Disentanglement of Emotional Style and Speaker Identity for Expressive Voice Conversion.
Zongyang DuBerrak SismanKun ZhouHaizhou LiPublished in: INTERSPEECH (2022)
Keyphrases
- emotion recognition
- speaker verification
- audio visual
- synthesized speech
- prosodic features
- speech recognition
- speech sounds
- identity management
- speaker recognition
- emotional intelligence
- real time
- text to speech
- knowledge base
- visual features
- multi modal
- facial expressions
- speech synthesis
- authorship attribution
- mel frequency cepstral coefficients
- feature space
- information systems