DeepAI AI Chat
Log In Sign Up

An Empirical Study on Channel Effects for Synthetic Voice Spoofing Countermeasure Systems

by   You Zhang, et al.

Spoofing countermeasure (CM) systems are critical in speaker verification; they aim to discern spoofing attacks from bona fide speech trials. In practice, however, acoustic condition variability in speech utterances may significantly degrade the performance of CM systems. In this paper, we conduct a cross-dataset study on several state-of-the-art CM systems and observe significant performance degradation compared with their single-dataset performance. Observing differences of average magnitude spectra of bona fide utterances across the datasets, we hypothesize that channel mismatch among these datasets is one important reason. We then verify it by demonstrating a similar degradation of CM systems trained on original but evaluated on channel-shifted data. Finally, we propose several channel robust strategies (data augmentation, multi-task learning, adversarial learning) for CM systems, and observe a significant performance improvement on cross-dataset experiments.


page 1

page 2

page 3

page 4


Multi-task Learning Based Spoofing-Robust Automatic Speaker Verification System

Spoofing attacks posed by generating artificial speech can severely degr...

The DKU-OPPO System for the 2022 Spoofing-Aware Speaker Verification Challenge

This paper describes our DKU-OPPO system for the 2022 Spoofing-Aware Spe...

UR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021

In this paper, we present UR-AIR system submission to the logical access...

A Study On Data Augmentation In Voice Anti-Spoofing

In this paper, we perform an in-depth study of how data augmentation tec...

Phase-Aware Spoof Speech Detection Based on Res2Net with Phase Network

The spoof speech detection (SSD) is the essential countermeasure for aut...

Dataset artefacts in anti-spoofing systems: a case study on the ASVspoof 2017 benchmark

The Automatic Speaker Verification Spoofing and Countermeasures Challeng...

Impact of Channel Variation on One-Class Learning for Spoof Detection

The value of Spoofing detection in increasing the reliability of the ASV...