A real-time prototype for small-vocabulary audio-visual ASR.
Jonathan H. ConnellNorman HaasEtienne MarcheretChalapathy NetiGerasimos PotamianosSenem VelipasalarPublished in: ICME (2003)
Keyphrases
- audio visual
- multi modal
- visual information
- multi stream
- visual data
- temporal context
- person authentication
- emotion recognition
- automatic speech recognition
- audio visual speech recognition
- multimedia
- information retrieval
- multimodal fusion
- data sets
- sensor data
- human computer interaction
- feature extraction
- three dimensional