Abstract:Zero-shot Text-to-Speech (TTS) models can generate speech that captures both the voice timbre and accent of a reference speaker. However, disentangling these attributes and individually controlling the output accent remains challenging. In this study, we introduce a post-hoc and training-free approach to neutralize accent while preserving the speaker's original timbre, utilizing inference-time activation steering. We first extract layer-specific "steering vectors" offline, which are derived from the activation differences within the TTS model between accented and native speech. During inference, the steering vectors guide the model to produce accent-neutralized, timbre-preserving speech. Empirical results demonstrate that the proposed steering vectors effectively mitigate the output accent and exhibit strong generalizability to unseen accented speakers, offering a practical solution for accent-free voice cloning. We further confirm that speaker timbre is largely preserved via speaker embedding cosine similarity and speaker verification acceptance rate computed in an estimated accent-orthogonal subspace, as well as subjective listening tests. Audio demo: this https URL
From: Mu Yang [view email]
[v1]
Fri, 6 Mar 2026 07:17:56 UTC (303 KB)
[v2]
Thu, 10 Sep 2026 06:12:20 UTC (358 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。