반응형
[Paper 리뷰] AdaptVC: High Quality Voice Conversion with Adaptive Learning
AdaptVC: High Quality Voice Conversion with Adaptive LearningVoice conversion을 위해서는 source에서 disentangled linguistic content를 추출하고 reference에서 voice style을 추출할 수 있어야 함AdaptVCAdapter를 활용하여 self-supervised speech feature를 tuning 해 content, speaker를 효과적으로 disentangleCross-attention speaker conditioning과 conditional flow matching을 활용하여 synthesis quality를 향상논문 (ICASSP 2025) : Paper Link1. Introductio..
Paper/Conversion
2025. 5. 9. 15:58
반응형