Universal background model based speech recognition

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

Volumn , Issue , 2008, Pages 4561-4564

  Povey, Daniel ^a   Chu, Stephen M ^a   Varadarajan, Balakrishnan ^a,b  

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

^b JOHNS HOPKINS UNIVERSITY   (United States)

Author keywords

Acoustic modeling; Speech recognition; UBM; Universal background model

Indexed keywords

ACOUSTICS; CONTINUOUS SPEECH RECOGNITION; PARAMETER ESTIMATION; SIGNAL PROCESSING; SPEECH ANALYSIS;

ACOUSTIC MODELING; INTERNATIONAL CONFERENCES; UBM; UNIVERSAL BACKGROUND MODEL;

SPEECH RECOGNITION;

EID: 51449086263     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2008.4518671     Document Type: Conference Paper

References (7)

1. D. A. Reynolds, T. F. Quatieri, and R. Dunn, "Speaker verification using adapted Gaussian mixture models," Digital Signal Processing, vol. 10, no. 1-3, pp. 19-41, 2000.
2. R. Vogt, J. Pelecanos, S. Sridharan, "Dependence of GMM adaptation on feature post-processing for speaker recognition," in Proc. EUROSPEECH'03, pp. 3013-3016, September 2003.
3. M. J. F. Gales, "Semi-tied covariance matrices for hidden Markov models" IEEE Transactions on Speech and Audio Processing, vol. 7, no. 3, pp. 272 - 281, 1999.
4. R. Kneser, H. Ney, "Improved backing-off for M-gram language modeling," in Proc. ICASSP'95, vol. 1, pp. 181-184, May 1995.
5. D. Povey and G. Saon, "Feature and model space feature adaptation with full covariance Gaussians," in Proc. ICSLP'06, September 2006.
6. S. M. Chu, H.-K. Kuo, Y. Y. Liu, Y. Qin, Q. Shi, and G. Zweig, "The IBM Mandarin broadcast speech transcription system," in Proc. ICASSP'07, vol. 2, pp. 345-348, May 2007.
7. K. C. Sim, M. J. F. Gales: "Minimum phone error training of precision matrix models," IEEE Transactions on Audio, Speech and language Processing, vol. 14, no. 3, pp. 882-889, 2006.