Multimodal fusion of polynomial classifiers for automatic person recognition

Proceedings of SPIE-The International Society for Optical Engineering

Volumn 4390, Issue , 2001, Pages 166-174

  Broun, Charles C ^a   Zhang, Xiaozheng ^b  

^a MOTOROLA INC   (United States)

^b GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Active shape model; Lip tracking; Markov random field; Multimodal fusion; Polynomial classifier; Speaker verification; Speech recognition

Indexed keywords

CONSTRAINT THEORY; FEATURE EXTRACTION; MARKOV PROCESSES; OPTICAL SENSORS; POLYNOMIALS; PROBABILISTIC LOGICS; ROBUSTNESS (CONTROL SYSTEMS); SIGNAL TO NOISE RATIO;

MULTIMODE FUSION; POLYNOMIAL CLASSIFIERS;

SPEECH RECOGNITION;

EID: 0034930302     PISSN: 0277786X     EISSN: None     Source Type: Journal    
DOI: 10.1117/12.421167     Document Type: Article

References (17)

1. Comparing models for audiovisual fusion in a noisy-vowel recognition task
2. Lip feature extraction towards an automatic speechreading system
3. A computational approach to edge detection
4. Computational vision and regularization theory
5. A confidence-based approach to the labeling problem
6. Speaker recognition: A tutorial
7. The use of cohort normalized scores for speaker verification
8. Automatic speaker recognition using gaussian mixture speaker models
9. Speaker recognition using neural networks and conventional classifiers
10. Polynomial classifier techniques for speaker verification
11. A computationally scalable speaker recognition system
12. XM2VTSDB: The extended M2VTS database