Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
10.55041/IJSREM.AITCON052
Volume:
10 |
4 |
April 2026
Pages:
1-3
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
AIML
Adarsh Institute of Technology & Research Centre ,Vita
AIML
Adarsh Institute of Technology & Research Centre ,Vita
AIML
Adarsh Institute of Technology & Research Centre ,Vita
AIML
Adarsh Institute of Technology & Research Centre ,Vita
AIML
Adarsh Institute of Technology & Research Centre ,Vita
The fast development of artificial intelligence systems and speech synthesis technology has made it easier to create deepfake audio, which produces realistic synthetic audio. The situation creates major risks, which endanger both digital security systems, authentication platforms, and the trustworthiness of information sources. The field of Deepfake Audio Detection has therefore gained significant importance in recent years. The research presents a Multifusion Multifeature Deepfake Audio Detection system, which performs exact detection of genuine speech against synthetic speech content. The proposed approach uses various audio features, which include speech signal spectral information, temporal data, and frequency-based elements. The system combines these features through a multiple fusion system, which produces better detection results. It also produces more robust performance. The system uses machine learning and deep learning methods to study the extracted features, which determine if audio samples belong to genuine or fake categories. The system detects minimal artificial audio defects, which human hearing fails to detect
KEYWORDS
The Multifusion Multifeature Deepfake Audio Detection project aims to identify whether an audio sample is real or fake. Using techniques from Artificial Intelligence and Machine Learning, the system extracts multiple audio features and analyzes them to detect manipulated speech in Deepfake Audio Detection. The results show that combining multiple features improves the accuracy and reliability of detecting fake audio, helping enhance security in voice-based systems
1. N. Jain, “Detecting Deepfakes: Exploring Machine Learning Models for Audio, Video, and Image Analysis,”International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 4, 2024. 2. S. Dilbar, M. A. Qureshi, S. K. Noon, and A. Mannan, “AudioFakeNet: A Model for Reliable Speaker Verification in Deepfake Audio,” Algorithms, vol. 18, no. 11, 2025. 3. L. Yu Gong and X. J. Li, “Deepfake Voice Detection Using End-to-End Transformer with Acoustic Feature Fusion,” Electronics, vol. 14, no. 10, 2025 4. M. P. Laureta, J. M. Atienza, and J. L. Tapel, “Deepfake Speech Detection Using Hybrid CNN-LSTM Model,” Journal of Engineering, Computing and Technology, 2024. 5. S. Borade et al., “Improving Deepfake Audio Detection Using SVM with Mel-Frequency Cepstral Coefficients,” International Journal of Intelligent Systems and Applications in Engineering, 2024.
Publication Date
4/30/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...