Language model and speaking rate adaptation for spontaneous presentation speech recognition

IEEE Transactions on Speech and Audio Processing

Volumn 12, Issue 4, 2004, Pages 391-400

  Nanjo, Hiroaki ^a   Kawahara, Tatsuya ^a  

^a KYOTO UNIVERSITY   (Japan)

Author keywords

Acoustic modeling; Language model adaptation; Pronunciation modeling; Speaking rate; Spontaneous speech recognition

Indexed keywords

ACOUSTICS; CONTEXT FREE GRAMMARS; DATABASE SYSTEMS; DECODING; FORMAL LANGUAGES; HUMAN COMPUTER INTERACTION; MATHEMATICAL MODELS; SPEECH SYNTHESIS;

ACOUSTIC MODELING; LANGUAGE MODEL ADAPTATION; PRONUNCIATION MODELING; SPEAKING RATES; SPONTANEOUS SPEECH RECOGNITION;

SPEECH RECOGNITION;

EID: 3042704466     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2004.828641     Document Type: Conference Paper

References (37)

1. S. Furui, "Recent advances in spontaneous speech recognition and understanding," in Proc. ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition (SSPR), 2003, pp. 1-6.
2. K. Maekawa, "Corpus of spontaneous Japanese: its design and evaluation," in Proc. ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition (SSPR), 2003, pp. 7-12.
3. T. Shinozaki and S. Furui, "Analysis on individual differences in automatic transcription of spontaneous presentations," in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), vol. 1, 2002, pp. 729-732.
4. T. Kawahara, H. Nanjo, T. Sinozaki, and S. Furui, "Benchmark test for speech recognition using the Corpus of spontaneous Japanese," in Proc. ISCA and IEEE Workshop on Spontaneous Speech Processing and Recognition (SSPR), 2003, pp. 135-138.
5. S. F. Chen, K. Seymore, and R. Rosenfeld, "Topic adaptation for language modeling using unnormalized exponential models," in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), vol. 2, 1998, pp. 681-684.
6. M. Mahajan, D. Beeferman, and X. D. Huang, "Improved topic-dependent language modeling using information retrieval techniques," in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Process. (ICASSP), vol. 1, 1999, pp. 541-544.
7. J. Zheng, H. Franco, and F. Weng, "Word-level rate of speech modeling using rate-specific phones and pronunciations," in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), 2000, pp. 1775-1778.
8. N. Morgan, E. Fosler, and N. Mirghafori, "Speech recognition using on-line estimation of speaking rate," in Proc. European Conf. Speech Communication and Technology (EUROSPEECH), 1997, pp. 2079-2082.
9. J. Nedel and R. Stern, "Duration normalization for improved recognition of spontaneous and read speech via missing feature methods," in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), vol. 1, 2001, pp. 313-316.
10. M. Richardson, M. Hwang, A. Acero, and X. D. Huang, "Improvements on speech recognition for fast talkers," in Proc. European Conf. Speech Communication and Technology (EUROSPEECH), 1999, pp. 411-414.
11. M. Finke and A. Waibel, "Speaking mode dependent pronunciation modeling in large vocabulary conversational speech recognition," in Proc. European Conf. Speech Communication and Technology (EUROSPEECH), 1997, pp. 2379-2382.
12. E. Fosler-Lussier, "Multi-level decision trees for static and dynamic pronunciation models," in Proc. European Conf. Speech Commun. & Tech. (EUROSPEECH), 1999, pp. 463-466.
13. P. R. Clarkson and R. Rosenfeld, "Statistical language modeling using the CMU-Cambridge toolkit," in Proc. European Conf. Speech Communication and Technology (EUROSPEECH), 1997, pp. 2707-2710.
14. K. Uchimoto, C. Nobata, A. Yamada, S. Sekine, and H. Isahara, "Morphological analysis of Corpus of spontaneous Japanese," in Proc. ISCA and IEEE Workshop on Spontaneous Speech Processing and Recognition (SSPR), 2003, pp. 159-162.
15. A. Lee, T. Kawahara, K. Takeda, and K. Shikano, "A new phonetic tied-mixture model for efficient decoding," in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), 2000, pp. 1269-1272.
16. A. Lee, T. Kawahara, K. Takeda, M. Mimura, A. Yamada, A. Ito, K. Itou, and K. Shikano, "Continuous speech recognition consortium - an open repository for CSR tools and models," in Proc. Int. Conf. Language Resources and Evaluation (LREC2002), 2002, pp. 1438-1441.
17. B. Peskin, M. Newman, D. McAllaster, V. Nagesha, H. Richards, S. Wegmann, M. Hunt, and L. Gillick, "Improvements in recognition of conversational telephone speech," in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), vol. 1, 1999, pp. 53-56.
18. H. Schramm and X. Aubert, "Efficient integration of multiple pronunciations in a large vocabulary decoder," in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), vol. 3, 2000, pp. 1659-1662.
19. J. M. Kessens, M. Wester, and H. Strik, "Improving the performance of a Dutch CSR by modeling within-word and cross-word pronunciation variation," Speech Commun., vol. 29, no. 2-4, pp. 193-207, 1999.
20. R. R. Sarukkai and D. H. Ballard, "Improved spontaneous dialogue recognition using dialogue and utterance triggers by adaptive probability boosting," in Proc. Int. Conf. Spoken Language Processing (ICSLP), vol. 1, Philadelphia, PA, 1996, pp. 208-211.
21. R. Iyer and M. Ostendorf, "Modeling long distance dependence in language: Topic mixtures vs. dynamic cache models," in Proc. Int. Conf. Spoken Language Processing (ICSLP), vol. 1, Philadelphia, PA, 1996, pp. 236-239.
22. P. Clarkson and A. J. Robinson, "Language model adaptation using mixtures and an exponentially decaying cache," in Proc. IEEE Int. Conf. Acoust., Speech & Signal Process. (ICASSP), vol. 2, 1997, pp. 799-802.
23. K. Kato, H. Nanjo, and T. Kawahara, "Automatic transcription of lecture speech using topic-independent language modeling," in Proc. Int. Conf. Spoken Language Processing (ICSLP), vol. 1, 2000, pp. 162-165.
24. L. Chen, J. L. Gauvain, L. Lamel, G. Adda, and M. Adda, "Using information retrieval methods for language model adaptation," in Proc. Eur. Conf. Speech Communication and Technology (EUROSPEECH), 2001, pp. 255-258.
25. T. Niesler and D. Willett, "Unsupervised language model adaptation for lecture speech transcription," in Proc. Int. Conf. Spoken Language Processing (ICSLP), Denver, CO, 2002, pp. 1413-1416.
26. T. Shinozaki and S. Furui, "Toward automatic transcription of spontaneous presentations," in Proc. European Conf. Speech Commun. & Tech. (EUROSPEECH), 2001, pp. 491-494.
27. K. Okuda, T. Kawahara, and S. Nakamura, "Speaking rate compensation based on likelihood criterion in acoustic model training and decoding," in Proc. Int. Conf. Spoken Language Processing (ICSLP), 2002, pp. 2589-2592.
28. J. P. Verhasselt and J. P. Martens, "A fast and reliable rate of speech detector," in Proc. Int. Conf. Spoken Language Processing (ICSLP), vol. 4, 1996, pp. 612-615.
29. R. Faltlhauser, T. Pfau, and G. Ruske, "On-line speaking rate estimation using gaussian mixture models," in Proc. IEEE Int. Conf. Acoust., Speech and Signal Processing (ICASSP), vol. III, 2000, pp. 1355-1358.
30. T. Pfau and G. Ruske, "Estimating the speaking rate by vowel detection," in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), vol. 2, 1998, pp. 945-948.
31. N. Morgan and E. Fosler-Lussier, "Combining multiple estimators of speaking rate," in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), vol. 2, 1998, pp. 729-732.
32. K. Hirose and K. Iwano, "Detection of prosodic word boundaries by statistical modeling of mora transitions of fundamental frequency contours and its use for continuous speech recognition," in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), vol. 3, 2000, pp. 1763-1766.
33. N. Takahashi and S. Nakagawa, "Syllable recognition using syllable-segment statistics and syllable-based HMM," in Proc. Int. Conf. Spoken Language Processing (ICSLP), 2002, pp. 2633-2636.
34. T. Kawahara, T. Munetsugu, N. Kitaoka, and S. Doshita, "Keyword and phrase spotting with heuristic language model," in Proc. Int. Conf. Spoken Language Processing (ICSLP), vol. 2, 1994, pp. 815-818.
35. A. Kai, Y. Hirose, and S. Nakagawa, "Dealing with out-of-vocabulary words and speech disfluencies in an n-gram based speech understanding system," in Proc. Int. Conf. Spoken Language Processing (ICSLP), vol. 6, 1998, pp. 2427-2430.
36. H. Nanjo, K. Kato, and T. Kawahara, "Speaking rate dependent acoustic modeling for spontaneous lecture speech recognition," in Proc. European Conf. Speech Communication and Technology (EUROSPEECH), 2001, pp. 2531-2534.
37. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Comput. Speech and Lang., vol. 9, no. 2, pp. 171-185, 1995.