A discriminative model for continuous speech recognition based on weighted finite state transducers

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2010, Pages 4922-4925

  Watanabe, Shinji ^a   Hori, Takaaki ^a   McDermott, Erik ^a   Nakamura, Atsushi ^a  

^a Nippon Telegraph and Telephone Corporation   (Japan)

Author keywords

Averaged perceptron; Discriminative model; Loglinear model; Parameter optimization in a decoding graph; Speech recognition; Weighted finite state transducer

Indexed keywords

COMPUTATIONAL LINGUISTICS; DECODING; MAXIMUM LIKELIHOOD; SOURCE SEPARATION; TRANSDUCERS;

ACOUSTICS MODEL; AVERAGED PERCEPTRON; DISCRIMINATIVE MODELS; KNOWLEDGE SOURCES; LANGUAGE MODEL; LOGLINEAR MODEL; PARAMETER OPTIMIZATION; PARAMETER OPTIMIZATION IN A DECODING GRAPH; SPEECH MODELS; WEIGHTED FINITE-STATE TRANSDUCERS;

SPEECH RECOGNITION;

EID: 78049374440     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2010.5495096     Document Type: Conference Paper

References (13)

1. M. Mohri, F. Pereira, and M. Riley, "Weighted finite-state transducers in speech recognition," in Proc. ASR2000, 2000, pp. 97-106.
2. T. Hori, C. Hori, Y. Minami, and A. Nakamura, "Efficient WFST-based one-pass decoding with on-the-fly hypothesis rescoring in extremely large vocabulary continuous speech recognition," IEEE Transactions on Audio, Speech, and Language Processing, vol. 15, no. 4, pp. 1352-1365, 2007.
3. S.S. Lin and F. Yvon, "Discriminative training of finite state decoding graphs," in Proc. Interspeech'05, 2005, pp. 733-736.
4. H.K.J. Kuo, B. Kingsbury, and G Zweig, "Discriminative training of decoding graphs for large vocabulary continuous speech recognition," in ICASSP'07, 2007, vol. 4, pp. 45-48.
5. D. Povey and P. C. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. ICASSP'02, 2002, vol. 1, pp. 13-17.
6. E. McDermott, T.J. Hazen, J. Le Roux, A. Nakamura, and S. Katagiri, "Discriminative training for large-vocabulary speech recognition using minimum classification error," IEEE Transactions on Audio, Speech, and Language Processing, vol. 15, no. 1, pp. 203-223, 2007.
7. F. Sha and L. K. Saul, "Comparison of large margin training to other discriminative methods for phonetic recognition by hidden Markov models," in ICASSP'07, 2007, vol. 4, pp. 313-316.
8. A. Gunawardana, M.Mahajan, A. Acero, and J. C. Platt, "Hidden conditional random fields for phone classification," in Proc. Interspeech'05, 2005, pp. 1117-1120.
9. H.K.J. Kuo and Y Gao, "Maximum entropy direct models for speech recognition," IEEE Transactions on Audio, Speech, and Language Processing, vol. 14, no. 3, pp. 873-881, 2006.
10. B. Roark, M. Saraclar, M. Collins, and M. Johnson, "Discriminative language modeling with conditional random fields and the perceptron algorithm," in Proc. ACL'04, 2004.
11. T. Oba, T. Hori, and A. Nakamura, "A study of efficient discriminative word sequences for reranking of recognition results based on n-gram counts," in Proc. Interspeech'07, 2007, pp. 1753-1756.
12. G. Heigold, G. Zweig, X. Li, and P. Nguyen, "A flat direct model for speech recognition," in Proc. ICASSP'09, 2009, pp. 3861-3863.
13. E. McDermott and S. Katagiri, "String-level MCE for continuous phoneme recognition," in Proc. Eurospeech, 1997, pp. 123-126.