Adapting acoustic models to new domains and conditions using untranscribed data

EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology

Volumn , Issue , 2003, Pages 1633-1636

  Gunawardana, Asela ^a   Acero, Alex ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER APPLICATIONS; COMPUTER SIMULATION;

ACOUSTIC CONDITIONS; ACOUSTIC MODEL; ACOUSTIC MODEL TRAININGS; NOCV1; UNSUPERVISED ADAPTATION; UNSUPERVISED TRAINING; WALL STREET JOURNAL;

SPEECH COMMUNICATION;

EID: 85009209270     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. D. Paul and J. Baker, "The design for theWall Street Journal based CSR corpus," DARPA, Feb. 1992.
2. H.-G. Hirsch and D. Pearce, "The AURORA experimental framework for the performance evaluation of speech recognition systems under noisy conditions," in Proc. ITRW ASR, (Paris), ISCA, 2000.
3. J. Droppo, L. Deng, and A. Acero, "Evaluation of the SPLICE algorithm on the Aurora2 databse," in Eurospeech, vol. 1, (Aarlborg, Denmark), pp. 217-220, ISCA, 2001.
4. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Comp. Spch. & Lang., vol. 9, pp. 171-185, Apr. 1995.
5. V. V. Digalakis, D. Rtischev, and L. G. Neumeyer, "Speaker adaptation using constrained estimation of Gaussian mixtures," IEEE Trans. Spch. & Aud. Proc., vol. 3, pp. 357-366, Sept. 1995.
6. C.-H. Lee and J.-L. Gauvain, "Speaker adaptation based on MAP estimation of HMM parameters," in ICASSP, vol. II, pp. 558-561, IEEE, 1993.
7. K. Shinoda and C.-H. Lee, "Structural MAP speaker adaptation using hierarchical priors," in IEEE Wkshp. Spch. Recog. & Und. (S. Furui, B.-H. Juang, andW. Chou, eds.), pp. 381-387, 1997.
8. G. Zavaliagkos and T. Colthurst, "Utilizing untranscribed training datat to improve performance," in Broad. Nws. Trans. & Und. Wkshp., DARPA, 1998.
9. L. Lamel, J.-L. Gauvain, and G. Adda, "Unsupervised acoustic model training," in ICASSP, vol. 1, pp. 877-880, IEEE, 2002.
10. A. P. Dempster, A. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data," J. Roy. Stat. Soc., Ser. B, vol. 39, no. 1, pp. 1-38, 1977.
11. P. Woodland, J. J. Odell, V. Valtchev, and S. J. Young, "Large vocabulary continuous speech recognition using HTK," in ICASSP, vol. II, pp. 125-128, 1994.