A Survey on Speech Deepfake Detection

M Li, Y Ahmadiadli, XP Zhang - ACM Computing Surveys, 2025 - dl.acm.org
The availability of smart devices leads to an exponential increase in multimedia content.
However, advancements in deep learning have also enabled the creation of highly …

The codecfake dataset and countermeasures for the universally detection of deepfake audio

Y **e, Y Lu, R Fu, Z Wen, Z Wang, J Tao… - … on Audio, Speech …, 2025 - ieeexplore.ieee.org
With the proliferation of Audio Language Model (ALM) based deepfake audio, there is an
urgent need for generalized detection methods. ALM-based deepfake audio currently …

Easy, Interpretable, Effective: openSMILE for voice deepfake detection

O Pascu, D Oneata, H Cucu, NM Müller - arxiv preprint arxiv:2408.15775, 2024 - arxiv.org
In this paper, we demonstrate that attacks in the latest ASVspoof5 dataset--a de facto
standard in the field of voice authenticity and deepfake detection--can be identified with …

Text-to-speech synthesis in the wild

J Jung, W Zhang, S Maiti, Y Wu, X Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Text-to-speech (TTS) systems are traditionally trained using modest databases of studio-
quality, prompted or read speech collected in benign acoustic environments such as …

Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set Condition

Y **e, X Wang, Z Wang, R Fu, Z Wen, S Cao… - arxiv preprint arxiv …, 2025 - arxiv.org
Current research in audio deepfake detection is gradually transitioning from binary
classification to multi-class tasks, referred as audio deepfake source tracing task. However …

WavLM model ensemble for audio deepfake detection

D Combei, A Stan, D Oneata, H Cucu - arxiv preprint arxiv:2408.07414, 2024 - arxiv.org
Audio deepfake detection has become a pivotal task over the last couple of years, as many
recent speech synthesis and voice cloning systems generate highly realistic speech …

Optimizing a-dcf for spoofing-robust speaker verification

O Kurnaz, J Mishra, TH Kinnunen, C Hanilçi - arxiv preprint arxiv …, 2024 - arxiv.org
Automatic speaker verification (ASV) systems are vulnerable to spoofing attacks. We
propose a spoofing-robust ASV system optimized directly for the recently introduced …

SpoofCeleb: Speech Deepfake Detection and SASV In The Wild

J Jung, Y Wu, X Wang, JH Kim, S Maiti… - IEEE Open Journal …, 2025 - ieeexplore.ieee.org
This paper introduces SpoofCeleb, a dataset designed for Speech Deepfake Detection
(SDD) and Spoofing-robust Automatic Speaker Verification (SASV), utilizing source data …

ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech

X Wang, H Delgado, H Tak, J Jung, H Shim… - arxiv preprint arxiv …, 2025 - arxiv.org
ASVspoof 5 is the fifth edition in a series of challenges which promote the study of speech
spoofing and deepfake attacks as well as the design of detection solutions. We introduce the …

Vision Graph Non-Contrastive Learning for Audio Deepfake Detection with Limited Labels

FG Febrinanto, K Moore, C Thapa, J Ma… - arxiv preprint arxiv …, 2025 - arxiv.org
Recent advancements in audio deepfake detection have leveraged graph neural networks
(GNNs) to model frequency and temporal interdependencies in audio data, effectively …