Light supervision in acoustic model training

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2004, Pages

  Nguyen, Long ^a   Xiang, Bing ^a  

^a BBN TECHNOLOGIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BROADCASTING; DECODING; ERROR ANALYSIS; MATHEMATICAL MODELS; PROBLEM SOLVING; SET THEORY;

ACOUSTIC MODEL TRAINING; CLOSED-CAPTION (CC) TRANSCRIPTS; ERROR REDUCTION; LIGHT SUPERVISION METHOD;

SPEECH RECOGNITION;

EID: 4544273245     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. L. Lamel, J.-L. Gauvain and G. Adda, "Investigating lightly supervised acoustic model training," Proc. ICASSP, Salt Lake City, May 2001.
2. P. Nguyen, "Large corpus experiments for broadcast news recognition," Proc. Eurospeech, Geneva, Switzerland, Sept. 2003.
3. L. Nguyen, et al., "The 1999 BBN Byblos 10xRT broadcast news transcription system," Proc. NIST 2000 Speech Transcription Workshop, Maryland, May 2000.
4. L. Nguyen and R. Schwartz, "Efficient 2-pass N-Best decoder," Proc. EuroSpeech, Rhodes, Greece, Sep. 1997, pp. 167-170.
5. L. Nguyen, S. Matsoukas, J. Davenport, F. Kubala, R. Schwartz and J. Makhoul, "Progress in transcription of broadcast news using Byblos," Speech Communication, 38, pp. 213-230, 2002.
6. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," Journal of the Acoustical Society of America, vol. 87, no. 4, pp. 1738-1752, April 1990.
7. S. Matsoukas and R. Schwartz, "Improved speaker adaptation using speaker dependent feature projections," to appear in IEEE ASRU Workshop, St. Thomas, Nov. 2003.
8. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer Speech and Language, 12, pp. 75-98, 1998.
9. P. C. Woodland and D. Povey, "Large scale discriminative training of hidden Markov models for speech recognition", Computer Speech and Language, 16, pp.25-47, 2002.
10. R. Schwartz, et al., "Speech recognition in multiple languages and domains: the 2003 BBN/LIMSI EARS system," Submitted to ICASSP, Montreal, Canada, May 2004.