AASIST: Audio Anti-Spoofing Using Integrated Spectro-Temporal Graph Attention Networks

Artefacts that differentiate spoofed from bona-fide utterances can reside in specific temporal or spectral intervals. Their reliable detection usually depends upon computationally demanding ensemble systems where each subsystem is tuned to some specific artefacts. We seek to develop an efficient, si...

Full description

Saved in:
Bibliographic Details
Main Authors: Jung, Jee-weon, Heo, Hee-Soo, Tak, Hemlata, Shim, Hye-jin, Chung, Joon Son, Lee, Bong-Jin, Yu, Ha-Jin, Evans, Nicholas
Format: Conference Proceeding
Language:English
Subjects:
Acoustics
anti-spoofing
audio spoofing detection
Computational modeling
Conferences
end-to-end
graph attention networks
Graph neural networks
heterogeneous
Reliability
Signal processing
Stacking
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Artefacts that differentiate spoofed from bona-fide utterances can reside in specific temporal or spectral intervals. Their reliable detection usually depends upon computationally demanding ensemble systems where each subsystem is tuned to some specific artefacts. We seek to develop an efficient, single system that can detect a broad range of different spoofing attacks without score-level ensembles. We propose a novel heterogeneous stacking graph attention layer that models artefacts spanning heterogeneous temporal and spectral intervals with a heterogeneous attention mechanism and a stack node. With a new max graph operation that involves a competitive mechanism and a new readout scheme, our approach, named AASIST, outperforms the current state-of-the-art by 20% relative. Even a lightweight variant, AASIST-L, with only 85k parameters, outperforms all competing systems.
ISSN:2379-190X
DOI:10.1109/ICASSP43922.2022.9747766