Japanese large-vocabulary continuous-speech recognition using a newspaper corpus and broadcast news

Speech Communication

Volumn 28, Issue 2, 1999, Pages 155-166

  Ohtsuki, Katsutoshi ^a   Matsuoka, Tatsuo ^a   Mori, Takeshi ^a   Yoshida, Kotaro ^b   Taguchi, Yuichi ^c   Furui, Sadaoki ^b   Shirai, Katsuhiko ^c  

^a NTT CORPORATION   (Japan)

^b TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

^c WASEDA UNIVERSITY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

MARKOV PROCESSES; MATHEMATICAL MODELS; SPEECH ANALYSIS; SPEECH SYNTHESIS; STATISTICAL METHODS;

BROADCAST-NEWS TRANSCRIPTIONS; STATISTICAL LANGUAGE MODELS;

CONTINUOUS SPEECH RECOGNITION;

EID: 0032650381     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(99)00006-0     Document Type: Article

References (26)

1. Bakis, R., Chen, S., Gopalakrishnan, P., Gopinath, R., Maes, S., Polymenakos, L., 1997. Transcription of broadcast news - system robustness issues and adaptation techniques. In: Proc. ICASSP, pp. 711-714.
2. Cook, G.D., Kershaw, D.J., Christie, J.D.M., Seymour, C.W., Waterhouse, S.R., 1997. Transcription of broadcast television and radio news: the 1996 ABBOT system. In: Proc. ICASSP, pp. 723-726.
3. Garofolo, J.S., Fiscus, J.G., Fisher, W.M., 1997. Design and preparation of the 1996 Hub-4 broadcast news benchmark test corpora. In: Proc. DARPA Speech Recognition Workshop, pp. 15-21.
4. Gauvain, J.L., Lamel, L.F., Eskenazi, M., 1990. Design considerations and text selection for BREF, a large French read-speech corpus. In: Proc. ICSLP, pp. 1097-1100.
5. Gauvain, J.L., Lamel, L., Adda, G., Matrouf, D., 1996. The LIMSI 1995 Hub3 system. In: Proc. DARPA Speech Recognition Workshop, pp. 105-111.
6. Gauvain, J.L., Lamel, L., Adda, G., Adda-Decker, M., 1997. Transcription of broadcast news. In: Proc. Eurospeech, pp. 907-910.
7. Inoue, T., Ohkubo, M., Sugizaki, M., 1997. InfoBee/TR - A full-text retrieval system. NTT R&D 46 (10), 1103-1108 (in Japanese).
8. Katz S.M. Estimation of probabilities from sparse data for the language model component of a speech recognizer. IEEE Trans. ASSP-35:1987;400-401.
9. Kubala, F., Chow, Y., Derr, A., Feng, M., Kimball, O., Makhoul, J., Price, P., Rohlicek, J., Roucos, S., Schwartz, R., Vandegrift, J., 1988. Continuous speech recognition results of the BYBLOS system on the DARPA 1000-word resource management database. In: Proc. ICASSP, pp. 291-294.
10. Kubala, F., Jin, H., Matsoukas, S., Nguyen, L., Schwartz, R., Makhoul, J., 1997. Advances in transcription of broadcast news. In: Proc. Eurospeech, pp. 927-930.
11. Lamel, L., DeMori, R., 1995. Speech recognition of European languages. In: Proc. IEEE Automatic Speech Recognition Workshop, pp. 51-54.
12. Matsuoka, T., Ohtsuki, K., Mori, T., Furui, S., Shirai, K., 1996a. Large-vocabulary continuous-speech recognition using a Japanese business newspaper (Nikkei). In: Proc. DARPA Speech Recognition Workshop, pp. 137-142.
13. Matsuoka, T., Ohtsuki, K., Mori, T., Furui, S., Shirai, K., 1996b. Japanese large-vocabulary continuous-speech recognition using a business-newspaper corpus. In: Proc. ICSLP, Vol. 1, pp. 22-25.
14. Matsuoka, T., Ohtsuki, K., Mori, T., Yoshida, K., Furui, S., Shirai, K., 1997a. Japanese large-vocabulary continuous-speech recognition using a business-newspaper corpus. In: Proc. ICASSP, Vol. 3, pp. 1803-1806.
15. Matsuoka, T., Taguchi, Y., Ohtsuki, K., Furui, S., Shirai, K., 1997b. Toward automatic recognition of Japanese broadcast news. In: Proc. DARPA Speech Recognition Workshop, pp. 181-184.
16. Matsuoka, T., Taguchi, Y., Ohtsuki, K., Furui, S., Shirai, K., 1997c. Toward automatic transcription of Japanese broadcast news. In: Proc. Eurospeech, Vol. 2, pp. 915-918.
17. Pallett, D.S., Fiscus, J.G., Fisher, W.M., Garofolo, J.S., Lund, B.A., Martin, A., Przybocki, M.A., 1995. 1994 Benchmark tests for the ARPA spoken language program. In: Proc. ARPA Spoken Language Systems Technology Workshop, pp. 5-36.
18. Pallett, D.S., Fiscus, J.G., Fisher, W.M., Garofolo, J.S., Martin, A.F., Przybocki, M.A., 1996. 1995 Hub-3 NIST multiple microphone corpus benchmark tests. In: Proc. DARPA Speech Recognition Workshop, pp. 27-52.
19. Paul, D.B., Baker, M., 1992. The design for the wall street journal-based CSR corpus. In: Proc. ICSLP, pp. 899-902.
20. Robinson, T., Fransen, J., Pye, D., Foote, J., Renals, S., 1995. WSJCAM0: A British English speech corpus for large vocabulary continuous speech recognition. In: Proc. ICASSP, pp. 81-84.
21. Schwartz, R., Nguyen, L., Makhoul, J., 1996. Multiple-pass search strategies. In: Lee, C.-H., Soong, F.K., Paliwal, K.K. (Eds.), Automatic Speech and Speaker Recognition, pp. 429-456.
22. Steeneken, H.J.M., van Leenwen, D.A., 1995. Multi-lingual assessment of speaker independent large vocabulary speech-recognition systems: SQALE-project. In: Proc. Eurospeech, pp. 1271-1274.
23. Woodland, P.C., Gales, M.J.F., Pye, D., Valtchev, V., 1996. The HTK large vocabulary recognition system for the 1995 ARPA H3 task. In: Proc. DARPA Speech Recognition Workshop, pp. 99-104.
24. Woodland, P.C., Gales, M.J.F., Pye, D., Young, S.J., 1997. Broadcast news transcription using HTK. In: Proc. ICASSP, pp. 719-722.
25. Young, S.J., Odell, J.J., Woodland, P.C., 1994. Tree-based state tying for high accuracy acoustic modeling. In: Proc. ARPA Human Language Technology Workshop, pp. 307-312.
26. Young S.J., Adda-Dekker M., Aubert X., Dugast C., Gauvain J.-L., Kershaw D.J., Lamel L., Leeuwen D.A., Pye D., Robinson A.J., Steeneken H.J.M., Woodland P.C. Multilingual large vocabulary speech recognition: the European SQALE project. Computer Speech and Language. 11:1997;73-89.