A discriminative training framework using N-best speech recognition transcriptions and scores for spoken utterance classification

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

Volumn 4, Issue , 2007, Pages 5-8

  Yaman, Sibeil ^a   Deng, Li ^b   Yu, Dong ^b   Wang, Ye Yi ^b   Acero, Alex ^b  

^a GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

^b MICROSOFT RESEARCH   (United States)

Author keywords

Automatic speech recognition; Discriminative training; Spoken utterance classification; Statistical language modeling

Indexed keywords

COMPUTER SIMULATION; DATA REDUCTION; DATABASE SYSTEMS; ERROR ANALYSIS; SEMANTICS;

AUTOMATIC SPEECH RECOGNITION; DISCRIMINATIVE TRAINING; SPOKEN UTTERANCE CLASSIFICATION; UTTERANCE CLASSIFICATION;

SPEECH RECOGNITION;

EID: 34547510837     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2007.367149     Document Type: Conference Paper

References (6)

1. H.-K, J. Kup, I. Zitpuni, E, Fosler-Lussier, E. Ammioht, and C.-H, Lee, "Discriminative training for Call classification and routing," in the Proceedings of International Conference on Speech and LanguageProcessing, Denver, Coloradp, 2002.
2. J. R. Bellegarda, "Semantic inference: A data driven solution for nl interaction," in the Proceedings of International Conference on Speech and Language Processing, Denver, Colorado, 2002.
3. Y-Y Wang, A. Acerp, and C. Chelba, "Is word error.rate a.gPPd indicator spoken language understanding?," in the Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, Virgin Islands, Dec 2003.
4. G. Riccardi and A.L. Gorin, "Stochastic language models for speech recpgnitipn and understanding," in the Proceedings of ICSLP, Sydney, Australia, 1998.
5. W. Chou, ''Discriminant-function-based minimum recognition error rate pattern-recognition approacht tp speech recognition," Proceedings of IEEE, VPI..88, np. 8, pp. 1201-1.224, August, 2000.
6. Y-Y Wang, J. Lee, and A. Acero, "SPeech utterance classification model training withput manual transcriptions," in the Proceedings of International Conference on Acoustics, Speech, and Signal Processing, Toulouse, France, 2006.