---
title: "EZ-Ar-VC: Robust Arabic Voice Anonymization with Generalization across Dialects and Code-Switching"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.01268v1"
permalink: "https://feed.astralor.com/items/itm_11806e1fdb198b42e05298c0"
published: "2026-10-31T21:08:53.000Z"
score: 55
channel: "ai"
tags: ["推理效率","EZ-Ar-VC","Robust Arabic Voice","Anonymization","Generalization","Dialects","Code-Switching Voice","Existing"]
---

# EZ-Ar-VC: Robust Arabic Voice Anonymization with Generalization across Dialects and Code-Switching

## 速览

Voice conversion (VC) models can be used to anonymize speech data while preserving naturalness. Existing models, however, are mainly optimized for English and other high-resource languages, and they fail to generalize w…

## 关键点

- Voice conversion (VC) models can be used to anonymize speech data while preserving naturalness.
- Existing models, however, are mainly optimized for English and other high-resource languages, and they fail to generalize well to Arabic due to its distinct phonology.
- In this work, we comprehensively evaluate existing zero-shot VC systems for Arabic speech, identifying limitations in pronunciation preservation.

## 全文

Voice conversion (VC) models can be used to anonymize speech data while preserving naturalness. Existing models, however, are mainly optimized for English and other high-resource languages, and they fail to generalize well to Arabic due to its distinct phonology. In this work, we comprehensively evaluate existing zero-shot VC systems for Arabic speech, identifying limitations in pronunciation preservation. We then train an Arabic-centric model based on EZ-VC on diverse Arabic speech, and demonstrate strong performance in intelligibility, naturalness, and pronunciation preservation, while maintaining high speaker dissimilarity. Through subjective evaluation, we further demonstrate its robustness to code-switching and cross-dialectal conversion, as well as its generalization to Arabic dialects with limited representation in the training data. Our findings highlight the limitations of zero-shot VC and the importance of target-language adaptation for robust voice anonymization.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_11806e1fdb198b42e05298c0