Rapid transition to new spoken dialogue domains: Language model training using knowledge from previous domain applications and web text resources

9th European Conference on Speech Communication and Technology

Volumn , Issue , 2005, Pages 1873-1876

  Akbacak, Murat ^a   Gao, Yuqing ^b   Gu, Liang ^b   Kuo, Hong Kwang Jeff ^b  

^a UNIVERSITY OF COLORADO   (United States)

^b IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

SEARCH ENGINES; TEXT PROCESSING; WORD PROCESSING; WORLD WIDE WEB;

AUTOMATIC SPEECH RECOGNITION (ASR); LANGUAGE MODELS (LM); SPOKEN DIALOGUE SYSTEMS (SDS); WORD ERROR RATE (WER);

SPEECH RECOGNITION;

EID: 33745224967     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. L. Galescu, E. K. Ringger, and J. F. Allen, "Rapid Language Model Development for New Task Domains", in Proc. of the ELBA First International Conference on Language Resources and Evaluation (LREC), Granada, Spain, 1998.
2. A. Rudnicky, "Language Modeling with limited domain data", in Proc. ARPA Workshop on Spoken Language Technology, 1995.
3. I. Bulyko, et al., "Getting Mileage from Web Text Sources for Conversational Speech Language Modeling using Class-Dependent Mixtures", in Proc. HLT Conference, Edmonton, Canada, 2003.
4. R. Sarikaya, A. Gravano, Y. Gao, "Rapid Language Model Development Using External Resources For New Spoken Dialogue Domains", in Proc. ICASSP-2005.
5. P. C. Chang, L. S. Lee, "Improved Language Model Adaptation Using Existing and Derived External Resources", in Proc. Automatic Speech Recognition and Understanding (ASRU), St. Thomas, Virgin Islands, USA, 2003.
6. X. Zhu, "Improving Trigram Language Modeling with the World Wide Web", in Proc. ICASSP-2001.
7. G. D. Fabbrizio, et al., "Bootstrapping Spoken Dialogue Systems with Data Reuse", in Proc. 5th SIGdial Workshop on Discourse and Dialogue, Cambridge, MA, USA, 2004.
8. T. Rose, et al., "The Effects of Corpus Size and Homogeneity on Language Model Quality", HP Technical Report, 1997.
9. A. L. Berger, S. A. Della Pietra, V. J. Della Pietra, "A Maximum Entropy Approach to Natural Language Processing", Computational Linguistics, vol. 22, no. 1, pp. 39-71, 1996.