AccentBox: Towards High-Fidelity Zero-Shot Accent Generation
Sound
2026-02-06 v2 Computation and Language
Audio and Speech Processing
Abstract
While recent Zero-Shot Text-to-Speech (ZS-TTS) models have achieved high naturalness and speaker similarity, they fall short in accent fidelity and control. To address this issue, we propose zero-shot accent generation that unifies Foreign Accent Conversion (FAC), accented TTS, and ZS-TTS, with a novel two-stage pipeline. In the first stage, we achieve state-of-the-art (SOTA) on Accent Identification (AID) with 0.56 f1 score on unseen speakers. In the second stage, we condition a ZS-TTS system on the pretrained speaker-agnostic accent embeddings extracted by the AID model. The proposed system achieves higher accent fidelity on inherent/cross accent generation, and enables unseen accent generation.
Cite
@article{arxiv.2409.09098,
title = {AccentBox: Towards High-Fidelity Zero-Shot Accent Generation},
author = {Jinzuomu Zhong and Korin Richmond and Zhiba Su and Siqi Sun},
journal= {arXiv preprint arXiv:2409.09098},
year = {2026}
}
Comments
Accepted by ICASSP 2025