Abstract: Vocoder-based speech synthesis has become a promising technique to accommodate the demands of high-quality speech analysis, manipulation, and synthesis. However, most existing works focus on ...

Abstract: In a neural vocoder capable of generating high-quality waveform, constructing a multi-speaker vocoder by training with data from various speakers reduces the necessary amount of target ...

Although deep neural networks have facilitated significant progress of neural vocoders in recent years, they usually suffer from intrinsic challenges like opaque modeling, inflexible retraining under ...

AutoVC achieves zero-shot voice conversion using only a vanilla auto-encoder loss. The authors provide in their repo a pretrained model and the speaker embeddings of 4 speakers. They use a wavenet ...