THE IBM 2004 conversational telephony system for rich transcription

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

Volumn I, Issue , 2005, Pages

  Soltau, Hagen ^a   Kingsbury, Brian ^a   Mangu, Lidia ^a   Povey, Daniel ^a   Saon, George ^a   Zweig, Geoffrey ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

FEATURE EXTRACTION; GRAPH THEORY; SPEECH; SPEECH CODING; TELECOMMUNICATION SYSTEMS;

CONVERSATIONAL TELEPHONY SYSTEM; COVARIANCE GAUSSIAN SYSTEM; RICH TRANSCRIPTION EVALUATION; STATIC DECODING GRAPHS;

SPEECH ANALYSIS;

EID: 33646798740     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2005.1415086     Document Type: Conference Paper

References (13)

1. A. Stolcke, R. Gadde, M. Graciarena, K. Precoda, A. Venkataraman, D. Vergyri, W. Wang, and J. Zheng, "Speech to text research at SRI-ICSI-UW," in NIST RT-03 Workshop. May 2003, DARPA.
2. S. Matsoukas, R. Iyer, O. Kimball, J. Ma, T. Colhurst, R. Pasad, and C. Kao, "BBN CTS english system," in NIST RT-03 Workshop. May 2003, DARPA.
3. P. Woodland, G. Evermann, M. Gales, T. Hain, R. Chan, B. Jia, DY. Kim, A. Liu, D. Mrva, D. Povey, KC Sim, M. Tomalin, S. Tramter, L. Wang, and K. Yu, "CU-HTK STT systems for rt03," in NIST RT-03 Workshop. May 2003, DARPA.
4. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, and G. Zweig, "fMPE: Discriminatively trained features for speech recognition," in ICASSP-2005. 2004, Submitted.
5. J. Huang, B. Kingsbury, L. Mangu, G. Saon, R. Sarikaya, and G. Zweig, "Improvements to the IBM hub5e system," in NIST RT-02 Workshop. 2002, DARPA.
6. B. Kingsbury, S. Chen, L. Mangu, D. Povey, G. Saon, H. Soltau, and G. Zweig, "Training a 2300-hour fisher system," in EARS STT Workshop, 2004.
7. D. Povey and P. Woodland, "Minimum phone error and i-smoothing for improved discriminative training," in ICASSP-2002, 2002.
8. D. Povey, Discriminative Training for Large Voculabulary Speech Recognition, Ph.D. thesis, Cambridge University, 2004.
9. H. Hermansky, D.P.W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional HMM systems," in ICASSP-2000, 2000.
10. G. Saon, G. Zweig, B. Kingsbury, E. Mangu, and U. Chaudhari, "An architecture for rapid decoding of large vocabulary conversational speech," in Eurospeech-2003, 2003.
11. H. Soltau, H. Yu, F. Metze, C. Fuegen, Q. Jin, and SC. Jou, "The 2003 ISE rich transcription system for conversational telephony speech," in ICASSP-2004, 2003.
12. S. Wegmann, D. McAllaster, J. Orloff, and B. Peskin, "Speaker normalization on conversational telephone speech," in ICASSP-1996, 1996.
13. M.J.F. Gales, "Maximum likelihood linear transformation for HMM-based speech recognition," in Tech. Report CUED/F-INFENG/TR291. 1997, Cambridge University.