An Empirical Study On Channel Effects For Synthetic Voice Spoofing Countermeasure Systems
2021 · You Zhang, Ge Zhu, Fei Jiang, et al.
Abstract
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.
Authors
(none)
Tags
Stats
Related papers
- Phase Perturbation Improves Channel Robustness For Speech Spoofing Countermeasures (2023)2.26
- A Comparative Study On Recent Neural Spoofing Countermeasures For Synthetic Speech Detection (2021)0.00
- Representation Selective Self-distillation And Wav2vec 2.0 Feature Exploration For Spoof-aware Speaker Verification (2022)9.03
- A Spoofing Benchmark For The 2018 Voice Conversion Challenge: Leveraging From Spoofing Countermeasures For Speech Artifact Assessment (2018)8.09
- Toward Improving Synthetic Audio Spoofing Detection Robustness Via Meta-learning And Disentangled Training With Adversarial Examples (2024)6.77
- Detecting Spoof Voices In Asian Non-native Speech: An Indonesian And Thai Case Study (2024)3.58
- Audio-replay Attack Detection Countermeasures (2017)6.34
- Experimental Study: Enhancing Voice Spoofing Detection Models With Wav2vec 2.0 (2024)0.00