Home / Current Issue / Paper 1712477
Wav2Vec Meets Conformer: A Novel Hybrid Approach for Multilingual Deepfake Audio Detection
Subject area: Science,Engineering and Technology · Area of research: Multilingual Deepfake Audio Detection
DOI: https://doi.org/10.64388/IREV9I5-1712477
Abstract
Deepfake audio refers to synthetic speech that closely mimics a person?s voice, posing risks to security and privacy. This paper proposes a hybrid detection framework combining XLS-R, a multilingual speech representation model, with the Conformer architecture, which captures both local and global audio dependencies. XLS-R extracts rich multilingual embeddings, while the Conformer leverages temporal and contextual features to distinguish genuine from AI-generated speech. Evaluation on benchmark datasets demonstrates that the proposed system achieves improved accuracy and robustness across multiple languages and acoustic conditions.
Keywords
Conformer, Deepfake Audio, Multilingual Speech Representation, XLS-R
How to cite this paper
@article{1712477,
author = {Usha Janakiraman, Priyadharshini Ambalavanan, Padmapriya S},
title = {Wav2Vec Meets Conformer: A Novel Hybrid Approach for Multilingual Deepfake Audio Detection},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {5},
pages = {2438-2446},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1712477.pdf},
abstract = {Deepfake audio refers to synthetic speech that closely mimics a person?s voice, posing risks to security and privacy. This paper proposes a hybrid detection framework combining XLS-R, a multilingual speech representation model, with the Conformer architecture, which captures both local and global audio dependencies. XLS-R extracts rich multilingual embeddings, while the Conformer leverages temporal and contextual features to distinguish genuine from AI-generated speech. Evaluation on benchmark datasets demonstrates that the proposed system achieves improved accuracy and robustness across multiple languages and acoustic conditions.},
keywords = {Conformer, Deepfake Audio, Multilingual Speech Representation, XLS-R},
month = {November},
doi = {https://doi.org/10.64388/IREV9I5-1712477}
}