The DKU Replay Detection System for the ASVspoof 2019 Challenge: On Data Augmentation, Feature Representation, Classification, and Fusion

Abstract

This paper describes our DKU replay detection system for the ASVspoof 2019 challenge. The goal is to develop spoofing countermeasure for automatic speaker recognition in physical access scenario. We leverage the countermeasure system pipeline from four aspects, including the data augmentation, feature representation, classification, and fusion. First, we introduce an utterance-level deep learning framework for antispoofing. It receives the variable-length feature sequence and outputs the utterance-level scores directly. Based on the framework, we try out various kinds of input feature representations extracted from either the magnitude spectrum or phase spectrum. Besides, we also perform the data augmentation strategy by applying the speed perturbation on the raw waveform. Our best single system employs a residual neural network trained by the speed-perturbed group delay gram. It achieves EER of 1.04% on the development set, as well as EER of 1.08% on the evaluation set. Finally, using the simple average score from several single systems can further improve the performance. EER of 0.24% on the development set and 0.66% on the evaluation set is obtained for our primary system.

Discriminative features based on modified log magnitude spectrum for playback speech detection

“…From Eqs. (18) and (19), we can see that F mro is determined by F vrs and then F vrs is determined by σ 2 X , σ 2 Y , X, and Y . However, as these parameters are unknown, it is not possible to determine the value of F 1 and F 2 directly.…”

“…According to the relationship between F mro and F vrs in Eqs. (18) and (19), we can know that the statistics value of F mro is above 1 on the two databases. Further, we can know that F X Y is larger than F XY .…”

“…According to the neural networks used, there are several types deep features. For example, light convolutional neural network was used to learn deep feature for the input of log power spectrum of constant-Q transform (CQT) and fast Fourier transform in [14,20,21], deep Siamese that is formed two convolutional neural networks with the input of spectrogram are used to learned to obtain Siamese embedding features in [31], residual network (ResNet) was used to learn deep feature from the input of group delay gram in [19,32,33].…”

“…which include linear prediction cepstral coefficients residual part and linear prediction cepstral coefficients cepstrum [13,19], frequency domain linear prediction [9]. • Spectral centroid-based features: which include subband spectral centroid frequency coefficients and subband spectral centroid magnitude coefficients [12] and spectral centroid deviation [16].…”

“…For the end-to-end systems such as *Correspondence: xlt@dhu.edu.cn † Jichen Yang and Longting Xu contributed equally to this work. 2 College of Information Science and Technology, Donghua University, Shanghai China Full list of author information is available at the end of the article [19][20][21][22][23], the output layer of the neural network can be seen as a virtual classifier and the rest of the neural network can be seen a deep feature extractor. In this paper, we mainly focus on how to extract discriminative feature for playback speech detection.…”