Unsupervised training and directed manual transcription for LVCSR

Speech Communication

Volumn 52, Issue 7-8, 2010, Pages 652-663

  Yu, Kai ^a   Gales, Mark ^a   Wang, Lan ^a,b   Woodland, Philip C ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^b SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY   (China)

Author keywords

Automatic transcription; Data selection; Discriminative training; Unsupervised training

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; DATA REDUCTION; MAXIMUM LIKELIHOOD; SPEECH RECOGNITION;

AUTOMATIC TRANSCRIPTION; DATA SELECTION; DISCRIMINATIVE TRAINING; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; RECOGNITION ACCURACY; RECOGNITION SYSTEMS; STATE OF THE ART; UNSUPERVISED TRAINING;

TRANSCRIPTION;

EID: 79951779719     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2010.02.014     Document Type: Article

References (25)

1. Chan, H., Woodland, P., 2004. Improving broadcast news transcription by lightly supervised discriminative training. In: ICASSP, Montreal.
2. Cohn, D., Atlas, L., Ladner, R., 1994. Improving generalization with active learning. Machine Learning 15, 201-221.
3. Doumpiotis, V., Tsakalidis, S., Byrne, W., 2003. Lattice segmentation and minimum Bayes risk discriminative training. In: Proc. EuroSpeech.
4. Evermann, G., Woodland, P.C., 2003. Design of fast LVCSR systems. In: Proc. ASRU, St. Thomas.
5. Evermann, G., Chan, H.Y., Gales, M.J.F., Jia, B., Mrva, D., Woodland, P.C., Yu, K., 2005. Training LVCSR systems on thousands of hours of data. In: Proc. ICASSP, Philadelphia.
6. Gales, M.J.F., Jia, B., Liu, X., Sim, K.C., Woodland, P.C., Yu, K., 2005. Development of the CUHTK2004 Mandarin conversational telephone speech transcription system. In: Proc. ICASSP, Philadelphia.
7. Gillick, L., Cox, S.J., 1989. Some statistical issues in the comparison of speech recognition. In: Proc. ICASSP, Glasgow.
8. Kamm, T.M., Meyer, G.G.L., 2002. Selective sampling of training data for speech recognition. In: Proc. Human Language Technology, San Diego.
9. Kemp, T., Waibel, A., 1999. Unsupervised training of a speech recognizer: recent experiments. In: Proc. EuroSpeech, Budapest.
10. Kumar, N., 1997. Investigation of silicon-auditory models and generalization of linear discriminant analysis for improved speech recognition. Ph.D. Thesis, Johns Hopkins University.
11. Lamel, L., Gauvian, J.L., Adda, G., 2001. Unsupervised acoustic model training. In: Proc. ICASSP, Salt Lake City.
12. Lamel, L., Gauvian, J.L., Adda, G., 2002. Lightly supervised and unsupervised acoustic model training. Computer Speech and Language 16, 115-129.
13. Ma, J., Matsoukas, S., Kimball, O., Schwartz, R., 2006. Unsupervised training on large amount of broadcast news data. In: Proc. ICASSP, Toulouse.
14. Mangu, L., 2000. Finding consensus in speech recognition. Ph.D. Thesis, Johns Hopkins University.
15. Nakamura, M., Iwanoa, K., Furui, S., 2007. Differences between acoustic characteristics of spontaneous and read speech and their effects on speech recognition performance. Computer Speech and Language 22 (2), 171-184.
16. Pallett, D.S., Fisher, W.M., Fiscus, J.G., 1990. Tools for the analysis of benchmark speech recognition tests. In: Proc. ICASSP.
17. Povey, D., 2003. Discriminative training for large vocabulary speech recognition. Ph.D. Thesis, Cambridge University.
18. Povey, D., Woodland, P.C., 2002. Minimum phone error and I - smoothing for improved discriminative training. In: Proc. ICASSP, Orlando.
19. Riccardi, G., Hakkani-Tur, D., 2003. Active and unsupervised learning for automatic speech recognition. In: Proc. EUROSPEECH, Geneva.
20. Sinha, R., Gales, M.J.F., Kim, D.Y., Liu, X.A., Sim, K.C., Woodland, P., 2006. The CU-HTK Mandarin broadcast news transcription system. In: Proc. ICASSP, Toulouse.
21. Wang, L., Gales, M.J.F., Woodland, P.C., 2007. Unsupervised training for Mandarin broadcast news and conversation transcription. In: Proc. ICASSP, Honolulu.
22. Wessel, F., Ney, H., 2005. Unsupervised training of acoustic models for large vocabulary continuous speech recognition. IEEE Transactions on Acoustics, Speech and Signal Processing 13 (1), 23-31.
23. Woodland, P.C., Odell, J.J., Valtchev, V., Young, S.J., 1995. The development of the 1994 HTK large vocabulary speech recognition system. In: ARPA Workshop on Spoken Language Systems Technology, pp.104-109.
24. Woodland, P.C., Gales, M.J.F., Pye, D., Young, S.J., 1997. The development of the1996 HTK broadcast news transcription system. In: DARPA Speech Recognition Workshop, pp.73-78.
25. Yu, K., Gales, M.J.F., Woodland, P.C., 2007. Unsupervised training with directed manual transcription for recognising Mandarin broadcast audio. In: Proc. INTERSPEECH, Antwerp.