Multi-Task Learning with Auxiliary Speaker Identification for Conversational Emotion Recognition.
Jingye LiMeishan ZhangDonghong JiYijiang LiuPublished in: CoRR (2020)
Keyphrases
- emotion recognition
- speaker identification
- multi task learning
- multi task
- audio visual
- speech recognition
- multi modal
- gaussian mixture model
- audio features
- speech signal
- facial expressions
- learning tasks
- learning problems
- noisy environments
- broadcast news
- feature extraction
- human computer interaction
- sentiment analysis
- transfer learning
- mixture model
- emotional state
- computer vision
- kernel methods
- text classification
- multi class