Publication

Oct 1, 2024

Towards Attention-based Contrastive Learning for Audio Spoof Detection

Summary

Vision transformers (ViT) have made substantial progress for classification tasks in computer vision. Recently, Gong et. al. '21, introduced attention-based modeling for several audio tasks. However, relatively unexplored is the use of a ViT for audio spoof detection task. We bridge this gap and introduce ViTs for this task. A vanilla baseline built on fine-tuning the SSAST (Gong et. al. '22) audio ViT model achieves sub-optimal equal error rates (EERs). To improve performance, we propose a novel attention-based contrastive learning framework (SSAST-CL) that uses cross-attention to aid the representation learning. Experiments show that our framework successfully disentangles the bonafide and spoof classes and helps learn better classifiers for the task. With appropriate data augmentations policy, a model trained on our framework achieves competitive performance on the ASVSpoof 2021 challenge. We provide comparisons and ablation studies to justify our claim.

Published on

ISCA Archive

Read title

Other Research

Patent: Identification of Neural-Network-Generated Fake Images

Publication
Oct 1, 2024

Published on

Published on

Matthias Niessner, Gaurav Bharaj

Generalized Spoofing Detection Inspired from Audio Generation Artifacts

Publication
Oct 1, 2024

Published on

Published on

Yang Gao, Tyler Vuong, Mahsa Elyasi, Gaurav Bharaj, Rita Singh

Subscribe to the Reality Defender Newsletter
Raised hand against a soft cloudy sky