A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion.
Benjamin van NiekerkMarc-André CarbonneauJulian ZaïdiMatthew BaasHugo SeutéHerman KamperPublished in: ICASSP (2022)
Keyphrases
- emotion recognition
- text to speech
- speech recognition
- speech synthesis
- discrete version
- speech recognition errors
- fundamental frequency
- pattern recognition
- information systems
- audio visual
- speech sounds
- automatic speech recognition
- endpoint detection
- speech quality
- speaker verification
- processing units
- speech signal
- statistical analysis