A coupled HMM for audio-visual speech recognition

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

Volumn 2, Issue , 2002, Pages 2013-2016

  Nefian, Ara V ^a   Liang, Luhong ^a   Pi, Xiaobo ^a   Xiaoxiang, Liu ^a   Mao, Crusoe ^a   Murphy, Kevin ^a  

^a INTEL CORPORATION   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DISCRETE FOURIER TRANSFORMS; MARKOV PROCESSES; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; PRINCIPAL COMPONENT ANALYSIS; SENSOR DATA FUSION;

ACOUSTIC NOISE PERTURBATION; AUDIO-VISUAL SPEECH RECOGNITION; COUPLED HIDDEN MARKOV MODEL; LINEAR DISCRIMINANT ANALYSIS;

SPEECH RECOGNITION;

EID: 0036297183     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2002.5745027     Document Type: Article

References (13)

1. Coupled hidden Markov models for complex action recognition
2. Nonlinear manifold learning for visual speech recognition
3. Audiovisual speech processing
4. Audio-visual speech modeling for continuous speech recognition
5. Speechreading using shape and intensity information
6. Hearing lips and seeing voices
7. Audio visual speech recognition
8. Asynchronous stream modeling for large vocabulary audio-visual speech recognition