Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake

Orchid Chetia Phukan, Gautam Kashyap, Arun Balaji Buduru, Rajesh Sharma


Abstract
In this work, we investigate multilingual speech Pre-Trained models (PTMs) for Audio deepfake detection (ADD). We hypothesize thatmultilingual PTMs trained on large-scale diverse multilingual data gain knowledge about diverse pitches, accents, and tones, during theirpre-training phase and making them more robust to variations. As a result, they will be more effective for detecting audio deepfakes. To validate our hypothesis, we extract representations from state-of-the-art (SOTA) PTMs including monolingual, multilingual as well as PTMs trained for speaker and emotion recognition, and evaluated them on ASVSpoof 2019 (ASV), In-the-Wild (ITW), and DECRO benchmark databases. We show that representations from multilingual PTMs, with simple downstream networks, attain the best performance for ADD compared to other PTM representations, which validates our hypothesis. We also explore the possibility of fusion of selected PTM representations for further improvements in ADD, and we propose a framework, MiO (Merge into One) for this purpose. With MiO, we achieve SOTA performance on ASV and ITW and comparable performance on DECRO with current SOTA works.
Anthology ID:
2024.findings-naacl.160
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2496–2506
Language:
URL:
https://aclanthology.org/2024.findings-naacl.160
DOI:
Bibkey:
Cite (ACL):
Orchid Chetia Phukan, Gautam Kashyap, Arun Balaji Buduru, and Rajesh Sharma. 2024. Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 2496–2506, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake (Chetia Phukan et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.160.pdf
Copyright:
 2024.findings-naacl.160.copyright.pdf