Monolingual and crosslingual comparison of tandem features derived from articulatory and phone MLPs

2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings

Volumn , Issue , 2007, Pages 36-41

  Çetin, Özgür ^a   Magimai Doss, Mathew ^b   Livescu, Karen ^c   Kantor, Arthur ^d   King, Simon ^e   Bartels, Chris ^f   Franken, Joe ^e  

^a YAHOO INC   (United States)

^b IDIAP RESEARCH INSTITUTE   (Switzerland)

^c MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

^d UNIVERSITY OF ILLINOIS AT URBANA CHAMPAIGN   (United States)

^e UNIVERSITY OF EDINBURGH   (United Kingdom)

^f UNIVERSITY OF WASHINGTON   (United States)

Author keywords

Feedforward neural networks; Hidden markov models; Speech recognition

Indexed keywords

CLASSIFICATION (OF INFORMATION); FEEDFORWARD NEURAL NETWORKS; HIDDEN MARKOV MODELS; LINGUISTICS; SPEECH; TELEPHONE SETS;

ARTICULATORY FEATURES; AUTOMATIC SPEECH RECOGNITION; CONVERSATIONAL TELEPHONE SPEECH; CROSS LANGUAGES; MULTI LAYER PERCEPTRON; OBSERVATION MODEL; PHONE CLASSIFICATIONS; PORTABLE PHONES;

SPEECH RECOGNITION;

EID: 44849132075     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/asru.2007.4430080     Document Type: Conference Paper

References (22)

1. H. Hermansky, D.P.W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional HMM systems," in Proc. ICASSP, 2000, pp. 1635-1638.
2. K. Kirchhoff, G. A. Fink, and G. Sagerer, "Combining acoustic and articulatory feature information for robust speech recognition," Speech Communication, vol. 37, pp. 303-319, 2000.
3. D.P.W. Ellis, R. Singh, and S. Sivadas, "Tandem acoustic modeling in large-vocabulary recognition," in Proc. ICASSP, 2001, pp. 517-520.
4. Q. Zhu, A. Stolcke, B. Y. Chen, and N. Morgan, "Incorporating Tandem/HATs MLP features into SRI's conversational speech recognition system," in Proc. EARS RT-04F Workshop, 2004.
5. X. Lei, M.-Y. Hwang, and M. Ostendorf, "Incorporating tone-related MLP posteriors in the feature representation for mandarin ASR," in Proc. INTERSPEECH, 2005, pp. 2981-2984.
6. M. Karafiat et al., "Robust heteroscedastic linear discriminant analysis and LCRC posterior features in meeting recognition," in Proc. MLMI, 2006.
7. A. Stolcke et al., "Cross-domain and cross-language portability of acoustic features estimated by multilayer perceptrons," in Proc. ICASSP, 2005, pp. 321-324.
8. M.-Y. Hwang et al., "Advances in Mandarin broadcast speech recognition," in Proc. INTERSPEECH, 2007.
9. J. Zheng et al., "Combining discriminative feature, transform, and model training for large vocabulary speech recognition," in Proc. ICASSP, 2007, pp. 633-636.
10. T. Schultz and A. Waibel, "Language independent and language adaptive large vocabulary speech recognition," in Proc. ICASSP, 1998, pp. 1819-1822.
11. M. Ostendorf, "Moving beyond the "beads-on-a-string" model of speech," in Proc. ASRU, 1999, pp. 79-84.
12. S. Stueker, F. Metze, T. Schultz, and A. Waibel, "Integrating multilingual articulatory features into speech recognition," in Proc. EUROSPEECH, 2003, pp. 1033-1036.
13. K. Livescu et al., "Articulatory feature-based methods for acoustic and audio-visual speech recognition: Summary from the 2006 JHU summer workshop," in Proc. ICASSP, 2007, pp. 621-624.
14. Ö. Çetin et al., "An articulatory feature-based tandem approach and factored observation modeling," in Proc. ICASSP, 2007, pp. 645-648.
15. S. King, J. Bilmes, and C. Bartels, "SVitchboard: Small-vocabulary tasks from Switchboard," in Proc. INTERSPEECH, 2005, pp. 3385-3388.
16. J. Bilmes and G. Zweig, "The Graphical Models Toolkit: An open source software system for speech and time-series processing," in Proc. ICASSP, 2002, pp. 3916-3919.
17. A. Venkataraman et al., "An efficient repair procedure for quick transcriptions," in Proc. ICSLP, 2004, pp. 1961-1964.
18. J. Frankel et al., "Articulatory feature classifiers trained on 2000 hours of telephone speech," in Proc. INTER-SPEECH, 2007.
19. M. Wester, J. Frankel, and S. King, "Asynchronous articulatory feature recognition using dynamic bayesian networks," in Proc. IEICI Beyond HMM Workshop, 2004.
20. J. P. Hosom, "Automatic phoneme alignment based on acoustic-phonetic modeling," in Proc. ICSLP, 2002, pp. 357-360.
21. X. Li and J. Bilmes, "Regularized adaptation of discriminative classifiers," in Proc. ICASSP, 2006, pp. 237-240.
22. J. Bilmes, "Data-driven extensions to HMM statistical dependencies," in Proc. ICSLP, 1998, pp. 69-72.