Linear hidden transformations for adaptation of hybrid ANN/HMM models

Speech Communication

Volumn 49, Issue 10-11, 2007, Pages 827-835

  Gemello, Roberto ^a   Mana, Franco ^a   Scanzio, Stefano ^b   Laface, Pietro ^b   De Mori, Renato ^c  

^a Loquendo   (Italy)

^b POLITECNICO DI TORINO   (Italy)

^c UNIVERSITY OF AVIGNON   (France)

Author keywords

Automatic Speech Recognition; Catastrophic forgetting; Neural network adaptation; Speaker adaptation

Indexed keywords

CLASSIFICATION (OF INFORMATION); FEATURE EXTRACTION; HIDDEN MARKOV MODELS; MATHEMATICAL TRANSFORMATIONS; NEURAL NETWORKS;

AUTOMATIC SPEECH RECOGNITION; CATASTROPHIC FORGETTING; NEURAL NETWORK ADAPTATION; SPEAKER ADAPTATION;

SPEECH RECOGNITION;

EID: 34548012893     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2006.11.005     Document Type: Article

References (20)

1. Abrash, V., Franco, H., Sankar, A., Cohen, M., 1995. Connectionist speaker normalization and adaptation. In: Proc. EUROSPEECH 1995, pp. 2183-2186.
2. Albesano, D., Gemello, R., Mana, F., 1997. Hybrid HMM-NN modeling of stationary-transitional units for continuous speech recognition. In: Proc. Neural Information Processing, pp. 1112-1115.
3. BenZeghiba, M.F., Bourlard, H., 2003. Hybrid HMM/ANN and GMM combination for user-customized password speaker verification. In: Proc. ICASSP-03, pp. 225-228.
4. Bernstein, J., Taussig, K. Godfrey, J., 1994. MACROPHONE, LDC Catalog LDC94S21. Available at http://www.ldc.upenn.edu.
5. Dupont, S., Cheboub. L., 2000. Fast speaker adaptation of artificial neural networks for automatic speech recognition. In: Proc. ICASSP-00, pp. 1795-1798.
6. Dupont, S., Ris, C., Couvreur L., Boite, J.M., 2005. A study of implicit and explicit modeling of coarticulation and pronunciation variation. In: Proc. Interspeech-05, pp. 1353-1356.
7. French M. Catastrophic forgetting in connectionist networks: causes, consequences and solutions. Trends Cognit. Sci. 3 4 (1994) 128-135
8. Gales M.J.F. Maximum likelihood linear transformations for HMM-based speech recognition. Comput. Speech Lang. 12 (1998) 75-98
9. Gauvain J.L., and Lee C.H. Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chain. IEEE Trans. Speech Audio Process. 2 2 (1994) 291-298
10. Hermansky, H., Ellis, D., Sharma, S., 2000. Tandem connectionist feature extraction for conventional HMM systems. In: Proc. ICASSP-00, pp. 1635-1638.
11. Hsiao, R., Mak, B., 2004. Discriminative feature transformation by guided discriminative training. In: Proc. ICASSP-04, Montreal, pp. 897-900.
12. Kuhn R., Junqua J.C., Nguyen P., and Niedzielski N. Rapid speaker adaptation in eigenvoice space. IEEE Trans. Speech Audio Process. 8 4 (2000) 695-707
13. Lee C.-H., and Huo Q. On adaptive decision rules and decision parameter adaptation for automatic speech recognition. Proc. IEEE 88 8 (2000) 1241-1269
14. Li, X., Bilmes, J., 2006. Regularized adaptation of discriminative classifiers. In: Proc. ICASSP-06, pp. 237-240.
15. Liu, X., Gales, M.J.F., 2004. Model complexity control and compression using discriminative growth functions. In: Proc. ICASSP-04, pp. 797-800.
16. Neto, J., Almeida, L., Hochberg, M., Martins, C., Nunes, L., Renals, S., Robinson, T., 1995. Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system. In: Proc. EUROSPEECH 1995, pp. 2171-2174.
17. Pallett, D.S., Fiscus, J.G., Fisher, W.M., Garofolo, J.S., Lund, B.A., Przybocki, M.A., 1994. 1993 Benchmark tests for the ARPA spoken language program. In: Proc. of the Human Language Technology Workshop, pp. 49-74.
18. Robins A. Catastrophic forgetting, rehearsal, and pseudo-rehearsal. Connect. Sci. 7 (1995) 123-146
19. Sagayama, S., Shinoda, K., Nakai, M., Shimodaira, H., 2001. Analytic methods for acoustic model adaptation: A review. In: Proc. Adaptation Methods for Speech Recognition, ISCA ITR-Workshop, pp. 67-76.
20. Stadermann, J., Rigoll, G., 2005. Two-stage speaker adaptation of hybrid tied-posterior acoustic models. In: Proc. ICASSP-05, Philadelphia, pp. I-997-1000.