Acoustic training from heterogeneous data sources: Experiments in Mandarin conversational telephone speech transcription

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn I, Issue , 2005, Pages 461-464

  Tsakalidis, Stavros ^a   Byrne, William ^a,b  

^a Johns Hopkins University   (United States)

^b UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC NOISE; OPTIMIZATION; PERFORMANCE; SPEECH RECOGNITION; TELECOMMUNICATION SYSTEMS;

ACOUSTIC TRAINING; CROSS-CORPUS NORMALIZATION PROCEDURE; SPEECH TRANSCRIPTION;

ACOUSTICS;

EID: 33646781551     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2005.1415150     Document Type: Conference Paper

References (20)

1. RT-03 Spring Evaluation, 2003, [Online]. Available: http://www.nist.gov/ speech/tests/rt/rt2003/spring/.
2. T. F. Zheng, P. Yan, H. Sun, M. Xu, and W. Wu, "Collection of a chinese spontaneous telephone speech corpus and proposai of robust rules for robust natural language parsing," in SNLP-O-COCOSDA, May 2002, pp. 60-67.
3. A. Acero, "Acoustical and enviromental robustness in automatic speech recognition," Kluwer Academic Publishers, Boston, MA, 1993.
4. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker-adaptive training," in ICSLP, Oct. 1996, pp. 1137-1140.
5. H. Jiang and L. Deng, "A robust compensation strategy for extraneous acoustic variations in spontaneous speech recognition," IEEE Trans. Spch. & Aud. Proc., vol. 10, no. 1, pp. 9-17, Jan. 2002.
6. Ananth Sankar and Chin-Hui Lee, "A maximum-likelihood approach to stochastic matching for robust speech recognition," IEEE Trans. Spch. & Aud. Proc., vol. 4, no. 3, pp. 190-202, May 1996.
7. R. Iyer, M. Ostendorf, and H. Gish, "Using out-of-domain data to improve in-domain language models," IEEE Sig. Proc. Let., vol. 4, no. 8, pp. 221-223, Aug. 1997.
8. A. P. Dempster, A. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data," J. Roy. Stat. Soc., Ser. B, vol. 39, no. 1, pp. 1-38, 1977.
9. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Comp. Spch. & Lang., vol. 12, no. 2, pp. 75-98, Apr. 1998.
10. RT-03 Spring Workshop, May 2003, [Online]. Available: http://www.nist.gov/speech/tests/rt/rt2003/spring/presentations/ cts-combined-sm-ok-v14.pdf.
11. S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland, The HTK Book, Version 3.0, July 2000.
12. F. Zheng, Z. Song, P. Fung, and W. Byrne, "Mandarin pronunciation modeling based on the CASS corpus," J. Comp. Sci. Tech. (Science Press, Beijing, China), vol. 17, no. 3, May 2002.
13. M. Mohri and M. Riley, "Integrated context-dependent networks in very large vocabulary speech recognition," in Eurospeech, Sept. 1999, pp. 811-814.
14. A. Stolcke, "SRILM - An Extensible Language Modeling Toolkit," in ICSLP, Sept. 2002, pp. 901-904.
15. C. J. Leggetter and P. C. Woodland, "Speaker adaptation of continuous density HMMs using multivariate linear regression," ICSLP, pp. 451-454, Sept. 1994.
16. W. Byrne et. al., "Towards language independent acoustic modeling," in ICASSP. IEEE, June 2000, pp. 1029-1032.
17. C. Nieuwoudt and E. C. Botha, "Cross-language use of acoustic information for automatic speech recognition," Spch. Comm., vol. 38, no. 1, pp. 101-113, Sept. 2002.
18. Z. Wang, T. Schultz, and A. Waibel, "Comparison of acoustic model adaptation techniques on non-native speech," in ICASSP. IEEE, Apr. 2003, pp. 540-543.
19. Special Session, "Multilinguality in Speech Processing," in ICASSP. IEEE, May 2004.
20. D. Vergyri, S. Tsakalidis, and W. Byrne, "Minimum Risk Acoustic Clustering for Multilingual Acoustic Model Combination," in ICSLP, Oct. 2000, pp. 873-876.