The existing fake audio detection systems often rely on expert experience to
design the acoustic features or manually design the hyperparameters of the
network structure. However, artificial adjustment of the parameters can have a
relatively obvious influence on the results. It is almost impossible to
manually set the best set of parameters. Therefore this paper proposes a fully
automated end-toend fake audio detection method. We first use wav2vec
pre-trained model to obtain a high-level representation of the speech.
Furthermore, for the network structure, we use a modified version of the
differentiable architecture search (DARTS) named light-DARTS. It learns deep
speech representations while automatically learning and optimizing complex
neural structures consisting of convolutional operations and residual blocks.
The experimental results on the ASVspoof 2019 LA dataset show that our proposed
system achieves an equal error rate (EER) of 1.08%, which outperforms the
state-of-the-art single system.

本文提出了一种完全自动化的端到端虚假音频检测方法，使用了 wav2vec 预训练模型和修改版的 differentiable architecture search 算法（light-DARTS），在 ASVspoof 2019 LA 数据集上取得了 1.08% 的等错误率，性能优于现有的单一系统。