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 …

Battling voice spoofing: a review, comparative analysis, and generalizability evaluation of state-of-the-art voice spoofing counter measures

A Khan, KM Malik, J Ryan, M Saravanan - Artificial Intelligence Review, 2023 - Springer
With the advent of automated speaker verification (ASV) systems comes an equal and
opposite development: malicious actors may seek to use voice spoofing attacks to fool those …

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 …

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 …

Towards end-to-end synthetic speech detection

G Hua, ABJ Teoh, H Zhang - IEEE Signal Processing Letters, 2021 - ieeexplore.ieee.org
The constant Q transform (CQT) has been shown to be one of the most effective speech
signal pre-transforms to facilitate synthetic speech detection, followed by either hand-crafted …

Replay and synthetic speech detection with res2net architecture

X Li, N Li, C Weng, X Liu, D Su, D Yu… - ICASSP 2021-2021 …, 2021 - ieeexplore.ieee.org
Existing approaches for replay and synthetic speech detection still lack generalizability to
unseen spoofing attacks. This work proposes to leverage a novel model structure, so-called …

A survey on the detection and impacts of deepfakes in visual, audio, and textual formats

R Mubarak, T Alsboui, O Alshaikh, I Inuwa-Dutse… - Ieee …, 2023 - ieeexplore.ieee.org
In the rapidly evolving digital landscape, the generation of fake visual, audio, and textual
content poses a significant threat to the trust of society, political stability, and integrity of …

[PDF][PDF] The effect of silence and dual-band fusion in anti-spoofing system

Y Zhang12, W Wang12, P Zhang12 - Proc. Interspeech, 2021 - isca-archive.org
The current neural network based anti-spoofing systems have poor robustness. Their
performance degrades further after voice activity detection (VAD) performed, making it …

[HTML][HTML] Voice spoofing detection for multiclass attack classification using deep learning

J Boyd, M Fahim, O Olukoya - Machine Learning With Applications, 2023 - Elsevier
Voice biometric authentication is increasingly gaining adoption in organisations with high-
volume identity verifications and for providing access to physical and other virtual spaces. In …

Light convolutional neural network with feature genuinization for detection of synthetic speech attacks

Z Wu, RK Das, J Yang, H Li - arxiv preprint arxiv:2009.09637, 2020 - arxiv.org
Modern text-to-speech (TTS) and voice conversion (VC) systems produce natural sounding
speech that questions the security of automatic speaker verification (ASV). This makes …