Coarse-to-fine Proposal Refinement Framework For Audio Temporal Forgery Detection And Localization

Abstract

Recently, a novel form of audio partial forgery has posed challenges to its forensics, requiring advanced countermeasures to detect subtle forgery manipulations within long-duration audio. However, existing countermeasures still serve a classification purpose and fail to perform meaningful analysis of the start and end timestamps of partial forgery segments. To address this challenge, we introduce a novel coarse-to-fine proposal refinement framework (CFPRF) that incorporates a frame-level detection network (FDN) and a proposal refinement network (PRN) for audio temporal forgery detection and localization. Specifically, the FDN aims to mine informative inconsistency cues between real and fake frames to obtain discriminative features that are beneficial for roughly indicating forgery regions. The PRN is responsible for predicting confidence scores and regression offsets to refine the coarse-grained proposals derived from the FDN. To learn robust discriminative features, we devise a diffe

Stats

• citations10
• S2 citations—
• github stars0
• HF likes0
• heat score7.81
• arxiv keywu2024coarse

Related papers

• Weakly-supervised Audio Temporal Forgery Localization Via Progressive Audio-language Co-learning Network (2025)0.00
• Multi-modal Deepfake Detection And Localization With Fpn-transformer (2025)2.23
• Pitch Imperfect: Detecting Audio Deepfakes Through Acoustic Prosodic Analysis (2025)0.00
• Generalized Source Tracing: Detecting Novel Audio Deepfake Algorithm With Real Emphasis And Fake Dispersion Strategy (2024)5.84
• MFAAN: Unveiling Audio Deepfakes With A Multi-feature Authenticity Network (2023)7.81
• Continual Learning For Fake Audio Detection (2021)11.49
• Enhancing Partially Spoofed Audio Localization With Boundary-aware Attention Mechanism (2024)11.86
• Detection Of Cross-dataset Fake Audio Based On Prosodic And Pronunciation Features (2023)0.00