Web-data augmented language models for Mandarin conversational speech recognition

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

Volumn I, Issue , 2005, Pages 589-592

  Ng, Tim ^a,b   Ostendorf, Mari ^a   Hwang, Mei Yuh ^a   Siu, Manhung ^b   Bulyko, Ivan ^a   Lei, Xin ^a  

^a UNIVERSITY OF WASHINGTON   (United States)

^b HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGY   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

DATA PROCESSING; ERROR ANALYSIS; FORMAL LANGUAGES; WORLD WIDE WEB;

LANGUAGE MODELS; MANDARIN TELEPHONE CONVERSATIONS; PERPLEXITY; WEB DATA;

SPEECH RECOGNITION;

EID: 29144436747     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2005.1415182     Document Type: Conference Paper

References (12)

1. A. Berger and R. Miller, "Just-in-time language modeling," in Proc. ICASSP, 1998, pp. 11:705-708.
2. X. Zhu and R. Rosenfeld, "Improving trigram language modeling with the World Wide Web," in Proc. ICASSP, 2001, pp. 1:533-536.
3. I. Bulyko, M. Ostendorf, and A. Stolcke, "Getting more mileage from web text sources for conversational speech language modeling using class-dependent mixtures," in Proc. HLT/NAACL, 2003, pp. 7-9.
4. W. Jin, "A case study: Chinese segmentation and its disambiguation," Tech. Rep. MCCS-92-227, New Mexico State University, Las Cruces, 1992.
5. Stolcke et al., A., "Speech-to-text research at SRI-ICSI-UW," in NIST RT-03 Workshop, 2003.
6. IP. C. Woodland and S. J. Young, "The HTK tied-state continuous speech recogniser," in Proc. Eurospeech, 1993, vol. 3, pp. 2207-2210.
7. Hwang et al., M.-Y., "Predicting unseen triphones with senones," in IEEE Trans. on Speech and Audio Processing, 1996, vol. 4, pp. 412-419.
8. Hwang et al., M., "Progress on Mandarin conversational telphone speech recognition," to appear in ISCSLP, 2004.
9. D. Klakow, "Selecting articles from the language model training corpus," in Proc. ICASSP, 2000, pp. III:1695-1698.
10. Liu et al., F., "IBM Switchboard progress and evaluation site report," in LVCSR Workshop, Gaithersburg, MD, 1995, NIST.
11. Kneser et al., R., "Language model adaptation using dynamic marginals," in Proc. Eurospeech, 1997, pp. 4:1971-1974.
12. L. Mangu, Personal Communication.