Speaker Dependency Analysis, Audiovisual Fusion Cues and a Multimodal BLSTM for Conversational Engagement Recognition.
Yuyun HuangEmer GilmartinNick CampbellPublished in: INTERSPEECH (2017)
Keyphrases
- audio visual
- multimodal fusion
- dependency analysis
- multi modal
- recognition rate
- multimodal biometrics
- visual information
- gait recognition
- ontology driven
- emotion recognition
- pattern recognition
- impact analysis
- human face recognition
- object recognition
- speaker verification
- visual data
- visual speech
- multimedia
- multi party
- information entropy
- database
- information fusion
- data fusion
- speech recognition
- domain knowledge
- feature extraction
- data mining