Controllable and Interpretable Singing Voice Decomposition via Assem-VC
Audio and Speech Processing
2021-10-26 v1 Sound
Abstract
We propose a singing decomposition system that encodes time-aligned linguistic content, pitch, and source speaker identity via Assem-VC. With decomposed speaker-independent information and the target speaker's embedding, we could synthesize the singing voice of the target speaker. In conclusion, we made a perfectly synced duet with the user's singing voice and the target singer's converted singing voice.
Keywords
Cite
@article{arxiv.2110.12676,
title = {Controllable and Interpretable Singing Voice Decomposition via Assem-VC},
author = {Kang-wook Kim and Junhyeok Lee},
journal= {arXiv preprint arXiv:2110.12676},
year = {2021}
}
Comments
Accepted to NeurIPS Workshop on ML for Creativity and Design 2021 (Oral)