Unsupervised stream-weights computation in classification and recognition tasks

IEEE Transactions on Audio, Speech and Language Processing

Volumn 17, Issue 3, 2009, Pages 436-445

  Sánchez Soto, Eduardo ^b,c   Potamianos, Alexandros ^a   Daoudi, Khalid ^b  

^a TECHNICAL UNIVERSITY OF CRETE   (Greece)

^b CNRS   (France)

^c ORANGE LABS   (France)

Author keywords

Decision fusion; Multistream weights estimation; Robust speech recognition

Indexed keywords

ARTIFICIAL DATA; AUDIO-VISUAL SPEECH; BACKGROUND MODEL; CLASS-DISTANCE; CLASSIFICATION AND RECOGNITION; CLASSIFICATION ERRORS; CLASSIFICATION TASKS; DECISION FUSION; INFORMATIVENESS; MODELING ERRORS; MULTISTREAM WEIGHTS ESTIMATION; NONLINEAR FUNCTIONS; ROBUST SPEECH RECOGNITION; STREAM RELIABILITY; TESTING CONDITIONS; THEORETICAL RESULT; TWO-STREAM; USE-MODEL; WEIGHT ESTIMATION;

ALGORITHMS; ESTIMATION;

SPEECH RECOGNITION;

EID: 70350439278     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2008.2011513     Document Type: Article

References (16)

1. H. Bourlard and S. Dupont, "A new ASR approach based on independent processing and recombination of partial frequency bands, " in Proc. ICSLP, Philadelphia, PA, Oct. 1996.
2. T. Stephenson, M. Mathew, and H. Bourlard, "Modeling auxiliary information in bayesian network based ASR, " in Proc. Eurospeech, Aalborg, Denmark, Sep. 2001.
3. G. Potamianos, C. Neti, G. Gravier, A. Garg, and A. Senior, "Recent advances in the automatic recognition of audiovisual speech, " Proc. IEEE, vol. 91, no. 9, pp. 1306-1326, Sep. 2003.
4. C. Chibelushi, J. Mason, and F. Deravi, "Integration of acoustic and visual speech for speaker recognition, " in Proc. EUROSPEECH, Berlin, Germany, Sep. 1993.
5. S. Dupont and J. Luettin, "Audio-visual speech modeling for continuous speech recognition, " IEEE Trans. Multimedia, vol. 2, no. 3, pp. 141-151, Sep. 2000.
6. M. Heckmann, F. Berthommier, and K. Kroschel, "Noise adaptive stream weighting in audio-visual speech recognition, " EURASIP J. Appl. Signal Process., vol. 1, no. 11, pp. 1260-1273, Nov. 2002.
7. A. Adjoudani and C. Benoit, "On the integration of auditory and visual parameters in an HMM-based ASR, " Springer Verlag, Series F: Comput. Syst. Sci., vol. 150, pp. 465-472, 1996.
8. J. Luettin, G. Potamianos, and C. Neti, "Asynchronous stream modeling for large vocabulary audio-visual speech recognition, " in Proc. ICASSP, Salt Lake City, UT, May 2001, pp. 169-172.
9. J. Hernando, "Maximum likelihood weighting of dynamic speech features forCDHMMspeech recognition, " in Proc. ICASSP, Munich, Germany, Apr. 1997, pp. 1267-1270.
10. G. Potamianos and H. P. Graf, "Discrimative training of HMM stream exponents for audio-visual speech recognition, " in Proc. ICASSP, Seattle, WA, May 1998, pp. 3733-3736.
11. C. Miyajima, K. Tokuda, and T. Kitamura, "Audio visual speech recognition using MCE-basedHMMsand model dependent stream weights, " in Proc. ICSLP, Beijing, China, Oct. 2000.
12. G. Potamianos, J. Luettin, and C. Neti, "Hierarchical discriminant features for audio-visual LVCSR, " in Proc. ICASSP, Salt Lake City, UT, May 2001, pp. 165-168.
13. S. Nakamura, K. Kumatani, and S. Tamura, "Robust bi-modal speech recognition based on state synchronous modeling stream weight optimization, " in Proc. ICASSP, Orlando, FL, May 2002, pp. 309-312.
14. A. Rogozan, P. Deléglise, and M. Alissali, "Adaptive determination of audio and visual weights for automatic speech recognition, " in Proc. Workshop Audio-Visual Speech Process., Rhodes, Greece, Sep. 1997.
15. H. Glotin, D. Vergyri, C. Neti, G. Potamianos, and J. Luettin, "Weighting schemes for audio-visual fusion in speech recognition, " in Proc. ICASSP, Salt Lake City, UT, May 2001.
16. S. Nakamura, H. Ito, and K. Shikano, "Stream weight optimization of speech and lip image sequence for audio-visul speech recognition, " in Proc. ICSLP, Beijing, China, Oct. 2000G. Potamianos and C. Neti, "Stream confidence estimation for audio-visual speech recognition, " in Proc. ICSLP, Beijing, China, Oct. 2000.