Discriminative adaptation for log-linear acoustic models

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 1648-1651

  Lööf, Jonas ^a   Schlüter, Ralf ^a   Ney, Hermann ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

Adaptation; Log linear models; Speech recognition

Indexed keywords

AFFINE TRANSFORMS; MAXIMUM LIKELIHOOD; REGRESSION ANALYSIS; SPEECH COMMUNICATION; ACOUSTIC MODELING;

ADAPTATION; FEATURE TRANSFORM; LOGLINEAR MODEL; MAXIMUM LIKELIHOOD LINEAR REGRESSION; PARAMETRISATION; SPEAKER ADAPTATION; SPEECH RECOGNITION SYSTEMS; UNSUPERVISED ADAPTATION; ACOUSTICS MODEL; GAUSSIAN MODELING; MAXIMUM-LIKELIHOOD; PARAMETRIZATIONS;

SPEECH RECOGNITION;

EID: 79959843405     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Heigold, G., Rybach, D., Schlüter, R., and Ney, H., "Investigations on convex optimization using log-linear HMMs for digit string recognition," in Interspeech, Brighton, U.K., Sep. 2009, pp. 216-219.
2. Gales, M. J. F., "Maximum likelihood linear transformations for HMM-based speech recognition," Computer Speech and Language, vol. 12, no. 2, pp. 75 - 98, Apr. 1998. (Pubitemid 128383747)
3. Lööf, J., Gollan, C., Hahn, S., Heigold, G., Hoffmeister, B., Plahl, C., Rybach, D., Schlüter, R., and Ney, H., "The RWTH 2007 TC-STAR evaluation system for European English and Spanish," in Proc. Int. Conf. on Spoken Language Processing, Antwerp, Belgium, Aug. 2007, pp. 2145 - 2148.
4. Tahir, M. A., Heigold, G., Plahl, C., Schlüter, R., and Ney, H., "Log-linear framework for linear feature transformations in speech recognition," in IEEE Automatic Speech Recognition and Understanding Workshop, Merano, Italy, Dec. 2009.
5. Uebel, L. F. and Woodland, P. C., "Discriminative linear transforms for speaker adaptation," in ISCA ITR-Workshop on Adaptation Methods in Speech Recognition, Sophia Antipolis, France, Aug. 2001, pp. 61 - 64.
6. Heigold, G., Wiesler, S., Nussbaum, M., Lehnen, P., Schlüter, R., and Ney, H., "Discriminative HMMs, log-linear models, and CRFs: What is the difference?" in IEEE International Conference on Acoustics, Speech, and Signal Processing, Dallas, Texas, USA, Mar. 2010, pp. 5546-5549.
7. Gunawardana, A., Mahajan, M., Acero, A., and Platt, J., "Hidden conditional random fields for phone classification," in Interspeech, Lisbon, Portugal, Sep. 2005.
8. Robinson, T., Hochberg, M., and Renals, S., "The use of recurrent networks in continuous speech recognition," in Automatic Speech and Speaker Recognition, K. K. Paliwal C.-H. Lee, F. K. S., Ed., Kluwer Academic Publishers, Norwell, MA, USA, 1996.
9. Riedmiller, M. and Braun, H., "A direct adaptive method for faster backpropagation learning: The Rprop algorithm," in ICNN, San Francisco, CA, USA, 1993.
10. Wiesler, S., Nußbaum, M., Heigold, G., Schlüter, R., and Ney, H., "Investigations on features for log-linear acoustic models in continuous speech recognition," in IEEE Automatic Speech Recognition and Understanding Workshop, Merano, Italy, Dec. 2009.
11. Lööf, J., Schlüter, R., and Ney, H., "Efficient estimation of speaker-specific projecting feature transforms," in Proc. Int. Conf. on Spoken Language Processing, Antwerp, Belgium, Aug. 2007, pp. 1557 - 1560.