Optimal weighting of posteriors for audio-visual speech recognition

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

Volumn 1, Issue , 2001, Pages 161-164

  Heckmann, Martin ^a,b   Berthommier, Frédéric ^a   Kroschel, Kristian ^b  

^a GIPSA LAB   (France)

^b UNIVERSITY OF KARLSRUHE   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

AUDIO-VISUAL SPEECH RECOGNITION; SEPARATE IDENTIFICATION;

ACOUSTIC SIGNAL PROCESSING; DATABASE SYSTEMS; FEATURE EXTRACTION; OPTIMIZATION; PATTERN RECOGNITION SYSTEMS; PROBABILITY; WHITE NOISE;

CONTINUOUS SPEECH RECOGNITION;

EID: 0034848499     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2001.940792     Document Type: Article

References (9)

1. Adaptive fusion of acoustic and visual sources for automatic spech recognition
2. Multi-stream adaptive evidence combination for noise robust asr
3. Labeling audio-visual speech corpora and training an ann/hmm audio-visual speech recognition system
4. On the integration of auditory and visual parameters in an hmm-based asr
5. Speech recognition and sensory integration
6. Channel separability in the audio-visual integration of speech: A bayesian approach
7. Audio-visual speech modeling for continuous speech recognition
8. Comparing models for audiovisual fusion in a noisy-vowel recognition task