arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1610.03009cs.SDcs.CL
收藏

基于帧和段重要性加权的合成语音检测研究

Investigation of Synthetic Speech Detection Using Frame- and Segment-Specific Importance Weighting

Özyeğin University(奥兹耶金大学)

Ali Khodabakhsh, Cenk Demiroglu

摘要:

说话人确认系统容易受到欺骗攻击,这在其实际部署中是一个主要问题。到目前为止,大多数提出的合成语音检测器(SSD)的加权语音的不同部分的重要性相等。然而,不同的攻击方法具有不同的优点和缺点,它们留下的痕迹可能是短期或长期的声学伪影。此外,这些可能只发生在特定的音素或声音。在这里,我们提出了三种算法,加权似然比分数的个别帧,音素,和声音类,根据其重要性的SSD。对于在训练SSD中使用的已知攻击方法,已经获得了与基线系统相比的显著改进。然而,未知攻击类型的改进并不显著。因此,由未知系统引起的失真的类型是不同的,并且与基线SSD相比,使用所提出的SSD不能更好地捕获。

英文摘要:

Speaker verification systems are vulnerable to spoofing attacks which presents a major problem in their real-life deployment. To date, most of the proposed synthetic speech detectors (SSDs) have weighted the importance of different segments of speech equally. However, different attack methods have different strengths and weaknesses and the traces that they leave may be short or long term acoustic artifacts. Moreover, those may occur for only particular phonemes or sounds. Here, we propose three algorithms that weigh likelihood-ratio scores of individual frames, phonemes, and sound-classes depending on their importance for the SSD. Significant improvement over the baseline system has been obtained for known attack methods that were used in training the SSDs. However, improvement with unknown attack types was not substantial. Thus, the type of distortions that were caused by the unknown systems were different and could not be captured better with the proposed SSD compared to the baseline SSD.

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。

↑