Language model adaptation for fixed phrases by amplifying partial N-gram sequences

Systems and Computers in Japan

Volumn 38, Issue 4, 2007, Pages 63-73

  Akiba, Tomoyosi ^a   Itou, Katunobu ^b,c   Fuji, Atsushi ^c,d  

^a NATIONAL INSTITUTE OF ADVANCED INDUSTRIAL SCIENCE AND TECHNOLOGY AIST   (Japan)

^b NAGOYA UNIVERSITY   (Japan)

^c JAPAN SCIENCE AND TECHNOLOGY AGENCY   (Japan)

^d UNIVERSITY OF TSUKUBA   (Japan)

Author keywords

Fixed phrases; Large vocabulary continuous speech recognition; N gram language model; Question answering (QA); Task adaptation

Indexed keywords

ADAPTIVE SYSTEMS; INFORMATION THEORY; MATHEMATICAL MODELS; PROBABILITY DISTRIBUTIONS; QUERY LANGUAGES;

FIXED PHRASES; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; N-GRAM LANGUAGE MODELS; QUESTION ANSWERING (QA); TASK ADAPTATION;

SPEECH PROCESSING;

EID: 34247374399     PISSN: 08821666     EISSN: 1520684X     Source Type: Journal    
DOI: 10.1002/scj.20142     Document Type: Article

References (22)

1. Special Issue - The performance of speech dialogue systems and current tasks. J Acoust Soc Japan 1998; 54(11). (in Japanese)
2. Akiba T, Itou K, Fujii A, Ishikawa T. Selective backoff smoothing for incorporating grammatical constraints into the N-gram language model. Proc International Conference of Spoken Language Processing, Denver 2002;2:881-884.
3. Barnett J, Anderson S, Broglio J, Singh M, Hudson R, Kuo SW. Experiments in spoken queries for document retrieval. Proc European Conference on Speech Communication and Technology, Rhodes, Greece, 1997, p 1323-1326.
4. Bellegarda JR. An overview of statistical language model adaptation. Proc Isca ITR Workshop on Adaptation Methods for Speech Recognition, Sophia-Antipolis, France, 2001.
5. Federico M. Bayesian estimation methods for N-gram language model adaptation. Proc International Conference on Spoken Language Processing, Philadelphia, 1996, p 240-243.
6. Fujii A, Itou K, Ishikawa T. Speech-driven text retrieval: Using target IR collections for statistical language model adaptation in speech recognition. In: Coden AR, Brown EQ, Srinivasan S (editors). Information retrieval techniques for speech applications (LNCS 2273). Springer; 2002. p 94-104.
7. Fukumoto J, Kato T, Masui F. Question answering challenge (QAC-1 ) question answering evaluation atNTCIR workshop 3. Working Notes of the Third NTCIR Workshop Meeting, Tokyo, 2002, p 1-6.
8. Galescu L, Ringger E, Allen J. Rapid language model development for new task domains. Proc International Conference on Language Resources and Evaluation, Granada, Spain, 1998, p 807-812.
9. Klakow D. Selecting articles from the language model training corpus. Proc International Conference on Acoustics Speech and Signal Processing, Istanbul 2000;3:1695-1698.
10. Knesner R, Peters J, Klakow D. Language model adaptation using dynamic marginals. Proc European Conference on Speech Communication and Technology, Rodos, Greece, 1997, p 1971-1974.
11. Kneser R, Steinbiss V. On the dynamic adaptation of stochastic language models. Proc International Conference on Acoustic Speech and Signal Processing, Minneapolis, 1993, p 586-589.
12. Mahajan M, Beeferman D, Huang XD. Improved topic-dependent language modeling using information retrieval techniques. Proc International Conference on Acoustic Speech and Signal Processing, Phoenix, 1999.
13. Niesler T, Willett D. Unsupervised language model adaptation for lecture speech transcription. Proc International Conference on Spoken Language Processing, Denver 2002;2:1413-1416.
14. Placeway P, Schwartz R, Fung P, Nguyen L. The estimation of powerful language models from small and large corpora. Proc International Conference on Acoustics Speech and Signal Processing, Minneapolis 1993;2:33-36.
15. Rosenfeld R. A maximum entropy approach to adaptive statistical language modeling. Comput Speech Lang 1996; 10:155-186.
16. Voorhees E, Tice D. The TREC-8 question answering track evaluation. Proc 8th Text Retrieval Conference, Gaithersburg, MD, 1999, p 83-106.
17. Itou A, Koda M. An analysis of the performance of task adaptation based on mixtures of N-gram frequencies. Trans IEICE 2000;J83-D-II:2418-2427. (in Japanese)
18. Okazumi Y, Ishii J, Hanazawa T. Constructing a language model for speech recognition of free utterances using example sentences for the task. J Acousl Soc Japan, p 73-74, 2001. (in Japanese)
19. Sasaki Y, Isozaki H, Taira H, Hirota K, Kazawa H, Nakajima H. A comparison and evaluation of question-answering systems. Tech Rep Inf Process SotJapan, NLC-24, 2000. (in Japanese)
20. Shikano K, Itou K, Kawahara T, Takeda K, Yamamoto T (editors). Speech recognition systems. Ohm; 2001. (in Japanese)
21. Nakawa S, Akamatsu H, Nishizaki H. Task adaptation and the use of fixed phrases for language models in speech recognition. Natural Language Process 1999;6:97-115. (in Japanese)
22. Wada Y, Kobayashi Y, Nakano Y, Kobayashi T. Effects of vocabulary expansion for large vocabulary speech recognition by the addition of chained words. J Inf Process Soc Japan 1999;40:1413-1420. (in Japanese)