Score: 1

Multilingual Dataset Integration Strategies for Robust Audio Deepfake Detection: A SAFE Challenge System

Published: August 28, 2025 | arXiv ID: 2508.20983v1

By: Hashim Ali , Surya Subramani , Lekha Bollinani and more

Potential Business Impact:

Finds fake voices in recordings.

Business Areas:
Speech Recognition Data and Analytics, Software

The SAFE Challenge evaluates synthetic speech detection across three tasks: unmodified audio, processed audio with compression artifacts, and laundered audio designed to evade detection. We systematically explore self-supervised learning (SSL) front-ends, training data compositions, and audio length configurations for robust deepfake detection. Our AASIST-based approach incorporates WavLM large frontend with RawBoost augmentation, trained on a multilingual dataset of 256,600 samples spanning 9 languages and over 70 TTS systems from CodecFake, MLAAD v5, SpoofCeleb, Famous Figures, and MAILABS. Through extensive experimentation with different SSL front-ends, three training data versions, and two audio lengths, we achieved second place in both Task 1 (unmodified audio detection) and Task 3 (laundered audio detection), demonstrating strong generalization and robustness.

Repos / Data Links

Page Count
8 pages

Category
Electrical Engineering and Systems Science:
Audio and Speech Processing