Speech Replay Detection with x-Vector Attack Embeddings and Spectral Features

Abstract

We present our system submission to the ASVspoof 2019 Challenge Physical Access (PA) task. The objective for this challenge was to develop a countermeasure that identifies speech audio as either bona fide or intercepted and replayed. The target prediction was a value indicating that a speech segment was bona fide (positive values) or "spoofed" (negative values). Our system used convolutional neural networks (CNNs) and a representation of the speech audio that combined x-vector attack embeddings with signal processing features. The x-vector attack embeddings were created from mel-frequency cepstral coefficients (MFCCs) using a time-delay neural network (TDNN). These embeddings jointly modeled 27 different environments and 9 types of attacks from the labeled data. We also used sub-band spectral centroid magnitude coefficients (SCMCs) as features. We included an additive Gaussian noise layer during training as a way to augment the data to make our system more robust to previously unseen attack examples. We report system performance using the tandem detection cost function (tDCF) and equal error rate (EER). Our approach performed better that both of the challenge baselines. Our technique suggests that our x-vector attack embeddings can help regularize the CNN predictions even when environments or attacks are more challenging.

Replay Attack Detection Based on Spatial and Spectral Features of Stereo Signal

“…For the ASVspoof 2019 PA scenario, 50 systems were submitted [19]. Many countermeasures used DNNs such as the CNN, light-CNN (LCNN), and residual network (ResNet) as backend systems [20], [21], [22], [23], [24], [25], [26]. For input features, spectrogram and phase information [22], [27], linear frequency cepstral coefficients (LFCC) [18], constant Q cepstral coefficients (CQCC) [17], Mel-frequency cepstral coefficients (MFCC), inverted MFCC (IMFCC) [28], and rectangular filter cepstral coefficients (RFCC) [29] were adopted.…”

Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification

“…However, recent studies have shown that a well-trained ASV system could be deceived by malicious attacks [1][2][3]. In the last decade, the speaker verification community held several ASVspoof challenge competitions [4][5][6] to develop countermeasures mainly against replay [7,8], speech synthesis [9,10] and voice conversion [10,11] attacks.…”

“…A separate detection countermeasure has the following advantages: 1) It separates the defense part and speaker verification into two independent stages, which avoids retraining a well-developed ASV model. 2) Since most existing countermeasures for replay and synthetic speech attacks are based on a separate detection network [7][8][9], the proposed approach provides the feasibility to develop a unified countermeasure against all spoofing attacks.…”

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

“…In which, the corpus has three subset, train, development, and evaluation set. According to ASVspoof 2019 challenge rule, tandem detection cost function (t-DCF) [56] and EER are used as the primary and secondary metric, respectively, which is the same as the previous works [57][58][59][60][61][62][63][64]. Table 10 gives the experimental results on ASVspoof 2019 physical access development set using dynamic features of CMOC and CVOC.…”