반응형
[Paper 리뷰] NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis
NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis대부분의 voice synthesis model은 annotated label과 pair 되는 audio data가 필요함NANSY++Annotated paired audio data 없이 self-supervised manner로 backbone network를 trainingTraining 이후 각 voice application에 맞는 analysis feature를 partially modeling 하여 사용논문 (ICLR 2023) : Paper Link1. IntroductionGlow-TTS, Diff-TTS와 같은 기존 voice synthesis model은 labele..
Paper/Conversion
2025. 5. 6. 08:42
반응형