Speaking rate compensation based on likelihood criterion in acoustic model training and decoding

7th International Conference on Spoken Language Processing, ICSLP 2002

Volumn , Issue , 2002, Pages 2589-2592

  Okuda, Kozo ^a   Kawahara, Tatsuya ^a,b   Nakamura, Satoshi ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^b KYOTO UNIVERSITY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

DECODING; SPEECH;

ACCURACY IMPROVEMENT; ACOUSTIC MODEL; ACOUSTIC MODEL TRAININGS; COMPENSATION METHOD; DECODING PROCESS; INSERTION PENALTY; LIKELIHOOD CRITERION; SPEAKING RATE;

SPEECH RECOGNITION;

EID: 85009250844     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. S. Furui, K. Maekawa and H. Isahara, "Toward the realization of spontaneous speech recognition - introduction of a Japanese priority program and preliminary results-", Proc. ICSLP2000, vol. 3, pp. 518-521, Oct. 2000.
2. H. Nanjo, K. Kato and T. Kawahara, "Speaking rate dependent acoustic modeling for spontaneous lecture speech recognition", Proc. EUROSPEECH2001, vol. 4, pp. 2531-2534, Sep. 2001.
3. J. P. Nedel and R. M. Stern, "Duration normalization for improved recognition of spontaneous and read speech via missing feature methods", Proc. ICASSP2001, Vol. 1, pp. 313-316, 2001.
4. S. Tsuge, T. Fukada and K. Kita, "Frame-period adaptation for speaking rate robust speech recognition", Proc. ICSLP2000, vol. 3, pp. 718-721, 2000.
5. T. Shinozaki, C. Hori and S. Furui, "Towards automatic transcription of spontaneous presentations", Proc. EUROSPEECH2001, vol. 1, pp. 491-494. Sep. 2001.
6. M. Ostendorf and H. Singer, "HMM topology design using maximum likelihood successive state splitting", Computer Speech and Language, 11, 1, pp. 17-41, 1997.
7. A. Lee, T. Kawahara and S. Doshita, "An efficient two-pass search algorithm using word trellis index", Proc. ICSLP1998, vol. 5, pp. 1831-1834, 1998.