Analyzing the impact of splicing artifacts in partially fake speech signals

V Negroni, D Salvi, P Bestagini, S Tubaro - arxiv preprint arxiv …, 2024 - arxiv.org
Speech deepfake detection has recently gained significant attention within the multimedia
forensics community. Related issues have also been explored, such as the identification of …

Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap

G Channing, J Sock, R Clark, P Torr… - arxiv preprint arxiv …, 2024 - arxiv.org
The rapid proliferation of AI-manipulated or generated audio deepfakes poses serious
challenges to media integrity and election security. Current AI-driven detection solutions lack …

BUT Systems and Analyses for the ASVspoof 5 Challenge

J Rohdin, L Zhang, O Plchot, V Staněk… - arxiv preprint arxiv …, 2024 - arxiv.org
This paper describes the BUT submitted systems for the ASVspoof 5 challenge, along with
analyses. For the conventional deepfake detection task, we use ResNet18 and self …

USTC-KXDIGIT System Description for ASVspoof5 Challenge

Y Chen, H Wu, N Jiang, X **a, Q Gu, Y Hao… - arxiv preprint arxiv …, 2024 - arxiv.org
This paper describes the USTC-KXDIGIT system submitted to the ASVspoof5 Challenge for
Track 1 (speech deepfake detection) and Track 2 (spoofing-robust automatic speaker …

Temporal Variability and Multi-Viewed Self-Supervised Representations to Tackle the ASVspoof5 Deepfake Challenge

Y **e, X Wang, Z Wang, R Fu, Z Wen, H Cheng… - arxiv preprint arxiv …, 2024 - arxiv.org
ASVspoof5, the fifth edition of the ASVspoof series, is one of the largest global audio security
challenges. It aims to advance the development of countermeasure (CM) to discriminate …

SZU-AFS Antispoofing System for the ASVspoof 5 Challenge

Y Xu, J Zhong, S Zheng, Z Liu, B Li - arxiv preprint arxiv:2408.09933, 2024 - arxiv.org
This paper presents the SZU-AFS anti-spoofing system, designed for Track 1 of the
ASVspoof 5 Challenge under open conditions. The system is built with four stages: selecting …

ASASVIcomtech: the Vicomtech-UGR speech deepfake detection and SASV systems for the ASVspoof5 Challenge

JM Martín-Doñas, E Rosello, AM Gomez… - arxiv preprint arxiv …, 2024 - arxiv.org
This paper presents the work carried out by the ASASVIcomtech team, made up of
researchers from Vicomtech and University of Granada, for the ASVspoof5 Challenge. The …

LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation Generation

HT Luong, H Li, L Zhang, KA Lee, ES Chng - arxiv preprint arxiv …, 2024 - arxiv.org
Previous fake speech datasets were constructed from a defender's perspective to develop
countermeasure (CM) systems without considering diverse motivations of attackers. To …

Exploring Generalization To Unseen Audio Data For Spoofing: Insights From SSL Models

A Kulkarni, HM Tran, A Kulkarni, S Dowerah… - ASVSpoof workshop …, 2024 - hal.science
Deep learning-based speech synthesis has significantly improved realistic audio deepfakes.
Despite advanced techniques such as self-supervised learning (SSL) and datasets, current …

Data augmentations for audio deepfake detection for the ASVspoof5 closed condition

R Duroselle, O Boeffard, A Courtois, H Nourtel… - ASVspoof Workshop …, 2024 - hal.science
This paper describes the joint participation of Inria Défense et Sécurité and Storyzy to the
ASVspoof5 challenge. We participated in the closed conditions of the audio deepfake …