Cross-domain and cross-language portability of acoustic features estimated by multilayer perceptrons

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

Volumn 1, Issue , 2006, Pages

  Stolcke, Andreas ^a,b   Grézl, František ^b,e   Hwang, Mei Yuh ^c   Lei, Xin ^c   Morgan, Nelson ^b,d   Vergyri, Dimitra ^a  

^a SRI INTERNATIONAL   (United States)

^b INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^c UNIVERSITY OF WASHINGTON   (United States)

^d UNIVERSITY OF CALIFORNIA   (United States)

^e BRNO UNIVERSITY OF TECHNOLOGY   (Czech Republic)

Author keywords

[No Author keywords available]

Indexed keywords

MATHEMATICAL MODELS; PARAMETER ESTIMATION; SPEECH RECOGNITION; TELEPHONE SETS; VOCABULARY CONTROL;

ACOUSTIC MODELS; CROSS LANGUAGE PORTABILITY; MULTILAYER PERCEPTRONS (MLP); PHONE CLASSIFICATION;

FEATURE EXTRACTION;

EID: 33947619591     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (22)

1. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech", J. Acoust. Soc. Am., vol. 87, pp. 1738-1752, Apr. 1990.
2. H. Hermansky, D. P. W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional HMM systems", in Proc. ICASSP, pp. 1635-1638, Istanbul, June 2000.
3. H. Bourlard and N. Morgan, Connectionist Speech Recognition. A Hybrid Approach, Kluwer Academic Publishers, Boston, MA, 1993.
4. H. Hermansky and S. Sharma, "Temporal patterns (TRAPs) in ASR of noisy speech", in Proc. ICASSP, vol. 2, pp. 289-292, Phoenix, AZ, Mar. 1999.
5. N. Morgan, B. Y. Chen, Q. Zhu, and A. Stolcke, "TRAPping conversational speech: Extending TRAP/Tandem approaches to conversational telephone speech recognition", in Proc. ICASSP, vol. 1, pp. 536-539, Montreal, May 2004.
6. Q. Zhu, A. Stolcke, B. Y. Chen, and N. Morgan, "Using MLP features in SRI's conversational speech recognition system", in Proc. Interspeech, pp. 2141-2144, Lisbon, Sep. 2005.
7. Q. Zhu, B. Chen, N. Morgan, and A. Stolcke, "On using MLP features in LVCSR", in S. H. Kim and D. H. Youn, editors, Proc. ICSLP, pp. 921-924, Jeju, Korea, Oct. 2004.
8. B. Y. Chen, Q. Zhu, and N. Morgan, "Learning long-term temporal features in LVCSR using neural networks", in S. H. Kim and D. H. Youn, editors, Proc. ICSLP, Jeju, Korea, Oct. 2004.
9. H. Misra, H. Bourlard, and V. Tyagi, "New entropy based combination rules in HMM/ANN multi-stream ASR", in Proc. ICASSP, vol. 2, pp. 741-744, Hong Kong, Apr. 2003.
10. C. Leggetter and P. Woodland, "Maximum likelihood linear regression for speaker adaptation of HMMs", Computer Speech and Language, vol. 9, pp. 171-186, 1995.
11. D. Vergyri, A. Stolcke, V. R. R. Gadde, L. Ferrer, and E. Shriberg, "Prosodic knowledge sources for automatic speech recognition", in Proc. ICASSP, vol. 1, pp. 208-211, Hong Kong, Apr. 2003.
12. S. Wegmann, D. McAllaster, J. Orloff, and B. Peskin, "Speaker normalization on conversational telephone speech", in Proc. ICASSP, vol. 1, pp. 339-341, Atlanta, May 1996.
13. N. Kumar, Investigation of Silicon-Auditory Models and Generalization of Linear Discriminant Analysis for Improved Speech Recognition, PhD thesis, John Hopkins University, Baltimore, 1997.
14. M. J. Gales, "Maximum likelihood multiple subspace projections for hidden Markov models", IEEE Trans. Speech Audio Process., vol. 10, pp. 37-47, 2002.
15. H. Jin, S. Matsoukas, R. Schwartz, and F. Kubala, "Fast robust inverse transform SAT and multi-stage adaptation", in Proceedings DARPA Broadcast News Transcription and Understanding Workshop, pp. 105-109, Lansdowne, VA, Feb. 1998. Morgan Kaufmann.
16. D. Povey and P. C. Woodland, "Minimum phone error and Ismoothing for improved discriminative training", in Proc. ICASSP, vol. 1, pp. 105-108, Orlando, FL, May 2002.
17. I. Bulyko, M. Ostendorf, and A. Stolcke, "Getting more mileage from web text sources for conversational speech language modeling using class-dependent mixtures", in M. Hearst and M. Ostendorf, editors, Proc. HLT-NAACL, vol. 2, pp. 7-9, Edmonton, Alberta, Canada, Mar. 2003. Association for Computational Linguistics.
18. A. Stolcke, X. Anguera, K. Boakye, Ö. Çetin, F. Grézl, A. Janin, A. Mandal, B. Peskin, C. Wooters, and J. Zheng, "Further progress in meeting recognition: The ICSISRI Spring 2005 speech-to-text evaluation system", in Proceedings of the Rich Transcription 2005 Spring Meeting Recognition Evaluation, pp. 39-50, Edinburgh, July 2005. National Institute of Standards and Technology.
19. X. Lei, M.-Y. Hwang, and M. Ostendorf, "Incorporating tone-related MLP posteriors in the feature representation for mandarin ASR", in Proc. Interspeech, pp. 2981-2984, Lisbon, Sep. 2005.
20. M. Hwang, X. Lei, T. Ng, M. Ostendorf, A. Stolcke, W. Wang, J. Zheng, and V. Gadde, "Porting Decipher from English to Mandarin", in Proc. DARPA Rich Transcription Workshop, Palisades, NY, Nov. 2004.
21. D. Vergyri, K. Kirchhoff, R. Gadde, A. Stolcke, and J. Zheng, "Development of a conversational telephone speech recognizer for Levantine Arabic", in Proc. Interspeech, pp. 1613-1616, Lisbon, Sep. 2005.
22. D. Vergyri, K. Kirchhoff, K. Duh, and A. Stolcke, "Morphology-based language modeling for Arabic speech recognition", in S. H. Kim and D. H. Youn, editors, Proc. ICSLP, pp. 2245-2248, Jeju, Korea, Oct. 2004.