TRAP-TANDEM: Data-driven extraction of temporal features from speech

2003 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2003

Volumn , Issue , 2003, Pages 255-260

  Hermansky, Hynek ^a  

^a IDIAP RESEARCH INSTITUTE   (Switzerland)

Author keywords

[No Author keywords available]

Indexed keywords

SPECTRAL DENSITY; SPEECH;

AUTOMATIC RECOGNITION; DATA DRIVEN; SHORT-TERM SPECTRUM; SUB WORDS; TEMPORAL FEATURES; TEMPORAL TRAJECTORIES;

SPEECH RECOGNITION;

EID: 84946730259     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2003.1318450     Document Type: Conference Paper

References (32)

1. A. Adami, L. Burget, S. Dupont, H. Garudadri, F. Grezl, H. Hermansky, P. Jain, S. Kajarekar, N. Morgan and S. Sivadas, "QUALCOMM-ICSI-OGI Features for ASR", in Proceedings ICSLP 2002, Denver, Colorado, USA, Sep, 2002
2. M. Athineos and D. Ellis, "Frequency-domain linear prediction for temporal features", Proc. IEEE ASRU-2003 Workshop, St. Thomas, US Virgin Islands, 2003 (this proceedings)
3. J.J. Atick, "Could information theory provide an ecological theory of sensory processing?", in Network: Computation in Neural Systems, Vol. 3, pp. 213-251, 1992
4. J. Bilmes, "Maximal mutual information based reduction strategies for cross-correlation based joint distributional modeling", Proc. ICASSP98, SP14.6, Seattle, 1998
5. H. Bourlard and Ch. Wellekens, "Links Between Markov Models and Multilayer Perceptrons.", IEEE Transactions on Pattern Analysis and Machine Intelligence 12: 1167-1178, 1990
6. D.D. Depireux, J.Z. Simon, D.J. Klein, S.S. Shamma, "Spectro-Temporal Response Fields Characterization with Dynamic Ripples in Ferret Primary Auditory Cortex", in J. Neurophysiology, Vol. 85, pp. 1220-1234, 2001
7. H. Fletcher, Speech and hearing in communication, The ASA edition, edited by J.B. Allen, Acoust. Soc. Am., reissue of the original edition from 1953
8. K. Fukunaga, Statistical Pattern Recognition, Academic Press, San Diego, 1990.
9. F. Grezl and H. Hermansky, "Local averaging and differentiating of spectral plane for TRAP-based ASR", Proc. Eurospeech 2003, Geneva 2003
10. H. Hermansky, Perceptual linear predictive (PLP) analysis of speech, J. Acoust. Soc. Am., vol. 87, no. 4, pp. 1738-1752.
11. H. Hermansky, "The Modulation Spectrum in Automatic Recognition of Speech", in 1997 IEEE Workshop on Automatic
12. H. Hermansky and S. Sharma, "TRAPS Classifiers of Temporal Patterns", in ICSLP'98, Sydney, Australia, 1998,
13. H. Hermansky and P. Jain, "Band-independent speech event categories for TRAP based ASR", Proc. Eurospeech 2003, Geneva 2003
14. H. Hermansky, "Should recognizers have ears?", in Speech Communication, vol. 25, num. 3-27, 1998
15. H. Hermansky and D.P.W. Ellis and S. Sharma, "Connectionist Feature Extraction for Conventional HMM Systems", in Proc. ICASSP'00, Istanbul, Turkey, 2000
16. H. Hermansky and S. Sharma, "Temporal Patterns (TRAPS) in ASR of Noisy Speech", in Proc. ICASSP'99, Phoenix, Arizona, USA, Mar, 1999
17. H. Hermansky and N. Malayath, "Spectral Basis Functions from Discriminant Analysis", in Proc. ICSLP'98, Sydney, Australia, 1998
18. M.J. Hunt, "A statistical approach to metrics for word and syllable recognition", J. Acoust. Soc. Am., 66(S1), S35(A), 1979
19. www.icsi.berkeley.edu/speech/faq/ICSI-SPEECH-FAQ
20. P. Jain, PhD. thesis, Department of Electrical and Computer Engineering, OGI School of Oregon Health & Sciences University, Portland, Oregon, 2003
21. P. Jain and H. Hermansky, "Effect of combining temporal patterns from critical-bands on ASR ", Proc. Eurospeech 2003, Geneva 2003
22. F. Jelinek, Statistical Methods for Speech Recognition, MIT Press, 1998
23. D.J. Klein, D.A. Depireux, J.Z. Simon, S.S. Shamma," Robust spectro-temporal reverse correlation for auditory system: Optimizing stimulus design", in J. Comp. Neuroscience, Vol. 9, pp. 85-111, 2000
24. S. Kajarekar, and H. Hermansky (2000), " Analysis of information in speech and its application in speech recognition", in Proceedings of Workshop in Text, Speech and Dialogue 2000, Brno, Czech Republic, Springer-Verlag.
25. N. Kanedera, T. Arai, H. Hermansky and M. Pavel, "On the relative importance of various components of modulation spectrum for automatic speech recognition", Speech Communication, 28, (43-55), Elsevier 1999
26. M.S. Lewicki, "Efficient coding of natural sounds", Nature Neuroscience, 5(4), pp. 356-363, 2002
27. N. Morgan et al., DARPA-EARS Meeting, Boston, MA, May 2003
28. M. Sachs and E. Young, "Encoding of steady state vowels in the auditory nerve: representation in terms of discharge rate", J. Acoust. Soc. Am. 66, pp. 470-479, 1979
29. P. Schwarz, P. Matejka and J.Cernocký, "Recognition of Phoneme Strings using TRAP Technique", Proc. Eurospeech 2003, Geneva 2003
30. S. Sivadas and H. Hermansky, "Hierarchical Tandem Feature Extraction", in Proceedings ICASSP 2002, Orlando, Florida, USA, May, 2002
31. H. H. Yang and S. Sharma and S. van Vuuren and H. Hermansky, "Relevance of TimeFrequency Features for Phonetic and Speaker/Channel Classification", in Speech Communication, Aug, 2000
32. E. Young and M. Sachs, "Representation of steady-state vowels in the temporal aspects of the discharge patterns of population of auditory nerve fibers, J. Acoust. Soc. Am 66, pp. 1381-1403, 1979.