7 5 (1994) 777-781
6. Hain, T. et al, 2005. The 2005 AMI system for the transcription of speech in meetings. In: NIST RT05 Workshop Edinburgh, UK.
7. Hermansky, H., Fousek, P., 2005. Multi-resolution rasta filtering for tandem-based asr. In: Proc. Interspeech 2005.
8. Hermansky, H., Malayath, N., 1998. Spectral basis functions from discriminant analysis. In: Proc. ICSLP'98, Sydney, Australia.
9. Hermansky, H. et al., 1996. Towards asr on partially corrupted speech. In: Proc. ICSLP.
10. Hermansky, H. et al., 2000. Connectionist feature extraction for conventional hmm systems. In: Proc. ICASSP.
11. Hwang, Mei-Yuh et al., 2007. Building a highly accurate mandarin speech recognizer. In: Proc. IEEE Workshop on Automatic Speech Recognition and Understanding.
12. Kittler J., et al. On combining classifiers. IEEE Trans. PAMI 20 (1998)
13. Kleinschmidt M. Methods for capturing spectro-temporal modulations in automatic speech recognition. Acustica united with acta acustica 88 3 (2002) 416-422
14. Mandler E.J., and Schurman J. Combining the classification results of independent classifiers based on Dempster/Shafer theory of evidence. Pattern Recognition Artificial Intell. X (1988) 381-393
15. Misra, H. et al., 2003. Entropy-based multi-stream combination. In: Proc. ICASSP.
16. Morgan, N. et al., 2004. Trapping conversational speech: extending trap/tandem approaches to conversational telephone speech recognition. In: Proc. ICASSP.
17. Plahl, C. et al, 2009. Recent improvements of the rwth gale mandarin LVCSR system. In: Proc. Interspeech, Brisbane, Australia.
18. Rich transcription evaluation campaign. .
19. Shafer G. A Mathematical Theory of Evidence (1976), MIT Press, Princeton
20. Stolcke A. et al., 2006. Cross-domain and cross-language portability of acoustic features estimated by multilayer perceptrons. In: Proc. ICASSP.
21. Thomas, S. et al., 2008. Hilbert envelope based spectro-temporal features for phoneme recognition in telephone speech. In: Proc. Interspeech.
22. Valente, F., Hermansky, H., 2007. Combination of acoustic classifiers based on Dempster-Shafer theory of evidence. In: Proc. ICASSP.
23. Valente, F. et al., 2007. Multi-stream features combination based on Dempster-Shafer rule for LVCSR system. In: Proc. Interspeech.
24. Xu L., et al. Methods of combining multiple classifiers and their applications to handwriting recognition. IEEE Trans. Systems Man Cybernet. 22 3 (1992) 418-435
25. Zhu, Q., Chen, B., Morgan, N., Stolcke, A., 2004. On using mlp features in lvcsr. In: Proc. ICSLP.