An unsupervised speaker adaptation method for lecture-style spontaneous speech recognition using multiple recognition systems

IEICE Transactions on Information and Systems

Volumn E88-D, Issue 3, 2005, Pages 463-470

  Nakagawa, Seiichi ^a   Watanabe, Tomohiro ^a   Nishizaki, Hiromitsu ^b   Utsuro, Takehito ^c  

^a TOYOHASHI UNIVERSITY OF TECHNOLOGY   (Japan)

^b UNIVERSITY OF YAMANASHI   (Japan)

^c KYOTO UNIVERSITY   (Japan)

Author keywords

Confidence measure; Multiple LVCSR models; Spontaneous speech recognition; Unsupervised speaker adaptation

Indexed keywords

ADAPTIVE SYSTEMS; SPEECH PROCESSING;

CONFIDENCE MEASURE; MULTIPLE LVCSR MODELS; SPONTANEOUS SPEECH RECOGNITION; UNSUPERVIZED SPEAKER ADAPTATION;

SPEECH RECOGNITION;

EID: 24144432267     PISSN: 09168532     EISSN: None     Source Type: Journal    
DOI: 10.1093/ietisy/e88-d.3.463     Document Type: Article

References (17)

1. T. Kemp and T. Schaaf, "Estimating confidence using word lattices," Proc. EUROSPEECH'97, pp.827-830, 1997.
2. T. Utsuro, H. Nishizaki, Y. Kodama, and S. Nakagawa, "Estimating high-confidence portions based on agreement among output of multiple LVCSR models," Syst. Comput. in Japan, vol.35, no.7, pp.33-39, 2004.
3. W. Zhang and S. Nakagawa, "Continuous speech recognition using an on-line speaker adaptation method based on automatic speaker clustering," IEICE Trans. Inf. & Syst., vol.E86-D, no.3, pp.188-196, March 2003.
4. T. Kemp and A. Waibel, "Unsupervised training of a speech recognizer: Recent experiments," Proc. EUROSPEECH'99, pp.2725-2728, 1999.
5. J. Ogata and Y. Ariki, "Unsupervised acoustic model adaptation based on phoneme error minimization," Proc. 7th ICSLP, pp. 1429-1432, 2002.
6. S. Nakagawa and Y. Tsurumi, "An supervised speaker adaptation method for continuous parameter HMM by using maximum a posteriori probability estimation and recognition results," IEICE Trans. Inf. & Syst (Japanese Edition), vol.J78-D-II, no.2, pp.188-196, Feb. 1995.
7. T. Yokoyama, T. Shinozaki, K. Iwano, and S. Furui, "Unsupervised batch-type topic adaptation for language models," ASJ Spring Conference Record, 3-4-1, pp.129-130, 2003.
8. T. Kawahara, T. Kobayashi, K. Takeda, N. Minematsu, K. Itoh, M. Yamamoto, A. Yamada, T. Utsuro, and K. Shikano, "Sharable software repository for Japanese large vocabulary continuous speech recognition," Proc. 5th ICSLP, pp.763-766, 1998.
9. A. Kai, Y. Hirose, and S. Nakagawa, "Dealing with out-of-cocabulary words and speech disfluencies in an N-gram based speech understanding system," Proc. 5th ICSLP, pp.2427-2430, 1998.
10. N. Kitaoka, N. Takahashi, and S. Nakagawa, "Large vocabulary continuous speech recognition using linear lexicon speaker with n-best approximation and tree lexicon search with 1-best approximation," IEICE Trans. Inf. & Syst. (Japanese Edition), vol.J87-D-II, no.3, pp.799-807, March 2004.
11. M. Moroto, K. Yamamoto, and H. Matsumoto, "An improvement of syllabic models in large vocabulary continuous speech recognition," ASJ Spring Conference Record, 3-1-3, pp.95-96, 2001.
12. S. Nakagawa and K. Yamamoto, "Evaluation of segmental unit input HMM," Proc. 21th ICASSP, pp.439-442, 1996.
13. T. Kawahara, H. Nanjo, T. Shinozaki, and S. Furui, "Benchmark test for speech recognition using the Corpus of Spontaneous Japanese," Proc. ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition, pp.135-138, 2003.
14. K. Itoh, M. Yamamoto, K. Takeda, T. Takezawa, T. Matsuoka, T. Kobayashi, K. Shikano, and S. Itahashi, "JNAS: Japanese speech corpus for large vocabulary continuous speech recognition research," J. Acoust. Soc. Jpn. (E), vol.20, no.3, pp.199-206, March 1999.
15. O. Segawa, K. Takeda, and F. Itakura, "Continuous speech recognition without end-point detection," IEEJ Trans. EIS, vol.124-C, no.5, pp.1121-1126, 1997.
16. A. Lee, K. Shikano, and T. Kawahara, "Real-time word confidence scoring using local posterior probabilities on tree trellis search," Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing, pp.I-793-796, May 2004.
17. S. Nakagawa and T. Koshikawa, "Speaker adaptation for continuous parameter HMM using maximum a posteriori probability estimation," J. Acoust. Soc. Jpn., vol.49, no. 10, pp.721-728, March 1993.