Discriminative rescoring based on minimization of word errors for transcribing broadcast news

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2008, Pages 1574-1577

  Kobayashi, Akio ^a   Oku, Takahiro ^a   Homma, Shinichi ^a   Sato, Shoei ^a   Imai, Toru ^a   Takagi, Tohru ^a  

^a NHK SCIENCE AND TECHNICAL RESEARCH LABORATORIES   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

BROADCAST NEWS; CONDITIONAL RANDOM FIELD; FEATURE FUNCTION; LATTICE RESCORING; NOVEL METHODS; RECOGNITION ERROR; SPONTANEOUS SPEECH; TRAINING TECHNIQUES; WEIGHTING FACTORS; WORD ERROR RATE;

ERROR DETECTION; FEATURE EXTRACTION; OPTIMIZATION; RANDOM ERRORS; SPEECH COMMUNICATION; TRANSCRIPTION;

SPEECH RECOGNITION;

EID: 84867217163     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. T. Imai, A. Kobayashi, S. Sato, S. Homma, K. Onoe, and T. Kobayakawa, "Speech recognition for subtitling Japanese live broadcasts," in Proc. ICA, vol. I, 2004, pp. 165-168.
2. D. Povey and P. C. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. ICASSP, vol. I, 2002, pp. 105-108.
3. B. Roark, M. Saraclar, and M. Collins, "Discriminative n-gram language modeling," Computer Speech and Language, vol. 21, pp. 373-392, 2007.
4. M. Collins, "Discriminative reranking for natural language parsing," in Proc. ICML, 2000, pp. 175-182.
5. Z. Zhou, J. Gao, F. Soong, and H. Meng, "A comparative study of discriminative methods for reranking LVCSR using n-best hypotheses in domain adaptation and generalization," in Proc. ICASSP, vol. I, 2006, pp. 141-144.
6. B. Roark, M. Saraclar, and M. Collins, "Corrective language modeling for large vocabulary asr with the perceptron algorithm," in Proc. ICASSP, 2004, pp. 789-792.
7. J. Lafferty, A. McCallum, and F. Pereira, "Conditional random fields: Probabilistic models for segmenting and labeling sequence data," in Proc. ICML, 2001, pp. 282-289.
8. D. Liu and J. Nocedal, "On the limited memory BFGS method for large scale optimization," Math. Programming, vol. 45, no. 3, pp. 503-528, 1989.
9. W. Macherey, L. Haferkamp, R. Schlüter, and H. Ney, "Investigations on error mimizing training criteria for discriminative training in automatic speech recognition," in Proc. Interspeech, 2005, pp. 2133-2136.
10. H. Ney, U. Essen, and R. Kneser, "On structuring probabilistic dependancies in stochastic language modeling," Computer Speech and Language, vol. 8, no. 1, pp. 1-38, 1994.
11. T. National Institute for Japanese Language, Word list by semantic principles. Dainippon-tosho, 2004.
12. M. Collins, "Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms," in Proc. EMNLP, vol. 10, 2002, pp. 1-8.
13. H. Hermansky and H. Morgan, "RASTA processing of speech," IEEE Trans. Speech and Audio, vol. 2, pp. 587-589, 1994.
14. A. Kobayashi, K. Onoe, T. Imai, and A. Ando, "Time dependent language model for broadcast news transcription and its postcorrection," in Proc. ICSLP, 1998, pp. 2435-2438.
15. L. Gillick and S. Cox, "Some statistical issues in the comparison of speech recognition algorithms," in Proc. ICASSP, 1989, pp. 532-535.