Hierarchical Component-attention Based Speaker Turn Embedding for Emotion Recognition.
Shuo LiuJinlong JiaoZiping ZhaoJudith DineleyNicholas CumminsBjörn W. SchullerPublished in: IJCNN (2020)
Keyphrases
- emotion recognition
- speaker verification
- audio visual
- emotional speech
- human computer interaction
- multi modal
- facial expressions
- sentiment analysis
- speaker recognition
- emotion classification
- visual information
- visual data
- information fusion
- acoustic features
- machine learning
- emotional state
- noisy environments
- speech recognition
- computational intelligence
- user interface
- feature vectors
- speaker diarization
- website
- multimedia