A lightweight feature extraction technique for deepfake audio detection
The DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“A cross-verifica-tion methodology has been established by Shan et al. [25] to verify audio recordings of global leaders.”
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“To solve this problem, the first Audio Deep Synthesis Detection Challenge (ADD 2022) [7] has been a success.”
KNN Model-Based Approach in Classification
Guo, G., Wang, H., Bell, D., Bi, Y., & Greer, K. (2003) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-39964-3_62 · Cited by 2,099 · cited 1×
“Chintha et al. [23] proposed a WIRENetSpoof architecture by combining convolutional, recurrent structure and entropy-based function for deepfake attack detection.”
Text Data Augmentation for Deep Learning
Shorten, C., Khoshgoftaar, T. M., & Furht, B. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00492-0 · Cited by 1,740 · cited 1×
“D hyperplane [48, 49].”
Continuous speech recognition by statistical methods
Jelinek, F. (1976) · Proceedings of the IEEE · doi:10.1109/proc.1976.10159 · Cited by 920 · cited 3×
“[ 27], the authors suggested two approaches; image and feature-based.”
ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection
Todisco, M., Wang, X., Vestman, V., Sahidullah, M., Delgado, H., Nautsch, A., Yamagishi, J., Evans, N., Kinnunen, T., & Lee, K. A. (2019) · arXiv · doi:10.48550/arxiv.1904.05441 · Cited by 688 · cited 1×
“The NB classifier may predict emotions that are not present in the dataset once it has been trained [55].”
ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection
Todisco, M., Wang, X., Vestman, V., Sahidullah, M., Delgado, H., Nautsch, A., Yamagishi, J., Evans, N., Kinnunen, T. H., & Lee, K. A. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2249 · Cited by 687
Detecting Affect States Using VGG16, ResNet50 and SE-ResNet50 Networks
Theckedath, D., & Sedamkar, R. R. (2020) · SN Computer Science · doi:10.1007/s42979-020-0114-9 · Cited by 634 · cited 2×
“[53].”
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 · cited 1×
“Chettri et al. [33] used IMFCC, CQCC, and MFCC[34], and Sub-band Centroid Magnitude Coefficients (SCMC).”
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
Research works printed but not linked: 8
- Dave N (2013) Feature extraction methods LPC, PLP and MFCC in speech recognition. Int J Adv Res Eng Technol 1(6):1–4
- Khalifa O, El-Darymli K, Daoud J (2013) Statistical modeling for speech recognition. World Appl Sci J 21:115–122. https://doi.org/10.5829/idosi.wasj.2013.21.mae.99935 · doi:10.5829/idosi.wasj.2013.21.mae.99935
- Khochare J, Joshi C, Yenarkar B, Suratkar S, Kazi F (2022) A deep learning framework for audio deepfake detection. Arab J Sci Eng 47(3):3447–3458 · DOI · Paper page
- Mittal A, Dua M (2021) Automatic speaker verification system using three dimensional static and contextual variation-based features with two dimensional convolutional neural network. Int J Swarm Intell 6(2):143–153
- Novaković JD, Veljović A, Ilić SS, Papić Ž, Milica T (2017) Evaluation of classification models in machine learning. Theory Appl Math Comput Sci 7(1):39–46
- Shan M, Tsai TJ (2020) A cross-verification approach for protecting world leaders from fake and tampered audio. ArXiv Preprint ArXiv:2010.12173 · arXiv
- Thiruvengatanadhan R (2017) Speech/Music Classification using MFCC and KNN. Int J Comput Intell Res 13(10):2449–2452
- Webb GI, Keogh E, Miikkulainen R (2010) Naïve bayes. Encycl Mach Learn 15:713–714
Cited by
Acoustic Features Analysis for Explainable Machine Learning-Based Audio Spoofing Detection
Bisogni, C., Loia, V., Nappi, M., & Pero, C. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104145 · Cited by 30
Chakravarty, N., & Dua, M. (2024) · International Journal of Speech Technology · doi:10.1007/s10772-024-10093-w · Cited by 28
“Chakravarty and Dua (2024b), Acoustic Ternary Pattern (ATP), Gammatone spectrogram and, Mel spectrogram, spectrogram were employed with ResNet27, achieving a low EER for impersonation attacks.”
InfluentialSelf-citationDetecting 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
“Chakravarty et. al., [3] employed a ResNet50 for feature extraction on audio Mel spectrograms, followed by Linear Discriminant Analysis (LDA) for dimensionality reduction and several machine learning algorithms like Random Forest (RF), Naive Bayes (NB), K-Nearest Neighbour (KNN) and Support Vector…”
MethodMuruganandham, P., Thangasamy, G. R., Jayaraman, S., & Dharmarajan, R. (2025) · Scientific Reports · doi:10.1038/s41598-025-08198-6 · Cited by 20
Deepfake video deception detection using visual attention-based method
Lal, K., Shiwani, S., & Gandhi, G. C. (2025) · Scientific Reports · doi:10.1038/s41598-025-23920-0 · Cited by 16
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
“Subsequently, the test example is assigned to the class that has the highest number of members among these neighbors [44].”
Enhancing wheat yellow rust detection through modified deep learning approach
Kumar, S., Singh, R., Kumar, S., & Gupta, S. (2025) · Current Plant Biology · doi:10.1016/j.cpb.2025.100472 · Cited by 8
Noise robust automatic speaker verification systems: review and analysis
Joshi, S., & Dua, M. (2024) · Telecommunication Systems · doi:10.1007/s11235-024-01212-8 · Cited by 10
Self-citationChakravarty, N., & Dua, M. (2024) · International Journal of Systems Assurance Engineering and Management · doi:10.1007/s13198-024-02550-1 · Cited by 9
Self-citationBenchmarking 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
“Additionally, other acoustic features, including Constant-Q Cepstral Coefficients (CQCC), Linear-Frequency Cep-stral Coefficients (LFCC), Mel-spectrograms, and constant-Q-transform [9]–[11], have also been extensively utilised.”
Dua, M., Chakravarty, N., Reddy, S. G. P., Bansal, A., Pawar, S., & Dua, S. (2024) · IETE Journal of Research · doi:10.1080/03772063.2024.2412799 · Cited by 10
“[11] proposed a lightweight ASD system for deepfake detection, using a combination of Mel-spectrogram and ResNet50 for front-end feature extraction.”
Self-citationA Contemporary and Comprehensive Bibliometric Exposition on Deepfake Research and Trends
AbdulQudus, A. B., Amodu, O. A., Bukar, U. A., Mahmood, R. A. R., Zakaria, A. F., Queen, S.-O., & Hanapi, Z. M. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.061427 · Cited by 9
Erlang Spectrogram and Residual Network-Based Features for Fake Audio Detection
Chakravarty, N., & Dua, M. (2025) · IETE Journal of Research · doi:10.1080/03772063.2025.2453882 · Cited by 5
“In such applications, the image or timefrequency representations of audio signals are commonly termed as spectrogram [15, 16].”
Self-citationEfficient Deep Fake Detection Technique on Video and Audio Dataset Using Deep Learning
Vadisetty, R. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-97-8457-8_11 · Cited by 12
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
Chakravarty, N., & Dua, M. (2024) · International Conference on Recent Innovation in Smart and Sustainable Technology (ICRISST) · doi:10.1109/icrisst59181.2024.10922028 · Cited by 4
“Mittal et al.[15] employed Constant Q Cepstral Coefficients (CQCC) with Convolutional Neural Network (CNN) and, separately, CQCC with Long Short Term Memory (LSTM), as well as a static-dynamic feature combination of CQCC with LSTM-CNN ensemble[16][17].”
Self-citationPerformance Evaluation of Enhanced DCGAN s for Detecting Deepfake Audio Across Selected FoR Datasets
Lapates, J. M., Gerardo, B. D., & Medina, R. P. (2024) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc62082.2024.10827547 · Cited by 5
Guo, T., Du, H., Huo, H., Liu, B., & Yu, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-1548-3_21 · Cited by 7
Deepfake Audio Detection in Low-Resource Languages: A Case Study of Urdu
Owais, M., Jadoon, K. K., Sandhu, A. I., Ali, Z., Mahmood, Z., Yahya, M., & Wahid, A. (2026) · IEEE Access · doi:10.1109/access.2026.3654621 · Cited by 8
“Models such as VGG-16, MesoNet, LCNN, and CNN–LSTM hybrids have demonstrated improved performance compared to handcrafted features, particularly when trained on large English datasets [17], [19], [25], [26].”
Ahmad, A. A., Tasnim, N., Antor, N. R., & Aman, N. (2025) · International Conference on Sustainable Technologies for Industry 5.0 (STI) · doi:10.1109/sti69347.2025.11367511 · Cited by 3
Nandal, A., & Dua, M. (2024) · International Conference on Circuits, Control, Communication and Computing (I4C) · doi:10.1109/i4c62240.2024.10748511 · Cited by 3
“Chakravarty et al.[10]developed an enhanced feature extraction method using a modified ResNet50 on Mel spectrograms, followed by Linear Discriminant Analysis (LDA) for dimensionality reduction.”
Self-citationLightweight noise robust spoofing attack detection using Cochleagram and ResNet amalgamated features
Chakravarty, N., & Dua, M. (2025) · Physica Scripta · doi:10.1088/1402-4896/ada9ad · Cited by 3
Self-citationNguyen-Le, H.-H., Tran, V.-T., Nguyen, D.-T., & Le-Khac, N.-A. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11608-4 · Cited by 28
Nandal, A., & Dua, M. (2025) · International Journal of Speech Technology · doi:10.1007/s10772-025-10195-z · Cited by 5
“Although it lags slightly behind the data-centralized approach in equal error rate (EER) by 1.43%, it still shows a notable 1.79% improvement over FedBA.”
InfluentialSelf-citationDetection of Audio Spoofing Attack Using Integrated Hand-Crafted Features with LSTM
Chakravarty, N., & Dua, M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-4170-3_16 · Cited by 1
Self-citationAudio Deepfake Detection Using Xception Model
Akmal, D., & Suryani, V. (2025) · doi:10.1109/icoict66265.2025.11193020 · Cited by 2
Çelik, B., ZEYBEK, B., Karadeniz, M. B., Koçyiğit, A., Arsalı, O., EFEOĞLU, E., & Türetken, B. (2026) · Alexandria Engineering Journal · doi:10.1016/j.aej.2026.01.009 · Cited by 1
DeepRawNet: empowering deepfake audio detection through dynamic enhancements
Alharbi, L. A., Alnahas, J., Javed, A., Alhakamy, A., Nawaz, M., Malik, H., Ilyas, H., & Alfaifi, F. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3670 · Cited by 2
Securing Automatic Speaker Verification Systems Using Residual Networks
Chakravarty, N., & Dua, M. (2024) · Advances in information security, privacy, and ethics book series · doi:10.4018/979-8-3693-2223-9.ch005 · Cited by 3
Self-citationSpectrogram Features and Xception Classifier Based Audio Spoof Detection System
Chakravarty, N., & Dua, M. (2024) · International Conference on Computer, Electronics & Electrical Engineering & their Applications (IC2E3) · doi:10.1109/ic2e362166.2024.10827392 · Cited by 1
“The backend acoustic models used in the paper included NB, SVM, DT, K-NN, and LSTM[14].”
Self-citationAnti-spoofing Using ResNet50 with Linear Discriminant Analysis for Automatic Speaker Verification
Uparakool, P., Kongprawechnon, W., Pipopsophonchai, N., Numsonthi, A., Rawanggij, K., Assawamanachai, N., & Karnjana, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-4606-7_24
FALSIFYX: Guarding Truth in the Age of Synthetic Media
Prof.Jenifer, A. (2025) · International Journal of Innovative Research in Information Security · doi:10.26562/ijiris.2025.v1108.02
Detecting Synthetic Voices: A Novel Approach to Audio Deepfake Identification
Dey, D., Paul, B., & Nandi, U. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-95-3671-9_18
Composite Model Design for Detecting AI-Generated Audio-Text Based on Feature Fusion
Zhou, X., Zhang, K., Zhu, F., Cao, Q., Liu, D., & Hou, J. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347304
“…(e.g., ASVspoof) [2], limited validation under Chinese linguistic environments and multi-codec settings;(3)Deployment Limitations: High-complexity models hinder real-time operation in law enforcement settings, necessitating unresolved trade-offs between lightweighting and security robustness [3].”
Ray, A. S., Haque, M., Parvez, F. M. R., & Islam, M. M. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11491707
“These fake images, produced mainly by generative adversarial networks (GANs) and analogous structures, are capable of convincingly emulating human faces, voices and even more complex gestures [1].”
Towards Improving the Robustness of Deepfake Audio Detection With Denoising Methods
Wang, J., & Kim, D. S. (2026) · doi:10.1145/3803629.3803671
“Pipeline models, such as those built on ResNet50, emphasis interpretability and efficiency by combining feature extraction with dimensionality reduction before classification [3].”
Renukadevi, M. N., Rajesh, T. M., Shaila, S. G., Kulkarni, P., Babu, T. L., Nair, R. R., & Yogarayan, S. (2026) · Scientific Reports · doi:10.1038/s41598-026-47033-4
“Magnitude, being a more conservative average of signal amplitude, is better suited for identifying silence vs. speech regions in the audio signal 7,27 .”
Towards Lightweight On-Device Audio Deepfake Detection Using Squeezeformers
Moradi, A., Zhu, Y., & Falk, T. H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-20732-6_24
Distinguishing Synthetic from Human Speech: A Machine Learning and Deep Learning Approach
Khedkar, A., Chaudhari, R., Rathi, R., & Gade, S. (2026) · Journal of The Institution of Engineers (India) Series B · doi:10.1007/s40031-026-01361-1
“The majority of studies concentrate on applied machine learning and deep learning systems to detect manipulated audio [13, 14], as well as community benchmarks and challenges (in particular, ASVspoof) to advance and reveal the limitations of generalizations when systems are applied in the real…”
L-ACDD: A Lightweight Automatic Crop Disease Detection System
Dua, S., Kumar, S., & Dewan, L. (2026) · IETE Journal of Research · doi:10.1080/03772063.2026.2701278
Tasnim, N., Ahmad, A. A., Antor, N. R., & Aman, N. (2026) · International Conference on Power, Electronics, Communications, Computing, and Intelligent Infrastructure (PECCII) · doi:10.1109/peccii70991.2026.11662063
Metadata
- Authors
- Chakravarty, N., & Dua, M.
- Affiliations
- National Institute of Technology Kurukshetra (IN)
- Corresponding author
- Chakravarty, Nidhi
- Venue
- Multimedia Tools and Applications
- Published
- 2024-01-25
- Volume
- 83
- Issue
- 26
- Pages
- 67443-67467
- ISSN
- 1380-7501 (ISSN-L)
- 1573-7721
- OpenAlex
- W4391229131
- Cited by
- 40
- References
- 55
- Citations by year
- 2026: 10 · 2025: 18 · 2024: 12
- FWCI
- 5.93
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- Multimedia Tools and Applications (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- audio deepfake detection, feature extraction, Mel spectrogram, ResNet50, linear discriminant analysis, dimensionality reduction, ASVspoof 2019, ASVspoof 2021, MFCC comparison, gammatone cepstral coefficients
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.