用于ADD 2022的带神经拼接的音频深度假检测系统
Audio Deep Fake Detection System with Neural Stitching for ADD 2022
摘要：
本文介绍了我们针对ADD 2022：首届音频深度合成检测挑战赛\cite{Yi2022ADD}的最佳系统和方法。轨道3.2的两轮评估使用了完全相同的系统，培训方法也类似。第一轮Track 3.2数据是由文本到语音（TTS）或语音转换（VC）算法生成的，而第二轮数据由Track 3.1中其他参与者生成的假音频组成，旨在欺骗我们的系统。我们的系统使用标准的34层ResNet，具有多头注意力池\cite{india2019self}来学习用于虚假音频和欺骗检测的判别式嵌入。我们进一步利用神经拼接来提高模型的泛化能力，以便在不同的任务中表现同样出色，更多细节将在下面的会议中解释。实验表明，我们提出的方法优于所有其他系统的10.1%的等错误率（EER）在轨道3.2。
英文摘要：
This paper describes our best system and methodology for ADD 2022: The First Audio Deep Synthesis Detection Challenge\cite{Yi2022ADD}. The very same system was used for both two rounds of evaluation in Track 3.2 with a similar training methodology. The first round of Track 3.2 data is generated from Text-to-Speech(TTS) or voice conversion (VC) algorithms, while the second round of data consists of generated fake audio from other participants in Track 3.1, aiming to spoof our systems. Our systems use a standard 34-layer ResNet, with multi-head attention pooling \cite{india2019self} to learn the discriminative embedding for fake audio and spoof detection. We further utilize neural stitching to boost the model's generalization capability in order to perform equally well in different tasks, and more details will be explained in the following sessions. The experiments show that our proposed method outperforms all other systems with a 10.1% equal error rate(EER) in Track 3.2.
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。
