Detecting fake audio of Arabic speakers using self-supervised deep learning

ZM Almutairi, H Elgibreen - IEEE Access, 2023 - ieeexplore.ieee.org
One of the most significant discussions in forensics is Audio Deepfake, where AI-generated
tools are used to clone audio content of people's voices. Although it was intended to improve …

Enhancing partially spoofed audio localization with boundary-aware attention mechanism

J Zhong, B Li, J Yi - arXiv preprint arXiv:2407.21611, 2024 - arxiv.org
The task of partially spoofed audio localization aims to accurately determine audio
authenticity at a frame level. Although some works have achieved encouraging results …

[PDF][PDF] The Vicomtech Partial Deepfake Detection and Location System for the 2023 ADD Challenge.

JM Martín-Doñas, A Álvarez - DADA@ IJCAI, 2023 - ceur-ws.org
This paper describes our submitted system to the 2023 Audio Deepfake Detection
Challenge Track 2. This track focuses on locating the manipulated regions in partially fake …

[PDF][PDF] “Whether, When, What”: Detection, Localization, and Diarization of Partially Spoofed Audio (“Whether, When, What”: 部分的なりすまし音声の検出 …

チョウリン - ir.soken.ac.jp
Speech can easily be altered through various manipulations and spoofing, such as text-to-
speech synthesis, voice conversion, replay, tampering, adversarial attacks, etc. However …