Skip to content
Open access

Deepfake Audio Detection Using Hybrid Audio Spectrogram Transformer with Dual-Attention Feature Fusion and Bayesian Optimization

Sep 2026 · Journal of Mathematics, Computations and Statistics · Vol 9, pp. 693-701 · 0 citations

TL;DR

A novel framework that leverages log-Mel spectrogram representations to capture informative time–frequency characteristics of audio signals and is further enhanced by a Dual-Attention Feature Fusion mechanism to improve discriminative capability at both spatial and channel levels is proposed.

Abstract

Deepfake audio has become a serious threat to digital security due to its ability to generate highly realistic synthetic speech for malicious purposes such as impersonation, fraud, and social engineering. Despite the rapid advancement of deepfake generation technologies, audio-based detection remains relatively underexplored compared to image and video domains. Moreover, existing approaches largely rely on handcrafted features and conventional machine learning methods, which are often insufficient to capture complex temporal and spectral dependencies and often exhibit limited generalization to unseen deepfake generation techniques. This study proposes a novel framework that leverages log-Mel spectrogram representations to capture informative time–frequency characteristics of audio signals. The proposed model integrates a Hybrid Audio Spectrogram Transformer to model global dependencies through self-attention and is further enhanced by a Dual-Attention Feature Fusion mechanism to improve discriminative capability at both spatial and channel levels. In addition, Bayesian Optimization is employed to efficiently optimize hyperparameters, leading to improved model performance, faster convergence, and better generalization. Experimental results demonstrate that the proposed model achieves an accuracy of 93.60% and an AUC of 0.9724, indicating excellent discriminative performance. The model also achieves a high recall in detecting deepfake audio, highlighting its effectiveness in minimizing false negatives and improving robustness in real-world scenarios. These findings demonstrate that the proposed framework provides an effective and reliable solution for deepfake audio detection and offers significant potential for deployment in practical cybersecurity and digital audio forensic applications.

Read PDF

Similar papers

Open access Nov 2026

Audio deepfake detection using constant-Q transform scalograms and spatial-transformer attention networks

Detecting synthetically generated speech has become increasingly important for forensic speaker verification and digital media security. In particular, recent advances in speech synthesis and voice conversion technologies have enabled the generation of increasingly natural speech samples that are difficult to distingui...

M. Kucuk, Zeynep Sude Şeker, B. Çelik et al. · 0 citations
Conference Open access Oct 2026

HybridSpec-MFCC: A Multi-Modal Approach for Robust Deepfake Audio Detection Using Spectral-Temporal Feature Fusion

The use of AI-generated synthetic audio presents some new security issues and creates validity issues with respect to the content. This paper describes a deepfake audio detection system called HybridSpec-MFCC that depends on MFCCs, spectral contrast and chromagram features in a combined convolutional-recurrent architec...

Ramesh G, Vaikunta Pai T, S. R · 0 citations
Open access 2026

Performance Evaluation of DenseNet-121 and Bi-LSTM with Attention Mechanism based Vocal Signal Separation

This paper presents a supervised attention-based deep learning approach for separating single-channel audio signals that establishes a low complexity, scalable, and interpretable solution to realistic problems in source separation.

Arfana Chowdhary, Parveen Kumar Lehana · 0 citations
Open access Oct 2026

Transformer-Based Multi-Modal Architecture for Real-Time Deepfake Detection in Streaming Video

The rapid diffusion of generative deep learning models—specifically Diffusion-based video synthesis, Neural Radiance Fields (NeRFs), and advanced voice cloning autoencoders—has made synthetic media creation accessible to non-experts. While these techniques drive innovations in entertainment and virtual reality, they al...

Manish Jain · 0 citations
Open access Oct 2026

An Optimized Audio–Visual Deepfake Detection Framework Using Mamba Vision Transformers with Linear Complexity

The rise of advanced deepfake technologies presents new challenges to media authenticity, making it harder to spot manipulated videos through traditional approaches. Current approaches have a quadratic time complexity O(n2), poor cross-dataset generalization with 20 to 35% accuracy degradation, and inadequate audio–vis...

Aisha Arain, Bushra Naz, Sania Bhatti et al. · 0 citations
Conference Open access 2026

A comparative evaluation of spectrogramand bispectrumbased transfer learning for drone audio classification

Acoustic signal analysis serves as an essential approach for detecting drones operated via optical fibers, which evade conventional radio-frequency detection methods. Nonetheless, achieving reliable acoustic-based detection poses notable challenges due to the pronounced sensitivity of classification models to environme...

S. Milanović, Miodrag S. Vračar, Ivan Pokrajac · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.