A Comparative Study On Recent Neural Spoofing Countermeasures For Synthetic Speech Detection

Abstract

A great deal of recent research effort on speech spoofing countermeasures has been invested into back-end neural networks and training criteria. We contribute to this effort with a comparative perspective in this study. Our comparison of countermeasure models on the ASVspoof 2019 logical access task takes into account recently proposed margin-based training criteria, widely used front ends, and common strategies to deal with varied-length input trials. We also measured intra-model differences through multiple training-evaluation rounds with random initialization. Our statistical analysis demonstrates that the performance of the same model may be significantly different when just changing the random initial seed. Thus, we recommend similar analysis or multiple training-evaluation rounds for further research on the database. Despite the intra-model differences, we observed a few promising techniques such as the average pooling to process varied-length inputs and a new hyper-parameter-fre

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2021a

Related papers

• Spoofed Training Data For Speech Spoofing Countermeasure Can Be Efficiently Created Using Neural Vocoders (2022)11.93
• Deep Residual Neural Networks For Audio Spoofing Detection (2019)0.00
• Asvspoof 2021: Towards Spoofed And Deepfake Speech Detection In The Wild (2022)17.95
• A Study On Convolutional Neural Network Based End-to-end Replay Anti-spoofing (2018)0.00
• Toward Improving Synthetic Audio Spoofing Detection Robustness Via Meta-learning And Disentangled Training With Adversarial Examples (2024)6.77
• Spoof Detection Using Time-delay Shallow Neural Network And Feature Switching (2019)8.35
• An Empirical Study On Channel Effects For Synthetic Voice Spoofing Countermeasure Systems (2021)9.92
• Experimental Study: Enhancing Voice Spoofing Detection Models With Wav2vec 2.0 (2024)0.00