Dialogue speech recognition using syntactic rules based on subtrees and preterminal bigrams

Systems and Computers in Japan

Volumn 28, Issue 5, 1997, Pages 22-32

  Takezawa, Toshiyuki ^a   Morimoto, Tsuyoshi ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

Continuous speech recognition; Integrated processing of speech and language, syntactic rules, subtrees, stochastic language modeling; Spoken language processing

Indexed keywords

CONTEXT SENSITIVE GRAMMARS; DATA STRUCTURES; DATABASE SYSTEMS; KNOWLEDGE BASED SYSTEMS; SPEECH PROCESSING;

DIALOGUE SPEECH RECOGNITION; PRETERMINAL BIGRAMS; STOCHASTIC LANGUAGE MODELING; SUBTREES; SYNTACTIC RULES;

SPEECH RECOGNITION;

EID: 0031144926     PISSN: 08821666     EISSN: None     Source Type: Journal    
DOI: 10.1002/(sici)1520-684x(199705)28:5<22::aid-scj3>3.0.co;2-q     Document Type: Article

References (18)

1. T. Akiba, K. Itou, and K. Tanaka. Incremental dialog processing with successive interpausal phrases. Proc. 1996 IEICE General Conf., SD-4-4, pp. 333-334. (in Japanese)
2. N.A. Daly. Acoustic-Phonetic and Linguistic Analysis of Spontaneous Speech: Implications for Speech Understanding. Massachusetts Inst. of Tech. (1994).
3. Y. Den. Extra-grammatical phenomena in spoken language and how to handle them with computers. JSAI, SIG-SLUD-9503-3, pp. 9-16 (1996). (in Japanese)
4. K. Hatazaki. Speech dialogue based on simultaneous understanding. Proc. 1996 IEICE General Conf., SD-4-5, pp. 335-336. (in Japanese)
5. K. Itou, T. Akiba, S. Kamijo, and K. Tanaka. A dialog processing method based on interpausal utterances. IPSJ SIG Notes, 95-SLP-7-21 (1995). (in Japanese)
6. T. Iwadera et al. integrating speech parser using pause information and dialogue situation manager: Prototype of spoken dialogue system. Proc. 1996 IEICE General Conf., SD-4-3, pp. 331-332. (in Japanese)
7. G.J.F. Jones, J.H. Wright, and E.N. Wrigley. The HMM interface with hybrid grammar-bigram language models for speech recognition. Proc. ICSLP '92, pp. 253-256.
8. K. Kita, T. Morimoto, K. Ohkura, and S. Sagayama. Continuously spoken sentence recognition by HMMLR. Proc. ICSLP '92, pp. 305-308.
9. T. Morimoto et al. A speech and language database for speech translation research. Proc. of ICSLP '94, pp. 1791-1794.
10. S. Nakagawa. Speech Recognition Based on Probabilistic Models. IEICE, Corona Press (1988). (in Japanese)
11. K. Ohtani and S. Nakagawa. Semi-automatic learning method of grammar rules by the combination of CFG and bigrams. IPSJ SIG Notes, 95-SLP-9-15 (1995). (in Japanese)
12. M. Sugito. Pauses and intonation in discourse. Japanese and Japanese Language Education, Vol. 2. Japanese Speech and Phonology. Meiji Shoin Press (1993). (in Japanese)
13. T. Takezawa and T. Morimoto. An efficient predictive LR parser using pause information for continuously spoken sentence recognition. Proc. ICSLP '94, pp. 1-4.
14. T. Takezawa, T. Tashiro, and T. Morimoto. A study of linguistic phenomena of spontaneous speech in the ATR spoken language database. JSAI, SIG-SLUD-9403-3, pp. 13-20 (1995). (in Japanese)
15. T. Takezawa, T. Tashiro, and T. Morimoto. Linguistic phenomena of spontaneous speech and Japanese grammar for speech recognition. IPSJ SIG Notes, 95-SLP-6-S (1995). (in Japanese)
16. T. Takezawa and T. Morimoto. Continuous speech recognition using a grammar based on subtrees and preterminal bigrams. Tech. Rep. I.E.I.C.E., NLC95-54, SP95-89, IPSJ SIG Notes, 95-SLP-9-8 (1995). (in Japanese)
17. T. Tashiro, T. Takezawa, and T. Morimoto. Handling partial trees for speech and language processing. IPSJ SIG Notes, 95-NL-109-4 (1995). (in Japanese)
18. M. Tonomura, T. Kosaka, S. Matsunaga, and A. Monden. Effectiveness of controlling the smoothing coefficient on speaker adaptation with MAP-VFS. Proc. ASJ Spring Meeting, 2-5-6 (1995). (in Japanese)