Amphion is an open-source toolkit for Audio, Music, and Speech Generation, targeting to
ease the way for junior researchers and engineers into these fields. It presents a unified …

The diffusion-based Singing Voice Conversion (SVC) methods have achieved remarkable
performances, producing natural audios with high similarity to the target timbre. However …

In this study, we present SingVisio, an interactive visual analysis system that aims to explain
the diffusion model used in singing voice conversion. SingVisio provides a visual display of …

We introduce HybridVC, a voice conversion (VC) framework built upon a pre-trained
conditional variational autoencoder (CVAE) that combines the strengths of a latent model …

Zero-shot voice conversion aims to transform a source speech utterance to match the timbre
of a reference speech from an unseen speaker. Traditional approaches struggle with timbre …

Singing voice conversion (SVC) is hindered by noise sensitivity due to the use of non-robust
methods for extracting pitch and energy during the inference. As clean signals are key for …

The lack of a publicly-available large-scale and diverse dataset has long been a significant
bottleneck for singing voice applications like Singing Voice Synthesis (SVS) and Singing …