A comparative study on methods of weighted language model training for reranking LVCSR N-best hypotheses

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

Volumn , Issue , 2010, Pages 5126-5129

  Oba, Takanobu ^a   Hori, Takaaki ^a   Nakamura, Atsushi ^a  

^a NTT Communication Science Laboratories   (Japan)

Author keywords

Discriminative LM; Error correction; MERT; Reranking boost; Weighted GCLM

Indexed keywords

COMPUTATIONAL LINGUISTICS; CONTINUOUS SPEECH RECOGNITION; REGRESSION ANALYSIS; SIGNAL PROCESSING;

COMPARATIVES STUDIES; DISCRIMINATIVE LM; ERRORS CORRECTION; LANGUAGE MODEL; MINIMUM ERROR RATE TRAININGS; MODEL TRAINING; N-BEST HYPOTHESIS; RE-RANKING; RERANKING BOOST; WEIGHTED GCLM;

ERROR CORRECTION;

EID: 78049393373     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2010.5495028     Document Type: Conference Paper

References (12)

1. Brian Roark, Murat Saraclar, and Michael Collins, "Corrective language modeling for large vocabulary asr with the perceptron algorithm," in Proceedings of ICASSP, May 2004, vol. 1, pp. 749-752.
2. Brian Roark, Murat Saraclar, Michael Collins, and Mark Johnson, "Discriminative language modeling with conditional random fields and the perceptron algorithm," in Proceedings of ACL, 2004, pp. 47-54.
3. Michael Collins, Brian Roark, and Murat Saraclar, "Discriminative syntactic language modeling for speech recognition," in Proceedings of ACL, 2005, pp. 507-514.
4. Zhengyu Zhou, Jianfeng Gao, Frank K. Soong, and Helen Meng, "A comparative study of discriminative methods for reranking lvcsr n-best hypotheses in domain adaptation and generalization," in Proceedings of ICASSP, 2006, vol. 1, pp. 141-144.
5. Natasha Singh-Miller and Michael Collins, "Trigger-based language modeling using a loss-sensitive perceptron algorithm," in Proceedings of ICASSP, 2006, pp. 141-144.
6. Brian Roark, Murat Saraclar, and Michael Collins, "Discriminative ngram language modeling," Computer Speech and Language, vol. 21, no. 2, pp. 373-392, 2007.
7. Takanobu Oba, Takaaki Hori, and Atsushi Nakamura, "An approach to efficient generation of high-accuracy and compact error-corrective models for speech recognition," in Proceedings of Interspeech, 2007, pp. 1753-1756.
8. Akio Kobayashi, Takahiro Oku, Shinichi Homma, Shoei Sato, Toru Imai, and Tohru Takagi, "Discriminative rescoring based on minimization of word errors for transcribing broadcast news," in Proceedings of Interspeech, 2008, pp. 1574-1577.
9. Michael Collins and Terry Koo, "Discriminative reranking for natural language parsing," Comput. Linguist., vol. 31, no. 1, pp. 25-70, 2005.
10. Franz Josef Och, "Minimum error rate training in statistical machine translation," in Proceedings of ACL, 2003, pp. 160-167.
11. Kikuo Maekawa, Hanae Koiso, Sadaoki Furui, and Hitoshi Isahara, "Spontaneous speech corpus of japanese," in Proceedings of ICLRE, 2000, pp. 947-952.
12. Takaaki Hori and Atsushi Nakamura, "Generalized fast on-the-fly composition algorithm for wfst-based speech recognition," in Proceedings of Interspeech, 2005, pp. 284-289.