arXiv cs.CL· Injy Hamed, Adarsh Arigala, Rufael Marew, Arjun Gangwar, Atharva Kulkarni, Hanan Aldarmaki, Srinivasan Umesh·· 11 小时前AI 评分24
EZ-Ar-VC：面向阿拉伯语的鲁棒语音匿名化模型，跨方言与语码转换均可用
EZ-Ar-VC: Robust Arabic Voice Anonymization with Generalization across Dialects and Code-Switching
AI 导读
研究团队基于 EZ-VC 训练出阿拉伯语语音匿名化模型 EZ-Ar-VC，在可懂度、自然度和发音保留上表现强劲，同时保持较高的说话人差异度。主观评测显示，该模型对语码转换和跨方言转换具备鲁棒性，并能泛化到训练数据中覆盖较少的阿拉伯语方言。研究同时指出，现有零样本 VC 系统在阿拉伯语发音保留上存在明显局限，目标语言适配对稳健语音匿名化十分关键。
正文 · 原文
Abstract: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.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.01268 [cs.CL] |
| (or arXiv:2611.01268v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.01268 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Injy Hamed [view email]
[v1]
Sat, 31 Oct 2026 21:08:53 UTC (29 KB)
来源：arXiv cs.CL · arxiv.org