Region Dependent Transform on MLP features for speech recognition

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2011, Pages 221-224

  Ng, Tim ^a   Zhang, Bing ^a   Matsoukas, Spyros ^a   Nguyen, Long ^a  

^a BBN TECHNOLOGIES   (United States)

Author keywords

Bottleneck features; Discriminative training; Mandarin speech recognition; Multi layer perceptrons; Region Dependent Transform

Indexed keywords

ACOUSTIC FEATURES; ADAPTIVE TRAINING; BOTTLENECK FEATURES; CHARACTER ERROR RATES; DISCRIMINATIVE TRAINING; HIGHER DIMENSIONAL FEATURES; MANDARIN SPEECH RECOGNITION; MULTI-LAYER PERCEPTRONS; RELATIVE REDUCTION; SPEAKER DEPENDENTS; TRAINING PROCEDURES;

CYBERNETICS; FEATURE EXTRACTION; PATTERN RECOGNITION SYSTEMS;

SPEECH RECOGNITION;

EID: 84865718241     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. H. Hermansky and S. Sharma, "TRAPS - classifiers of temporal patterns," in Proceedings of ICSLP, Sydney, Australia, December 1998.
2. H. Hermansky, D. P. W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional hmm systems," in Proceedings of ICASSP, 2000, pp. 1635-1638.
3. F. Grézl, M. Karafit, S. Kontr, and J. Cernocky, "Probabilistic and bottle-neck features for LVCSR of meetings," in Proceedings of ICASSP, Hononulu, U.S.A., May 2007.
4. P. Fousek, L. Lamel, and J. L. Gauvain, "Transcribing broadcast data using MLP features," in Proceedings of InterSpeech, Brisbane, Australia, September 2008.
5. J. Park, F. Diehl, M. J. F. Gales, M. Tomalin, and P. C. Woodland, "Training and adapting MLP features for Arabic speech recognition," in Proceedings of ICASSP, Taipei, Taiwan, April 2009.
6. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," Journal of the Acoustical Society of America, vol. 87(4), pp. 1738-1752, 1990.
7. T. Ng, B. Zhang, and L. Nguyen, "Jointly optimized discriminative features for speech recognition," in Proceedings of Inter- Speech, Makuhari, Chiba, Japan, September 2010.
8. B. Zhang, S. Matsoukas, and R. Schwartz, "Discriminatively trained region-dependent transform for speech recognition," in Proceedings of ICASSP, Toulouse, France, May 2006.
9. J. Zheng and A. Stolcke, "Improved discriminative training using phone lattices," in Proceedings of InterSpeech, Lisbon, Portugal, September 2005.
10. T. Ng, B. Zhang, K. Nguyen, and L. Nguyen, "Progress in the BBN 2007 Mandarin speech to text system," in Proceedings of ICASSP, Las Vegas, U.S.A., April 2008.
11. P. Fousek, "Extraction of features for automatic recognition of speech based on spectral dynamics," Ph.D. dissertation, Czech Technical University, March 2007.
12. B. Zhang, S. Matsoukas, and R. Schwartz, "Recent progress on the discriminative region-dependent transform for speech feature extraction," in Proceedings of ICSLP, Pittsburgh, U.S.A., September 2006.
13. D. C. Liu and J. Nocedal, "On the limited memory BFGS methods for large scale optimization," Mathematical Programming 45, pp. 503-528, 1989.
14. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer Speech and Language, vol. 12, pp. 75-98, 1998.