Speaker clustering and transformation for speaker adaptation in speech recognition systems

IEEE Transactions on Speech and Audio Processing

Volumn 6, Issue 1, 1998, Pages 71-77

  Padmanabhan, Mukund ^a   Bahl, Laut R ^a   Nahamoo, David ^a   Picheny, Michael A ^a  

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

Author keywords

Data transformation; Speaker adaptation; Speaker clustering

Indexed keywords

PARAMETER ESTIMATION; PATTERN RECOGNITION SYSTEMS;

DATA TRANSFORMATION; SPEAKER ADAPTATION; SPEAKER CLUSTERING;

SPEECH RECOGNITION;

EID: 0031704151     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.650313     Document Type: Article

References (16)

1. Proc. ARPA Speech and Natural Language Workshop, Jan. 1995. Austin, TX.
2. L. Bahl, P. de Souza, P. Gopalakrishnan, and M. Picheny, "Context-dependent vector quantization for continuous speech recognition," in Proc. 1CASSP, Minneapolis, MN, Apr. 1993, pp. 11-632-635.
3. L. R. Bahl et ai., "Robust methods for using context-dependent features and models in a continuous speech recognizer," in Proc. ICASSP, Adelaide, Australia, May 1994, pp. 1-533-536.
4. L. R. Bahl el al, "Performance of the IBM large vocabulary continuous speech recognition system on the ARPA Wall Street Journal task," in Proc. ICASSP, Detroit, MI, 1995, pp. 41-M.
5. C. J. Legetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density HMM's," in Compiil. Speech Lang., vol. 9, pp. 171-186, 1996.
6. V. Digalakis and L. Neumeyer, "Speaker adaptation using combined Transformation and Bayesian methods," in Proc. ICASSP, Detroit, MI, 1995, pp. 680-683.
7. J. R. Bellergarda et al., "Experiments using data augmentation for speaker adaptation," in Proc. ICASSP, Detroit, MI, May 1995, pp. 692-695.
8. J. L. Gauvain and C. H. Lee, "Ma\\mum-a-posteriori estimation for multivariate Gaussian observations of Markov chains," IEEE Trans. Speech Audio Processing, vol. 2, pp. 291-298, Apr. 1994.
9. G. Zavagliogkos, R. Schwartz, and J. Makhoul, "Batch, incremental and instantaneous adaptation techniques for speech recognition," in Proc. ICASSP, Detroit, MI, May 1995, pp. 676-679.
10. M. Padmanabhan et al., "Speaker clustering and transformation for speaker adaptation in large-vocabulary speech recognition systems," in Proc. ICASSP, Atlanta, GA, May 1996, vol. II, pp. 701-704.
11. A. Sankar et al., 'Training data clustering for improved speech recognition," in Proc. EUROSPEECH, Madrid, Spain, Sept. 1995, pp. 503-506.
12. T. Anastasakos et al., "A compact model for speaker-adaptive training," in Proc. ICSLP, 1996, pp. 1137-1140.
13. T. Kosaka and S. Sagayama, "Tree-structured speaker clustering for fast speaker adaptation," in Proc. ICASSP, Adelaide, Australia, May 1994, pp. I-245-I-248.
14. T. Kosaka, J. Takami, and S. Sagayama, "Rapid speaker-adaptation using speaker-mixture allophone models applied to speaker-independent speech recognition," in Proc. ICASSP, Adelaide, Australia, May 1994, pp. II-570-II-573.
15. P. S. Gopalakrishnan et al., 'Transcription of radio broadcast news with the IBM large vocabulary speech recognition system," in Proc. Spoken Language Technology Workshop, Feb. 1996, pp. 72-76.
16. P. S. Gopalakrishnan et al, "Acoustic models used in the IBM system for the ARPA hub 4 task," in Proc. Spoken Language Technology Workshop, Feb. 1996, pp. 77-80.