Audio deepfake detection: A survey

J Yi, C Wang, J Tao, X Zhang, CY Zhang… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Audio deepfake detection is an emerging active topic. A growing number of literatures have
aimed to study deepfake detection algorithms and achieved effective performance, the …

Aasist: Audio anti-spoofing using integrated spectro-temporal graph attention networks

J Jung, HS Heo, H Tak, H Shim… - ICASSP 2022-2022 …, 2022‏ - ieeexplore.ieee.org
Artefacts that differentiate spoofed from bona-fide utterances can reside in specific temporal
or spectral intervals. Their reliable detection usually depends upon computationally …

Deepfakes as a threat to a speaker and facial recognition: An overview of tools and attack vectors

A Firc, K Malinka, P Hanáček - Heliyon, 2023‏ - cell.com
Deepfakes present an emerging threat in cyberspace. Recent developments in machine
learning make deepfakes highly believable, and very difficult to differentiate between what is …

Does audio deepfake detection generalize?

NM Müller, P Czempin, F Dieckmann… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Current text-to-speech algorithms produce realistic fakes of human voices, making deepfake
detection a much-needed area of research. While researchers have presented various …

SASV 2022: The first spoofing-aware speaker verification challenge

J Jung, H Tak, H Shim, HS Heo, BJ Lee… - arxiv preprint arxiv …, 2022‏ - arxiv.org
The first spoofing-aware speaker verification (SASV) challenge aims to integrate research
efforts in speaker verification and anti-spoofing. We extend the speaker verification scenario …

Rawboost: A raw data boosting and augmentation method applied to automatic speaker verification anti-spoofing

H Tak, M Kamble, J Patino, M Todisco… - ICASSP 2022-2022 …, 2022‏ - ieeexplore.ieee.org
This paper introduces RawBoost, a data boosting and augmentation method for the design
of more reliable spoofing detection solutions which operate directly upon raw waveform …

Fake audio detection based on unsupervised pretraining models

Z Lv, S Zhang, K Tang, P Hu - ICASSP 2022-2022 IEEE …, 2022‏ - ieeexplore.ieee.org
This work presents our systems for the ADD2022 challenge. The ADD2022 challenge is the
first audio deep synthesis detection challenge, which aims to spot various kinds of fake …

Discriminative frequency information learning for end-to-end speech anti-spoofing

B Huang, S Cui, J Huang, X Kang - IEEE Signal Processing …, 2023‏ - ieeexplore.ieee.org
End-to-end technology is an active research topic in speech anti-spoofing. Although end-to-
end methods have achieved remarkable success in the speech anti-spoofing, channel …

FairSSD: Understanding Bias in Synthetic Speech Detectors

AKS Yadav, K Bhagtani, D Salvi… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Methods that can generate synthetic speech which is perceptually indistinguishable from
speech recorded by a human speaker are easily available. Several incidents report misuse …

Domain generalization via aggregation and separation for audio deepfake detection

Y **e, H Cheng, Y Wang, L Ye - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
In this paper, we propose an Aggregation and Separation Domain Generalization (ASDG)
method for Audio DeepFake Detection (ADD). Fake speech generated from different …