MFAAN: Unveiling Audio Deepfakes with a Multi-Feature Authenticity Network

TL;DR

This paper introduces MFAAN, a multi-feature neural network that effectively detects audio deepfakes by combining various audio representations, achieving high accuracy on benchmark datasets and enhancing the fight against manipulated audio content.

Contribution

MFAAN is a novel architecture that fuses multiple audio features for robust deepfake detection, outperforming existing methods on standard datasets.

Findings

Achieved 98.93% accuracy on 'In-the-Wild' dataset.

Achieved 94.47% accuracy on Fake-or-Real dataset.

Demonstrated superior performance over baseline models.

Abstract

In the contemporary digital age, the proliferation of deepfakes presents a formidable challenge to the sanctity of information dissemination. Audio deepfakes, in particular, can be deceptively realistic, posing significant risks in misinformation campaigns. To address this threat, we introduce the Multi-Feature Audio Authenticity Network (MFAAN), an advanced architecture tailored for the detection of fabricated audio content. MFAAN incorporates multiple parallel paths designed to harness the strengths of different audio representations, including Mel-frequency cepstral coefficients (MFCC), linear-frequency cepstral coefficients (LFCC), and Chroma Short Time Fourier Transform (Chroma-STFT). By synergistically fusing these features, MFAAN achieves a nuanced understanding of audio content, facilitating robust differentiation between genuine and manipulated recordings. Preliminary evaluations of MFAAN on two benchmark datasets, 'In-the-Wild' Audio Deepfake Data and The Fake-or-Real Dataset, demonstrate its superior performance, achieving accuracies of 98.93% and 94.47% respectively. Such results not only underscore the efficacy of MFAAN but also highlight its potential as a pivotal tool in the ongoing battle against deepfake audio content.