Speech-like Emotional Sound Generator by WaveNet.
Kento MatsumotoSunao HaraMasanobu AbePublished in: APSIPA (2019)
Keyphrases
- emotion recognition
- emotional state
- speech recognition
- automatic speech recognition systems
- audio visual
- speech signal
- affect sensing
- speech synthesis
- acoustic features
- recognition engine
- spoken language
- speech processing
- noisy environments
- speaker identification
- speaker recognition
- text to speech
- human behaviour
- visual information
- facial expressions
- database
- broadcast news
- spoken dialogue systems
- hidden markov models
- information retrieval
- data sets
- real time