Super-human multi-talker speech recognition: A graphical modeling approach

Computer Speech and Language

Volumn 24, Issue 1, 2010, Pages 45-66

  Hershey, John R ^a   Rennie, Steven J ^a   Olsen, Peder A ^a   Kristjansson, Trausti T ^b  

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

^b GOOGLE INC   (United States)

Author keywords

Algonquin; Factorial hidden Markov model; Multiple talker speaker identification; Speaker dependent labeling; Speech separation

Indexed keywords

ALGONQUIN; FACTORIAL HIDDEN MARKOV MODEL; MULTIPLE TALKER SPEAKER IDENTIFICATION; SPEAKER-DEPENDENT LABELING; SPEECH SEPARATION;

COMPUTATIONAL LINGUISTICS; HIDDEN MARKOV MODELS; INFERENCE ENGINES; LABELS; LOUDSPEAKERS; OBJECT RECOGNITION; SEPARATION; SPEECH ANALYSIS; VITERBI ALGORITHM;

SPEECH RECOGNITION;

EID: 69249222720     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2008.11.001     Document Type: Article

References (22)

1. Bocchieri, E., 1993. Vector quantization for the efficient computation of continuous density likelihoods. In: ICASSP, vol. II. pp. 692-695.
2. Cooke M., Barker J., Cunningham S., and Shao X. An audio-visual corpus for speech perception and automatic speech recognition. Journal of the Acoustical Society of America 120 (2006) 2421-2424
3. Cooke, M., Hershey, J.R., Rennie, S.J., 2009. The speech separation and recognition challenge. Computer Speech and Language, this issue.
4. Ephraim Y. A Bayesian estimation approach for speech enhancement using hidden Markov models. IEEE Transactions on Signal Processing 40 4 (1992) 725-735
5. Frey, B.J., Deng, L., Acero, A., Kristjansson, T., 2001. Algonquin: Iterating laplace's method to remove multiple types of acoustic distortion for robust speech recognition, proceedings of Eurospeech.
6. Gales M., and Young S. Robust continuous speech recognition using parallel model combination. IEEE Transactions on Speech and Audio Processing 4 5 (1996) 352-359
7. Gauvain J., and Lee C. Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Transactions on Speech and Audio Processing 2 2 (1994) 291-298
8. Ghahramani, Z., Jordan, M.I., 1995. Factorial hidden Markov models. In: Advances in Neural Information Processing Systems, vol. 8.
9. Hershey, J.R., Olsen, P.A., 2007. Approximating the Kullback Leibler divergence between gaussian mixture models. In: ICASSP. Honolulu, Hawaii.
10. Hershey, J.R., Kristjansson, T.T., Rennie, S.J., Olsen, P.A., 2006. Single channel speech separation using factorial dynamics. In: Advances in Neural Information Processing Systems, vol. 19, December 4-7, Vancouver, British Columbia, Canada.
11. Kristjansson, T.T., Attias, H., Hershey, J.R., 2004. Single microphone source separation using high-resolution signal reconstruction. In: ICASSP.
12. Kschischang F., Frey B., and Loeliger H. IEEE Transactions on Information Theory 47 2 (2001) 498-519
13. Linde Y., Buzo A., and Gray R.M. An algorithm for vector quantizer design. IEEE Transactions on Communications 28 1 (1980) 84-95
14. Nádas, A., Nahamoo, D., Picheny, M.A., 1989. Speech recognition using noise-adaptive prototypes. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 37. pp. 1495-1503.
15. Olsen, P.A., Dharanipragada, S., 2003. An efficient integrated gender detection scheme and time mediated averaging of gender dependent acoustic models proceedings of Eurospeech. vol. 4. pp. 2509-2512.
16. Radfar M.H., Dansereau R.M., and Sayadiyan A. Nonlinear minimum mean square error estimator for mixture-maximisation approximation. Electronics Letters 42 12 (2006) 724-725
17. Rennie, S.J., Olsen, P.A., Hershey, J.R., Kristjansson, T.T., 2006. Separating multiple speakers using temporal constraints. In: ISCA Workshop on Statistical And Perceptual Audition.
18. Rennie, S.J., Hershey, J.R., Olsen, P.A., 2009. Single-channel speech separation and recognition using loopy belief propagation. In: IEEE International Conference on Acoustics, Speech, and Signal Processing.
19. Roweis S. Factorial models and refiltering for speech separation and denoising. Eurospeech (2003) 1009-1012
20. Varga, P., Moore, R.K., 1990. Hidden Markov model decomposition of speech and noise. In: ICASSP. pp. 845-848.
21. Virtanen, T., 2006. Speech recognition using factorial hidden Markov models for separation in the feature space. In: ICSLP.
22. Weiss Y., and Freeman W.T. On the optimality of solutions of the max-product belief-propagation algorithm in arbitrary graphs. IEEE Transactions on Information Theory 47 2 (2001) 736-744