Speech recognition with flat direct models

IEEE Journal on Selected Topics in Signal Processing

Volumn 4, Issue 6, 2010, Pages 994-1006

  Nguyen, Patrick ^a   Heigold, Georg ^b   Zweig, Geoffrey ^a  

^a MICROSOFT RESEARCH   (United States)

^b GOOGLE INC   (United States)

Author keywords

Direct model; features; log linear model; maximum mutual information (MMI); speech recognition

Indexed keywords

ACOUSTIC DETECTION; AUDIO SIGNAL; DIRECT MODEL; DIRECT MODELING; FEATURES; INHERENT STRUCTURES; KEY PROBLEMS; LINEAR MODELING; LOGLINEAR MODEL; MARKOV ASSUMPTIONS; MARKOV MODEL; MAXIMUM MUTUAL INFORMATION; MUTUAL INFORMATIONS; SENTENCE ERRORS; TEMPLATE-BASED;

FEATURE EXTRACTION; HIDDEN MARKOV MODELS; REGRESSION ANALYSIS; STEREOPHONIC BROADCASTING; TELEPHONE SETS;

SPEECH RECOGNITION;

EID: 78649280264     PISSN: 19324553     EISSN: None     Source Type: Journal    
DOI: 10.1109/JSTSP.2010.2080812     Document Type: Article

References (25)

1. S. Chen, B. Kingsbury, L. Mangu, D. Povey, G. Saon, H. Soltau, and G. Zweig, "Advances in speech transcription at IBM under the DARPA EARS program," IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 5, pp. 1596-1608, Sep. 2006.
2. M. Gales, D. Kim, P. Woodland, H. Chan, D. Mrva, R. Sinha, and S. Tranter, "Progress in the CU-HTK broadcast news transcription system," IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 5, pp. 1513-1525, Sep. 2006. (Pubitemid 46547578)
3. S. Matsoukas, J.-L. Gauvain, G. Adda, T. Colhurst, C.-L. Kao, O. Kim-ball, L. Lamel, F. Lefevre, J. Ma, J. Makhoul, L. Nguyen, R. Prasad, R. Schwartz, H. Schwenk, and B. Xiang, "Advances in transcription of broadcast news and conversational telephone speech within the combined EARS BBN/LIMSI system," IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 5, pp. 1541-1556, Sep. 2006.
4. M. Ostendorf, "Moving beyond the 'beads-on-a-string' model of speech," in Proc. IEEE ASRU Workshop, 1999, pp. 79-84.
5. B. Y. Chen, Q. Zhu, and N. Morgan, "Learning long-term temporal features in LVCSR using neural networks," in Proc. ICSLP, 2004.
6. H. Hermansky and S. Sharma, "Temporal patterns (TRAPS) in ASR of noisy speech," in Proc. ICASSP, 1999, pp. 289-292.
7. W. D. Wachter, K. Demuynck, D. V. Compernolle, and P. Wambacq, "Data driven example based continuous speech recognition," in Proc. Eurospeech, 2003, pp. 1133-1136.
8. M. De Wachter, M. Matton, K. Demuynck, P. Wambacq, R. Cools, and D. Van Compernolle, "Template-based continuous speech recognition," IEEE Trans. Audio, Speech, Lang. Process., vol. 15, no. 4, pp. 1377-1390, May 2007.
9. A. Acero, N. Bernstein, R. Chambers, Y. Ju, X. Li, J. Odell, P. Nguyen, O. Scholz, and G. Zweig, "Live search for mobile: Web services by voice on the cellphone," in Proc. ICASSP, 2007, pp. 5256-5259.
10. [Online]. Available: http://www.tellme.com/you
11. [Online]. Available: http://vlingo.com
12. [Online]. Available: http://www.google.com/mobile/apple/app.html
13. [Online]. Available: http://mobile.yahoo.com/onesearch
14. H.-K. J. Kuo and Y. Gao, "Maximum entropy direct models for speech recognition," in Proc. ASRU, 2003.
15. G. Heigold, G. Zweig, X. Li, and P. Nguyen, "A flat direct model for speech recognition," in Proc. ICASSP, 2009, pp. 3861-3864.
16. G. Zweig and P. Nguyen, "Maximum mutual information multiphone units in direct modeling," in Proc. Interspeech, 2009.
17. A. Gunawardana, M. Mahajan, A. Acero, and J. C. Platt, "Hidden conditional random fields for phone classification," in Proc. Interspeech, 2005.
18. S. Chen and R. Rosenfeld, "A survey of smoothing techniques for ME models," IEEE Trans. Speech Audio Process., vol. 8, no. 1, pp. 37-50, Jan. 2000.
19. M. Reidmiller, Rprop\Description and implementation details Univ. of Karlsruhe, Jan. 1994, Tech. Rep.
20. B. Roark, M. Saraclar, M. Collins, and M. Johnson, "Discriminative language modeling with conditional random fields and the perceptron algorithm," in Proc. ACL, 2004.
21. V. Maier and R. Moore, "An investigation into a simulation of episodic memory for automatic speech recognition," in Proc. Interspeech, Sep. 2005.
22. J. R. Bellegarda, "A multispan language modeling framework for large vocabulary speech recognition," IEEE Trans. Speech Audio Process., vol. 6, no. 5, pp. 456-467, 1998.
23. A. Ganapathiraju, J. Hamaker, J. Picone, M. Ordowski, and G. Dod-dington, "Syllable-based large vocabulary continuous speech recognition," IEEE Trans. Speech and Audio Processing, vol. 9, no. 4, pp. 358-366, May 2001.
24. M. Bacchiani, M. Ostendorf, Y. Sagisaka, and K. Paliwal, "Design of a speech recognition system based on acoustically derived segmental units," in Proc. ICASSP, 1996, pp. 443-446.
25. R. Singh, B. Raj, and R. Stern, "Automatic generation of subword units for speech recognition systems," IEEE Trans. Speech and Audio Processing, vol. 10, no. 2, pp. 89-99, Feb. 2002