Boosting HMM performance with a memory upgrade

INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP

Volumn 4, Issue , 2006, Pages 1730-1733

  De Wachter, Mathias ^a   Demuynck, Kris ^a   Van Compernolle, Dirk ^a  

^a UNIVERSITY OF LEUVEN   (Belgium)

Author keywords

DTW; Episodic; Example based speech recognition

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; DEEP NEURAL NETWORKS; HIDDEN MARKOV MODELS; MARKOV PROCESSES; TELEPHONE SETS;

AUTOMATIC SPEECH RECOGNITION; DYNAMIC INFORMATION; EPISODIC; EXAMPLE BASED; MARKOVIAN; NEW APPROACHES; STABLE STATE; STATE OF THE ART;

SPEECH RECOGNITION;

EID: 34547512577     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. M. Ostendorf, V. V. Digalakis, and O. A. Kimball, "From HMM's to segment models: A unified view of stochastic modeling for speech recognition," IEEE Trans, on SAP, vol. 4, no. 5, pp. 360-378, 1996.
2. J. A. Bilmes, G. Zweig, T. Richardson, K. Filali, K. Livescu, P. Xu, K. Jackson, Y. Brandman, E. Sandness, E. Holtz, J. Torres, and B. Byrne, "Discriminatively structured graphical models for speech recognition," 2001, Report of the JHU 2001 Summer Workshop.
3. M. De Wachter, K. Demuynck, D. Van Compernolle, and P. Wambacq, "Data driven example based continuous speech recognition," in Proc. EUROSPEECH, Geneva, Switzerland, Sept. 2003, pp. 1133-1136.
4. M. De Wachter, K. Demuynck, P. Wambacq, and D. Van Compernolle, "A locally weighted distance measure for example based speech recognition," in Proc. ICASSP, Montreal, Canada, May 2004, vol. I, pp. 181-184.
5. M. Matton, M. De Wachter, D. Van Compernolle, and R. Cools, "A discriminative locally weighted distance measure for speaker independent template based speech recognition," in Proc. ICSLP, Jeju Island, Korea, Oct. 2004, vol. I, pp. 429-432.
6. S. Axelrod and B. Maison, "Combination of hidden markov models with dynamic time warping for speech recognition," in Proc. ICASSP, Montreal, May 2004, pp. 173-176.
7. G. Aradilla, J. Vepa, and H Bourlard, "Improving speech recognition using a data-driven approach," in Proc. EUROSPEECH, Lisbon, Portugal, Sept. 2005, pp. 3333-3336.
8. K. Demuynck, T. Laureys, D. Van Compernolle, and H. Van hamme, "Flavor: a flexible architecture for LVCSR," in Proc. EUROSPEECH, Geneva, Switzerland, Sept. 2003, pp. 1973-1976.
9. J. Duchateau, K. Demuynck, and D. Van Compernolle, "Fast and accurate acoustic modelling with semi-continuous HMMs," Speech Comm., vol. 24, no. 1, pp. 5-17, Apr. 1998.
10. K. Demuynck, J. Duchateau, D. Van Compernolle, and P. Wambacq, "An efficient search space representation for large vocabulary continuous speech recognition," Speech Comm., vol. 30, no. 1, pp. 37-53, Jan. 2000.
11. K. Demuynck, J. Duchateau, and D. Van Compernolle, "Optimal feature sub-space selection based on discriminant analysis," in Proc. EUROSPEECH, Budapest, Hungary, Sept. 1999, vol. III, pp. 1311-1314.
12. J.-L. Gauvain, L.F. Lamel, G. Adda, and M. Adda-Decker, "Speaker-independent continuous speech dictation," Speech Communication, vol. 15, no. 1-2, pp. 21-37, Oct. 1994.
13. M. Bisani and H. Ney, "Bootstrap estimates for confidence intervals in asr performance evaluation," in Proc. ICASSP, Montreal, Canada, May 2004, pp. 409-412.