Multi-class composite N-gram language model

Speech Communication

Volumn 41, Issue 2-3, 2003, Pages 369-379

  Yamamoto, Hirofumi ^a   Isogai, Shuntaro ^a   Sagisaka, Yoshinori ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

Class N gram; N gram language model; Variable length N gram; Word clustering

Indexed keywords

COMPUTATIONAL METHODS; SPEECH RECOGNITION; STATISTICAL METHODS;

WORD CLUSTERING;

SPEECH COMMUNICATION;

EID: 0038373395     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(02)00179-6     Document Type: Article

References (11)

1. Bai, S., Li, H., Yuan, B., 1998. Building class-based language models with contextual statistics. In: Proc. ICASSP, pp. 173-176.
2. Brown P.F., Pietra V.J.D., Souza P.V., Lai J.C., Mercer R.L. Class-based. N -gram models of natural language Computat. Ling. 18(4):1992;467-479.
3. Deligne, S., Bimbot, F., 1995. Language modeling by variable length sequences. In: Proc. ICASSP, pp. 169-172.
4. Katz S.M. Estimation of probabilites from sparse data for the language model component of a speech recognizer. IEEE Trans. Acoust. Speech Signal Process. 1:1987;400-401.
5. Masataki, H., Matsunaga, S., Sagisaka, Y., 1996. Variable-order N -gram generation by word-class splitting and consecutive word grouping. In: Proc. ICASSP, pp. 188-191.
6. Ostendorf M., Singer H. HMM topology design using maximum likelihood successive state splitting. Comput. Speech Lang. 11(1):1997;17-41.
7. Shimizu, T., Yamamoto, H., Masataki, H., Matsunaga, S., Sagisaka, Y., 1996. Spontaneous dialogue speech recognition using cross-word context constrained word graphs. In: Proc. ICASSP, pp. 145-148.
8. Takezawa, T., Morimoto, T., Sagisaka, Y., 1998. Speech and language databases for speech translation research in ATR. In: Proc. 1st Internat. Workshop East-Asian Lang. Resour. Evaluation, pp. 148-155.
9. Ward J.H. Jr. Hierachical grouping to optimize an objective function. J. Amer. Statist. Assoc. 58:1963;236-244.
10. Yamamoto, H., Sagisaka, Y., 1999. Multi-class composite N -gram based on connection direction. In: Proc. ICASSP, pp. 533-536.
11. Zhang, S., Singer, H., Wu, D., Sagisaka, Y., 1999. Improving N -gram modeling using distance-related unit association maximum entropy language modeling. In: Proc. EuroSpeech, pp. 1611-1614.