Long-Time Speech Emotion Recognition Using Feature Compensation and Accentuation-Based Fusion.
Jiu SunJinxin ZhuJun ShaoPublished in: Circuits Syst. Signal Process. (2024)
Keyphrases
- emotion recognition
- emotional state
- multimodal fusion
- information fusion
- feature set
- audio visual
- text to speech synthesis
- data fusion
- multiple features
- emotional speech
- emotion classification
- multimodal interfaces
- feature fusion
- speech recognition
- neural network
- speech signal
- user interface
- video sequences
- combining multiple
- language acquisition
- matching score
- broadcast news
- fusion framework
- relevance feedback
- feature vectors