Non-Parallel Voice Conversion System With WaveNet Vocoder and Collapsed Speech Suppression.
Yi-Chiao WuPatrick Lumban TobingKazuhiro KobayashiTomoki HayashiTomoki TodaPublished in: IEEE Access (2020)
Keyphrases
- text to speech
- emotion recognition
- speech recognition
- speech synthesis
- speech recognition errors
- voice activity detection
- fundamental frequency
- speech sounds
- speech signal
- speech quality
- parallel processing
- audio visual
- information retrieval
- linear prediction
- text to speech synthesis
- parallel computing
- multiscale
- genetic algorithm