跳至内容
  • 首页
  • 资讯
  • 资源下载
  • 行业方案
  • Job招聘
  • Paper论文
  • Patent专利
  • 映维会员
  • 导航收录
  • 合作
  • 关于
  • 微信群
  • All
  • XR
  • CV
  • CG
  • HCI
  • Video
  • Optics
  • Perception
  • Reconstruction

Enhancing Robustness in Audio Deepfake Detection for VR Applications using data augmentation and Mixup

编辑:广东客   |   分类:XR   |   2025年3月19日

Note: We don't have the ability to review paper

PubDate: Otc 2024

Teams:AKCIT Federal University of Goiás

Writers:Gustavo dos Reis Oliveira, Rafaello Virgilli, Lucas Alcântara Souza, Lucas Stefanel Gris, Evellyn Nicole Machado Rosa, Isadora Stéfany Rezende Remigio Mesquita, Daniel Tunnermann, Arlindo Rodrigues Galvão Filho

PDF:Enhancing Robustness in Audio Deepfake Detection for VR Applications using data augmentation and Mixup

Abstract

The rapid advancement of virtual reality (VR) technology has heightened the need for robust and reliable deepfake audio detection to ensure the authenticity and integrity of virtual interactions. Although current state-of-the-art models exhibit promising results, they are often overconfident, which can lead to poor generalization and reduced effectiveness against novel or slightly altered deepfake attacks. In this work, we investigate the application of data augmentation techniques and Mixup techniques to increase the diversity of training data and improve the generalization of deepfake audio detection models. Mixup creates new training examples by combining pairs of existing examples, promoting smoother and more robust decision boundaries, while data augmentation creates new training examples altering a sample with a given probability. Our results demonstrate that applying such techniques to the Wav2vec 2.0 model significantly improves its generalization ability, leading to more reliable deepfake detection in VR environments.

本文链接:https://paper.nweon.com/16243

您可能还喜欢...

  • 5ea33ff01bbb138359d75525965154c3-thumb-medium

    Using Cybersickness Indicators to Adapt Navigation in Virtual Reality: A Pre-Study

    2020年11月03日 映维

  • c7258cb7c989c5dce14a1ce440fb551b-thumb-medium

    Unsupervised Learning of 3D Object Categories from Videos in the Wild

    2021年07月08日 映维

  • Development of a desktop haptic interface for teleoperation and virtual environments interaction

    2020年10月12日 映维

关注:

最新AR/VR行业分享

  • ★ 映维日报:Valve申请Steam Frame商标,谷歌XR专利申请波导光栅边缘切趾化技术 2025年9月5日
  • ★ Meta专利申请XR头戴显示器多状态面板技术 2025年9月5日
  • ★ 谷歌XR专利申请波导光栅边缘切趾化技术 2025年9月5日
  • ★ 安徽工程大学100万元采购沉浸式虚拟现实教学系统 2025年9月5日
  • ★ 新疆兵团疾控中心276万元采购传染病监测VR平台 2025年9月5日

最新AR/VR专利

  • ★ Meta Patent | Systems and methods for improved spatial computing systems 2025年9月4日
  • ★ Apple Patent | Methods for sharing content and interacting with physical devices in a three-dimensional environment 2025年9月4日
  • ★ MagicLeap Patent | Matching content to a spatial 3d environment 2025年9月4日
  • ★ Meta Patent | Techniques for coordinating artificial-reality interactions using augmented-reality interaction guides for performing interactions with physical objects within a user's physical surroundings, and systems and methods for using such techniques 2025年9月4日
  • ★ Meta Patent | Solution of body-garment collisions in avatars for immersive reality applications 2025年9月4日

最新AR/VR行业招聘

  • ★ Microsoft AR/VR Job | High Performance Compute, Director 2025年6月5日
  • ★ Microsoft AR/VR Job | Data Center Technician/ Technicien de Centre de Données 2025年6月3日
  • ★ Microsoft AR/VR Job | Senior Product Designer 2025年5月16日
  • ★ Apple AR/VR Job | AirPlay Audio Engineer 2025年3月27日
  • ★ Apple AR/VR Job | iOS Perception Engineer 2025年3月27日
  • 首页
  • 资讯
  • 资源下载
  • 行业方案
  • Job招聘
  • Paper论文
  • Patent专利
  • 映维会员
  • 导航收录
  • 合作
  • 关于
  • 微信群

联系微信:ovalics

版权所有:广州映维网络有限公司 © 2025

备案许可:粤ICP备17113731号-2

备案粤公网安备:44011302004835号

友情链接: AR/VR行业导航

读者QQ群:251118691

Quest QQ群:526200310

开发者QQ群:688769630

Paper