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 2011.01130eess.AScs.CL
收藏

使用McAdams系数的说话人匿名

Speaker anonymisation using the McAdams coefficient

EURECOM(欧洲通信系统工程师学校与研究中心)

Jose Patino, Natalia Tomashenko, Massimiliano Todisco, Andreas Nautsch, Nicholas Evans

摘要:

匿名化的目标是操纵语音信号,以便降低说话人识别的自动方法的可靠性,同时保留语音的其他方面,例如与可懂度和自然度相关的方面。本文报告了一种匿名化方法,与其他当前的方法不同,不需要训练数据,是基于众所周知的信号处理技术,是高效和有效的。该方案利用McAdams系数对语音信号进行频谱包络变换。使用常见的VoicePrivacy 2020数据库和协议得出的结果表明,随机的优化转换可以在匿名化方面优于竞争解决方案,同时只会导致适度的可理解性降低,即使在半知情的隐私对手的情况下。

英文摘要:

Anonymisation has the goal of manipulating speech signals in order to degrade the reliability of automatic approaches to speaker recognition, while preserving other aspects of speech, such as those relating to intelligibility and naturalness. This paper reports an approach to anonymisation that, unlike other current approaches, requires no training data, is based upon well-known signal processing techniques and is both efficient and effective. The proposed solution uses the McAdams coefficient to transform the spectral envelope of speech signals. Results derived using common VoicePrivacy 2020 databases and protocols show that random, optimised transformations can outperform competing solutions in terms of anonymisation while causing only modest, additional degradations to intelligibility, even in the case of a semi-informed privacy adversary.

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。

↑