Audio-visual feature-decision level fusion for spontaneous emotion estimation in speech conversations.
Aya SayedelahlRodrigo AraujoMohamed S. KamelPublished in: ICME Workshops (2013)
Keyphrases
- audio visual
- emotion recognition
- decision level fusion
- feature level
- multi modal
- conversational speech
- visual information
- audio features
- speaker verification
- visual data
- multimedia
- multi stream
- estimation algorithm
- automatic speech recognition
- multi sensor
- image processing
- computer vision
- broadcast news
- wordnet
- language model
- facial expressions
- high level