arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.09307eess.AScs.CLcs.CR
收藏

多说话人录音中的目标说话人匿名化

Target speaker anonymization in multi-speaker recordings

1 Universit\'e de Lorraine, CNRS, Inria, Loria, F-54000, Nancy, France 2 National Institute of Informatics, 2-1-2 Hitotsubashi, 101-8430, Tokyo, Japan

Natalia Tomashenko, Junichi Yamagishi, Xin Wang, Yun Liu, Emmanuel Vincent

AI总结:

本研究针对多说话人对话音频中的目标说话人匿名化难题,探索有效策略,指出开发中的潜在问题,并提出改进的评估方法,以弥补现有技术与评估的不足。

摘要:

现有的说话人匿名化研究大多集中于单说话人音频,从而推动了针对此类条件优化的技术和评估指标的发展。本研究解决了多说话人对话音频中说话人匿名化的重大挑战,特别是当仅需对单个目标说话人进行匿名化时。该场景在呼叫中心等环境中高度相关,因为在这些环境中,客户隐私要求仅对客户在与操作员互动中的声音进行匿名化。传统的匿名化方法通常不适用于此任务。此外,当前的评估方法无法使我们准确评估这一复杂多说话人场景中的隐私保护和效用。本研究旨在通过探索对话音频中目标说话人匿名化的有效策略、突出其开发中的潜在问题并提出相应的改进评估方法来弥合这些差距。

英文摘要:

Most of the existing speaker anonymization research has focused on single-speaker audio, leading to the development of techniques and evaluation metrics optimized for such condition. This study addresses the significant challenge of speaker anonymization within multi-speaker conversational audio, specifically when only a single target speaker needs to be anonymized. This scenario is highly relevant in contexts like call centers, where customer privacy necessitates anonymizing only the customer's voice in interactions with operators. Conventional anonymization methods are often not suitable for this task. Moreover, current evaluation methodology does not allow us to accurately assess privacy protection and utility in this complex multi-speaker scenario. This work aims to bridge these gaps by exploring effective strategies for targeted speaker anonymization in conversational audio, highlighting potential problems in their development and proposing corresponding improved evaluation methodologies.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑