Cross-stream observation dependencies for multi-stream speech recognition

EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology

Volumn , Issue , 2003, Pages 2517-2520

  Çetin, Özgür ^a   Ostendorf, Mari ^a  

^a University of Washington   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH COMMUNICATION;

ASYNCHRONY; DISCRIMINANT INFORMATIONS; FRAME-BASED; MULTI-STREAM; PARTIAL STATE; RECOGNITION ACCURACY; SHORT TERM; SMALL GAIN;

SPEECH RECOGNITION;

EID: 84946757881     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. H. Bourlard and S. Dupont, "A new ASR approach based on independent processing and recombination of partial frequency bands," Proc. ICSLP, pp. 426-429, 1996.
2. J. Luettin, G. Potamianos and C. Neti, "Asynchronous stream modeling for large vocabulary audio-visual speech recognition," Proc. ICASSP, pp. 169-172, 2001.
3. H. Nock and S.Young, "Loosely coupledHMMsforASR," Proc. ICSLP, pp. 143-146, 2000.
4. N. Mirghafori and N. Morgan, "Transmissions and transitions: A study of two common assumptions in multi-band ASR," Proc. ICASSP, pp. 713-716, 2001.
5. J. Bilmes, "Buried Markov models for speech recognition," Proc. ICASSP, pp. 713-716, 1999.
6. H. Hermansky, S. Sharma and P. Jain, "Data-derived nonlinear mapping for feature extraction in HMM," Proc. ASRU Workshop, 1999.
7. J. Bilmes and G. Zweig, "The Graphical Models Toolkit: An open source software system for speech and time-series processing," Proc. ICASSP, pp. 3916-3919, 2002.