@inproceedings{7e0313961a534eac81ac8a508f0d2e8c,
title = "AASIST: AUDIO ANTI-SPOOFING USING INTEGRATED SPECTRO-TEMPORAL GRAPH ATTENTION NETWORKS",
abstract = "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.",
keywords = "anti-spoofing, audio spoofing detection, end-to-end, graph attention networks, heterogeneous",
author = "Jung, {Jee Weon} and Heo, {Hee Soo} and Hemlata Tak and Shim, {Hye Jin} and Chung, {Joon Son} and Lee, {Bong Jin} and Yu, {Ha Jin} and Nicholas Evans",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE; 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 ; Conference date: 23-05-2022 Through 27-05-2022",
year = "2022",
doi = "10.1109/ICASSP43922.2022.9747766",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2405--2409",
booktitle = "2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings",
address = "United States",
}