A combined punctuation generation and speech recognition system and its performance enhancement using prosody

Speech Communication

Volumn 41, Issue 4, 2003, Pages 563-577

  Kim, Ji Hwan ^a,b   Woodland, Philip C ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^b LG Electronics Inc   (South Korea)

Author keywords

Classification And Regression Tree (CART); N best rescoring; Prosody; Punctuation generation; Speech recognition

Indexed keywords

ERROR ANALYSIS; REGRESSION ANALYSIS; SPEECH RECOGNITION;

PUNCTUATION GENERATION;

SPEECH COMMUNICATION;

EID: 0242552344     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(03)00049-9     Document Type: Article

References (25)

1. Abney S. Chunks and dependencies: bringing processing evidence to bear on syntax. Comput. Linguistics Foundat. Linguistic Theor. 1995;145-164.
2. Beeferman, D., Berger, A., Lafferty, J., 1998. Cyberpunc: a lightweight punctuation annotation system for speech. In: Proc. ICASSP. Seattle, pp. 689-692.
3. Breiman L., Friedman J., Olshen R., Stone C. Classification and Regression Trees. 1983;Wadsworth and Brooks.
4. Chen, C., 1999. Speech recognition with automatic punctuation. In: Proc. Eurospeech. Budapest. pp. 447-450.
5. Fach, M., 1999. A comparison between syntactic and prosodic phrasing. In: Proc. Eurospeech. Budapest. pp. 527-530.
6. Gotoh, Y., Renals, S., 2000. Sentence boundary detection in broadcast speech transcripts. In: Proc. ISCA ITRW ASR. Paris. pp. 228-235.
7. Grishman, R., Sundheim, B., 1995. Design of the MUC-6 evaluation. In: Proc. 6th Message Understanding Conference. pp. 1-11.
8. Hakkani-Tur, D., Tur, G., Stolcke, A., Shriberg, E., 1999. Combining words and prosody for information extraction from speech. In: Proc. Eurospeech. Budapest. pp. 1991-1994.
9. Leggetter C., Woodland P. Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models. Comput. Speech Language. 9:1995;171-185.
10. Makhoul, J., Kubala, F., Schwartz, R., Weischedel, R., 1999. Performance measures for information extraction. In: Proc. DARPA Broadcast News Workshop, Dulles, Virginia. pp. 249-252.
11. Niesler, T., Whittaker, E., Woodland, P., 1998. Comparison of part-of-speech and automatically derived category-based language models for speech recognition. In: Proc. ICASSP, Seattle. pp. 177-180.
12. NIST, 1998. NIST Hub-4 Information Extraction (Named Entity) Broadcast News Benchmark Test Evaluation. Available from 〈 ftp://jaguar.ncsl.nist.gov/csr98/h4iene_98_official_scores_990107/index.htm 〉.
13. Odell, J., Woodland, P., Hain, T., 1999. The CUHTK-Entropic 10 × RT broadcast news transcription system. In: Proc. DARPA Broadcast News Workshop, Dulles, Virginia. pp. 271-275.
14. Pallett, D., Fiscus, J., Garofolo, J., Martin, A., Przybocki, M., 1999. 1998 Broadcast news benchmark test results: English and non-English word error rate performance measures. In: Proc. DARPA Broadcast News Workshop, Dulles, Virginia. pp. 5-12.
15. Palmer D., Hearst M. Adaptive multilingual sentence boundary disambiguation. Comput. Linguistics. 23(2):1997;241-269.
16. Rabiner L., Juang B. Fundamentals of Speech Recognition. 1993;Prentice Hall.
17. Shaw H. Punctuate it Right! 1993;Harper-Collins.
18. Shriberg E., Bates R., Stolcke A., Taylor P., Ju-rafsky D., Ries K., Coccaro N., Martin R., Meteer M., Ess-Dykema C. Can prosody aid the automatic classification of dialog acts in conversational speech? Language Speech. 41(3-4):1998;439-487.
19. Silverman, K., Beckman, M., Pitrelli, J., Ostendorf, M., Wightman, C., Price, P., Pierrehumbert, J., Hirschberg, J., 1992. ToBI: a standard for labelling English prosody. In: Proc. ICSLP. Banff, Canada. pp. 867-870.
20. Stolcke, A., Shriberg, E., Hakkani-Tur, D., Tur, G., Rivlin, Z., Sonmez, K., 1999. Combining words and speech prosody for automatic topic segmentation. In: Proc. DARPA Broadcast News Workshop, Dulles, Virginia. pp. 61-64.
21. Taylor P., King S., Isard S., Wright H. Intonation and dialog context as constraints for speech recognition. Language Speech. 41(3-4):1998;489-508.
22. University of Chicago, 1993. The Chicago Manual of Style, 14th ed. The University of Chicago Press.
23. Woodland, P., Hain, T., Johnson, S., Niesler, T., Whittaker, E., Young, S., 1998. The 1997 HTK broadcast news transcription system. In: Proc. Broadcast News Transcription and Understanding Workshop, Lansdowne, Virginia.
24. Woodland, P., Hain, T., Moore, G., Niesler, T., Povey, D., Tuerk, A., Whittaker, E., 1999. The 1998 HTK broadcast news transcription system: development and results. In: Proc. DARPA Broadcast News Workshop, Dulles, Virginia. pp. 265-270.
25. Woodland P. The development of the HTK broadcast news transcription system: An overview. Speech Commun. 37(1-2):2002;47-67.