# Dual-Branch Gated Fusion for Open-Set Audio Deepfake Source Tracing

Source: [Dual-Branch Gated Fusion for Open-Set Audio Deepfake Source Tracing](<https://www.sota2.com/research/paper/6a28f35290966ade919c1850>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-11T05:00:05.512Z

Authors: Awais Khan, Kutub Uddin, Khalid Malik

Published: 2026-06-08T22:22:48.000Z

## Abstract

Attributing a synthetic utterance to its originating system remains an open challenge: closed-set models fail to reject unseen synthesizers and produce overconfident predictions. To address this, we propose a dual-branch gated fusion framework that pairs XLSR-53 with CORES, a 66-dimensional descriptor that, unlike prior Linear Filter Bank (LFB)-only work, spans cepstral, oscillatory, rhythmic, energy, and spectral dimensions to capture complementary synthesis artifacts. Our analysis shows XLSR-53 remains discriminative in-domain (ID) while CORES generalizes stably under distribution shift (OOD), yet their naive concatenation fails due to SSL representational imbalance. To resolve this, an input-conditioned gate adaptively weights each branch under joint training with cross-entropy, an energy margin loss for ID/OOD separation, and a gate diversity term. On the MLAAD benchmark, our system achieves 97.6\\% ID accuracy, 4.9\\% EERc, and an 83.5\\% relative FPR95 reduction over the Interspeech 2025 baseline.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Audio Source Attribution on MLAAD In-Domain (Eval)](<https://www.sota2.com/research/sota/audio-source-attribution-on-mlaad-in-domain-eval.md>): Audio Source Attribution; MLAAD In-Domain (Eval); Accuracy: 97.6.

- [Audio Source Attribution on MLAAD (OOD Eval)](<https://www.sota2.com/research/sota/audio-source-attribution-on-mlaad-ood-eval.md>): Audio Source Attribution; MLAAD (OOD Eval); Accuracy: 94.3.

- [Audio Source Tracing on MLAAD (eval)](<https://www.sota2.com/research/sota/audio-source-tracing-on-mlaad-eval.md>): Audio Source Tracing; MLAAD (eval); ID Accuracy: 97.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.10223>)

[PDF](<https://arxiv.org/pdf/2606.10223.pdf>)