Voice-preserving Zero-shot Multiple Accent Conversion

TL;DR

This paper introduces a zero-shot accent conversion system that changes a speaker's accent while preserving their voice identity, enabling conversion for unseen speakers across multiple accents with high fidelity.

Contribution

We propose a novel adversarial learning approach that disentangles accent features from speaker identity, allowing zero-shot conversion to multiple accents while maintaining voice characteristics.

Findings

Model effectively converts unseen speakers to target accents.

Generated audio closely resembles target accent and original speaker.

Subjective evaluations confirm high quality and naturalness.

Abstract

Most people who have tried to learn a foreign language would have experienced difficulties understanding or speaking with a native speaker's accent. For native speakers, understanding or speaking a new accent is likewise a difficult task. An accent conversion system that changes a speaker's accent but preserves that speaker's voice identity, such as timbre and pitch, has the potential for a range of applications, such as communication, language learning, and entertainment. Existing accent conversion models tend to change the speaker identity and accent at the same time. Here, we use adversarial learning to disentangle accent dependent features while retaining other acoustic characteristics. What sets our work apart from existing accent conversion models is the capability to convert an unseen speaker's utterance to multiple accents while preserving its original voice identity. Subjective evaluations show that our model generates audio that sound closer to the target accent and like the original speaker.