Robust bi-modal speech recognition based on state synchronous modeling and stream weight optimization

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

Volumn 1, Issue , 2002, Pages 309-312

  Nakamura, Satoshi ^a   Kumatani, Ken’ichi ^a,b   Tamura, Satoshi ^a,c  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^b NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

^c TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

AUDIO VISUAL SYSTEMS; AUTOMATIC SPEECH RECOGNITION; BIMODAL SPEECH RECOGNITION; HIDDEL MARKOV MODELS; STATE SYNCHRONOUS MODELING; STREAM WEIGHT OPTIMIZATION;

ALGORITHMS; CORRELATION METHODS; FEATURE EXTRACTION; MARKOV PROCESSES; MATHEMATICAL MODELS; MODAL ANALYSIS; OPTIMIZATION; SPURIOUS SIGNAL NOISE; TIME DOMAIN ANALYSIS; VOICE/DATA COMMUNICATION SYSTEMS;

SPEECH RECOGNITION;

EID: 0036295828     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2002.5743716     Document Type: Article

References (7)

1. Improved bimodal speech recognition using tied-mixture HMMs and 5000 word audio-visual synchronous database
2. Stream weight optimization of speech and lip image sequence for audio-visual speech recognition
3. An adaptive integration method based on product HMM for Bi-modal speech recognition
4. Integrating audio and visual information to provide highly robust speech recognition
5. State synchronous modeling of audio-visual information for bi-modal speech recognition
6. Maximum likelihood weighting of dynamic speech features for CDHMM speech recognition
7. Discriminative training of HMM stream exponents for audio-visual speech recognition