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 2410.07428eess.AScs.CLcs.CR
收藏

首届 VoicePrivacy 攻击者挑战赛评估方案

The First VoicePrivacy Attacker Challenge Evaluation Plan

Inria(法国国家信息与自动化研究所);Singapore Institute of Technology(新加坡理工学院);National Institute of Informatics(信息学研究所)

Natalia Tomashenko, Xiaoxiao Miao, Emmanuel Vincent, Junichi Yamagishi

AI总结:

首届 VoicePrivacy 攻击者挑战赛旨在开发针对语音匿名化的自动说话人验证攻击系统,以等错误率(EER)为评估指标,结果将在 ICASSP 2025 特别分会展示。

摘要:

首届 VoicePrivacy 攻击者挑战赛是一种新型挑战赛,作为 VoicePrivacy 倡议的一部分组织举办,并作为 SP Grand Challenge 得到 ICASSP 2025 支持。该挑战赛聚焦于开发针对语音匿名化的攻击者系统,这些系统将针对提交至 VoicePrivacy 2024 挑战赛的一组匿名化系统进行评估。主办方提供了训练、开发和评估数据集,并附带一个基线攻击者系统。参赛者应以自动说话人验证系统的形式开发其攻击者系统,并向主办方提交其在开发和评估数据上的得分。为此,参赛者可以使用任何额外的训练数据和模型,前提是这些数据和模型公开可用,并在指定截止日期之前进行声明。评估指标为等错误率(EER)。结果将在 ICASSP 2025 特别分会上展示,届时将邀请 5 名排名靠前的入选参赛者提交并展示其挑战赛系统。

英文摘要:

The First VoicePrivacy Attacker Challenge is a new kind of challenge organized as part of the VoicePrivacy initiative and supported by ICASSP 2025 as the SP Grand Challenge It focuses on developing attacker systems against voice anonymization, which will be evaluated against a set of anonymization systems submitted to the VoicePrivacy 2024 Challenge. Training, development, and evaluation datasets are provided along with a baseline attacker system. Participants shall develop their attacker systems in the form of automatic speaker verification systems and submit their scores on the development and evaluation data to the organizers. To do so, they can use any additional training data and models, provided that they are openly available and declared before the specified deadline. The metric for evaluation is equal error rate (EER). Results will be presented at the ICASSP 2025 special session to which 5 selected top-ranked participants will be invited to submit and present their challenge systems.

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。

↑