arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.02746cs.SDcs.CRcs.LGeess.AS
收藏

寂静之声:合成音频检测中第一位特征的有效性

The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection

University of Padova(帕多瓦大学)

Daniele Mari, Federica Latora, Simone Milani

摘要:

最近生成神经策略和音频处理技术的集成促进了合成语音合成或变换算法的广泛应用。事实证明,这种能力在许多法律和信息流程(新闻、生物识别认证、法庭音频证据等)中是有害的。因此,有效的检测算法的发展是至关重要的和具有挑战性的,由于伪造技术的异质性。这项工作研究了合成语音检测中的静音部分的歧视性作用,并显示了如何从MFCC系数提取的第一位统计数据可以有效地实现鲁棒检测。所提出的过程是计算轻量级的,并且在许多不同的算法上是有效的,因为它不依赖于大型神经检测架构,并且在ASVSpoof数据集的大多数类中获得了90%以上的准确度。

英文摘要:

The recent integration of generative neural strategies and audio processing techniques have fostered the widespread of synthetic speech synthesis or transformation algorithms. This capability proves to be harmful in many legal and informative processes (news, biometric authentication, audio evidence in courts, etc.). Thus, the development of efficient detection algorithms is both crucial and challenging due to the heterogeneity of forgery techniques. This work investigates the discriminative role of silenced parts in synthetic speech detection and shows how first digit statistics extracted from MFCC coefficients can efficiently enable a robust detection. The proposed procedure is computationally-lightweight and effective on many different algorithms since it does not rely on large neural detection architecture and obtains an accuracy above 90\% in most of the classes of the ASVSpoof dataset.

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。

↑