Deep Learning Based Feature Level and Image Level Framework for Fake voice Detection

S. Sharanyaa; Shalini S; Madhumitha P; Sherlin Jemima J

Back

Research Article Matrix Node

Deep Learning Based Feature Level and Image Level Framework for Fake voice Detection

Author(s): S. Sharanyaa, Shalini S, Madhumitha P, Sherlin Jemima J

Volume RegistryVolume 2

Issue PeriodIssue 03

Published Date08 Aug 2026

DOI Identifier—

Abstract

This paper introduces a new framework for the identification of artificial (Deep Fake Audio) voice using both the feature level and image level learning approaches in deep learning based technique. The rapid development in Artificial Intelligence and generation techniques has made the creation of highly believable audio possible; this poses serious threats to digital security and credibility of the information. In order to deal with this issue, the proposed system consists of a two-branch system consisting of Mel Frequency Cepstral Coefficient (MFCC) and Gammatone Frequency Cepstral Coefficient (GFCC) with a feature level approach using a Long Short-Term Memory (LSTM) model and Mel spectrogram images with an image-level approach using Deep Convolutional Neural Network (DCNN). The system uses advanced techniques of preprocessing, feature extraction and CatBoost based feature fusion. Experiments have been performed using the ASV spoof 2021 dataset for testing the efficacy of the proposed system in discriminating between real and fake audio. The system gives better accuracy, precision and robustness as compared to some existing state-of-the-art techniques. The system can also be used for real-time detection through graphical user interface.

Keywords

Deepfake Audio MFCC GFCC Long Short Term memory Convolutional Neural Network Deep Learning Spectrogram

References (22)

[Multimodaltrace: Deepfake Detection using Audiovisual Representation Learning,Muhammad Anas Raza Khalid Mahmood Malik,Oakland University,2023 IEEE/CVF Conference on Computer Vision and Pat-tern Recognition Workshops (CVPRW) — 979-83503- 0249-3/23/31.00©2023IEEE—DOI: https://doi.org/10.1109/CVPRW59228.2023.00106
C. Stupp, “Fraudsters used Ai to mimic CEO’s voice in unusual cybercrime case,” Wall Street J., vol. 30, no. 8, pp. 12, 2019.
Deepfake audio detection by speaker verification,Alessandro Pianese,Davide Cozzolino, Giovanni Poggi and Luisa Verdoliva ,University Federico II of Naples, Italy,2022 IEEE International Workshop on Information Forensics and Security (WIFS) — 979- 83503-0967-6/22/31.00©2022IEEE—DOI: https://doi.org/10.1109/WIFS55849.2022.9975428
Deepfake detection using deep learning methods: A systematic and comprehensive review , Arash Heidari, Nima Jafari Navimipour, Hasan Dag, Mehmet Unal, 2023,https://doi.org/10.1002/widm.1520
D. Garg and R. Gill, ”Deepfake Generation and Detection - An Exploratory Study,” 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON), Gautam Buddha Nagar, India, 2023, pp. 888 893, doi: https://doi.org/10.1109/UPCON59197.2023.10434896
R. Mahyavanshi, C. V. M. Reddy, A. J. Shah and H. A. Patil, ”Teager Energy Cepstral Coefficients for Audio Deepfake Detection,” 2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Macau, Macao, 2024, pp. 1 6, doi: https://doi.org/10.1109/APSIPAASC63619.2025.10848893
I. Altalahin, S. AlZu’bi, A. Alqudah and A. Mughaid, ”Unmasking the Truth: A Deep Learning Approach to Detecting Deepfake Audio Through MFCC Features,” 2023 International Conference on Information Technology (ICIT), Amman, Jordan, 2023, pp. 511–518, doi: https://doi.org/10.1109/ICIT58056.2023.10226172
Y. Xie et al., ”Does Current Deepfake Audio Detection Model Effectively Detect ALM-Based Deepfake Audio?,” 2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP), Beijing, China, 2024, pp. 481–485, doi: https://doi.org/10.1109/ISC- SLP63861.2024.10800375.
Z. Hao et al., ”Integrating Spectro-Temporal Cross Aggregation and Multi-Scale Dynamic Learning for Audio Deepfake Detection,” ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2025,pp. 1–5, doi: https://doi.org/10.1109/ICASSP49660.2025.10889337
Y. Guo, H. Huang, X. Chen, H. Zhao and Y. Wang, ”Audio Deepfake Detection With Self-Supervised Wavlm And Multi-Fusion Attentive Classifier,” ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, Republic of, 2024, pp. CASSP48485.2024.10447923. 12702–12706
Z. Jin, L. Lang and B. Leng, ”Wave-Spectrogram Cross-Modal Aggregation for Audio Deepfake Detection,” ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Pro- cessing (ICASSP), Hyderabad, India, 2025, pp. 1–5, doi: https://doi.org/10.1109/I- CASSP49660.2025.10890563.
J. Choi, T. Kim and J. Choi, ”ID-Flow: Leveraging Voice Identity for Generalizing Audio Deepfake Detection,” 2025 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA, 2025, pp. 1–5, doi: https://doi.org/10.1109/ICCE63647.2025.10929900
K. M. Lapates, B. D. Gerardo and R. P. Medina, ”Performance Evaluation of Enhanced DCGANs for Detecting Deepfake Audio Across Selected FoR Datasets,” 2024 15th International Confer- ence on Information and Communication Technology Convergence (ICTC), Jeju Island, Korea, Republic of, 2024, pp. 54–59, doi: https://doi.org/10.1109/ICTC62082.2024.10827547
S.-P. Doan, L. Nguyen-Vu, S. Jung and K. Hong, ”BTS-E: Au- dio Deepfake Detection Using Breathing-Talking-Silence Encoder,” ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1–5, doi: https://doi.org/10.1109/ICASSP49357.2023.10095927
E. Jain and A. Singh, ”Deepfake Voice Detection Using Convolu- tional Neural Networks: A Comprehensive Approach to Identifying Synthetic Audio,” 2024 International Conference on Communication, Control, and Intelligent Systems (CCIS), Mathura, India, 2024, pp. 1 5, doi: https://doi.org/10.1109/CCIS63231.2024.10931997
H.S. Shin, J. Heo, J.-H. Kim, C.-Y. Lim, W. Kim and H.-J. Yu, ”HM CONFORMER: A Conformer -Based Audio Deepfake Detection System with Hierarchical Pooling and Multi-Level Clas- sification Token Aggregation Methods,” ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, Republic of, 2024, pp. 10581–10585, doi: https://doi.org/10.1109/ICASSP48485.2024.10448453
L. Astrid, E. Ghorbel and D. Aouada, ”Audio-Visual Deepfake Detection With Local Temporal Inconsistencies,” ICASSP 2025- 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2025, pp. 1–5, doi: https://doi.org/10.1109/ICASSP49660.2025.10889087
P. Chiddarwar, ”Real-Time Detection of AI-Generated Deepfake Audio: A Novel Approach,” 2024 IEEE 4th International Conference on ICT in Business Industry & Government (ICTBIG), Indore, India, 2024, pp. 1–5, doi: https://doi.org/10.1109/ICTBIG64922.2024.10911062
D. Song, N. Lee, J. Kim and E. Choi, ”Anomaly Detection of Deepfake Audio Based on Real Audio Using Generative Adversarial Network Model,” IEEE Access, vol. 12, pp. 184311–184326, 2024, doi: https://doi.org/10.1109/ACCESS.2024.3506973
Q. A. Samiha, M. T. Alom, R. Hossain, R. Islam and A. Sul- tana, ”Leveraging Deep Learning Methods for Detecting Deepfake Speeches,” 2025 IEEE 4th International Conference on Computing and Machine Intelligence (ICMI), MI, USA, 2025, pp. 1–5, doi: https://doi.org/10.1109/ICMI65310.2025.11141035
M. Pham, P. Lam, T. Nguyen, H. Nguyen and A. Schindler, ”Deepfake Audio Detection Using Spectrogram-based Feature and Ensemble of Deep Learning Models,” 2024 IEEE 5th International Symposium on the Internet of Sounds (IS2), Erlangen, Germany, 2024, pp. 1–5, doi: https://doi.org/10.1109/IS262782.2024.10704095
A. E. Djire´, A. Sabane´, A.-K. Kabore, R. Kafando and T. F. Bissyande´, ”Evaluating Acoustic Parameters for DeepFake Audio Identification,” 2023 IEEE Afro-Mediterranean Conference on Arti- ficial Intelligence (AMCAI), Hammamet, Tunisia, 2023, pp. 1–6, doi: https://doi.org/10.1109/AMCAI59331.2023.10431521

S. Sharanyaa, Shalini S, Madhumitha P, and Sherlin Jemima J, "Deep Learning Based Feature Level and Image Level Framework for Fake voice Detection," Int. J. Adv. Eng. Manag. Syst., vol. 2, no. 3, pp. 380-387, 2026.

Deep Learning Based Feature Level and Image Level Framework for Fake voice Detection

Abstract

Keywords

References (22)

Format Citation Record