Controlling the Strength of Emotions in Speech-Like Emotional Sound Generated by WaveNet.
Kento MatsumotoSunao HaraMasanobu AbePublished in: INTERSPEECH (2020)
Keyphrases
- emotion recognition
- emotional state
- affective computing
- emotional speech
- audio visual
- affect sensing
- human computer interaction
- speech recognition
- emotion classification
- facial expressions
- human behaviour
- speech synthesis
- sentiment analysis
- automatic speech recognition systems
- cognitive model
- automatic speech recognition
- emotional intelligence
- virtual characters
- acoustic features
- information processing
- multi modal
- video sequences