Bootstrapping Non-Parallel Voice Conversion from Speaker-Adaptive Text-to-Speech.
Hieu-Thi LuongJunichi YamagishiPublished in: ASRU (2019)
Keyphrases
- text to speech
- prosodic features
- speech synthesis
- programming tool
- text to speech synthesis
- vocal tract
- word processing
- speaker verification
- multimodal interaction
- speech recognition
- english text
- shared memory
- named entity recognition
- parallel programming
- feature extraction
- parallel implementation
- speaker diarization
- multi modal
- pattern recognition