An empirical study on multiple LVCSR model combination by machine learning

HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Short Papers

Volumn , Issue , 2004, Pages 13-16

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

^a KYOTO UNIVERSITY   (Japan)

^b SONY CORPORATION   (Japan)

^c TOYOHASHI UNIVERSITY OF TECHNOLOGY   (Japan)

^d UNIVERSITY OF YAMANASHI   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

EMPIRICAL STUDIES; ERROR REDUCTION; MACHINE LEARNING TECHNIQUES; MODEL COMBINATION; MULTIPLE LVCSR MODELS; SINGLE MODELS; VOTING SCHEMES; WORD RECOGNITION;

MACHINE LEARNING;

EID: 77950347836     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. G. Evermann and P. Woodland. 2000. Posterior probability decoding, confidence estimation and system combination. In Proc. NIST Speech Transcription Workshop.
2. J. G. Fiscus. 1997. A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER). In Proc. ASRU, pages 347–354.
3. K. Itou et al. 1998. The design of the newspaper-based Japanese large vocabulary continuous speech recognition corpus. In Proc. 5th ICSLP, pages 3261–3264.
4. A. Kai, Y. Hirose, and S. Nakagawa. 1998. Dealing with out-of-vocabulary words and speech disfluencies in an n-gram based speech understanding system. In Proc. 5th ICSLP, pages 2427–2430.
5. T. Kawahara et al. 1998. Sharable software repository for Japanese large vocabulary continuous speech recognition. In Proc. 5th ICSLP, pages 3257–3260.
6. T. Kemp and T. Schaaf. 1997. Estimating confidence using word lattices. In Proc. 5th Eurospeech, pages 827–830.
7. S. Nakagawa and K. Yamamoto. 1996. Evaluation of segmental unit input HMM. In Proc. 21st ICASSP, pages 439–442.
8. T. Utsuro, T. Harada, H. Nishizaki, and S. Nakagawa. 2002. A confidence measure based on agreement among multiple LVCSR models — correlation between pair of acoustic models and confidence —. In Proc. 7th ICSLP, pages 701–704.
9. T. Utsuro, Y. Kodama, T. Watanabe, H. Nishizaki, and S. Nakagawa. 2003. Confidence of agreement among multiple LVCSR models and model combination by SVM. In Proc. 28th ICASSP, volume I, pages 16–19.
10. V. N. Vapnik. 1995. The Nature of Statistical Learning Theory. Springer-Verlag.