The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
A comparison of features for synthetic speech detection
Open accessAbstract
The performance of biometric systems based on automatic speaker recognition technology is severely degraded due to spoofing attacks with synthetic speech generated using different voice conversion (VC) and speech synthesis (SS) techniques. Various countermeasures are proposed to detect this type of at-tack, and in this context, choosing an appropriate feature extrac-tion technique for capturing relevant information from speech is an important issue. This paper presents a concise experi-mental review of different features for synthetic speech detec-tion task. A wide variety of features considered in this study include previously investigated features as well as some other potentially useful features for characterizing real and synthetic speech. The experiments are conducted on recently released ASVspoof 2015 corpus containing speech data from a large number of VC and SS technique. Comparative results using two different classifiers indicate that features representing spectral information in high-frequency region, dynamic information of speech, and detailed information related to subband characteris-tics are considerably more useful in detecting synthetic speech. Index Terms: anti-spoofing, ASVspoof 2015, feature extrac-tion, countermeasures
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
“a significant body of research [64,96,97,98,99] has demonstrated that the performance of detection models largely depends on the choice of input features.”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [96]
In the citing paper
“other machine learning models, such as the Support Vector Machine and Logistic Regression, were widely studied in earlier research [96,134,135,136]. With the advancement of feature extraction techniques, these models continue to play a significant role in current studies [137,138,139].”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [96]
Citations
Cites
Multiresolution gray-scale and rotation invariant texture classification with local binary patterns
Ojala, T., Pietikainen, M., & Maenpaa, T. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2002.1017623 · Cited by 15,398 · cited 1×
“The authors of [8], in turn, proposed to use one-class approach us-ing local binary pattern [9] of linear frequency cepstral coef-ficients (LFCCs) followed by support vector machine (SVM) for voice conversion, speech synthesis and artificial signal detection [8].”
MethodFundamentals of speech recognition
Rabiner, L. R., & Juang, B.-H. F. (1993) · Cited by 7,680
Davis, S., & Mermelstein, P. (1980) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1980.1163420 · Cited by 5,465 · cited 1×
“In MFCC, the filters are placed in mel scale, having denser spacing in t he low-frequency region [21].”
MethodPerceptual linear predictive (PLP) analysis of speech
Hermansky, H. (1990) · The Journal of the Acoustical Society of America · doi:10.1121/1.399423 · Cited by 2,536 · cited 1×
“Another all-pole representation of speech called perceptual linear prediction cepstral coefficients (PLPCC) is also computed by first performing a series of perceptual processing prior to LP analysis [24].”
MethodCepstral analysis technique for automatic speaker verification
Furui, S. (1981) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1981.1163530 · Cited by 1,173
Continuous probabilistic transform for voice conversion
Stylianou, Y., Cappe, O., & Moulines, E. (1998) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.661472 · Cited by 931 · cited 1×
“Synthetic speech signal created using different voice conv ersion (VC) and speech synthesis (SS) techniques can be used to poof biometric systems based on automatic speaker recognition t echnology [1, 2, 3, 4].”
MethodConstruction and evaluation of a robust multifeature speech/music discriminator
Scheirer, E., & Slaney, M. (2002) · 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.1997.596192 · Cited by 873 · cited 1×
“Spectral flux based feature: Spectral flux measures the frame-by-frame change in the power spectrum [25].”
BackgroundCOVAREP — A collaborative voice analysis repository for speech technologies
Degottex, G., Kane, J., Drugman, T., Raitio, T., & Scherer, S. (2014) · 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2014.6853739 · Cited by 695 · cited 1×
“2, First 20 coefficients are retained after DCT [5] Short-term APGDF (60) LP Order=20 — phase features CosPhase (60) First 20 coefficients are retained after DCT [5] RPS (60) RPS computed with COVAREP tool [14], 20 filters in mel filter ba nk [6, 7]”
MethodSpoofing and countermeasures for speaker verification: A survey
Wu, Z., Evans, N., Kinnunen, T., Yamagishi, J., Alegre, F., & Li, H. (2015) · Speech Communication · doi:10.1016/j.specom.2014.10.005 · Cited by 601
Self-citationThe cepstrum: A guide to processing
Childers, D. G., Skinner, D. P., & Kemerait, R. C. (1977) · Proceedings of the IEEE · doi:10.1109/proc.1977.10747 · Cited by 600 · cited 1×
“Cepstrum: Cepstral coefficients (Cep) are computed from the power spectrum by applying discrete cosine transform (DCT) [17].”
Method
Cited by
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
“ms. They use a common Gaussian mixture model (GMM) back-end classifier with either constant Q cepstral coefficient (CQCC) features [22, 23] (B01) or linear frequency cepstral coefficient (LFCC) features [24] (B02). 4. Challenge results Table 1 shows results4 in terms of the t-DCF and EER for primary systems, pooled over…”
MethodSelf-citationASVspoof 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
Self-citationASVspoof 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
“Both use a common Gaussian mixture model (GMM) back-end classifier with either constant-Q cepstral coefficient (CQCC) features [64, 65] (B01) or linear frequency cepstral coefficient (LFCC) features [66] (B02).”
MethodSelf-citationTrends in audio signal feature extraction methods
Sharma, G., Umapathy, K., & Krishnan, S. (2020) · Applied Acoustics · doi:10.1016/j.apacoust.2019.107020 · Cited by 479
Constant Q Cepstral Coefficients: A Spoofing Countermeasure for Automatic Speaker Verification
Todisco, M., Delgado, H., & Evans, N. (2017) · Computer Speech & Language · doi:10.1016/j.csl.2017.01.001 · Cited by 424
End-to-End anti-spoofing with RawNet2
Tak, H., Patino, J., Todisco, M., Nautsch, A., Evans, N., & Larcher, A. (2021) · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp39728.2021.9414234 · Cited by 402
“These choices are motivated by the success of linear and inverseMel [21] front-ends for anti-spoofing.”
BackgroundASVspoof 2021: accelerating progress in spoofed and deepfake speech detection
Yamagishi, J., Wang, X., Todisco, M., Sahidullah, M., Patino, J., Nautsch, A., Liu, X., Lee, K. A., Kinnunen, T., Evans, N., et al. (2021) · 2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge · doi:10.21437/asvspoof.2021-8 · Cited by 380
Self-citationSTC Antispoofing Systems for the ASVspoof2019 Challenge
Lavrentyeva, G., Novoselov, S., Tseren, A., Volkova, M., Gorlanov, A., & Kozlov, A. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-1768 · Cited by 245
One-class learning towards synthetic voice spoofing detection
Zhang, Y., Jiang, F., & Duan, Z. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3076358 · Cited by 241
ASVspoof: The Automatic Speaker Verification Spoofing and Countermeasures Challenge
Wu, Z., Yamagishi, J., Kinnunen, T., Hanilci, C., Sahidullah, M., Sizov, A., Evans, N., Todisco, M., & Delgado, H. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2017.2671435 · Cited by 229
Self-citationStatistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks
Saito, Y., Takamichi, S., & Saruwatari, H. (2018) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2017.2761547 · Cited by 223
“[Identity:] φ(y) = y [Static & delta [52]:] φ(y) = Wy”
Generalization of Audio Deepfake Detection
Chen, T., Kumar, A., Nagarsheth, P., Sivaraman, G., & Khoury, E. (2020) · The Speaker and Language Recognition Workshop (Odyssey 2020) · doi:10.21437/odyssey.2020-19 · Cited by 200
“Similar filter bank based cepstral features such as linear frequency cepstral coef-ficients (LFCCs) also showed competitive performance in synthetic speech detection [22] and speaker recognition [23].”
BackgroundNautsch, A., Wang, X., Evans, N., Kinnunen, T. H., Vestman, V., Todisco, M., Delgado, H., Sahidullah, M., Yamagishi, J., & Lee, K. A. (2021) · IEEE Transactions on Biometrics, Behavior, and Identity Science · doi:10.1109/tbiom.2021.3059479 · Cited by 185
“A short description of each follows: T45 [25]: A light CNN (LCNN) which operates upon LFCC features extracted from the first 600 frames and with the same frontend configuration as the B2 baseline CM [18].”
BackgroundMethodSelf-citationTowards End-to-End Synthetic Speech Detection
Hua, G., Teoh, A. B. J., & Zhang, H. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3089437 · Cited by 176
FoR: A Dataset for Synthetic Speech Detection
Reimao, R., & Tzerpos, V. (2019) · 2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD) · doi:10.1109/sped.2019.8906599 · Cited by 193
“Previous studies [14], [15] show that dynamic acoustic features (such as dynamic filter banks, dynamic MFCCs, and dynamic linear prediction”
BackgroundADD 2022: the first Audio Deep Synthesis Detection Challenge
Yi, J., Fu, R., Tao, J., Nie, S., Ma, H., Wang, C., Wang, T., Tian, Z., Bai, Y., Fan, C., et al. (2022) · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp43922.2022.9746939 · Cited by 165
ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual Networks
Lai, C.-I., Chen, N., Villalba, J., & Dehak, N. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1794 · Cited by 200
Investigating Self-Supervised Front Ends for Speech Spoofing Countermeasures
Wang, X., & Yamagishi, J. (2022) · The Speaker and Language Recognition Workshop (Odyssey 2022) · doi:10.21437/odyssey.2022-14 · Cited by 138
ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan
Delgado, H., Evans, N., Kinnunen, T., Lee, K. A., Liu, X., Nautsch, A., Patino, J., Sahidullah, M., Todisco, M., Wang, X., et al. (2021) · arXiv · doi:10.48550/arxiv.2109.00535 · Cited by 129
“They include: a high resolution LFCCGMM [4], [5] system; a CQCC-GMM [6], [7] system; an LFCC-LCNN [8] system; a RawNet2 [9] system.”
Self-citationAn Investigation of Deep-Learning Frameworks for Speaker Verification Antispoofing
Zhang, C., Yu, C., & Hansen, J. H. L. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2016.2647199 · Cited by 130
Wu, Z., Das, R. K., Yang, J., & Li, H. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-1810 · Cited by 155
“hlear filter cepstral coefficient and instantaneous frequency (CFCCIF) [13], linear frequency cepstral coefficients (LFCC), subband spectral flux coefficients and spectral centroid frequency coeffi- cients [14]. Later, the long-term constant-Q transform (CQT) based constant-Q cepstral coefficients (CQCC) proved to be one of…”
BackgroundYu, H. T., Tan, Z., Ma, Z., Martin, R., & Guo, J. H. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2771947 · Cited by 116
“Published results show that GMM-LLR classifiers trained using dynamic acoustic features work better than DNN and other classifiers [18]–[20], [34], so we select GMM-LLR”
BackgroundMethodResultInfluentialEvaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors
Khalid, H., Kim, M., Tariq, S., & Woo, S. S. (2021) · Proceedings of the 1st Workshop on Synthetic Multimedia - Audiovisual Deepfake Generation and Detection · doi:10.1145/3476099.3484315 · Cited by 110
“Traditional spoofed or fake audio detection methods gave attention to hand-crafted features such as Linear Frequency Cepstral Coefficients (LFCC) [62], Session 1: Deepfake Detection ADGD ’21, October 24, 2021, Virtual Event, China”
MethodKinnunen, T., Sahidullah, M., Falcone, M., Costantini, L., Hautamäki, R. G., Thomsen, D. A. L., Sarkar, A. K., Tan, Z., Delgado, H., Todisco, M., et al. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7953187 · Cited by 120
“Table 4 shows the results using the best LFCC configuration reported in [13] and the best CQCC configuration reported in [12].”
MethodSelf-citationFont, R., Espín, J. M., & Cano, M. J. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-450 · Cited by 109
“We have adopted a similar approach to that presented in [9, 10].”
MethodEnsemble Models for Spoofing Detection in Automatic Speaker Verification
Chettri, B., Stoller, D., Morfi, V., Ramírez, M. A. M., Benetos, E., & Sturm, B. L. T. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-2505 · Cited by 125
Deepfake 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
“For instance, the authors of [121] exploit classic audio features inherited from the Music Information Retrieval (MIR) community to detect speech deepfakes.”
Advances in anti-spoofing: from the perspective of ASVspoof challenges
Kamble, M. R., Sailor, H. B., Patil, H. A., & Li, H. (2020) · APSIPA Transactions on Signal and Information Processing · doi:10.1017/atsip.2019.21 · Cited by 127
“The features extracted using subband processing were also explored, such as Linear Frequency Cepstral Coefficients (LFCC) [96], Energy Separation Algorithm-Instantaneous Frequency Cepstral Coefficients (ESA-IFCC) [91], and Constant-Q Statistics-plus-Principal Information Coefficient (CQSPIC) [97].”
MethodA Survey on Speech Deepfake Detection
Li, M., Ahmadiadli, Y., & Zhang, X.-P. (2025) · ACM Computing Surveys · doi:10.1145/3714458 · Cited by 101
“In contrast to short-term spectral features derived from fixed short window lengths, long-term window transforms have been proposed to capture long-range information and achieve higher frequency resolution.”
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
“For instance, [32] exploits classic audio features inherited from the Music Information Retrieval (MIR) community to perform speech deepfake detection.”
Security in smart cities: A brief review of digital forensic schemes for biometric data
Ross, A., Banerjee, S., & Chowdhury, A. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.07.009 · Cited by 85
Synthetic speech detection through short-term and long-term prediction traces
Borrelli, C., Bestagini, P., Antonacci, F., Sarti, A., & Tubaro, S. (2021) · EURASIP Journal on Information Security · doi:10.1186/s13635-021-00116-3 · Cited by 80
Graph Attention Networks for Anti-Spoofing
Tak, H., Jung, J.-W., Patino, J., Todisco, M., & Evans, N. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-993 · Cited by 79
Do Deepfakes Feel Emotions? A Semantic Approach to Detecting Deepfakes Via Emotional Inconsistencies
Hosler, B., Salvi, D., Murray, A., Antonacci, F., Bestagini, P., Tubaro, S., & Stamm, M. C. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00112 · Cited by 78
“This is the case of [49] that relies on classic audio features inherited from the music information retrieval community.”
BackgroundSpectral Features for Synthetic Speech Detection
Paul, D., Pal, M., & Saha, G. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2017.2684705 · Cited by 85
“To capture this, inverted warping scale based spectral features are expected to be useful that provide higher resolution in higher frequency regions [23], [33].”
BackgroundMethodInfluentialToward Robust Audio Spoofing Detection: A Detailed Comparison of Traditional and Learned Features
Balamurali, B. T., Lin, K. W. E., Lui, S., Chen, J., & Herremans, D. (2019) · IEEE Access · doi:10.1109/access.2019.2923806 · Cited by 83
“The procedure for calculating LFCCs is similar to that of RFCCs [41], however, it uses triangular filters instead of rectangular filters [19], [42].”
BackgroundMethodInfluentialDeepfake audio detection by speaker verification
Pianese, A., Cozzolino, D., Poggi, G., & Verdoliva, L. (2022) · 2022 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs55849.2022.9975428 · Cited by 74
“Also effective are first- and second-order spectral features [4] as well as higher-order polyspectral features [5], exploiting the observation that synthesized speech can introduce uncommon spectral correlations.”
BackgroundMLAAD: The Multi-Language Audio Anti-Spoofing Dataset
Müller, N. M., Kawa, P., Choong, W. H., Casanova, E., Gölge, E., Müller, T., Syga, P., Sperl, P., & Böttinger, K. (2024) · 2024 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650962 · Cited by 73
“The field is supported by numerous open-source toolkits [37]–[40], which offer access to various speech synthesis methods.”
Introduction to Voice Presentation Attack Detection and Recent Advances
Sahidullah, M., Delgado, H., Todisco, M., Kinnunen, T., Evans, N., Yamagishi, J., & Lee, K. A. (2019) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-92627-8_15 · Cited by 84
Self-citationSignificance of Subband Features for Synthetic Speech Detection
Yang, J., Das, R. K., & Li, H. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2956589 · Cited by 93
“Several features that fall into this category were investigated in [32], which include rectangular filter cepstral coefficients [36], linear frequency cepstral coefficients [37] and inverted mel frequency cepstral coefficients [38], [39].”
BackgroundResultInfluentialSpeech is Silver, Silence is Golden: What do ASVspoof-trained Models Really Learn?
Müller, N., Dieckmann, F., Czempin, P., Canals, R., Böttinger, K., & Williams, J. (2021) · 2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge · doi:10.21437/asvspoof.2021-9 · Cited by 69
End-to-end spoofing detection with raw waveform CLDNNS
Dinkel, H., Chen, N., Qian, Y., & Yu, K. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7953080 · Cited by 72
“Successful attempts can be seen in [6, 7].”
Human Perception of Audio Deepfakes
Müller, N. M., Pizzi, K., & Williams, J. (2022) · Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia · doi:10.1145/3552466.3556531 · Cited by 68
“Such artifacts include noisy glitch, phase mismatch, reverberation, or loss of intelligibility [16, 17].”
BackgroundSpoofing Attack Detection Using the Non-Linear Fusion of Sub-Band Classifiers
Tak, H., Patiño, J. F., Nautsch, A., Evans, N., & Todisco, M. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-1844 · Cited by 89
DNN Filter Bank Cepstral Coefficients for Spoofing Detection
Yu, H., Tan, Z.-H., Zhang, Y., Ma, Z., & Guo, J. (2017) · IEEE Access · doi:10.1109/access.2017.2687041 · Cited by 67
Overview of BTAS 2016 speaker anti-spoofing competition
Korshunov, P., Marcel, S., Muckenhirn, H., Gonçalves, A. R., Mello, A. G. S., Violato, R. P. V., Simões, F. O., Neto, M. U., Angeloni, M. D. A., Stuchi, J. A., et al. (2016) · IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS) · doi:10.1109/btas.2016.7791200 · Cited by 64
“Speech activity detector (SAD) is not employed as non-speech frames could be helpful for spoofing detection [13].”
BackgroundSelf-citationAutomatic speaker verification systems and spoof detection techniques: review and analysis
Mittal, A., & Dua, M. (2021) · International Journal of Speech Technology · doi:10.1007/s10772-021-09876-2 · Cited by 97
“LFCCs are helpful in speech recognition as well as in speaker identification as they can model the length of the vocal tract in higher frequency regions (Sahidullah et al., 2015; Pritam et al., 2018).”
BackgroundFake Speech Detection Using Residual Network with Transformer Encoder
Zhang, Z., Yi, X., & Zhao, X. (2021) · Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security · doi:10.1145/3437880.3460408 · Cited by 66
“[20] made a comparative study and demonstrated the efficacy of various short-term power spectrum and phase features for synthetic speech detection.”
BackgroundTIMIT-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
“For example, [38] exploits the deepfake detection task by relying on classic audio features inherited from the music information retrieval community.”
Cai, W., Wu, H., Cai, D., & Li, M. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1230 · Cited by 70
Long Range Acoustic and Deep Features Perspective on ASVspoof 2019
Das, R. K., Yang, J., & Li, H. (2019) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru46091.2019.9003845 · Cited by 75
Multimodaltrace: Deepfake Detection using Audiovisual Representation Learning
Anas Raza, M., & Mahmood Malik, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00106 · Cited by 63
“Traditional approaches for detecting spoofed or fake audio employed hand-crafted features such as Cochlear Filter Cepstral Coefficients Instantaneous Frequency (CFCCIF) [14], Linear Frequency Cepstral Coefficients (LFCC) [16], and Constant-Q Cepstral Coefficients (CQCC) [17], combining with the Gaussian Mixture Model…”
MethodAudio 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
“Apart from the GMM, other machine learning models, such as the Support Vector Machine and Logistic Regression, were widely studied in earlier research [96,134–136].”
Generalized end-to-end detection of spoofing attacks to automatic speaker recognizers
Monteiro, J., Alam, J., & Falk, T. H. (2020) · Computer Speech & Language · doi:10.1016/j.csl.2020.101096 · Cited by 74
Hanilçi, C., Kinnunen, T., Sahidullah, M., & Сизов, А. С. (2016) · Speech Communication · doi:10.1016/j.specom.2016.10.002 · Cited by 70
“A comparative evalation of a large number of speech features for this task is availble in Sahidullah et al. (2015) .”
BackgroundSelf-citationUR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021
Chen, X., Zhang, Y., Zhu, G., & Duan, Z. (2021) · 2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge · doi:10.21437/asvspoof.2021-12 · Cited by 61
“Efforts have been put into the study of generalization with a focus on feature engineering [7], backend model [8], loss function [9, 10], data augmentation [11], and model ensemble [12].”
BackgroundResultInfluentialFake Audio Detection Based On Unsupervised Pretraining Models
Lv, Z., Zhang, S., Tang, K., & Hu, P. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747605 · Cited by 87
Synthetic speech detection using fundamental frequency variation and spectral features
Pal, M., Paul, D., & Saha, G. (2017) · Computer Speech & Language · doi:10.1016/j.csl.2017.10.001 · Cited by 59
Classifiers for synthetic speech detection: a comparison
Hanilçi, C., Kinnunen, T., Sahidullah, M., & Сизов, А. С. (2015) · Interspeech (USB) · doi:10.21437/interspeech.2015-466 · Cited by 67
“While our companion paper [30] demonstrates that these may not be the optimal features for synthetic speech detection task, t hey are the standard features in speaker verification and provid e st ll low error rates on ASVspoof 2015.”
BackgroundSelf-citationDefending Your Voice: Adversarial Attack on Voice Conversion
Huang, C., Lin, Y. Y., Lee, H.-Y., & Lee, L.-S. (2021) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt48900.2021.9383529 · Cited by 96
“Detecting any of such artifacts or defending against such activities is thus increasingly important [6, 7, 8, 9], which applies equally to voice conversion.”
BackgroundEnd-to-End convolutional neural network-based voice presentation attack detection
Muckenhirn, H., Magimai.-Doss, M., & Marcel, S. (2017) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/btas.2017.8272715 · Cited by 67
“More precisely, different magnitude spectrum based features [15, 20, 21], phase spectrum based features [15, 17, 20] and modulation spectrum based features [26], which are all computed on short-term spectrum, have been investigated in conjunction with classifiers such as Gaussian mixture models [15, 17, 21, 26], suppo…”
BackgroundMethodTodisco, M., Delgado, H., Lee, K. A., Sahidullah, M., Evans, N., Kinnunen, T., & Yamagishi, J. (2018) · Interspeech (USB) · doi:10.21437/interspeech.2018-2289 · Cited by 88
“Mel-frequency cepstral coefficients (MFCCs): MFCCs are used widely in speech and speaker recognition and have been explored extensively as features for spoofing detection [3].”
BackgroundMethodSelf-citationModified Magnitude-Phase Spectrum Information for Spoofing Detection
Yang, J., Wang, H., Das, R. K., & Qian, Y. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3060810 · Cited by 66
“Some of these include mel frequency cepstral coefficients (MFCC) [27]–[29], rectangular filter cepstral coefficients [30], inverted MFCC [31] (IM-FCC), Gammatone filter bank cepstral coefficients (GFCC) and inverted GFCC (IGFCC) [32].”
BackgroundMethodInfluentialDetection of AI-Synthesized Speech Using Cepstral & Bispectral Statistics
Singh, A. K., & Singh, P. (2021) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr51284.2021.00076 · Cited by 50
Lei, Z., Yang, Y., Liu, C., & Ye, J. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2723 · Cited by 55
Das, R. K., Kinnunen, T., Huang, W.-C., Ling, Z.-H., Yamagishi, J., Yi, Z., Tian, X., & Toda, T. (2020) · doi:10.21437/vcc_bc.2020-15 · Cited by 64
Self-citationVoice Spoofing Countermeasure for Logical Access Attacks Detection
Arif, T., Javed, A., Alhameed, M. H., Jeribi, F., & Tahir, A. (2021) · IEEE Access · doi:10.1109/access.2021.3133134 · Cited by 62
“This argues the use of linear scale frequency for speaker identification and spoofing detection.”
BackgroundExtraction of Octave Spectra Information for Spoofing Attack Detection
Yang, J., Das, R. K., & Zhou, N. (2019) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2019.2946897 · Cited by 48
“formation [23], [30], subband [21], [45], [46] and deep learning based extractor [27], [32].”
BackgroundMethodInfluentialSpoofing detection from a feature representation perspective
Tian, X., Wu, Z., Xiao, X., Chng, E. S., & Li, H. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472051 · Cited by 56
“Previous studies [8, 17] shown that single type of feature is usually effective for certain types of artifact, while may not be sensitive to other types of artifact.”
BackgroundResultInfluentialSynthetic speech detection using phase information
Saratxaga, I., Sánchez, J., Wu, Z., Hernáez, I., & Navas, E. (2016) · Speech Communication · doi:10.1016/j.specom.2016.04.001 · Cited by 54
Robust Voice Liveness Detection and Speaker Verification Using Throat Microphones
Sahidullah, M., Thomsen, D. A. L., Hautamäki, R. G., Kinnunen, T., Tan, Z., Parts, R., & Pitkänen, M. (2017) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2017.2760243 · Cited by 54
“Speech-based spoofing countermeasures mostly employ spectral features as a front-end for speech representation [64] followed by a statistical classifier [65].”
BackgroundSelf-citationOn Joint Optimization of Automatic Speaker Verification and Anti-Spoofing in the Embedding Space
Gomez-Alanis, A., González, J. A., Dubagunta, S. P., Peinado, A. M., & Magimai.-Doss, M. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3039045 · Cited by 58
“A wide range of features have been proposed to train these models, such as spectrogram [37], linear frequency cepstral coefficients (LFCC) [38], constant Q cepstral coefficients (CQCC) [39], and raw speech samples [40].”
BackgroundLong-term high frequency features for synthetic speech detection
Yang, J., & Das, R. K. (2019) · Digital Signal Processing · doi:10.1016/j.dsp.2019.102622 · Cited by 53
An assessment of automatic speaker verification vulnerabilities to replay spoofing attacks
Janicki, A., Alegre, F., & Evans, N. (2016) · Security and Communication Networks · doi:10.1002/sec.1499 · Cited by 54
“these findings conflict with other researchers’ results [71] published after the completion of this work.”
ResultLong-Term Spectral Statistics for Voice Presentation Attack Detection
Muckenhirn, H., Korshunov, P., Magimai.-Doss, M., & Marcel, S. (2017) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2017.2743340 · Cited by 47
“3) spectral-temporal features: this includes modulation spectrum [16], frequency domain linear prediction [7], extraction of local binary patterns in the cepstral domain [17],”
BackgroundMethodInfluentialTan, C. B., Hijazi, M. H. A., Khamis, N., Nohuddin, P. N. E. B., Zainol, Z., Coenen, F., & Gani, A. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11235-x · Cited by 40
“Recently several Synthetic Speech Detectors (SSDs) were introduced to protect speaker verification systems from speech synthesis attacks [38, 102].”
BackgroundContinual Learning for Fake Audio Detection
Ma, H., Yi, J., Tao, J., Bai, Y., Tian, Z., & Wang, C. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-794 · Cited by 39
“We extract 60-dimensional linear frequency cepstral coefficients (LFCC) [28] of speech as low-level input feature to the neural network.”
MethodNoise robust automatic speech recognition: review and analysis
Dua, M., Akanksha, A., & Dua, S. (2023) · International Journal of Speech Technology · doi:10.1007/s10772-023-10033-0 · Cited by 59
“Also, the front-end of ASV systems is designed using a variety of hybrid feature extraction approaches that may catch the signs of voice manipulation (Sahidullah et al., 2015).”
BackgroundCochlear Filter and Instantaneous Frequency Based Features for Spoofed Speech Detection
Patel, T. B., & Patil, H. A. (2016) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2016.2647201 · Cited by 49
“A recent work in [36], has shown that the dynamic features alone can contribute effectively to the detection process and achieve almost similar or less % EER than the static features.”
BackgroundInfluentialGeneralization of spoofing countermeasures: A case study with ASVspoof 2015 and BTAS 2016 corpora
Paul, D., Sahidullah, M., & Saha, G. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7952516 · Cited by 49
“A concise experimental review of spoofing detection was presented in [13].”
BackgroundResultSelf-citationVoice Spoofing Countermeasure for Synthetic Speech Detection
Hassan, F., & Javed, A. (2021) · doi:10.1109/icai52203.2021.9445238 · Cited by 37
“The proposed system outperforms the ASVspoof baseline models by achieving 5.52% and 5.03% lesser EER than CQCC+GMM [15] andLFCC+GMM [16]) respectively.”
MethodResultInfluentialStatic–dynamic features and hybrid deep learning models based spoof detection system for ASV
Mittal, A., & Dua, M. (2021) · Complex & Intelligent Systems · doi:10.1007/s40747-021-00565-w · Cited by 39
“However, utilization of this factor for frontend development of speech driven devices [18, 19] can be done by using All Pole Group Delay Function (APGDF), Modified Group Delay Function (MODGDF), etc.”
MethodA Comparative Study on Physical and Perceptual Features for Deepfake Audio Detection
Li, M., Ahmadiadli, Y., & Zhang, X.-P. (2022) · Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia · doi:10.1145/3552466.3556523 · Cited by 35
“[23] compare 19 acoustic features based on first-order Fourier coefficients and second-order spectral features.”
BackgroundOne-Class Neural Network With Directed Statistics Pooling for Spoofing Speech Detection
Lin, G., Luo, W., Luo, D., & Huang, J. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3352429 · Cited by 39
“…variety of features, including relative phase shift, modified group delay, cochlear filter cepstral coefficients, instantaneous frequency, linear frequency cepstral coefficients, and constant-Q cepstral coefficients, along with various combinations and variations [12], [13], [14], [15], [16], [17].”
BackgroundKorshunov, P., & Marcel, S. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2017.2692389 · Cited by 36
“[6] on ASVspoof database with an addition of CQCC features based method [14].”
BackgroundMethodInfluentialDeepfake audio detection with vision transformer based method
Ulutas, G., Tahaoglu, G., & Ustubioglu, B. (2023) · 2023 46th International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp59544.2023.10197715 · Cited by 34
“These methods were submitted to the ASVSpoof 2019 competition and those reported in works afterward [16-20].”
MethodThe Impact of Silence on Speech Anti-Spoofing
Zhang, Y., Li, Z., Lu, J., Hua, H., Wang, W., & Zhang, P. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3306711 · Cited by 53
“The input features of CNN based classifiers are two-dimensional features including short-time Fourier transform (STFT) spectrogram, constant Q transform (CQT) spectrogram, Mel-scale transform (MSTFT), as well as cepstral features such as constant Q cepstral coefficient (CQCC) [15] and linear frequency cepstral coeffic…”
MethodInfluentialImproved Lightcnn with Attention Modules for Asv Spoofing Detection
Ma, X., Liang, T., Zhang, S., Huang, S., & He, L. J. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428313 · Cited by 50
“As for feature learning, in addition to the linear frequency cesptral coeffcients (LFCC) [10] and constant Q cepstral co-effcients (CQCC) [11] recommended by the ASVspoof competition organizer, most studies involve in investigating raw spectrums, such as STFT power spectrum [8], log-CQT features…”
BackgroundVoice Deepfake Detection Using the Self-Supervised Pre-Training Model HuBERT
Li, L., Lu, T., Ma, X., Yuan, M., & Wan, D. (2023) · Applied Sciences · doi:10.3390/app13148488 · Cited by 33
End-to-End Dual-Branch Network Towards Synthetic Speech Detection
Ma, K., Feng, Y., Chen, B., & Zhao, G. (2023) · IEEE Signal Processing Letters · doi:10.1109/lsp.2023.3262419 · Cited by 35
What to remember: Self-adaptive continual learning for audio deepfake detection
Zhang, X., Yi, J., Wang, C., Zhang, C. Y., Zeng, S., & Tao, J. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29929 · Cited by 32
Effect of multi-condition training and speech enhancement methods on spoofing detection
Yu, H. T., Sarkar, A. K., Thomsen, D. A. L., Tan, Z., Ma, Z., & Guo, J. H. (2016) · International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE) · doi:10.1109/splim.2016.7528399 · Cited by 31
“The same as in paper [17], human and spoof GMM models are trained using their corresponding labeled training data using an expectation maximization algorithm.”
BackgroundMethodInfluentialDetection of replay spoof speech using teager energy feature cues
Kamble, M. R., & Patil, H. A. (2020) · Computer Speech & Language · doi:10.1016/j.csl.2020.101140 · Cited by 32
Data Augmentation with Signal Companding for Detection of Logical Access Attacks
Das, R. K., Yang, J., & Li, H. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413501 · Cited by 50
SpecRNet: Towards Faster and More Accessible Audio DeepFake Detection
Kawa, P., Plata, M., & Syga, P. (2022) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom56396.2022.00111 · Cited by 52
“One of the reasons behind that is that classical approaches like GMMs tend to require a separate model for each attack type, which decreases the scalability and flexibility of such solutions.”
BackgroundInfluentialAttack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection
Kawa, P., Plata, M., & Syga, P. (2022) · Interspeech 2022 · doi:10.21437/interspeech.2022-10078 · Cited by 33
“GMM’s front–ends and training procedure followed [18].”
MethodInfluentialCross-Database Evaluation of Audio-Based Spoofing Detection Systems
Korshunov, P., & Marcel, S. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-1326 · Cited by 38
“We kept only deltas and double-deltas, because [12] reported that static features degraded performance of PAD systems.”
BackgroundMethodResultInfluentialSriskandaraja, K., Sethu, V., Eliathamby Ambikairajah, A., & Li, H. (2016) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2016.2647202 · Cited by 36
“to MFCC features have also been proposed for use in spoofing detectors [41].”
BackgroundMethodRobust Detection of Machine-induced Audio Attacks in Intelligent Audio Systems with Microphone Array
Li, Z., Shi, C., Zhang, T., Xie, Y., Liu, J., Yuan, B., & Chen, Y. J. (2021) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3460120.3484755 · Cited by 40
“In addition to these power spectrum features, relative phase shift [17], pitch patterns [33], and neuron activation patterns [73], alongwith other spectral features [42] have been proposed to help discriminate between human and synthetic speech.”
BackgroundFully Automated End-to-End Fake Audio Detection
Wang, C., Yi, J., Tao, J., Sun, H., Chen, X., Tian, Z., Ma, H., Fan, C., & Fu, R. (2022) · DDAM@MM · doi:10.1145/3552466.3556530 · Cited by 50
“[12] replace the Mel scale filters with linear filters and propose linear frequency cepstrum coefficients(LFCC), making it more focused on high frequency band features compared to MFCC.”
Method
Metadata
- Authors
- Sahidullah, M., Kinnunen, T., & Hanilçi, C.
- Affiliations
- University of Eastern Finland (FI)
- Venue
- Interspeech 2015
- Publisher
- ISCA
- Published
- 2015-09-06
- Pages
- 2087-2091
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2295634712
- Cited by
- 382
- References
- 36
- Citations by year
- 2026: 23 · 2025: 41 · 2024: 42 · 2023: 50 · 2022: 38 · 2021: 51 · 2020: 35 · 2019: 41 · 2018: 15 · 2017: 29 · 2016: 15 · 2015: 2
- FWCI
- 11.46
- Type
- conference paper
- Language
- en
- Open access
- green
- erepo.uef.fi
- Licence
- other-oa
- Locations
- Interspeech (USB) (publishedVersion)
- UEF eRepo (University of Eastern Finland) (submittedVersion, other-oa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Keywords
- synthetic speech detection, spoofing attacks, anti-spoofing, speaker verification, voice conversion, speech synthesis, feature extraction
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.