Speech-Emotion Control for Text-to-Speech in Spoken Dialogue Systems Using Voice Conversion and x-vector Embedding.
Shunichi KoharaMasanobu AbeSunao HaraPublished in: APSIPA ASC (2023)
Keyphrases
- text to speech
- text to speech synthesis
- spoken dialogue systems
- speech synthesis
- vector space
- multimodal interaction
- prosodic features
- dialogue management
- dialogue system
- human machine interaction
- human behaviour
- word processing
- english text
- programming tool
- machine learning
- writing skills
- emotion recognition
- virtual humans
- user interaction
- knowledge acquisition
- feature selection