One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation

TL;DR

This paper introduces a one-shot voice conversion method that uses speaker adaptation and a prosody module to improve style transfer, speaker similarity, and speech quality with minimal training data.

Contribution

It proposes a novel one-shot voice conversion approach combining speaker normalization, weight regularization, and prosody extraction within a recognition-synthesis framework.

Findings

Outperforms state-of-the-art one-shot VC systems in style and speaker similarity.

Maintains high speech quality despite limited training data.

Effectively decouples speech factors like content, speaker, and style.

Abstract

One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the recognition-synthesis framework and propose a one-shot voice conversion approach for style transfer based on speaker adaptation. First, a speaker normalization module is adopted to remove speaker-related information in bottleneck features extracted by ASR. Second, we adopt weight regularization in the adaptation process to prevent over-fitting caused by using only one utterance from target speaker as training data. Finally, to comprehensively decouple the speech factors, i.e., content, speaker, style, and transfer source style to the target, a prosody module is used to extract prosody representation. Experiments show that our approach is superior to the state-of-the-art one-shot VC systems in terms of style and speaker similarity; additionally, our approach also maintains good speech quality.