Spoofing detection with DNN and one-class SVM for the ASVspoof 2015 challenge
The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Speaker verification systems have achieved great performance in recent times. However, we usually measure performance on a ideal scenarios with naive impostors that do not modify their voices to impersonate the target speakers. The fact of impersonating a legitimate user is known as spoofing attack. Recent works show the vulnerability of current speaker verification technology to several types of attacks. Most of these works use non-public databases and different performance measures, which makes difficult to compare approaches. The spoofing challenge (ASVspoof 2015) tries to overcome this problem by proposing a common evaluation framework. This paper describes our submission to the challenge. We proposed to use spectral log-filter-bank and relative phase shift features as input to classifiers based on deep neural networks (DNN). The first of our classifiers used DNN posteriors to decide if the trial is spoof or non-spoof. The second used a bottleneck feature from the DNN as input to a one-class SVM. The one-class SVM models the distribution of legitimate speech, not needing spoofing data for training. We fused the score of the different classifiers to produce our final submission. Our system attained very competitive results with EER<0.05% in 9 out of 10 spoofing types.
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
“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 [136]
Citations
Cites
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · cited 1×
“To train the SVM, we used the libsvm toolkit [17].”
MethodPractical Bayesian Optimization of Machine Learning Algorithms
Snoek, J., Larochelle, H., & Adams, R. P. (2012) · arXiv · doi:10.48550/arxiv.1206.2944 · Cited by 6,691 · cited 1×
“We tuned the network hyperparameters (number, type and size of hidden layers, learning rates, etc) by Bayesian optimization with the Spearmint toolkit [14].”
MethodSupport Vector Method for Novelty Detection
Schölkopf, B., Williamson, R. C., Smola, A. J., Shawe-Taylor, J. S., & Platt, J. C. (1999) · Cited by 2,040
Kawahara, H., Masuda-Katsuse, I., & de Cheveigné, A. (1999) · Speech Communication · doi:10.1016/s0167-6393(98)00085-5 · Cited by 1,831 · cited 1×
“MaryTTS uses MBROLA 3 to generate the speech wave-form while the rest of spoofs used the STRAIGHT [24] or the MLSA [25] vocoders.”
MethodVoice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory
Toda, T., Black, A. W., & Tokuda, K. (2007) · IEEE Transactions on Audio, Speech and Language Processing · doi:10.1109/tasl.2007.907344 · Cited by 937
COVAREP — 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×
“We computed the RPS with the help of the COVAREP toolkit [12].”
MethodSeide, F., Li, G., Chen, X., & Yu, D. (2011) · 2011 IEEE Workshop on Automatic Speech Recognition & Understanding · doi:10.1109/asru.2011.6163899 · Cited by 632 · cited 1×
“For weight initialization, we applied layer-wise discriminative pre-training, described in detail in [13].”
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
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 ASV spoofing challenge provides a standard corpora and evaluation metric to compare different spoofing detection approaches [7].”
BackgroundMethodThe NIST speaker recognition evaluation – Overview, methodology, systems, results, perspective
Doddington, G. R., Przybocki, M. A., Martin, A. F., & Reynolds, D. A. (2000) · Speech Communication · doi:10.1016/s0167-6393(99)00080-1 · Cited by 365 · cited 1×
“According to the “rule of 30” [23], to be 90% confident that the true error rate is ±30% of the measured error rate there must be at least 30 errors.”
Background
Cited by
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
“It is noted that “ResNet + OC-SVM” was adapted from [28], which is the only existing one-class classification method; We replaced their DNN with our ResNet and run the experiments on the ASVspoof 2019 LA dataset for a fair comparison.”
MethodASVspoof: 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
“J System J [57] used both magnitude and phase informa-”
MethodDeep Residual Neural Networks for Audio Spoofing Detection
Alzantot, M., Wang, Z., & Srivastava, M. B. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-3174 · Cited by 215
An 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 122
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 102
“In ASVspoof 2015 Challenge, the systems in [95,113] use DNN as the classifiers.”
MethodSpectral 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 77
“The performance of spectral and phase features on deep neural network (DNN) and one-class support vector machine (SVM) classifier was reported in [31].”
BackgroundAutomatic 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
“Villalba et al. (2015) are training a HMM with static and dynamic MFCC features, extracted from ATR speech data, for speaker verification task of a TD-ASV system that achieves 0% EER for human speakers and a HMM system is used for speech synthesis.”
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].”
Significance of Subband Features for Synthetic Speech Detection
Yang, J., Das, R. K., & Li, H. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2956589 · Cited by 70
“There are also several other classifiers that are trained to be discriminative between classes, such as, support vector machine [54], multi-layer perceptron [20], [55], recurrent neural network [23], deep neural network (DNN) [29], [56]–[60], convolutional neural network [61], ResNet [62] and linear discriminant analy…”
BackgroundDeep features for automatic spoofing detection
Qian, Y., Chen, N., & Yu, K. (2016) · Speech Communication · doi:10.1016/j.specom.2016.10.007 · Cited by 78
“Moreover, compared to the recent works which utilized some handcrafted delicate features for spoofing detection, such as phase feature (Alam et al., 2015; Liu et al., 2015b,b; Wang et al., 2015; Xiao et al., 2015; Sanchez et al., 2015; Novoselov et al., 2015; Villalba et al., 2015; Weng et al., 2015), cochlea feature…”
BackgroundMethodInfluentialDNN 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
Hanilçi, C., Kinnunen, T., Sahidullah, M., & Sizov, A. (2016) · Speech Communication · doi:10.1016/j.specom.2016.10.002 · Cited by 61
Investigating Raw Wave Deep Neural Networks for End-to-End Speaker Spoofing Detection
Dinkel, H., Qian, Y., & Yu, K. (2018) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2018.2851155 · Cited by 60
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
End-to-End convolutional neural network-based voice presentation attack detection
Muckenhirn, H., Magimai-Doss, M., & Marcel, S. (2017) · 2017 IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/btas.2017.8272715 · Cited by 53
“The approaches proposed in [2, 14, 23, 29] employ deep learning methods for PAD.”
BackgroundMethodSynthetic 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
Extraction 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
“linear discriminant analysis [32], multi-layer perceptron [24], [33], recurrent neural network [27] and deep neural network (DNN) [34]–[39].”
BackgroundLong-term high frequency features for synthetic speech detection
Yang, J., & Das, R. K. (2020) · Digital Signal Processing · doi:10.1016/j.dsp.2019.102622 · Cited by 45
Long-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
“eral works, classified either with a GMM [7], a SVM [29], a MLP [11], [12] or with deep architectures [27]–[30].”
MethodInfluentialDeep Feature Engineering for Noise Robust Spoofing Detection
Qian, Y., Chen, N., Dinkel, H., & Wu, Z. (2017) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2017.2732162 · Cited by 46
Spoofing Speech Detection Using Modified Relative Phase Information
Wang, L., Nakagawa, S., Zhang, Z., Yoshida, Y., & Kawakami, Y. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2017.2694139 · Cited by 45
“Some back-end processing approaches (classifiers), such as the Gaussian mixture model (GMM) [35], [36], support vector machine, and deep neural network, have been used for spoofing speech detection [29], [33], [37].”
MethodTan, 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
“The two most frequently used individual features, CQCC and MFCC, became less preferred due to the most recent work showing the superiority of multiple features in detecting presentation attacks [20, 112, 127].”
BackgroundExploitation of Phase-Based Features for Whispered Speech Emotion Recognition
Deng, J., Xu, X., Zhang, Z., Frühholz, S., & Schuller, B. W. (2016) · IEEE Access · doi:10.1109/access.2016.2591442 · Cited by 43
“In the first automatic speaker verification spoofing and countermeasures challenge 2015, the phase-based feature representations were a highly popular choice in the feature extraction [38], [39], [44].”
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
“Moreover, the i-vector-based systems [40], Deep Neural Networks (DNN)-based representation [41], [42] and the use of DNN and Support Vector Machine (SVM) classifier [43] for spoofing detection were explored.”
MethodRecurrent Neural Networks for Automatic Replay Spoofing Attack Detection
Chen, Z., Zhang, W., Xie, Z., Xu, X., & Chen, D. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8462644 · Cited by 39
“Traditional feed-forward neural networks [10] or simple multiple layer perceptron [11] is needed if the input features are high dimensional.”
BackgroundMethodAnalysing The Predictions Of a CNN-Based Replay Spoofing Detection System
Chettri, B., Mishra, S., Sturm, B. L., & Benetos, E. (2018) · 2018 IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2018.8639666 · Cited by 34
“Several machine learning systems have shown success in spoofing attack detection in both the ASVspoof 2015 [8, 9] and ASVspoof 2017(2) public evaluation challenges.”
BackgroundUnseen Face Presentation Attack Detection Using Sparse Multiple Kernel Fisher Null-Space
Arashloo, S. R. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3046505 · Cited by 37
“for instance, in speech [23], fingerprint [15], or iris [24] antispoofing as well as in face PAD [7], [8] by considering bona fide samples as target objects and then trying to detect PA’s as novelties in reference to the population of target observations.”
BackgroundEffect of multi-condition training and speech enhancement methods on spoofing detection
Yu, H., Sarkar, A., Thomsen, D. A. L., Tan, Z.-H., Ma, Z., & Guo, J. (2016) · 2016 First International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE) · doi:10.1109/splim.2016.7528399 · Cited by 31
“Those techniques can be divided into different domains namely feature space: Mel-frequency cepstral coefficients (MFCC) [10], linear frequency cepstral coefficients (LFCC) [12], Group Delay (GD) feature [13], relative phase shift (RPS) [14], spectral centroid magnitude coefficients (SCMC) [15], deep neural network (DN…”
BackgroundNew Acoustic Features for Synthetic and Replay Spoofing Attack Detection
Wei, L., Long, Y., Wei, H., & Li, Y. (2022) · Symmetry · doi:10.3390/sym14020274 · Cited by 29
“Most of the deep models are based on the DNNs [13–15], recurrent neural networks [16,17], and convolution neural networks (CNN) [18,19].”
Patel, T. B., & Patil, H. A. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472650 · Cited by 29
“The various approaches proposed at the challenge used features based on magnitude and phase spectrum of group delay [12]- [13], relative phase [14]- [15] and exploring back-end of spoofing detectors [16]- [17].”
MethodLightweight Voice Spoofing Detection Using Improved One-Class Learning and Knowledge Distillation
Ren, Y., Peng, H., Li, L., & Yang, Y. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3321505 · Cited by 27
“Villaba et al. [32] input the bottleneck feature extracted from DNN into one-class SVM.”
MethodLi, J., Wang, H., He, P., Abdullahi, S. M., & Li, B. (2022) · Digital Signal Processing · doi:10.1016/j.dsp.2021.103256 · Cited by 20
Zhang, C., Ranjan, S., Nandwana, M. K., Zhang, Q., Misra, A., Liu, G., Kelly, F., & Hansen, J. H. L. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472636 · Cited by 24
Deep domain adaptation for anti-spoofing in speaker verification systems
Himawan, I., Villavicencio, F., Sridharan, S., & Fookes, C. (2019) · Computer Speech & Language · doi:10.1016/j.csl.2019.05.007 · Cited by 21
Demiroğlu, C., Büyük, O., Khodabakhsh, A., & Maia, R. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2017.2673807 · Cited by 17
“Phase and magnitude spectrum features are also used together in [26]–[28] and [29].”
MethodVoice Presentation Attack Detection through Text-Converted Voice Command Analysis
Kwak, I., Huh, J. H., Han, S. T., Kim, I., & Yoon, J. (2019) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300828 · Cited by 16
“However, voice biometric based authentication methods achieve about 80–90% accuracy when there are background noises present [3, 17, 29, 31, 33, 37], and are often CHI 2019 Paper CHI 2019, May 4–9, 2019, Glasgow, Scotland, UK”
BackgroundWang, Z., & Hansen, J. H. L. (2024) · IEEE Access · doi:10.1109/access.2024.3421281 · Cited by 19
“In [77], spectral log-filter-bank and relative phase shift features were taken as input to train DNN classifiers for synthetic spoofing detection.”
MethodLinear prediction residual features for automatic speaker verification anti-spoofing
Hanilçi, C. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5181-0 · Cited by 15
“to magnitude based features, in general [23,32,33,39].”
Speech frame selection for spoofing detection with an application to partially spoofed audio-data
Kumar, A. K., Paul, D., Pal, M., Sahidullah, M., & Saha, G. (2021) · International Journal of Speech Technology · doi:10.1007/s10772-020-09785-w · Cited by 14
“Other than the use of SAD for discarding non-speech frames (Villalba et al. 2015a; Jahangir et al. 2015), our work is the first attempt to explore the frame selection method for voice spoofing detection task.”
BackgroundMethodPatil, A. T., Patil, H. A., & Khoria, K. (2021) · Computer Speech & Language · doi:10.1016/j.csl.2021.101301 · Cited by 13
Comprehensive review of automatic speaker verification with spoofing detection techniques attacks
Al-Karawi, K. A., Abdelwahab, M. M., & Alenizi, A. S. (2025) · International Journal of Speech Technology · doi:10.1007/s10772-025-10203-2 · Cited by 15
“Villalba et al. (2015) are training a Hidden Markov Model (HMM) utilizing both stationary and dynamic Mel-frequency ceps - tral coefficients (MFCC) derived from Automatic Speech Recognition (ATR) data for the speaker validation task of a Text-Dependent Automatic Speaker Verification (TD-ASV)…”
Liu, L., & Yang, J. (2020) · IEEE Access · doi:10.1109/access.2020.3013066 · Cited by 10
“DNN has been reported to outperform GMM in many classification applications [41], [42].”
Rahmeni, R., Aicha, A. B., & BenAyed, Y. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.09.103 · Cited by 9
Ketabi, S., Rashidi, S., & Fallah, A. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105218 · Cited by 9
A comparison of different support vector machine kernels for artificial speech detection
Tan, C. B., Hijazi, M. H. A., & Nohuddin, P. N. E. (2022) · TELKOMNIKA (Telecommunication Computing Electronics and Control) · doi:10.12928/telkomnika.v21i1.24259 · Cited by 9
Speech-Forensics: Towards Comprehensive Synthetic Speech Dataset Establishment and Analysis
Ji, Z., Lin, C., Wang, H., & Shen, C. (2024) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2024/46 · Cited by 11
“…of forensic scenarios escalated, machine learning, especially deep learning techniques, began to receive heightened attention from researchers, leading to significant breakthroughs in numerous instances [Villalba et al. , 2015; Alzantot et al. , 2019; Li et al. , 2023a; Zeng et al. , 2023].”
BackgroundRevealing the processing history of pitch-shifted voice using CNNs
Wang, L., Liang, H., Lin, X., & Kang, X. (2018) · IEEE International Workshop on Information Forensics and Security · doi:10.1109/wifs.2018.8630783 · Cited by 7
Voice Presentation Attack Detection Using Convolutional Neural Networks
Himawan, I., Madikeri, S. R., Motlíček, P., Cerňak, M., Sridharan, S., & Fookes, C. (2019) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-92627-8_17 · Cited by 12
Lai, X. (2021) · International Journal of Speech Technology · doi:10.1007/s10772-021-09872-6 · Cited by 10
RetractedA Comparison of Features for Replay Attack Detection
Xie, Z., Zhang, W., Chen, Z., & Xu, X. (2019) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1229/1/012079 · Cited by 6
“Deep Neural Networks DNN have obtained great success in many fields including spoof detection [10].”
MethodOne-Class Fake Speech Detection Based on Improved Support Vector Data Description
Zhang, J., Yi, X., & Zhao, X. (2023) · Security and Communication Networks · doi:10.1155/2023/8830894 · Cited by 7
Speech spoofing detection using SVM and ELM technique with acoustic features
Rahmeni, R., Aicha, A. B., & BenAyed, Y. (2020) · International Conference on Advanced Technologies for Signal and Image Processing · doi:10.1109/atsip49331.2020.9231799 · Cited by 8
“They use the phase information extracted from Relative Phase Shift (RPS) with comparaison with MFCCs in [6].”
BackgroundMethodXu, X., Fu, C., Du, X., & Ratazzi, E. P. (2023) · International Conference on Dependable Systems & Networks/Proceedings · doi:10.1109/dsn58367.2023.00060 · Cited by 6
One-Class SVMs Based Pronunciation Verification Approach
Shahin, M. A., Ji, J., & Ahmed, B. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545687 · Cited by 5
“The OCSVM is used commonly for anomaly detection applications [24]; in speech analysis, it has been used successfully to classify between speech and music [25], audioevent detection [26] and spoofing detection [27].”
MethodImproved One-class Learning for Voice Spoofing Detection
Li, L., Xue, X., Peng, H., Ren, Y., & Zhao, M. (2023) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc58517.2023.10317117 · Cited by 5
Anti-spoofing Methods for Automatic Speaker Verification System
Lavrentyeva, G., Novoselov, S., & Simonchik, K. (2017) · Communications in computer and information science · doi:10.1007/978-3-319-52920-2_17 · Cited by 5
Leow, S. J., Chng, E. S., & Lee, C.-H. (2016) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2016.7820863 · Cited by 3
“Results from the challenge [12], [13], [14], [20], [15], [23], [16], [26], [17]”
BackgroundMethodSpeaker-Specific Method of Spoofing Attack Detection Based on Anomaly Detection
Evsyukov, M. (2025) · Informatics and Automation · doi:10.15622/ia.24.1.8 · Cited by 3
DEEPFAKE AUDIO DETECTION USING YOLOV8 WITH MEL-SPECTROGRAM ANALYSIS: A CROSS-DATASET EVALUATION
Zbezhkhovska, U. (2025) · Radio Electronics Computer Science Control · doi:10.15588/1607-3274-2025-1-14 · Cited by 2
“Traditional classifiers such as Support Vector Machines, Gaussian Mixture Models, and Logistic Regression have been employed in deepfake audio detection [16–18].”
Phonetic-enhanced acoustic features: a step forward in synthetic speech detection
Fayyazi, H., & Shekofteh, Y. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21628-5 · Cited by 2
Deepfake Audio Detection with Sinc and Wavelet Filters in RawNet2
Zbezhkhovska, U., & Хапілін, О. С. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-81372-6_20 · Cited by 3
Zhou, F., Yang, H., Yan, X., & Xiong, Y. (2024) · Research Square · doi:10.21203/rs.3.rs-4446190/v1 · Cited by 2
Database dependence comparison in detection of physical access voice spoofing attacks
Chica, M., Gomez-Alanis, A., Roselló, E., Gomez, A. M., Gonzalez, J. A. S., & Peinado, A. M. (2022) · IberSPEECH · doi:10.21437/iberspeech.2022-41 · Cited by 1
“The effectiveness of DNNs has been extensively demonstrated in terms of their generalization and deep learning capabilities, as can be seen in [11], [12], [13].”
BackgroundA Simple Neural Network Based Countermeasure for Replay Attack
Pang, W., & He, Q. (2017) · International Conference on Communication and Information Systems (ICCIS) · doi:10.1145/3158233.3159308 · Cited by 1
“proposed to use DNN (deep neural network) as the basic classifiers with spectral log-filter-bank and relative phase shift features as the input features [6].”
MethodGeneralizing Voice Presentation Attack Detection to Unseen Synthetic Attacks and Channel Variation
Zhang, Y., Jiang, F., Zhu, G., Chen, X., & Duan, Z. (2023) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-19-5288-3_15 · Cited by 2
Speech Spoofing Detection Based on One-Class Residual Attention Network
Zhao, J., Bai, X., Chen, Y., Wang, F., & Zhang, P. (2023) · International Conference on Intelligent Computing and Signal Processing (ICSP) · doi:10.1109/icsp58490.2023.10248504 · Cited by 2
Image processing techniques for speech signal processing
Leow, S. J. (2018) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/73231 · Cited by 1
“The more common feature used to discriminate between natural and synthetic speech is the phase information [92, 101, 102, 103, 104, 105, 106, 107, 108].”
BackgroundMethodLu, Y.-D., Lee, H.-S., Tsao, Y., & Wang, H. (2017) · International Conference on Computational Linguistics
A One-class Model for Voice Replay Attack Detection
Cheng, X., Li, L., Xu, M., Wang, D., & Zheng, T. F. (2023) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-19-5288-3_14
Employing Discrete Fractional Wavelet Transform for Text-Dependent Speaker VerificationPreprint
Ketabi, S., Rashidi, S., & Fallah, A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4892095
Employing Discrete Fractional Wavelet Transform for Text-Dependent Speaker VerificationPreprint
Ketabi, S., Rashidi, S., & Fallah, A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5142453
TrueEar: A Lightweight and Accurate Fake Voice Detector for Mobile Devices
Baird, C., Li, K., & Lin, D. (2025) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi66578.2025.11339332
“Initial approaches often relied on hand-crafted spectral features, such as MFCC and LFCC [12], [13], along with ML methods such as GMM and SVM [14], [15] to classify the input features.”
Quantum-inspired temporal modeling with WavLM for audio spoofing detection
-, A. K. P., & Rudra, B. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21448-7
Audio Deepfake Detection: A Comprehensive Survey of Generation, Datasets, and Detection Strategies
Abbas, S. S., Al-Obaidi, S., & Al-Sultan, A. Y. (2026) · International Journal of Safety and Security Engineering · doi:10.18280/ijsse.160718
Barrera, A., Ticllacuri, C., Valerio, P., & Ticona, W. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-38806-3_3
Metadata
- Authors
- Villalba, J., Miguel, A., Ortega, A., & Lleida, E.
- Affiliations
- Universidad de Zaragoza (ES)
- Venue
- Interspeech 2015
- Publisher
- ISCA
- Published
- 2015-09-06
- Pages
- 2067-2071
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2401315748
- Cited by
- 72
- References
- 23
- Citations by year
- 2026: 3 · 2025: 6 · 2024: 4 · 2023: 8 · 2022: 3 · 2021: 6 · 2020: 5 · 2019: 8 · 2018: 6 · 2017: 14 · 2016: 9
- FWCI
- 5.45
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Interspeech (USB) (publishedVersion)
- 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
- anti-spoofing, speaker verification, deep neural network, one-class support vector machine, classifier combination, spoofing attacks
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.