Deepfakes generation and detection: State-of-the-art, open challenges, countermeasures, and way forward

M Masood, M Nawaz, KM Malik, A Javed, A Irtaza… - Applied …, 2023 - Springer
Easy access to audio-visual content on social media, combined with the availability of
modern tools such as Tensorflow or Keras, and open-source trained models, along with …

A review of modern audio deepfake detection methods: challenges and future directions

Z Almutairi, H Elgibreen - Algorithms, 2022 - mdpi.com
A number of AI-generated tools are used today to clone human voices, leading to a new
technology known as Audio Deepfakes (ADs). Despite being introduced to enhance human …

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 …

Add 2022: the first audio deep synthesis detection challenge

J Yi, R Fu, J Tao, S Nie, H Ma, C Wang… - ICASSP 2022-2022 …, 2022 - ieeexplore.ieee.org
Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021.
However, the recent shared tasks have not covered many real-life and challenging …

One-class learning towards synthetic voice spoofing detection

Y Zhang, F Jiang, Z Duan - IEEE Signal Processing Letters, 2021 - ieeexplore.ieee.org
Human voices can be used to authenticate the identity of the speaker, but the automatic
speaker verification (ASV) systems are vulnerable to voice spoofing attacks, such as …

Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation

H Tak, M Todisco, X Wang, J Jung, J Yamagishi… - arxiv preprint arxiv …, 2022 - arxiv.org
The performance of spoofing countermeasure systems depends fundamentally upon the use
of sufficiently representative training data. With this usually being limited, current solutions …

TweepFake: About detecting deepfake tweets

T Fagni, F Falchi, M Gambini, A Martella, M Tesconi - Plos one, 2021 - journals.plos.org
The recent advances in language modeling significantly improved the generative
capabilities of deep neural models: in 2019 OpenAI released GPT-2, a pre-trained language …

A comparative study on recent neural spoofing countermeasures for synthetic speech detection

X Wang, J Yamagishi - arxiv preprint arxiv:2103.11326, 2021 - arxiv.org
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 …

End-to-end spectro-temporal graph attention networks for speaker verification anti-spoofing and speech deepfake detection

H Tak, J Jung, J Patino, M Kamble, M Todisco… - arxiv preprint arxiv …, 2021 - arxiv.org
Artefacts that serve to distinguish bona fide speech from spoofed or deepfake speech are
known to reside in specific subbands and temporal segments. Various approaches can be …

ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech

A Nautsch, X Wang, N Evans… - … and Identity Science, 2021 - ieeexplore.ieee.org
The ASVspoof initiative was conceived to spearhead research in anti-spoofing for automatic
speaker verification (ASV). This paper describes the third in a series of bi-annual …