Differentiable WORLD Synthesizer-based Neural Vocoder With Application To End-To-End Audio Style Transfer. (arXiv:2208.07282v2 [eess.AS] UPDATED)

In this paper, we propose a differentiable WORLD synthesizer and demonstrate
its use in end-to-end audio style transfer tasks such as (singing) voice
conversion and the DDSP timbre transfer task. Accordingly, our baseline
differentiable synthesizer has no model parameters, yet it yields adequate
synthesis quality. We can extend the baseline synthesizer by appending
lightweight black-box postnets which apply further processing to the baseline
output in order to improve fidelity. An alternative differentiable approach
considers extraction of the source excitation spectrum …

application arxiv audio style transfer transfer