Recent innovations in speech-to-text transcription at SRI-ICSI-UW

IEEE Transactions on Audio, Speech and Language Processing

Volumn 14, Issue 5, 2006, Pages 1729-1742

  Stolcke, Andreas ^a,b,c   Chen, Barry ^b,d   Franco, Horacio ^a,e   Gadde, Venkata Ramana Rao ^e   Graciarena, Martin ^a,e   Hwang, Mei Yuh ^c   Kirchhoff, Katrin ^a,c   Mandal, Arindam ^c   Morgan, Nelson ^a,f   Lei, Xin ^c   Ng, Tim ^e,f   Ostendorf, Mari ^a,c   Sönmez, Kemal ^a,e   Venkataraman, Anand ^e   Vergyri, Dimitra ^a,e   Wang, Wen ^a,e   Zheng, Jing ^a,e   Zhu, Qifeng ^a,c,g  

^a IEEE   (United States)

^b SRI INTERNATIONAL   (United States)

^c INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^d LAWRENCE LIVERMORE NATIONAL LABORATORY   (United States)

^e University of Washington   (United States)

^f BBN TECHNOLOGIES   (United States)

^g TEXAS INSTRUMENTS   (United States)

Author keywords

Broadcast news (BN); Conversational telephone speech (CTS); Specch to text (STT)

Indexed keywords

ACOUSTIC FEATURES; BROADCAST NEWS (BN); CONVERSATIONAL TELEPHONE SPEECH (CTS); SPEECH TO TEXT (STT);

COMPUTATIONAL COMPLEXITY; FORMAL LANGUAGES; MATHEMATICAL MODELS; REGRESSION ANALYSIS; SPEECH RECOGNITION; VOCABULARY CONTROL;

SPEECH PROCESSING;

EID: 34047270914     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2006.879807     Document Type: Article

References (53)

1. Y. Liu, E. Shriberg, A. Stolcke, D. Hillard, M. Ostendorf, and M. Harper, "Enriching speech recognition with automatic detection of sentence boundaries and disfluencies," IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 5, pp. 1524-1538, Sep. 2006.
2. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," J. Acoust. Soc. Amer., vol. 87, pp. 1738-1752, Apr. 1990.
3. C. Leggetter and P. Woodland, "Maximum likelihood linear regression for speaker adaptation of HMMs," Comput. Speech Lang., vol. 9, pp. 171-186, 1995.
4. D. Vergyri, A. Stolcke, V. R. R. Gadde, L. Ferrer, and E. Shriberg, "Prosodic knowledge sources for automatic speech recognition," in Proc. IEEE Conf. Acoust., Speech, Signal Process., vol. 1, Hong Kong, China, Apr. 2003, pp. 208-211.
5. S. Wegmann, D. McAllaster, J. Orloff, and B. Peskin, "Speaker normalization on conversational telephone speech," in Proc. IEEE Conf. Acoust., Speech. Signal Process., vol. 1, Atlanta, GA, May 1996, pp. 339-341.
6. N. Kumar, "Investigation of silicon-auditory models and generalization of linear discriminant analysis for improved speech recognition," Ph.D. dissertation, Johns Hopkins Univ., Baltimore, MD, 1997.
7. M. J. Gales, "Maximum likelihood multiple subspace projections for hidden Markov models," IEEE Trans. Speech Audio Process., vol. 10, no. 2, pp. 37-17, Feb. 2002.
8. H. Jin, S. Matsoukas, R. Schwartz, and F. Kubala, "Fast robust inverse transform SAT and multi-stage adaptation," in Proc. DARPA Broadcast News Transcription and Understanding Workshop, Lansdowne, VA, Feb. 1998, pp. 105-109.
9. D. Povey and P. C. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. IEEE Conf. Acoust., Speech, Signal Process., vol. 1, Orlando, FL, May 2002, pp. 105-108.
10. I. Bulyko, M. Ostendorf, and A. Stolcke, "Getting more mileage from web text sources for conversational speech language modeling using class-dependent mixtures," in Proc. HLT-NAACL, Conf. North Amer. Chap. Assoc. Comput. Ling., vol. 2, M. Hearst and M. Ostendorf, Eds., Edmonton, AB, Canada, Mar. 2003, pp. 7-9.
11. M. Graciarena, H. Franco, J. Zheng, D. Vergyri, and A. Stolcke, "Voicing feature integration in SRI's Decipher LVCSR system," in Proc. IEEE Conf. Acoust., Speech, Signal Process., vol. 1, Montreal, QC, Canada, May 2004, pp. 921-924.
12. B. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," J. Acoust. Soc. Amer., vol. 55, pp. 1304-1312, 1974.
13. H. Hermansky and N. Morgan, "RASTA processing of speech," IEEE Trans. Speech Audio Process., vol. 2, no. 4, pp. 578-589, Oct. 1994.
14. H. Hermansky and S. Sharma, "Temporal patterns (TRAPs) in ASR of noisy speech," in Proc. IEEE Conf. Acoust., Speech, Signal Process., vol. 2, Phoenix, AZ, Mar. 1999, pp. 289-292.
15. H. Bourlard and C. Wellekens, "Multilayer perceptrons and automatic speech recognition," in Proc. 1st Int. Conf. Neural Netw., vol. IV, San Diego, CA, 1987, pp. 407-416.
16. H. Misra, H. Bourlard, and V. Tyagi, "New entropy based combination rules in HMM/ANN multi-stream ASR," in Proc. IEEE Conf. Acoust., Speech. Signal Process., vol. 2, Hong Kong, Apr. 2003, pp. 741-744.
17. B. Y. Chen, "Learning discriminant narrow-band temporal patterns for automatic recognition of conversational telephone speech," Ph.D. dissertation, Univ. California, Berkeley, 2005.
18. Q. Zhu, A. Stolcke, B. Y. Chen, and N. Morgan, "Using MLP features in SRI's conversational speech recognition system," in Proc. 9th Eur. Conf. Speech Commun. Technol., Lisbon, Portugal, Sep. 2005, pp. 2141-2144.
19. S. Furui, "Cepstral analysis technique for automatic speaker verification," IEEE Trans. Acoust., Speech. Signal Process., vol. ASSP-29, no. 2, pp. 254-272, Apr. 1981.
20. J. L. Gauvain, G. Adda, L. Lamel, and M. Adda-Decker, "Transcribing broadcast news: The LIMSI Nov96 Hub4 system," in Proc. DARPA Speech Recognition Workshop, Chantilly, VA, Feb. 1997, pp. 56-63.
21. V. R. R. Gadde, A. Stolcke, D. Vergyri, J. Zheng, K. Sonmez, and A. Venkataraman, "Building an ASR system for noisy environments: SRI's 2001 SPINE evaluation system," in Proc. Int. Conf. Spoken Lang. Process., vol. 3, J. H. L. Hansen and B. Pellom, Eds., Denver, CO, Sep. 2002, pp. 1577-1580.
22. V. R. Gadde, K. Sonmez, and H. Franco, "Multirate ASR models for phone-class dependent n-best list rescoring," in Proc. IEEE Workshop Speech Recognition and Understanding, San Juan, PR, Nov. 2005, pp. 265-269.
23. L. R. Bahl, P. F. Brown, P. V. de Souza, and R. L. Mercer, "Maximum mutual information estimation of hidden Markov model parameters for speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech. Signal Process., vol. 1, Tokyo, Japan, Apr. 1986, pp. 49-52.
24. P. C. Woodland and D. Povey, "Large scale discriminative training of hidden Markov models of speech recognition," Comput. Speech Lang., vol. 16, pp. 25-47, 2002.
25. J. Huang, B. Kingsbury, L. Mangu, G. Saon, R. Sarikaya, and G. Zweig, :. "Improvements to the IBM Hub-5E system," in Proc. NIST Rich Transcription Workshop, Vienna, VA, May 2002.
26. M. Mohri, "Finite-state transducers in language and speech processing," Comput. Ling., vol. 23, pp. 269-311, 1997.
27. A. Ljolje, F. Pereira, and M. Riley, "Efficient general lattice generation and rescoring," in Proc. 6th Eur. Conf. Speech Commun. Technol., vol. 3, Budapest, Hungary, Sep. 1999, pp. 1251-1254.
28. L. Mangu, E. Brill, and A. Stolcke, "Finding consensus in speech recognition: Word error minimization and other applications of confusion networks," Comput. Speech Lang., vol. 14, no. 4, pp. 373-400, 2000.
29. G. Evermann and P. Woodland, "Posterior probability decoding, confidence estimation, and system combination," in Proc. NIST Speech Transcription Workshop, College Park, MD, May 2000.
30. A. Mandal, M. Ostendorf, and A. Stolcke, "Leveraging speaker-dependent variation of adaptation," in Proc. 9th Eur. Conf. Speech Commun. Technol., Lisbon, Portugal, Sep. 2005, pp. 1793-1796.
31. C. J. Leggetter and P. C. Woodland, "Flexible speaker adaptation using maximum likelihood linear regression," in Proc. ARPA Spoken Lang. Technol. Workshop, 1995, pp. 104-109.
32. M. J. Gales, "The generation and use of regression class trees for MLLR adaptation," Cambridge Univ., Cambridge, U.K., Tech. Rep. CUED/F-INFENG/TR263, 1996.
33. W. Wang and M. Harper, "The SuperARV language model: Investigating the effectiveness of tightly integrating multiple knowledge sources," in Proc. Conf. Empirical Methods Natural Language Process., 2002, pp. 238-247.
34. H. Maruyama, "Structural disambiguation with constraints propagation," in Proc. 28th Annu. Meeting Assoc. Comput. Ling., Pittsburgh, PA, Jun. 1990, pp. 31-38.
35. W. Wang, "Statistical parsing and language modeling based on constraint dependency grammar," Ph.D. dissertation, Purdue Univ., West Lafayette, IN, 2003.
36. W. Wang, M. P. Harper, and A. Stolcke, "The robustness of an almost-parsing language model given errorful training data," in Proc. IEEE Conf. Acoust., Speech, Signal Process., vol. 1, Hong Kong, China, Apr. 2003, pp. 240-243.
37. W. Wang, A. Stolcke, and M. P. Harper, "The use of a linguistically motivated language model in conversational speech recognition," in Proc. IEEE Conf. Acoust., Speech, Signal Process., vol. 1, Montreal, QC, Canada, May 2004, pp. 261-264.
38. S. F. Chen and J. Goodman, "An empirical study of smoothing techniques for language modeling," Computer Science Group, Harvard Univ., Cambridge, MA, Tech. Rep. TR-10-98, 1998.
39. A. Venkataraman and W. Wang, "Techniques for effective vocabulary selection," in Proc. 8th Eur. Conf. Speech Commun. Technol., Geneva, Switzerland, Sep. 2003, pp. 245-248.
40. M. J. F. Gales, D. Y. Kim, P. C. Woodland, H. Y. Chan, D. Mrva, R. Sinha, and S. E. Tranter, "Progress in the CU-HTK broadcast news transcription system," IEEE Trans. Audio, Speech. Lang. Process., vol. 14, no. 5, pp. 1511-1523, Sep. 2006.
41. A. Venkataraman, A. Stolcke, W. Wang, D. Vergyri, V. R. R. Gadde, and J. Zheng, "An efficient repair procedure for quick transcriptions," in Proc. Int. Conf. Spoken Language Process., S. H. Kim and D. H. Youn, Eds., Jeju Island, Korea, Oct. 2004, pp. 1961-1964.
42. S. Young, J. Odell, and P. Woodland, "Tree-based state tying for high accuracy acoustic modeling," in Proc. ARPA Workshop Human language, 1994, pp. 307-312.
43. P. Woodland, C. Leggetter, J. Odell, V. Valtchev, and S. Young, "The 1994 HTK large vocabulary speech recognition system," in Proc. ICASSP, Detroit, MI, 1995, pp. 73-76.
44. K. Kirchhoff et al., "Novel approaches to Arabic speech recognition-Final report from the JHU Summer Workshop 2002," Johns Hopkins Univ., Baltimore, MD, Tech. Rep., 2002.
45. J. Bilmes and K. Kirchhoff, "Factored language models and generalized parallel backoff," in Proc. HLT/NACCL, 2003, pp. 4-6.
46. K. Duh and K. Kirchhoff, "Automatic learning of language model structure," in Proc. 20th Int. Conf. Comput. Ling. (COUNG), 2004, pp. 148-154.
47. D. Vergyri, K. Kirchhoff, K. Duh, and A. Stolcke, "Morphology-based language modeling for Arabic speech recognition," in Proc. ICSLP, 2004, pp. 2245-2248.
48. K. Darwish, "Building a shallow Arabic morphological analyzer in one day," in Proc. ACL Workshop Computational Approaches to Semitic Languages, Philadelphia, PA, 2002, pp. 47-54.
49. M. Hwang, X. Lei, T. Ng, M. Ostendorf, A. Stolcke, W. Wang, J. Zheng, and V. Gadde, "Porting Decipher from English to Mandarin," presented at the NIST RT-04 EARS Fall Workshop 2004. Elect. Eng. Dept., Univ. Washington, Tech. Rep. UWEETR-2006-0013, Seattle, WA.
50. W. Jin, "Chinese segmentation and its diambiguation," New Mexico State Univ., Las Cruces, NM, Tech. Rep. MCCS-92-227, 1992.
51. T. Ng, M. Ostendorf, M.-Y. Hwang, M. Siu, I. Bulyko, and X. Lei, "Webdata augmented language models for Mandarin conversational speech recognition," in Proc. IEEE Conf. Acoust., Speech, Signal Process., vol. 1, Philadelphia, PA, Mar. 2005, pp. 589-593.
52. C. J. Chen, R. A. Gopinath, M. D. Monkowski, M. A. Picheny, and K. Shen, "New methods in continuous Mandarin speech recognition," in Proc. 5th Eur. Conf. Speech Commun. Technol., vol. 3, G. Kokkinakis, N. Fakotakis, and E. Dermatas, Eds., Rhodes, Greece, Sep. 1997, pp. 1543-1546.
53. M. K. Sönmez, L. Heck, M. Weintraub, and E. Shriberg, "A lognormal tied mixture model of pitch for prosody-based speaker recognition," in Proc. 5th Eur. Conf. Speech Commun. Technol., G. Kokkinakis, N. Fakotakis, and E. Dermatas, Eds., Rhodes, Greece, Sep. 1997, pp. 1391-1394.