Unsupervised versus supervised training of acoustic models

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2008, Pages 2374-2377

  Ma, Jeff ^a   Schwartz, Richard ^a  

^a BBN TECHNOLOGIES   (United States)

Author keywords

Fisher conversational telephone speech; Supervised training; Unsupervised training

Indexed keywords

ACOUSTIC MODEL; CONVERSATIONAL TELEPHONE SPEECH; RECOGNITION PERFORMANCE; SUPERVISED TRAINING; TRAINING DATA; UNSUPERVISED TRAINING;

TELEPHONE; TELEPHONE SETS;

SPEECH COMMUNICATION;

EID: 84867196264     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. G. Zavaliagkos and T. Colthurst, "Utilizing Untranscribed Training Data to Improve Performance," in DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne, VA, USA, Feb. 1998, pp. 301-305
2. J. Ma, S. Matsoukas, O. Kimball, and R. Schwartz, "Unsupervised Training on Large Amounts of Broadcast News Data," in IEEE Int. Conf. On Acoustics, Speech, and Signal Processing, Toulouse, France, May 2006, Vol. 3, pp. 1057-1060.
3. J. Ma and S. Matsoukas, "Unsupervised training on A large amount of Arabic Broadcast news Data", in IEEE Int. Conf. On Acoustics, Speech, and Signal Processing, 2007.
4. T. Kemp and A. Waibel, "Unsupervised training of a speech recognizer: recent experiments", Proc. Eurospeech 99, pp 2725-2728, September 1999.
5. L. Lamel, J. L. Gauvain, G. Adda, "Unsupervised acoustic model training", Proc. ICASSP 2002, pp 877-880, 2002.
6. C. Gollan, S. Hahn, R. Schlüter, and H. Ney. "An improved method for unsupervised training of LVCSR systems", In Interspeech 2007, pages 2101-2104, Antwerp, Belgium, 2007.
7. L. Nugyen, B. Xiang, "Light supervision in acoustic training", Proc. ICASSP 2004, pp 185-188, 2004.
8. L. Lamel, J.L. Gauvain, and G. Adda, "Lightly supervised and unsupervised acoustic model training", Computer Speech and Language, 16(1):115-229, 2002
9. H.Y. Chan, P. Woodland, "Improving broadcast news transcription by lightly supervised discriminative training", ICASSP2004, pp 737-740, 2004.
10. O. Kimball, C. Kao, R. Iyer, T. Arvizo and J. Makhoul, "Using quick transcriptions to improve conversational speech recognition", in Proc. of Int. Conf. Spoken Language Processing, Jeju, Korea, Sept. 2004.
11. I. Bulyko and M. Ostendorf and A. Stolcke, "Getting more mileage from web text sources for conversational speech language modeling using class-dependent mixtures", in Proc. HLT/NAACL, 2003, PP. 7-9.
12. S. Matsoukas and R. Schwartz, "Improved speaker adaptation using speaker dependent feature projections," ASRU 2003.