Feature and score level combination of subspace Gaussinas in LVCSR task

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

Volumn , Issue , 2013, Pages 7604-7608

  Motlicek, Petr ^a   Povey, Daniel ^b   Karafiat, Martin ^c  

^a IDIAP RESEARCH INSTITUTE   (Switzerland)

^b JOHNS HOPKINS UNIVERSITY   (United States)

^c BRNO UNIVERSITY OF TECHNOLOGY   (Czech Republic)

Author keywords

Automatic Speech Recognition; Discriminative features; System combination

Indexed keywords

ACOUSTIC FEATURES; AUTOMATIC SPEECH RECOGNITION; DISCRIMINATIVE FEATURES; INDIVIDUAL SYSTEMS; MEETING RECOGNITION; RICH TRANSCRIPTIONS; SUBSPACE GAUSSIAN MIXTURE MODELS; SYSTEM COMBINATION;

SIGNAL PROCESSING;

SPEECH RECOGNITION;

EID: 84890476830     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2013.6639142     Document Type: Conference Paper

References (16)

1. H. Hermansky, D. Ellis and S. Sharma, 'Tandem connectionist feature extraction for conventional HMM systems," in Proc. of ICASSP, pp. 1635-1638, Turkey, 2000.
2. S. B. Davis and P. Mermelstein, "Comparison of parametric representation for monosyllabic word recognition in continuously spoken sentences," in IEEE Trans. on ASSP, 28(4):357-366, 1980.
3. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," in The Journal of the Acoustical Society of America, vol. 87, pp. 1738, 1990.
4. S. Dupont, C. Ris, O. Deroo and S. Poitoux, "Feature extraction and acoustic modeling: an approach for improved generalization across languages and accents," in Proc. of ASRU, pp. 29-34, Mexico, November 2005.
5. F. Grezl, M. Karafiat, S. Kontar, and J. Cernocky, "Probabilistic and bottle-neck features for LVCSR of meetings," in Proc. of ICASSP, pp. 757-760, Honolulu, USA, 2007.
6. F. Grezl and P. Fousek, "Optimizing bottle-neck features for LVCSR," in Proc. ofICASSP, pp. 4729-4732, Las Vegas, USA, 2008.
7. F. Grezl, M. Karafiat and L. Burget, "Investigation into bottleneck features for meeting speech recognition," in Proc. of Interspeech, pp. 2947-2950, Brighton, GB, 2009.
8. D. Povey, L. Burget, M. Agarwal, P. Akyazi, K. Feng, A. Ghoshal, O. Glembek, N. K. Goel, M. karafiat, A. Rastrow, R. C. Rose, P. Schwarz and S. Thomas, "The Subspace Gaussian mixture model-A structured model for speech recognition," In Computer Speech &Language, vol. 25, no. 2, pp. 404-439, 2011.
9. L. Burget, P. Schwarz, M. Agarwal, P. Akyazi, K. Feng, A. Ghoshal, O. Glembek, N. K. Goel, M. karafiat, D. Povey, A. Rastrow, R. C. Rose and S. Thomas, "Multilingual Acoustic Modeling For Speech Recognition Based On Subspace Gaussian Mixture Models", in Proc. of ICASSP, pp. 4334-4337, Dallas, USA, 2010.
10. T. N. Vu, T. Schultz and D. Povey., "Modeling Gender Dependency in the Subspace GMM Framework," in Proc. of ICASSP, pp. 4345-4348, Japan, 2012.
11. D. Povey, A. GhoshaJ, G. Boulianne, L. Burget, O. G1embek, N. K. Goel, M. Hannemann, P. Motlicek, Y. Qian, P. Schwarz, J. Silovsky, G. Stemmer and K. Vesely, "The Kaldi Speech Recognition Toolkit," in Proc. of ASRU, Hawai, USA, December 2011.
12. D. Povey, M. Karafiat, A. Ghoshal and P. Schwarz, "A Symmetrization of the Subspace Gaussian Mixture Model", in Proc. of ICASSP, pp. 4504-4507, Prague, Czech Republic, 2011.
13. J. G. Fiscus, "A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER)," in Proc. of ASRU, pp. 347-354, USA, 1997.
14. T. Hain, L. Burget, J. Dines, G. Garau, V. Wan, M. Karafiat, J. Vepa and M. Lincoln, "The AMI system for the transcription of speech meetings," in Proc. of ICASSP, pp. 357-360, Honolulu, USA, April 2007.
15. N. Kumar and A. G. Andreou, "Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognition," Speech Communication, 26(4):283-297, 1998.
16. P. Schwarz, P. Matejka and J. Cernocky, "Towards lower error rates in phoneme recognition," in Lecture Notes in Computer Science, pp. 465-472, Brno, 2004.