Research Article
Audio Deepfake Detection Using a Hybrid Model of Convolutional and Bidirectional Long Short-term Memory Networks
Samar Al-Halabi*
,
Adnan Kafri
Issue:
Volume 11, Issue 1, March 2026
Pages:
1-7
Received:
1 November 2025
Accepted:
13 November 2025
Published:
7 January 2026
Abstract: With the rapid advancement of audio deepfake technologies, detecting such manipulations has become a critical cybersecurity challenge. This study proposes a novel hybrid model that combines Convolutional Neural Networks (CNNs) with Bidirectional Long Short-Term Memory (BiLSTM) networks to detect spoofed audio. The research is based on the Release-in-the-Wild dataset, which simulates real-world acoustic conditions, and employs a preprocessing pipeline involving the extraction of Mel-Frequency Cepstral Coefficients (MFCCs) enhanced with first- and second-order derivatives. The proposed model achieved an accuracy of 99% with an Equal Error Rate (EER) of 0.011, while maintaining remarkable lightness with only 473k trainable parameters. Beyond numerical performance, the model demonstrates strong robustness against acoustic variability, environmental noise, and speaker diversity, highlighting its potential for deployment in uncontrolled real-world scenarios. Its compact design ensures low computational demand, making it practical for integration into online verification systems, intelligent voice assistants, and security monitoring infrastructures. Comparative experiments further confirm that the hybrid CNN–BiLSTM architecture achieves a superior balance between accuracy, efficiency, and generalization compared to recent Transformer-based models. Overall, this work contributes an interpretable and resource-efficient framework for generalized audio deepfake detection. The findings underline that high detection accuracy and lightweight design are not mutually exclusive, and future research will focus on extending the approach to multimodal systems that jointly analyze both audio and visual cues for more reliable deepfake forensics.
Abstract: With the rapid advancement of audio deepfake technologies, detecting such manipulations has become a critical cybersecurity challenge. This study proposes a novel hybrid model that combines Convolutional Neural Networks (CNNs) with Bidirectional Long Short-Term Memory (BiLSTM) networks to detect spoofed audio. The research is based on the Release-i...
Show More
Research Article
The Impediments and Solutions for Achieving Sustainable Water Management in Borno State, Nigeria
Ali Bakari*,
Babagana Muktar
Issue:
Volume 11, Issue 1, March 2026
Pages:
8-17
Received:
28 January 2026
Accepted:
7 February 2026
Published:
23 March 2026
DOI:
10.11648/j.aas.20261101.12
Downloads:
Views:
Abstract: In Borno State, Nigeria, and much of sub-Saharan Africa, particularly the Sudano-Sahel region, groundwater is crucial for the development of both urban and rural areas. More than half of the state's population depends directly on this resource for daily water needs. This study aims to develop a local, sustainable water management framework, based on the opinions of primary local stakeholders, to address water management challenges in Borno State, Northeastern Nigeria. To achieve this, a stakeholder analysis methodology was employed, and relevant stakeholders in Borno State were engaged through Focus Group Discussions and Interviews to provide the necessary solutions. The main challenges to sustainable water management in the state include limited technical and human resources, insufficient investment, and funding shortages. Additional issues include a lack of stakeholder participation in groundwater management and the fragmentation of national institutions responsible for water oversight. The results from the interviews and focus groups show that educating citizens to raise awareness about the benefits of safe, clean water and environmental protection is crucial. The current legislative framework is not producing sustainable results in water management. Some problems in achieving sustainable water management stem from the people's ethics, beliefs, and cultural norms regarding water issues in the state. Additionally, institutional stakeholders noted that the state's current top-down governance structure is a significant obstacle, often leading to inconsistencies in government policy implementation. University stakeholders emphasized the need for stronger connections between various national and regional institutions. Overall, the stakeholders suggested five key strategies to address the problem. The findings of this study will be vital for achieving sustainable water management in Borno State, and the lessons learned can be applied to other states. The recommendations can be implemented by water managers and may support the attainment of the Sustainable Development Goals in the state.
Abstract: In Borno State, Nigeria, and much of sub-Saharan Africa, particularly the Sudano-Sahel region, groundwater is crucial for the development of both urban and rural areas. More than half of the state's population depends directly on this resource for daily water needs. This study aims to develop a local, sustainable water management framework, based o...
Show More
