Speech recognition using stochastic phonemic segment model based on phoneme segmentation

Systems and Computers in Japan

Volumn 31, Issue 10, 2000, Pages 89-98

  Furuichi, Chieko ^a,b,c,d   Aizawa, Katsura ^a,d   Inoue, Kazuhiko ^a,d  

^a TOIN UNIVERSITY OF YOKOHAMA   (Japan)

^b OCHANOMIZU UNIVERSITY   (Japan)

^c TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

^d Acoustic Society of Japan   (Singapore)

Author keywords

[No Author keywords available]

Indexed keywords

STOCHASTIC PHONEME SEGMENTATION;

COMPUTER SIMULATION; RANDOM PROCESSES; SPEECH ANALYSIS;

SPEECH RECOGNITION;

EID: 0034270090     PISSN: 08821666     EISSN: None     Source Type: Journal    
DOI: 10.1002/1520-684X(200009)31:10<89::AID-SCJ9>3.0.CO;2-7     Document Type: Article

References (15)

1. Austin S, Zavaliagkos G, Makhoul J, Schwartz R. Speech recognition using segmental neural nets. Proc ICASSP, p 625-628, 1992.
2. Gish H, Ng K. A segmental speech model with applications to word spotting. Proc ICASSP, p 447-450, 1993.
3. Ostendorf M, Digalakis V, Kimball O. From HMM's to segment models: A unified view of stochastic modeling for speech recognition. IEEE Trans Speech Audio Process 1996;4:360-378.
4. Verhasselt J, Illina I, Martens J, Gong Y, Haton J. The importance of segmentation probability in segment based speech recognizers. Proc ICASSP, p 1407-1410, 1997.
5. Nakagawa S, Yamamoto K. Speech recognition by hidden Markov model using segment statistics. Trans IEICE 1996;J79-D-II:2032-2038.
6. Renals S, Morgan N, Bourlard H, Cohen M, Franco H. Connectionist probability estimators in HMM speech recognition. IEEE Trans Speech Audio Process 1994;2:161-174.
7. Imai S, Furuichi C. Segmentation of continuous speech to phonemic units. Trans IEICE 1989;J72-D-II:11-21.
8. Furuichi C, Imai S. Segmentation to phonemic units in diversified phoneme context. Trans IEICE 1989;J72-D-II:1221-1227.
9. Furuichi C, Imai S. Phoneme recognition in speaker-dependent arbitrary-vocabulary continuous speech. Trans IEICE 1990;J73-D-II:501-511.
10. Furuichi C, Taniguchi I, Imai S. Spoken word recognition using phoneme lattice with reliability measure obtained by context-independent phoneme recognition. Trans IEICE 1992;J75-D-II:449-458.
11. Imai S, Taniguchi I, Furuichi C, Kawasaki T, Doi H. A speaker-independent spoken word recognition systern based on parallel phoneme labeling (PPL). Trans IEICE 1994;J77-A:143-152.
12. Ostendorf M, Roukos S. A stochastic segment model for phoneme-based continuous speech recognition. IEEE Trans Acoust Speech Signal Process 1989;37:1857-1869.
13. Imai S, Furuichi C. Unbiased estimation of log spectrum. Trans IEICE 1987;J70-A:471-480.
14. Tanaka K, Hayami S. A speech database for research at the Electrotechnical Laboratory. J Acoust Soc Jpn 1992;48:883-887.
15. Kosaka Y, Uraya N. ATR speech/language database. J Acoust Soc Jpn 1992;48:878-882.