Multi-resolution modulation-filtered cochleagram feature for LSTM-based dimensional emotion recognition from speech.
Zhichao PengJianwu DangMasashi UnokiMasato AkagiPublished in: Neural Networks (2021)
Keyphrases
- emotion recognition
- multiresolution
- audio visual
- emotional speech
- human computer interaction
- speaker verification
- facial expressions
- sentiment analysis
- feature vectors
- emotion classification
- facial images
- information fusion
- emotional state
- multi modal
- human subjects
- affective states
- machine learning
- multi stream
- low level
- metadata