Feature selection for log-linear acoustic models

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2011, Pages 5324-5327

  Wiesler, S ^a   Richard, A ^a   Kubo, Y ^a   Schluter R ^a   Ney, H ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

1 regularization; acoustic modeling; feature selection; log linear models; ReliefF

Indexed keywords

ACOUSTIC MODEL; ACOUSTIC MODELING; FEATURE SELECTION ALGORITHM; FEATURE SELECTION METHODS; FULL MODEL; GAUSSIAN MIXTURE MODEL; LOGLINEAR MODEL; LOSS OF PERFORMANCE; PERFORMANCE DEGRADATION; RECOGNITION TIME; RELIEFF; TRAINING TIME; UNIVARIATE; WALL STREET JOURNAL;

ALGORITHMS; REGRESSION ANALYSIS; SIGNAL PROCESSING; SPEECH COMMUNICATION; SPEECH RECOGNITION;

FEATURE EXTRACTION;

EID: 80051636049     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2011.5947560     Document Type: Conference Paper

References (12)

1. S. Wiesler et.al., "Investigations on features for log-linear acoustic models in continuous speech recognition," in Proc. IEEE Automatic Speech Recognition and Understanding workshop, Merano, Italy, 2009.
2. Y. Hifny and S. Renals, "Speech recognition using augmented conditional random fields," IEEE Transactions on Audio, Speech, and Language Processing, vol. 17, no. 2, pp. 354-365, 2009.
3. A. Gunawardana et.al., "Hidden conditional random fields for phone classification," in Proc. Interspeech, 2005.
4. G. Zweig and P. Nguyen, "A segmental CRF approach to large vocabulary continuous speech recognition," in Proc. IEEE Automatic Speech Recognition and Understanding workshop, Merano, Italy, 2009.
5. I. Guyon and A. Elisseeff, "An introduction to variable and feature selection," The Journal of Machine Learning Research, vol. 3, pp. 1157-1182, 2003.
6. M. Riedmiller and H. Braun, "A direct adaptive method for faster backpropagation learning: The Rprop algorithm," in Proc. IEEE International Conference on Neural Networks, Nagoya, Japan, 1993.
7. D. Kershaw et.al., "Context-dependent classes in a hybrid recurrent network-HMM speech recognition system," Advances in Neural Information Processing Systems, vol. 8, pp. 750-756, 1995.
8. I.S. Duff, M.A. Heroux, and R. Pozo, "An overview of the sparse basic linear algebra subprograms: The new standard from the BLAS technical forum," ACM Transactions on Mathematical Software, vol. 28, no. 2, pp. 239-267, 2002.
9. D. Povey and P.C. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Orlando, USA, 2002.
10. Y. Yang and J.O. Pedersen, "A comparative study on feature selection in text categorization," in Proc. International Conference on Machine Learning, Nashville, USA, 1997.
11. I. Kononenko, "Estimating attributes: Analysis and extensions of RELIEF," in Proc. European Conference on Machine Learning, Catania, Italy, 1994.
12. G. Andrew and J. Gao, "Scalable training of L1-regularized log-linear models," in Proc. International Conference on Machine Learning, Corvallis, USA, 2007.