The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Deepfake Speech Detection: A Spectrogram Analysis
Open accessAbstract
The current voice biometric systems have no natural mechanics to defend against deepfake spoofing attacks. Thus, supporting these systems with a deepfake detection solution is necessary. One of the latest approaches to deepfake speech detection is representing speech as a spectrogram and using it as an input for a deep neural network. This work thus analyzes the feasibility of different spectrograms for deepfake speech detection. We compare types of them regarding their performance, hardware requirements, and speed. We show the majority of the spectrograms are feasible for deepfake detection. However, there is no general, correct answer to selecting the best spectrogram. As we demonstrate, different spectrograms are suitable for different needs.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Experimental results on the ASVspoof 2019 LA and FoR datasets indicated that MFCC-Cepstrogram achieved exceptional performance and exhibited better stability on unseen data compared to other spectral features.”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [112]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Moreover, the study demonstrated that enhancing MFCC features through visualisation can further improve detection performance.”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [112]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Advances in neural information processing systems 7
(1996) · Computers & Mathematics with Applications · doi:10.1016/s0898-1221(96)90463-0 · Cited by 14,281
Temporal Convolutional Networks for Action Segmentation and Detection
Lea, C., Flynn, M. D., Vidal, R., Reiter, A., & Hager, G. D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.113 · Cited by 2,238 · cited 1×
“The network employs causal convolutions and dilations, making it suitable for sequential data such as spectrograms [23, 40].”
Method“Waveglow: a flow-based generative network for speech synthesis,”
Prenger, R., Valle, R., & Catanzaro, B. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8683143 · Cited by 1,004
Calculation of a constant Q spectral transform
Brown, J. C. (1991) · The Journal of the Acoustical Society of America · doi:10.1121/1.400476 · Cited by 884 · cited 1×
“This transform is used to obtain a constant pattern in the frequency domain for sounds with harmonic frequency components [5].”
MethodInformation Retrieval for Music and Motion
Müller, M. (2007) · doi:10.1007/978-3-540-74048-3 · Cited by 818 · cited 1×
“IIRT-Spectrogram IIRT-Spectrogram is a time-frequency representation using a multi-rate filter bank consisting of IIR filters [26].”
MethodStatistical parametric speech synthesis using deep neural networks
Zen, H., Senior, A., & Schuster, M. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639215 · Cited by 809
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×
“If this issue remains unad-dressed, the reliability of voice biometrics will degrade over time due to spoofing attacks [3, 11, 36].”
BackgroundASVspoof 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
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech
Wang, X., Yamagishi, J., Todisco, M., Delgado, H., Nautsch, A., Evans, N., Sahidullah, M., Vestman, V., Kinnunen, T., Lee, K. A., et al. (2020) · Computer Speech & Language · doi:10.1016/j.csl.2020.101114 · Cited by 505 · cited 1×
“In total, 19 synthesis systems are used [37].”
MethodA New Feature for Automatic Speaker Verification Anti-Spoofing: Constant Q Cepstral Coefficients
Todisco, M., Delgado, H., & Evans, N. (2016) · The Speaker and Language Recognition Workshop (Odyssey 2016) · doi:10.21437/odyssey.2016-41 · Cited by 335 · cited 1×
“Todisco et al. [35] propose a novel feature named Q-cepstral coefficient and use a Gaussian Mixture Model (GMM) based classifier.”
Method
Research works printed but not linked: 9
- Muhammad Ejaz Ahmed, Il-Youp Kwak, Jun Ho Huh, Iljoo Kim, Taekkyung Oh, and Hyoungshick Kim. 2020. Void: A Fast and Light Voice Liveness Detection System. USENIX Association, USA.
- Jemine Corentin. 2019. Real-time Voice Cloning. Master thesis. Université de Liège Liège Belgique. https://matheo.uliege.be/handle/2268.2/6801?locale=en
- Frank C. Cwitkowitz Jr. 2019. End-to-End Music Transcription Using Fine-Tuned Variable-Q Filterbanks. Thesis. Rochester Institute of Technology.
- Hasam Khalid, Shahroz Tariq, Minha Kim, and Simon S. Woo. 2021. FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). https://openreview.net/forum?id=TAXFsg6ZaOl
- Jungil Kong, Jaehyeon Kim, and Jaekyoung Bae. 2020. HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 17022--17033. https://proceedings.neurips.cc/paper_files/paper/2020/file/c5d736809766d46260d816d8dbc9eb44-Paper.pdf
- Ricardo Reimao. 2019. Synthetic Speech Detection Using Deep Neural Networks. Master's thesis. York University, Toronto, Ontario.
- Ryosuke Sonobe Shinnosuke Takamichi and Hiroshi Saruwatari. 2017. JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis. arXiv:1711.00354 [cs.CL] · arXiv
- Junichi Yamagishi, Xin Wang, Massimiliano Todisco, Md Sahidullah, Jose Patino, Andreas Nautsch, Xuechen Liu, Kong Aik Lee, Tomi Kinnunen, Nicholas Evans, and Héctor Delgado. 2021. ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection. arXiv:2109.00537 [eess.AS] · arXiv
- Frank Zalkow and Meinard Müller. 2015. Log-Frequency Spectrogram and Chromagram. Retrieved March 1, 2022 from https://www.audiolabs-erlangen.de/resources/MIR/FMP/C3/C3S1_SpecLogFreq-Chromagram.html
Cited by
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
“Firc et al. [112] expanded the application of MFCC by introducing the MFCC-Cepstrogram, a visualised cepstral feature representation used as input to Temporal Convolutional Networks (TCNs).”
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
Firc, A., Malinka, K., & Hanáček, P. (2025) · Cybersecurity · doi:10.1186/s42400-024-00346-1 · Cited by 34
Self-citationComprehensive multiparametric analysis of human deepfake speech recognition
Malinka, K., Firc, A., Šalko, M., Prudký, D., Radačovská, K., & Hanáček, P. (2024) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-024-00641-4 · Cited by 20
Self-citationDiffuse or Confuse: A Diffusion Deepfake Speech Dataset
Firc, A., Malinka, K., & Hanáček, P. (2024) · International Conference of the Biometrics Special Interest Group (BIOSIG) · doi:10.1109/biosig61931.2024.10786752 · Cited by 15
“IDSD [25]: This method transforms audio signals into Short-Time Fourier Transform (STFT) spectrograms, processed by a Temporal Convolutional Network (TCN).”
MethodSelf-citation
Metadata
- Authors
- Firc, A., Malinka, K., & Hanáček, P.
- Affiliations
- Brno University of Technology (CZ)
- Venue
- Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing
- Publisher
- ACM
- Published
- 2024-04-08
- Pages
- 1312-1320
- OpenAlex
- W4398186462
- Cited by
- 16
- References
- 29
- Citations by year
- 2026: 3 · 2025: 8 · 2024: 5
- FWCI
- 4.62
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Symposium on Applied Computing (publishedVersion, cc-by)
- Brno University of Technology Digital Library (Brno University of Technology) (submittedVersion, cc-by)
- Funders
- Brno University of Technology (FIT-S-23-8151)
- Ministry of the Interior of the Czech Republic (VB02000060)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Keywords
- speech deepfake detection, spectrogram representation, voice biometrics, spoofing attacks, spectrogram comparison, hardware requirements, detection speed
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Deepfake Speech Detection: A Spectrogram Analysis. https://app.cochat.ai/papers/10.1145/3605098.3635911
- The paper
- Firc, A., Malinka, K., & Hanáček, P. (2024). Deepfake Speech Detection: A Spectrogram Analysis. Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing. https://doi.org/10.1145/3605098.3635911
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.