Aug 2026· arXiv.org· Vol abs/2608.23437· 1 citation· 137 references
Computer Science
TL;DR
The results show that large-scale self-supervised representations, condition-aware augmentation, multi-crop inference, and structured fusion or routing are central to generalization, while generator-specific robustness and balanced detection across heterogeneous audio types remain unresolved.
Abstract
Recent audio generation models can synthesize high-fidelity speech, environmental sound, singing voice, and music, creating new risks for multimedia trust. Existing audio deepfake detection (ADD) benchmarks remain predominantly speech-centric and often under-represent realistic channel variation and heterogeneous audio types. This paper presents all-type ADD (AT-ADD), a large-scale benchmark and challenge designed to evaluate both robust speech deepfake detection and all-type audio deepfake detection. Track 1 evaluates speech deepfake detection under unseen synthesizers, diverse recording conditions, signal perturbations, and replay effects. Track 2 evaluates type-agnostic deepfake detection over speech, sound, singing, and music when the audio type is unknown at test time. We detail the dataset construction, evaluation protocol, and reproducible baselines, and analyze the final systems submitted to the ACM Multimedia 2026 Grand Challenge. The strongest official baseline obtains 76.73% and 79.47% Macro-F1 on the Track 1 and Track 2 evaluation sets, respectively, whereas the winning challenge systems reach 90.71% and 96.10%. Beyond the aggregate rankings, sample-level analysis of the top five submissions reveals concentrated failures on specific synthesis methods and replayed speech. It also quantifies cross-system error complementarity and separates stable leaderboard gaps from statistically ambiguous adjacent ranks. Our results show that large-scale self-supervised representations, condition-aware augmentation, multi-crop inference, and structured fusion or routing are central to generalization, while generator-specific robustness and balanced detection across heterogeneous audio types remain unresolved.
Modern generative audio can fabricate not only voices but also the acoustic environments that provide evidence of when and where speech occurred. This capability undermines a longstanding forensic assumption that background sound provides reliable evidence of a recording's provenance. Yet existing detectors produce onl...
Xin-Dong Zheng, Jia-Shu Zhu, Ke Li et al.· 0 citations
A forensic-preserving neural audio codec (FP-NAC), which fine-tunes a pretrained codec using a detector-guided objective while preserving its native hard quantization path and bitrate, and highlights forensic transparency as a codec design objective alongside perceptual quality.
Jungwoo Kim, Joonyong Park, Junyoung Koh et al.· arXiv.org· 0 citations
B BabelFake is introduced, a multilingual audio-visual DeepFake benchmark recorded with consenting participants, and it is shown that detection difficulty depends on the audio-visual generation pairing, with substantial performance degradation when authentic audio is preserved.
Carlotta Segna, Joel Tschesche, Anna Rohrbach· 0 citations
Real-world audio recordings for deepfake detection rarely consist solely of speech; they often are mixtures of speech and background events that themselves may also be synthetic. When processing these mixtures, it remains unclear whether detectors attend to the speech or the background event, and where their spectral e...
Online audio-visual target-speaker extraction aims to remove competing voices while preserving speech quality and bounding lookahead. Existing extractors are built and evaluated for separation on synthetic mixtures, leaving listening quality and meeting behavior largely untested. We introduce Audio-Visual Personalized...
Rayhan Rashed, Senja Filipi, Ross Cutler· 0 citations
Broadcast archives offer scale and diversity for self-supervised learning (SSL) but contain substantial noisy, non-speech, and multilingual content. Prior work typically relies on voice activity detection or language identification (LID) to extract speech, ensuring presence rather than quality. Whether and how to filte...
Yaroslav Getman, Tamás Grósz, Tommi Lehtonen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.