A system for transforming the emotion in speech: combining data-driven conversion techniques for prosody and voice quality.
Zeynep InanogluSteve J. YoungPublished in: INTERSPEECH (2007)
Keyphrases
- text to speech
- data driven
- emotion recognition
- speech synthesis
- text to speech synthesis
- synthesized speech
- audio visual
- prosodic features
- speech quality
- high quality
- speech recognition
- emotional state
- speaker verification
- emotional speech
- higher quality
- pattern recognition
- human computer interaction
- multi stream
- facial expressions
- quality assessment
- multi modal
- multimedia
- spoken language
- language acquisition