Deepfake Audio Detection via MFCC Features Using Machine Learning
Open accessThe DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Abstract
Deepfake content is created or altered synthetically using artificial intelligence (AI) approaches to appear real. It can include synthesizing audio, video, images, and text. Deepfakes may now produce natural-looking content, making them harder to identify. Much progress has been achieved in identifying video deepfakes in recent years; nevertheless, most investigations in detecting audio deepfakes have employed the ASVSpoof or AVSpoof dataset and various machine learning, deep learning, and deep learning algorithms. This research uses machine and deep learning-based approaches to identify deepfake audio. Mel-frequency cepstral coefficients (MFCCs) technique is used to acquire the most useful information from the audio. We choose the Fake-or-Real dataset, which is the most recent benchmark dataset. The dataset was created with a text-to-speech model and is divided into four sub-datasets: for-rece, for-2-sec, for-norm and for-original. These datasets are classified into sub-datasets mentioned above according to audio length and bit rate. The experimental results show that the support vector machine (SVM) outperformed the other machine learning (ML) models in terms of accuracy on for-rece and for-2-sec datasets, while the gradient boosting model performed very well using for-norm dataset. The VGG-16 model produced highly encouraging results when applied to the for-original dataset. The VGG-16 model outperforms other state-of-the-art approaches.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Their experiments revealed that while traditional machine learning models performed well on clean datasets, deep learning models exhibited superior robustness in more complex data scenarios.”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [111]
In the citing paper
“Hamza et al. [111] further investigated MFCC in various machine learning and deep learning frameworks, demonstrating its effectiveness in distinguishing genuine and fake audio.”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [111]
In the citing paper
“Traditional detection methods [3], [4] rely on classical machine learning models; however, these approaches often struggle with generalization and scalability when confronted with the latest generative adversarial networks (GANs) and advanced deep learning architectures that are used to create deepfakes [5].”
From Quantum-Trained Convolutional Neural Network for Deepfake Audio Detection (2025) · cites this paper as [3]
In the citing paper
“Existing unimodal deepfake detectors are primarily designed to detect a single type of manipulation, such as visual, acoustic, and text.”
From Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization (2024) · cites this paper as [23]
Citations
Cites
Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions
Shen, J., Pang, R., Weiss, R. J., Schuster, M., Jaitly, N., Yang, Z., Chen, Z., Zhang, Y., Wang, Y., Skerrv-Ryan, R., et al. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8461368 · Cited by 2,791
Javed, A. R., Shahzad, F., Rehman, S. U., Zikria, Y. B., Razzak, I., Jalil, Z., & Xu, G. (2022) · Cities · doi:10.1016/j.cities.2022.103794 · Cited by 606
Self-citationThe CMU Arctic speech databases.
Kominek, J., & Black, A. W. (2004) · Cited by 600
The ASVspoof 2017 challenge: assessing the limits of replay spoofing attack detection
Kinnunen, T., Sahidullah, M., Delgado, H., Todisco, M., Evans, N., Yamagishi, J., & Lee, K. A. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-1111 · Cited by 535
Sampling, data transmission, and the Nyquist rate
Landau, H. J. (1967) · Proceedings of the IEEE · doi:10.1109/proc.1967.5962 · Cited by 499
ASVspoof 2015: the first automatic speaker verification spoofing and countermeasures challenge
Wu, Z., Kinnunen, T., Evans, N., Yamagishi, J., Hanilçi, C., Sahidullah, M., & Sizov, A. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-462 · Cited by 484 · cited 2×
“The ASVspoof2015 [11] is the first automatic speaker verification spoofing and countermeasures dataset that stimulates research in this field.”
BackgroundDeep Learning for Deepfakes Creation and Detection: A Survey
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh-The, T., Nahavandi, S., Nguyen, T. T., Pham, Q.-V., & Nguyen, C. M. (2019) · arXiv · doi:10.48550/arxiv.1909.11573 · Cited by 464
Probabilistic forecasting with temporal convolutional neural network
Chen, Y., Kang, Y., Chen, Y., & Wang, Z. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.03.011 · Cited by 393
Deep voice 3: scaling text-to-speech with convolutional sequence learning
Ping, W., Peng, K., Gibiansky, A., Arik, S. O., Kannan, A., Narang, S., Raiman, J., & Miller, J. (2017) · arXiv · doi:10.48550/arxiv.1710.07654 · Cited by 313
9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)
(2016) · doi:10.21437/ssw.2016 · Cited by 195
Research works printed but not linked: 3
- Stupp, 2019, Fraudsters used Ai to mimic CEO’s voice in unusual cybercrime case, Wall Street J., 30, 1
- Ito, 2017, The LJ Speech Dataset
- MacLean, 2018, Voxforge
Cited by
A Survey of Explainable Artificial Intelligence for Smart Cities
Javed, A. R., Ahmed, W., Pandya, S., Maddikunta, P. K. R., Alazab, M., & Gadekallu, T. R. (2023) · Electronics · doi:10.3390/electronics12041020 · Cited by 193
Self-citationA Survey on the Detection and Impacts of Deepfakes in Visual, Audio, and Textual Formats
Mubarak, R., Alsboui, T., Alshaikh, O., Inuwa-Dutse, I., Khan, S., & Parkinson, S. (2023) · IEEE Access · doi:10.1109/access.2023.3344653 · Cited by 132
Abbas, F., & Taeihagh, A. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124260 · Cited by 184
“Hamza et al. (2022) analyzed audio deepfakes through Mel-frequency cepstral coefficients (MFCC) features by employing different deep learning models.”
MethodDeepfake Media Forensics: Status and Future Challenges
Amerini, I., Barni, M., Battiato, S., Bestagini, P., Boato, G., Bruni, V., Caldelli, R., De Natale, F., De Nicola, R., Guarnera, L., et al. (2025) · Journal of Imaging · doi:10.3390/jimaging11030073 · Cited by 113
“Alternatively, the authors of [115,116] propose end-to-end networks trained for extracting deep features from speech, while [117] uses Mel-Frequency Cepstral Coefficient (MFCC) features as input of a Support Vector Machine (SVM) classifier.”
A Robust Approach to Multimodal Deepfake Detection
Salvi, D., Liu, H., Mandelli, S., Bestagini, P., Zhou, W., Zhang, W., & Tubaro, S. (2023) · Journal of Imaging · doi:10.3390/jimaging9060122 · Cited by 96
“In [40], the authors establish a mapping between audio and video frames by analyzing the changes in the lip opening degree.”
Data Augmentation-based Novel Deep Learning Method for Deepfaked Images Detection
Iqbal, F., Abbasi, A., Javed, A. R., Almadhor, A. S., Jalil, Z., Anwar, S., & Rida, I. (2023) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3592615 · Cited by 79
“Hyper-realistic digital graphics may now be created with little resources and simple how-to-do instructions accessible online [4, 5] hence leading to fake audios, videos and images [6, 7].”
BackgroundSelf-citationTIMIT-TTS: A Text-to-Speech Dataset for Multimodal Synthetic Media Detection
Salvi, D., Hosler, B., Bestagini, P., Stamm, M. C., & Tubaro, S. (2023) · IEEE Access · doi:10.1109/access.2023.3276480 · Cited by 65
“synthetic speech, while those of [40] perform the detection task based on the use of MFCC features and an SVM.”
MethodKosarkar, U. P., & Sakarkar, G. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19220-w · Cited by 210
Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead
Zhang, B., Cui, H., Nguyen, V., & Whitty, M. (2025) · Sensors · doi:10.3390/s25071989 · Cited by 72
“Hamza et al. [111] further investigated MFCC in various machine learning and deep learning frameworks, demonstrating its effectiveness in distinguishing genuine and fake audio.”
Mutual information based logistic regression for phishing URL detection
Vajrobol, V., Gupta, B. B., & Gaurav, A. (2024) · Cyber Security and Applications · doi:10.1016/j.csa.2024.100044 · Cited by 93
A novel hybrid model integrating MFCC and acoustic parameters for voice disorder detection
Verma, V., Benjwal, A., Chhabra, A., Singh, S. K., Kumar, S., Gupta, B. B., Arya, V., & Chui, K. T. (2023) · Scientific Reports · doi:10.1038/s41598-023-49869-6 · Cited by 55
“VOICED used a built-in microphone of a mobile device 39 and an applicable m-health system, Vox4Health 40,41 , to collect a speech signal of vowel ‘a’ in real time.”
MethodKhan, A. A., Chen, Y., Hajjej, F., Shaikh, A. A., Yang, J., Ku, C. S., & Por, L. Y. (2024) · Egyptian Informatics Journal · doi:10.1016/j.eij.2024.100502 · Cited by 75
Exploring autonomous methods for deepfake detection: A detailed survey on techniques and evaluation
Sunil, R., Mer, P., Diwan, A., Mahadeva, R., & Sharma, A. (2025) · Heliyon · doi:10.1016/j.heliyon.2025.e42273 · Cited by 54
Kumar, A., Singh, D., Jain, R., Jain, D. K., Gan, C., & Zhao, X. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.102993 · Cited by 59
Data augmentation and hybrid feature amalgamation to detect audio deep fake attacks
Chakravarty, N., & Dua, M. (2023) · Physica Scripta · doi:10.1088/1402-4896/acea05 · Cited by 46
NFTs for combating deepfakes and fake metaverse digital contents
Hasan, H. R., Salah, K. M., Jayaraman, R., Yaqoob, I., & Omar, M. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101133 · Cited by 39
Unmasking the Truth: A Deep Learning Approach to Detecting Deepfake Audio Through MFCC Features
Altalahin, I., AlZu’bi, S. M. F., Alqudah, A. A. M., & Mughaid, A. S. (2023) · doi:10.1109/icit58056.2023.10226172 · Cited by 27
EDL-Det: A Robust TTS Synthesis Detector Using VGG19-Based YAMNet and Ensemble Learning Block
Mahum, R., Irtaza, A., & Javed, A. (2023) · IEEE Access · doi:10.1109/access.2023.3332561 · Cited by 33
“Various fake speech-detecting systems have been tested along with ResNet [13] and explored with other classifiers for better performance [14].”
MethodSelf-citationQuantum-Trained Convolutional Neural Network for Deepfake Audio Detection
Lin, C.-H. A., Liu, C.-Y., Chen, S. Y.-C., & Chen, K.-C. (2025) · 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · doi:10.1109/icasspw65056.2025.11011133 · Cited by 30
“…consisted of extracted audio features such as chroma STFT [27], spectral centroid [28], spectral bandwidth [29], roll-off frequency, zero-crossing rate [30], and Mel-Frequency Cepstral Coefficients (MFCCs) [3], which were read into a pandas DataFrame for exploratory data analysis (EDA) [31].”
Unmasking the Fake: Machine Learning Approach for Deepfake Voice Detection
Tanveer, M. U., Munir, K., Amjad, M., Rehman, A. U., & Bermak, A. (2024) · IEEE Access · doi:10.1109/access.2024.3521026 · Cited by 41
MIS-AVoiDD: Modality Invariant and Specific Representation for Audio-Visual Deepfake Detection
Katamneni, V. S., & Rattani, A. (2023) · International Conference on Machine Learning and Applications · doi:10.1109/icmla58977.2023.00207 · Cited by 47
“As a countermeasure, several unimodal audio and visual deepfake detectors have been proposed [4]– [10].”
BackgroundInfluentialDetecting Audio Deepfakes: Integrating CNN and BiLSTM with Multi-Feature Concatenation
Wani, T. M., Qadri, S. A. A., Comminiello, D., & Amerini, I. (2024) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/3658664.3659647 · Cited by 30
Anomaly Detection of Deepfake Audio Based on Real Audio Using Generative Adversarial Network Model
Song, D., Lee, N., Kim, J., & Choi, E. (2024) · IEEE Access · doi:10.1109/access.2024.3506973 · Cited by 28
MFCC as Features for Speaker Classification using Machine Learning
Mu, X., & Min, C.-H. (2023) · IEEE World AI IoT Congress (AIIoT) · doi:10.1109/aiiot58121.2023.10174566 · Cited by 22
Deepfakes Audio Detection Leveraging Audio Spectrogram and Convolutional Neural Networks
Wani, T. M., & Amerini, I. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43153-1_14 · Cited by 25
Triple-modality interaction for deepfake detection on zero-shot identity
Yoon, J., Panizo-LLedot, Á., Camacho, D., & Choi, C. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102424 · Cited by 28
Deepfakes in digital media forensics: Generation, AI-based detection and challenges
Bendiab, G., Haiouni, H., Moulas, I., & Shiaeles, S. N. (2024) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2024.103935 · Cited by 35
Pushing the boundaries of deepfake audio detection with a hybrid MFCC and spectral contrast approach
Jellali, A., Fredj, I. B., & Ouni, K. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19819-z · Cited by 24
A Hybrid CNN-LSTM Approach for Deepfake Audio Detection
Chitale, M., Dhawale, A., Dubey, M., & Ghane, S. (2024) · International Conference on Artificial Intelligence for Internet of Things (AIIoT) · doi:10.1109/aiiot58432.2024.10574576 · Cited by 30
“In [1], proposed by Hamza et al. , Support Vector Machines (SVM) and Gradient Boosting Models, specifically VGG-16, with VGG-16 outperforming other approaches have been used.”
MethodNovel transfer learning based acoustic feature engineering for scene fake audio detection
Al‐Shamayleh, A. S., Riasat, H., Alluhaidan, A. S., Raza, A., Rahman, S. A. E., & AbdElminaam, D. S. (2025) · Scientific Reports · doi:10.1038/s41598-025-93032-2 · Cited by 23
Wani, T. M., Qadri, S. A. A., Wani, F. A., & Amerini, I. (2024) · Foundations and Trends® in Privacy and Security · doi:10.1561/3300000048 · Cited by 16
Backdoor Attacks against Voice Recognition Systems: A Survey
Yan, B., Lan, J., & Yan, Z. (2024) · ACM Computing Surveys · doi:10.1145/3701985 · Cited by 30
“[26] selected MFCCs to acquire the most useful information from the audio and used DNN based approaches to identify deepfake audio.”
MethodTaviti, R., Taviti, S., Reddy, P. A., Sankar, N. R., Veneela, T., & Goud, P. B. (2023) · International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT) · doi:10.1109/iconscept57958.2023.10170580 · Cited by 20
“In order to evaluate the visual and audio characteristics of a video, researchers have created a variety of deepfake detection techniques that use various combos of these techniques [1-4].”
MethodContextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization
Katamneni, V. S., & Rattani, A. (2024) · 2024 IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb62174.2024.10744480 · Cited by 20
“As a countermeasure, several unimodal audio and visual deepfake detectors have been proposed [32, 23, 2, 39, 13, 24, 46].”
BackgroundABC-CapsNet: Attention based Cascaded Capsule Network for Audio Deepfake Detection
Wani, T. M., Gulzar, R., & Amerini, I. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00253 · Cited by 14
“Taking inspiration from the state-of-the-art works, this work proposes a novel architecture, ABC-CapsNet (Attention-Based Cascaded Capsule Network), designed to tackle the challenges of audio deepfake detection.”
MethodSar, A., Sati, S., Choudhury, T., Joshi, P., Sille, R., Srihari, K., & Bansal, K. (2025) · IEEE Access · doi:10.1109/access.2025.3550770 · Cited by 24
“Sach-AI, state-of-the-art research, which stands as a strong pioneering framework, was designed and made to address this type of sophisticated nature of different deepfake contents, which spanned itself over video [7], [8], audio [9] and image [10] domains.”
Detecting Deepfake Audio Using Spectrogram-Based Machine Learning Approaches
Bohara, R., & Bairwa, A. K. (2025) · IEEE Access · doi:10.1109/access.2025.3602531 · Cited by 21
“Hamza et al. [1] had suggested a mechanism of deepfake audio detection using Mel-frequency cepstral coefficients (MFCCs) as the feature extractors.”
InfluentialRetrieval-Augmented Audio Deepfake Detection
Kang, Z., He, Y., Zhao, B., Qu, X., Peng, J., Xiao, J. Z., & Wang, J. (2024) · International Conference on Multimedia Retrieval · doi:10.1145/3652583.3658086 · Cited by 25
Dual-Channel Deepfake Audio Detection: Leveraging Direct and Reverberant Waveforms
Lee, G., Lee, J., Jung, M., Lee, J., Hong, K., Jung, S., & Han, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3532775 · Cited by 22
“Recently, numerous convolutional neural network (CNN) architectures have been proposed [6], [7], [8], [9], [10], [11], [12], [13] to capture spatial image features and/or temporal audio features, such as mel-frequency cepstral coefficients (MFCC) and linear-frequency cepstral coefficients (LFCC),…”
InfluentialTransferable Adversarial Attacks on Audio Deepfake Detection
Farooq, M. U., Khan, A. A., Uddin, K., & Malik, K. M. (2025) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw65960.2025.00178 · Cited by 35
“The first category involves extracting critical features from audio signals using techniques such as MFCCs [6], LFCCs [17], and Constant Q Cepstral Coefficients (CQCCs) [24].”
Deepfake Audio Detection for Urdu Language Using Deep Neural Networks
Ahmad, O., Khan, M. S., Jan, S., & Khan, I. (2025) · IEEE Access · doi:10.1109/access.2025.3571293 · Cited by 20
“Hamza et al. [11] utilized employed a Support Vector Machine (SVM) as a component of its deep learning and machine learning techniques to identify counterfeit audio.”
A Survey on Face‐Swapping Methods for Identity Manipulation in Deepfake Applications
Dhanyalakshmi, R., Stoian, G., Dănciulescu, D., & Hemanth, D. J. (2025) · IET Image Processing · doi:10.1049/ipr2.70132 · Cited by 15
Deepfake detection: critical review of state-of-the-art approaches and future perspectives
Soundarya, B. C., & Gururaj, H. L. (2026) · Discover Applied Sciences · doi:10.1007/s42452-025-08174-9 · Cited by 27
“Researchers in [90] utilized the Fake-or-Real dataset, which comprises a range of fake audio file types, to evaluate various approaches to this task.”
Beyond the Illusion: Ensemble Learning for Effective Voice Deepfake Detection
Ali, G., Rashid, J., Hussnain, M. R. U., Tariq, M. U., Ghani, A., & Kwak, D. (2024) · IEEE Access · doi:10.1109/access.2024.3457866 · Cited by 21
“Reference [9] proposed a feature extraction approach using Mel-frequency Cepstral Coefficients (MFCC) from audio sources.”
MethodInfluentialMFAAN: Unveiling Audio Deepfakes with a Multi-Feature Authenticity Network
Krishnan, K. S., & Krishnan, K. S. (2023) · doi:10.1109/icsc60394.2023.10441405 · Cited by 22
“[7] • Processing: The MFCCs are subsequently processed via a series of 1D convolutional layers, adept at discerning temporal patterns embedded within the features, thereby highlighting both localized and overarching structures.”
BackgroundInfluentialHolla, L., & Kavitha, K. (2024) · Journal of Advances in Information Technology · doi:10.12720/jait.15.2.202-211 · Cited by 24
“In recent days, the issues based on detecting fake news is extensively addressed by researchers, but a proper fake news detection system is still in some crises [18, 19].”
CNN-LSTM for Heartbeat Sound Classification
Aji, N. B., Kurnianingsih, K., Masuyama, N., & Nojima, Y. (2024) · JOIV International Journal on Informatics Visualization · doi:10.62527/joiv.8.2.2115 · Cited by 25
Deepfake Video Detection Using Convolutional Neural Network Based Hybrid Approach
Koçak, A., Alkan, M., & Arıkan, S. M. (2025) · Journal of Polytechnic · doi:10.2339/politeknik.1523983 · Cited by 15
“Furthermore, the RF algorithm is employed to determine the importance of features by adding the gain of each feature and scaling by the number of samples that pass through the node [45].”
Mel Spectrogram-Based CNN Framework for Explainable Audio Deepfake Detection
Bajwa, M. K. Z., Castiglione, A., & Pero, C. (2025) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-031-87784-1_37 · Cited by 20
GAN Discriminator based Audio Deepfake Detection
Doan, T.-P., Hong, K., & Jung, S. (2023) · doi:10.1145/3595353.3595883 · Cited by 11
“Deepfake is a technique that uses artificial intelligence to create fake videos, audios or images that look very similar to real people[4].”
BackgroundAudioGuard: Deep Learning Based Telugu DeepFake Audio Detection
Karna, S., Haneesha, S. S. S., Jahanve, P. R., Pati, P. B., & Balakrishnan, R. M. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10725692 · Cited by 10
“Hamza et al. [12] employed DL and ML techniques to detect deepfake audio, with a particular focus on the Fake-or-Real dataset.”
MethodA comprehensive survey of audio forgery detection: challenges and novel trends
Nasr, M. A., El‐Shafai, W., Abdel-Salam, N., El‐Rabaie, E. M., El‐Fishawy, A. S., & El‐Samie, F. E. A. (2025) · Journal of Electrical Systems and Information Technology · doi:10.1186/s43067-025-00225-w · Cited by 16
An Interpretable Fake News Detection Method Based on Commonsense Knowledge Graph
Gao, X., Chen, W., Lu, L., Cui, Y., Dai, X., Dai, L., Wang, K., Shen, J., Wang, Y., Wang, S., et al. (2023) · Applied Sciences · doi:10.3390/app13116680 · Cited by 10
Terraf, Y., & Iraqi, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3356730 · Cited by 13
“A. CONVENTIONAL FEATURE EXTRACTION TECHNIQUES 1) MFCC MFCC [24], is a technique frequently used in speech and audio research for its efficacy in capturing significant characteristics of speech signals [2], [11], [46].”
MethodA Comparative Study of Deep Audio Models for Spectrogram- and Waveform-Based SingFake Detection
Nguyen-Duc, M., Nguyen, L. V., Nguyen-Ho-Nhat, H., Nguyen, T., & Lee, O. (2025) · IEEE Access · doi:10.1109/access.2025.3571728 · Cited by 12
“Hamza et al. [28] investigated the detection of audio deepfakes using machine learning and deep learning methods.”
Synthetic Speech Detection Using Deep Neural Networks
Mutica, I., Mihalache, Ş., & Burileanu, D. (2024) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp63128.2024.10605922 · Cited by 9
“For this work, the for-2seconds version of the FoR dataset was chosen, since it is balanced in terms of gender and class, and it is normalized in terms of sample rate, volume, and number of channels, with all files being truncated to 2 s duration [2].”
BackgroundMethodBenchmarking Audio Deepfake Detection Robustness in Real-World Communication Scenarios
Shi, H., Shi, X., Dogan, S., Alzubi, S., Huang, T., & Zhang, Y. (2025) · 2025 33rd European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco63237.2025.11226601 · Cited by 8
“For example, Mel-frequency Cepstral Coefficients (MFCC) have been widely used in classifiers such as support vector machines, AdaBoost, decision trees, etc., demonstrating their effectiveness in ADD tasks [8].”
Deepfake Audio Detection in Voice Authentication: A Spectral and CNN-Based Comprehensive Review
Salih, A. O. M., Emam, A. H. M., Ahmed, A. B. G. E., Khalifa, M., Suliman, A., & Babiker, N. B. M. (2025) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.13400 · Cited by 17
Listening Between the Lines: Synthetic Speech Detection Disregarding Verbal Content
Salvi, D., Balcha, T. S., Bestagini, P., & Tubaro, S. (2024) · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · doi:10.1109/icasspw62465.2024.10669901 · Cited by 16
“Several synthetic speech detection techniques have been introduced employing a diverse range of approaches, including end-to-end methods [4, 5], and systems based on the analysis of acoustic [6], and semantic features [7, 8].”
Li, X., Zhou, H., & Zhao, M. (2024) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2024183 · Cited by 9
Exploring Advanced Neural Networks For Cross-Corpus Fake News Detection
Girdhar, M., Singh, S., Kumar, S., Mahto, D., Sharma, S. K., Gupta, B. B., Arya, V., & Chui, K. T. (2023) · International Conference on Information Management & Machine Intelligence (ICIMMI) · doi:10.1145/3647444.3652457 · Cited by 7
“Identifying misinformation within the vast expanse of big data presents a notable hurdle [19, 37].”
BackgroundAutomated Stuttering Detection Using Deep Learning Techniques
Alhakbani, N., Alnashwan, R., Al-Nafjan, A., & Almudhi, A. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14103552 · Cited by 13
“It achieves this by incorporating a logarithmic function and mel filters to replicate the human auditory system and using triangular bandpass filters to convert frequency information, thereby simulating the way humans perceive sound [30].”
A Decade of Deepfake Research in the Generative AI Era, 2014–2024: A Bibliometric Analysis
Acim, B., Boukhlif, M., Ouhnni, H., Kharmoum, N., & Ziti, S. (2025) · Publications · doi:10.3390/publications13040050 · Cited by 16
Assessment of Pepper Robot’s Speech Recognition System through the Lens of Machine Learning
Pande, A., & Mishra, D. (2024) · Biomimetics · doi:10.3390/biomimetics9070391 · Cited by 10
“Furthermore, they are also a useful indicator of the human auditory system [23].”
BackgroundMethodClassification of Deep Fake Audio Using MFCC Technique
Sivaramakrishnan, M., Rajput, A., & Saravanan, M. (2024) · IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS) · doi:10.1109/iciteics61368.2024.10625305 · Cited by 10
Mitigating Unauthorized Speech Synthesis for Voice Protection
Zhang, Z., Yang, Q., Wang, D., Huang, P., Cao, Y., Ye, K., & Hao, J. (2023) · doi:10.1145/3689217.3690615 · Cited by 20
Prathibha, P., Tamizharasan, P. S., Panthakkan, A., Mansoor, W., & Al-Ahmad, H. (2024) · IEEE Access · doi:10.1109/access.2024.3517170 · Cited by 12
“Hamza et al. [21] explored the audio frequency signals in the videos to identify deepfakes.”
Baby Crying Sound Classification using Convolutional Neural Network
Muhammad, N. F., Dewan, R., Pusppanathan, J., & Suryanata, F. A. (2024) · Journal of Human Centered Technology · doi:10.11113/humentech.v3n1.66 · Cited by 6
Detection of Manipulated Multimedia In Digital Forensics Using Machine Learning
Anvekar, P., Gudnavar, A., Naregal, K., & Nagarmunoli, S. R. (2024) · International Conference on Device Intelligence, Computing and Communication Technologies (DICCT) · doi:10.1109/dicct61038.2024.10533016 · Cited by 10
“This scenario is often regarded more as a theoretical concept than a practically executable undertaking within the confines of current capabilities [7].”
BackgroundAudio Deepfakes: Feature Extraction and Model Evaluation for Detection
Bhukya, R. K., Raj, A., & Raja, D. N. (2024) · International Conference for Emerging Technology (INCET) · doi:10.1109/incet61516.2024.10593405 · Cited by 7
“Hamza et al. [9] proposed a novel methodology for effectively identifying deepfake audio by leveraging ML and DL-based approaches.”
BackgroundMethodDeepfake Audio Detection Using Quantum Learning Models
Pandey, A., & Rudra, B. (2024) · IEEE Middle East Conference on Communications and Networking (MECOM) · doi:10.1109/mecom61498.2024.10881096 · Cited by 9
“Authors [11] presented a method that handles the large dataset and performs the classification using the Machine Learning (ML) algorithm.”
Katamneni, V. S., Nadimpalli, A. V., & Rattani, A. (2024) · Springer eBooks · doi:10.1007/978-981-97-2059-0_8 · Cited by 9
Deepfake Technologies in Financial Fraud: Generation, Detection, and Mitigation Strategies
Shetye, A., Jain, N., Borade, S., & Rai, V. K. (2025) · Global Conference in Emerging Technology (GINOTECH) · doi:10.1109/ginotech63460.2025.11076798 · Cited by 7
“Conversion was done by estimating the target speaker’s features using the trained GMM. 4) Speaker Verification to Multi speaker Text to Speech Synthesis [12]: Enables high-quality voice conversion with minimal target speaker data, a significant leap.”
Emergent Capability in Audio Deepfake Detection
Deng, Y., Laprevotte, A., Dunn, R. B., Khorrami, P., Dagli, C. K., & Torres‐Carrasquillo, P. A. (2025) · International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf63717.2025.11113428 · Cited by 5
“Current state-of-the-art methods for detecting deepfake audio rely on neural networks that exploit spectral, temporal, and prosodic features [1][2].”
Deep Learning Approach for Detecting Audio Deepfakes in Urdu
Mateen, M., & Bawany, N. Z. (2023) · NUML International Journal of Engineering and Computing · doi:10.52015/nijec.v2i1.37 · Cited by 5
Unmasking deepfakes: Eye blink pattern analysis using a hybrid LSTM and MLP-CNN model
Sharma, R., & Dwivedi, R. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105370 · Cited by 11
Audio-Visual Deepfake Detection System Using Multimodal Deep Learning
Parikh, A., Pereira, K., Kumar, P. S., & Devadkar, K. (2023) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit59222.2023.10205804 · Cited by 10
“In [9] The models were evaluated on for-rece, for2-sec, for-norm, and for-original datasets.”
MethodNon-Intrusive Air Traffic Control Speech Quality Assessment with ResNet-BiLSTM
Wu, Y., Li, G., & Fu, Q. (2023) · Applied Sciences · doi:10.3390/app131910834 · Cited by 5
Significance of Lower Frequency Regions for Audio Deepfake Detection
Shah, A. J., & Patil, H. A. (2024) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc63619.2025.10849121 · Cited by 5
“In [5], the authors explore machine learning-based approach, such as Long Short-Term Memory (LSTM), and VGG-16 for ADD task on FoR dataset.”
Anomaly Detection and Localization for Speech Deepfakes via Feature Pyramid Matching
Coletta, E., Salvi, D., Negroni, V., Leonzio, D. U., & Bestagini, P. (2025) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco63237.2025.11226156 · Cited by 7
Anusha, T., & Srinagesh, A. (2025) · International Conference on Multi-Agent Systems for Collaborative Intelligence (ICMSCI) · doi:10.1109/icmsci62561.2025.10894187 · Cited by 7
Deepfake Detection Using AI And Machine Learning Algorithms
Chandel, G., Kumar, A., Malik, K., Gurani, K., Gahlawat, K., & Saini, S. K. (2025) · International Conference on Computer, Electronics & Electrical Engineering & their Applications (IC2E3) · doi:10.1109/ic2e365635.2025.11167331 · Cited by 6
“Deepfake technology has very many applications in the entertainment and education industry, but it is being misused on a very large scale which poses significant risks, including misinformation, manipulation, fraud etc. [1].”
A multi-level and iterative feature engineering framework for deepfake audio detection
Çelik, B., & Akbal, A. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130722 · Cited by 5
A Hybrid Approach for Deep Fake Detection Using Deep Learning Algorithm
Aarthe, S., Sindhuja, S., Ranjan, V., Vishal, V., Sinha, A., & Agarwal, M. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-6714-4_11 · Cited by 7
ID-Flow: Leveraging Voice Identity for Generalizing Audio Deepfake Detection
Choi, J., Kim, T. H., & Choi, J.-W. (2025) · International Conference on Consumer Electronics · doi:10.1109/icce63647.2025.10929900 · Cited by 6
“The previous methods [5], [6] rely on raw voice data to discriminate between real and synthetic voices.”
Detection of Fake Audio: A Deep Learning-Based Comprehensive Survey
Sahane, P. B., Badole, D., Kale, C., Chavare, S., & Walunj, S. (2024) · Smart innovation, systems and technologies · doi:10.1007/978-981-99-8612-5_22 · Cited by 5
Audio Classification through MFCC features using RNN algorithm
Bhargavi, K., Deepa, V., & Harshitha, I. (2024) · Asian Conference on Innovation in Technology (ASIANCON) · doi:10.1109/asiancon62057.2024.10838024 · Cited by 7
“The model is assessed using evaluation criteria such as equal error rate (EER) and minimum-detection cost function (min t-DCF) on ASVspoof 2021 LA and DF subsets after being trained on ASVspoof 2019 LA sets [11].”
Detection of Deepfake Videos Using a Deep Learning Approach with Res-Next and LSTM
Kumar, K. G., Sowndharya, A., Pradeep, D. M., Suriya, S., & Kumar, K. D. (2024) · International Conference on System Modeling & Advancement in Research Trends (SMART) · doi:10.1109/smart63812.2024.10882518 · Cited by 4
Dousios, D., Korfiatis, N., & Spanaki, K. (2025) · IEEE Transactions on Engineering Management · doi:10.1109/tem.2025.3549597 · Cited by 5
“This is a generally accepted feature used in speech recognition [140] and speech-based human emotion recognition research [141], with its applications recently expanding to the crowdfunding context [32].”
Detecting Manipulated Audio Using Adaboost Machine Learning Algorithm
Bandarapalli, V. K., Ayyappa, Y., Sai, P. J., Varun, T., Babu, S. N., & Teja, Y. U. S. S. (2024) · International Conference on Advancement in Computation & Computer Technologies (InCACCT) · doi:10.1109/incacct61598.2024.10550994 · Cited by 5
“This shows how fake videos, when used as propaganda, can be dangerous and cause a lot of harm [1].”
BackgroundA systematic review of audio deepfake detection techniques for digital investigation
Alnaqbi, M. M., & Ikuesan, R. A. (2026) · Discover Computing · doi:10.1007/s10791-026-10077-1 · Cited by 7
Guan, C., Shang, R., Yang, F., Shao, A.-X., & Zhang, S. (2024) · Systems Science & Control Engineering · doi:10.1080/21642583.2024.2343311 · Cited by 3
“The MFCC features of signals are calculated as follows Biswas et al. (2023) and Hamza et al. (2022): (1) Framing and window: framing is the process of defining the N sampling points as a new observation unit which is called a frame.”
Iqbal, F., Abbasi, A., Almadhor, A. S., Alsubai, S., & Greguš, M. (2025) · Frontiers in Computer Science · doi:10.3389/fcomp.2025.1517346 · Cited by 4
Self-citationSound to expression: Using emotional sound to guide facial expression editing
Liu, W., Zhang, S., Zhou, L. M., Luo, N., & Chen, Q. (2024) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2024.101998 · Cited by 4
Artificial Intelligence to Combat Audio Fraud: A Flask-Deployed Hybrid Deep Learning System
Solanki, S., Ravikumar, R. N., Devataval, T., Gajera, J., Singh, S. K., & Gupta, H. (2024) · IEEE Region Humanitarian Technology Conference · doi:10.1109/r10-htc59322.2024.10778737 · Cited by 4
“By combining the logistic regression scores from 12 individual detection models, our resulting system achieves impressive performance gains: a First Gain of 7%, a Second Gain of 11%, and a RES-Efficient CNN Macro F1 score of 97.61 [3].”
InfluentialTeager Energy Cepstral Coefficients for Audio Deepfake Detection
Mahyavanshi, R., Reddy, C., Shah, A. J., & Patil, H. A. (2024) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc63619.2025.10848893 · Cited by 6
“Features, such as Mel Frequency Cepstral Coefficients (MFCC) [4], [5] and Linear Frequency Cepstral Coefficients (LFCC) [6], [7] closely mimic human auditory traits and concentrate on low frequency information crucial for speech detection tasks.”
Detection of Deepfake Audio Using Deep Learning
Lakshmi, A. R., Sindhuja, V., Meghana, B., & Gupta, G. S. (2024) · International Conference on Communication and Electronics Systems (ICCES) · doi:10.1109/icces63552.2024.10859752 · Cited by 3
Palani, M., & Perumalsamy, A. (2025) · Security and Privacy · doi:10.1002/spy2.70027 · Cited by 3
“Hamza et al. [12] employed DL models for detecting deepfake audio.”
Leveraging Acoustic Features and Deep Neural Architectures for Audio Deepfake Detection
Sundaram, V., Babitha, S., & Vekkot, S. (2024) · International Conference on Advances in Computing and Communications (ICACC) · doi:10.1109/icacc63692.2024.10845392 · Cited by 4
“Research detailed in [15] employs the FoR dataset, consisting of four distinct subsets with varying audio lengths and processing characteristics.”
The Interpretable and Transferable Adversarial Attack against Synthetic Speech Detectors
Deng, J., Ye, D., Li, J., Liu, Z., Tang, L., & Zhang, Y. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3727341 · Cited by 2
Metadata
- Authors
- Hamza, A., Javed, A. R. R., Iqbal, F., Kryvinska, N., Almadhor, A. S., Jalil, Z., & Borghol, R.
- Affiliations
- Air University (PK)
- Lebanese American University (LB)
- Zayed University (AE)
- Comenius University Bratislava (SK)
- Jouf University (SA)
- Rochester Institute of Technology - Dubai (AE)
- ORCID
- Venue
- IEEE Access
- Published
- 2022
- Volume
- 10
- Pages
- 134018-134028
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4312743281
- Cited by
- 264
- References
- 35
- Citations by year
- 2026: 67 · 2025: 103 · 2024: 68 · 2023: 26
- FWCI
- 16.20
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Keywords
- audio deepfake detection, Mel-frequency cepstral coefficients, support vector machine, gradient boosting, VGG16, text-to-speech, anti-spoofing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.