A comparative study of discriminative methods for reranking LVCSR N-best hypotheses in domain adaptation and generalization

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

Volumn 1, Issue , 2006, Pages

  Zhou, Zhengyu ^b   Gao, Jianfeng ^a   Soong, Frank K ^a   Meng, Helen ^b  

^a MICROSOFT RESEARCH   (United States)

^b CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; COMPUTATIONAL COMPLEXITY; ERROR ANALYSIS; OPTIMIZATION; SUPPORT VECTOR MACHINES;

DISCRIMINATIVE METHODS; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNIZER (LVCSR); MANDARIN DICTATION SPEECH;

SPEECH RECOGNITION;

EID: 33947677739     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. B. Roark, M. Saraclar, and M. Collins, "Corrective language modeling for large vocabulary ASR with the perceptron algorithm", Proc, ICASSP, 2004.
2. R. Zhang, and A.I. Rudnicky, "Apply N-best list re-ranking to acoustic model combinations of Boosting Training", Proc. ICSLP, 2004.
3. thth Hub-5 Conversational Speech Recognition Workshop, 1998.
4. C. Meyer, "Utterance-level boosting of HMM speech recognizers", Proc. ICASSP, 2002.
5. V. Goel and W. Byrne, "Minimum bayes-risk automatic speech recognition", Computer Speech and Language, 14(2), pp. 115-135, 2000.
6. R.E. Schapire, Y. Freund, P. Bartlett, and W.S. Lee, "Boosting the margin: A new explanation for the effectiveness of voting methods", The Annals of Statistics, 26(5), pp. 1651-1686, Oct. 1998.
7. M. Collins, "Discriminative reranking for natural language parsing", Proc. ICML, 2000.
8. H. Suzuki, J. Gao, "A comparative study on language model adaptation techniques using new evaluation metrics", Proc. HLT/EMNLP, 2005.
9. M. Collins, "Discriminative training methods for hidden markov models: theory and experiments with perceptron Algorithms", Proc. EMNLP, 2002
10. T. Joachims, "Optimizing search engines using clickthrough data", Proc. ACM, 2002.
11. T. Joachims, Making large-scale SVM learning practical. advances in kernel methods - support vector learning, MIT-Press, 1999.
12. J. Gao, H. Yu, W. Yuan and P. Xu, "Minimum sample risk methods for language modeling", Proc. HLT/EMNLP 2005.