AccentBox: Towards High-Fidelity Zero-Shot Accent Generation
Abstract
A two-stage pipeline improves accent fidelity and control in zero-shot speech synthesis by using an accent identification model to condition a zero-shot TTS system on speaker-agnostic accent embeddings, enabling foreign accent conversion, accented TTS, and unseen accent generation.
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.
Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper