3-Tracer: A Tri-level Temporal-Aware Framework for Audio Forgery Detection and Localization

TL;DR

The paper introduces T3-Tracer, a hierarchical framework that jointly analyzes audio at multiple temporal levels to improve detection and localization of partial audio forgeries, addressing limitations of previous frame-only methods.

Contribution

It presents the first joint multi-level analysis framework for audio forgery detection, combining frame, segment, and audio levels with novel modules for comprehensive forgery trace identification.

Findings

Achieves state-of-the-art performance on three datasets.

Effectively detects both intra-frame and boundary forgeries.

Outperforms existing methods in accuracy and robustness.

Abstract

Recently, partial audio forgery has emerged as a new form of audio manipulation. Attackers selectively modify partial but semantically critical frames while preserving the overall perceptual authenticity, making such forgeries particularly difficult to detect. Existing methods focus on independently detecting whether a single frame is forged, lacking the hierarchical structure to capture both transient and sustained anomalies across different temporal levels. To address these limitations, We identify three key levels relevant to partial audio forgery detection and present T3-Tracer, the first framework that jointly analyzes audio at the frame, segment, and audio levels to comprehensively detect forgery traces. T3-Tracer consists of two complementary core modules: the Frame-Audio Feature Aggregation Module (FA-FAM) and the Segment-level Multi-Scale Discrepancy-Aware Module (SMDAM). FA-FAM is designed to detect the authenticity of each audio frame. It combines both frame-level and audio-level temporal information to detect intra-frame forgery cues and global semantic inconsistencies. To further refine and correct frame detection, we introduce SMDAM to detect forgery boundaries at the segment level. It adopts a dual-branch architecture that jointly models frame features and inter-frame differences across multi-scale temporal windows, effectively identifying abrupt anomalies that appeared on the forged boundaries. Extensive experiments conducted on three challenging datasets demonstrate that our approach achieves state-of-the-art performance.