DeepAI AI Chat
Log In Sign Up

Dynamically Mitigating Data Discrepancy with Balanced Focal Loss for Replay Attack Detection

by   Yongqiang Dou, et al.
Beijing Forestry University

It becomes urgent to design effective anti-spoofing algorithms for vulnerable automatic speaker verification systems due to the advancement of high-quality playback devices. Current studies mainly treat anti-spoofing as a binary classification problem between bonafide and spoofed utterances, while lack of indistinguishable samples makes it difficult to train a robust spoofing detector. In this paper, we argue that for anti-spoofing, it needs more attention for indistinguishable samples over easily-classified ones in the modeling process, to make correct discrimination a top priority. Therefore, to mitigate the data discrepancy between training and inference, we propose to leverage a balanced focal loss function as the training objective to dynamically scale the loss based on the traits of the sample itself. Besides, in the experiments, we select three kinds of features that contain both magnitude-based and phase-based information to form complementary and informative features. Experimental results on the ASVspoof2019 dataset demonstrate the superiority of the proposed methods by comparison between our systems and top-performing ones. Systems trained with the balanced focal loss perform significantly better than conventional cross-entropy loss. With complementary features, our fusion system with only three kinds of features outperforms other systems containing five or more complex single models by 22.5 and 0.55 results on real replay data apart from the simulated ASVspoof2019 data, indicating that research for anti-spoofing still has a long way to go.


page 1

page 7


ConvNext Based Neural Network for Anti-Spoofing

Automatic speaker verification (ASV) has been widely used in the real li...

Anti-spoofing Methods for Automatic SpeakerVerification System

Growing interest in automatic speaker verification (ASV)systems has lead...

A Study of Using Cepstrogram for Countermeasure Against Replay Attacks

In this paper, we investigate the properties of the cepstrogram and demo...

Data Quality as Predictor of Voice Anti-Spoofing Generalization

Voice anti-spoofing aims at classifying a given speech input either as a...

ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks

We present JHU's system submission to the ASVspoof 2019 Challenge: Anti-...

STC Anti-spoofing Systems for the ASVspoof 2015 Challenge

This paper presents the Speech Technology Center (STC) systems submitted...

Graph Attention Networks for Anti-Spoofing

The cues needed to detect spoofing attacks against automatic speaker ver...