반응형
[Paper 리뷰] TokSing: Singing Voice Synthesis based on Discrete Tokens
TokSing: Singing Voice Synthesis based on Discrete TokensSelf-supervised learning model에서 추출된 discrete token을 활용하여 singing voice synthesis의 성능을 향상할 수 있음TokSingFlexible token blending을 제공하는 token formulator를 갖춘 discrete-based singing voice synthesis modelMelody signal을 discrete token과 integrate 하고 musical encoder에 melody enhancement strategy를 도입논문 (INTERSPEECH 2024) : Paper Link1. IntroductionSin..
Paper/SVS
2024. 7. 11. 09:09
반응형