Modeling both Context- and Speaker-Sensitive Dependence for Emotion Detection in Multi-speaker Conversations.
Dong ZhangLiangqing WuChanglong SunShoushan LiQiaoming ZhuGuodong ZhouPublished in: IJCAI (2019)
Keyphrases
- speech recognition
- speaker recognition
- audio visual
- speaker verification
- detection method
- speaker identification
- speaker diarization
- detection algorithm
- automatic speech recognition
- contextual information
- automatic detection
- detection accuracy
- object detection
- noisy environments
- gaussian mixture model
- false positives
- speech signal
- false alarms
- context sensitive
- emotion recognition
- vector quantization
- feature extraction