论文解读
Dynamic Spectrogram Analysis with Local-Aware Graph Networks for Audio Anti-Spoofing
音频深度伪造检测 | 8.5/10
音频深度伪造检测
论文解读
EchoFake: A Replay-Aware Dataset For Practical Speech Deepfake Detection
音频深度伪造检测 | 8.5/10
论文解读
Few-Shot Recognition of Audio Deepfake Generators using Graph-Based Prototype Adaptation
音频深度伪造检测 | 7.5/10
论文解读
Hanui: Harnessing Distributional Discrepancies for Singing Voice Deepfake Detection
音频深度伪造检测 | 8.0/10
论文解读
How to Label Resynthesized Audio: The Dual Role of Neural Audio Codecs in Audio Deepfake Detection
音频深度伪造检测 | 7.5/10
会议任务专题
ICASSP 2026 - 音频深度伪造检测
共 29 篇 ICASSP 2026 音频深度伪造检测 方向论文
论文解读
保留高维 XLS-R 特征时单层 KAN 能否以更少参数替代复杂后端
📄 保留高维 XLS-R 特征时单层 KAN 能否以更少参数替代复杂后端 会议论文 ID：conference:icassp:2026:icassp-arnumber:11460320
论文解读
Leveraging Large Multimodal Models for Audio-Video Deepfake Detection: A Pilot Study
音频深度伪造检测 | 7.0/10
论文解读
Localizing Speech Deepfakes Beyond Transitions via Segment-Aware Learning
音频深度伪造检测 | 8.0/10
论文解读
MSCT: Differential Cross-Modal Attention for Deepfake Detection
音频深度伪造检测 | 6.5/10
论文解读
On deepfake voice detection - It’s all in the presentation
音频深度伪造检测 | 8.0/10
论文解读
Robust Deepfake Audio Detection via Multi-Level Intermediate Feature Fusion
音频深度伪造检测 | 7.5/10
论文解读
StreamMark: A Deep Learning-Based Semi-Fragile Audio Watermarking for Proactive Deepfake Detection
音频深度伪造检测 | 8.0/10
论文解读
Subgraph Localization in the Subbands for Partially Spoofed Speech Detection
音频深度伪造检测 | 8.0/10
论文解读
The Impact of Audio Watermarking on Audio Anti-Spoofing Countermeasures
音频深度伪造检测 | 8.5/10
论文解读
Towards Data Drift Monitoring for Speech Deepfake Detection in the Context of MLOps
音频深度伪造检测 | 7.0/10
论文解读
Understanding the Strengths and Weaknesses of SSL Models for Audio Deepfake Model Attribution
音频深度伪造检测 | 7.0/10
论文解读
Environmental Sound Deepfake Detection Using Deep-Learning Framework
1. **问题**：针对环境声音（包括声音场景和声音事件）的深度伪造检测（ESDD）任务，现有研究不足，且尚不清楚声音场景与声音事件的伪造检测是否需要不同模型。 2. **方法核心**：提出一个深度学习框架，核心是采用预训练的音频模型（BEATs）作为特征提取器，并结合一种三阶段训练策略（包含对
论文解读
Indic-CodecFake meets SATYAM: Towards Detecting Neural Audio Codec Synthesized Speech Deepfakes in Indic Languages
1. **问题**：现有针对基于神经音频编解码器的语音深度伪造（CodecFake）检测的研究主要集中在英语和中文，对于语言多样性极高的印度语言缺乏大规模的基准数据集和有效的检测方法。 2. **方法**：作者构建了首个大规模印度语言CodecFake数据集（ICF），并提出了一个名为SATYA
论文解读
Environmental Sound Deepfake Detection Using Deep-Learning Framework
本文针对环境声音（如声音事件、声音场景）的深度伪造检测这一新兴任务，提出了一个系统的深度学习框架。**核心贡献**在于通过大量实验，系统评估了不同频谱图（MEL, CQT, Gammatone）、多种CNN架构（ResNet, Inception等）以及预训练模型（BEATs）在该任务上的表现，并验