ASVspoof 2017 Version 2.0: meta-data analysis and baseline enhancements
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
The now-acknowledged vulnerabilities of automatic speaker verification (ASV) technology to spoofing attacks have spawned interests to develop so-called spoofing countermeasures. By providing common databases, protocols and metrics for their assessment, the ASVspoof initiative was born to spear-head research in this area. The first competitive ASVspoof challenge held in 2015 focused on the assessment of countermeasures to protect ASV technology from voice conversion and speech synthesis spoofing attacks. The second challenge switched focus to the consideration of replay spoofing attacks and countermeasures. This paper describes Version 2.0 of the ASVspoof 2017 database which was released to correct data anomalies detected post-evaluation. The paper contains as-yet unpublished meta-data which describes recording and playback devices and acoustic environments. These support the analysis of replay detection performance and limits. Also described are new results for the official ASVspoof baseline system which is based upon a constant Q cesptral coefficient frontend and a Gaussian mixture model backend. Reported are enhancements to the baseline system in the form of log-energy coefficients and cepstral mean and variance normalisation in addition to an alternative i-vector backend. The best results correspond to a 48% relative reduction in equal error rate when compared to the original baseline system.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Citations
Cites
Front-End Factor Analysis for Speaker Verification
Dehak, N., Kenny, P. J., Dehak, R., Dumouchel, P., & Ouellet, P. (2011) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2010.2064307 · Cited by 3,549 · cited 3×
“The alternative i-vector backend [18] uses a universal background model of 64 components which is trained on the ASVspoof 2017 training partition.”
BackgroundMethodAn overview of text-independent speaker recognition: From features to supervectors
Kinnunen, T., & Li, H. (2010) · Speech Communication · doi:10.1016/j.specom.2009.08.009 · Cited by 1,434 · cited 1×
“Automatic speaker verification (ASV) [1, 2] has matured considerably over the last few decades.”
BackgroundSelf-citationCalculation 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 6×
“CQCC features are derived using the constant Q transform (CQT) [15, 16], a perceptually motivated time-frequency analysis tool and alternative to the short-term Fourier transform (STFT).”
MethodInfluentialScore Normalization for Text-Independent Speaker Verification Systems
Auckenthaler, R., Carey, M., & Lloyd-Thomas, H. (2000) · Digital Signal Processing · doi:10.1006/dspr.1999.0360 · Cited by 698 · cited 1×
“Cepstral mean and variance normalization (CMVN) [20] is an efficient normalisation technique used to remove nuisance channel effects which might otherwise degrade the performance of a variety of different approaches to automatic speech and speaker recognition.”
MethodSpeaker Recognition by Machines and Humans: A tutorial review
Hansen, J. H. L., & Hasan, T. (2015) · IEEE Signal Processing Magazine · doi:10.1109/msp.2015.2462851 · Cited by 621 · cited 1×
“Automatic speaker verification (ASV) [1, 2] has matured considerably over the last few decades.”
BackgroundThe 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 6×
“Differences between systems B01 and B02 lie only in the use of training (T) or pooled training and development data (T+D); the systems are otherwise the same.”
BackgroundInfluentialSelf-citationConstant 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 · cited 18×
“CQCC features are derived using the constant Q transform (CQT) [15, 16], a perceptually motivated time-frequency analysis tool and alternative to the short-term Fourier transform (STFT).”
BackgroundMethodInfluentialSelf-citationA 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 17×
“CQCC features are derived using the constant Q transform (CQT) [15, 16], a perceptually motivated time-frequency analysis tool and alternative to the short-term Fourier transform (STFT).”
BackgroundMethodInfluentialSelf-citationAudio replay attack detection with deep learning frameworks
Lavrentyeva, G., Novoselov, S., Malykh, E., Kozlov, A., Kudashev, O., & Shchemelinin, V. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-360 · Cited by 292 · cited 1×
“[21, 22, 23, 24], all of which relate to replay detection within the scope of ASVspoof 2017.”
BackgroundText-dependent speaker verification: Classifiers, databases and RSR2015
Larcher, A., Lee, K. A., Ma, B., & Li, H. (2014) · Speech Communication · doi:10.1016/j.specom.2014.03.001 · Cited by 237 · cited 3×
“It uses a Mel-frequency cepstral coefficient (MFCC) front-end and a 512-component UBM trained using RSR2015 [14] and TIMIT(7) databases.”
MethodInfluentialSelf-citation
Cited by
Items 101–178 of 178
The Clever Hans Effect in Voice Spoofing Detection
Chettri, B. (2023) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt54892.2023.10022624 · Cited by 10
“See [37] and [4] for more details on ASVspoof 2017 and 2019 baseline systems.”
BackgroundDiscriminative feature based on FWMW for playback speech detection
Yang, J., Liu, L., & He, Q. (2019) · Electronics Letters · doi:10.1049/el.2019.1025 · Cited by 6
Voice liveness detection under feature fusion and cross-environment scenario
Garg, S., & Mankad, S. H. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09281-y · Cited by 5
Significance of CMVN for Replay Spoof Detection
Patil, A. T., & Patil, H. A. (2020) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · Cited by 6
Capsule Network based End-to-end System for Detection of Replay Attacks
Ouyang, M., Das, R. K., Yang, J., & Li, H. (2021) · International Symposium on Chinese Spoken Language Processing (ISCSLP) · doi:10.1109/iscslp49672.2021.9362111 · Cited by 8
“The second edition ASVspoof 2017 projected the threat of replay attacks in uncontrolled setup [11].”
BackgroundReplay-Attack Detection Using Features With Adaptive Spectro-Temporal Resolution
Liu, M., Wang, L., Lee, K. A., Chen, X., & Dang, J. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414250 · Cited by 6
“In this regard, the effectiveness of Constant Q cepstral coefficients (CQCC) feature [7, 8], with a realization of variable resolution, has been well acknowledged in this task.”
BackgroundSelf-citationSingh, S., Khoria, K., & Patil, H. A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87802-3_58 · Cited by 6
Altuwayjiri, S. M., Bchir, O., & Ismail, M. M. B. (2022) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2022.0130596 · Cited by 6
“The training set had 1507 genuine and 1507 replay files, the development set had 760 genuine and 950 replay files, and the evaluation set had 1298 genuine and 12,008 replay files [13].”
Gupta, P., Chodingala, P. K., & Patil, H. A. (2022) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco55093.2022.9909533 · Cited by 5
“organized in the past during INTERSPEECH conferences, such as ASVspoof 2015 [5], ASVspoof 2017 [6], ASVspoof 2019 [7], and ASVspoof 2021 [8] to develop countermeasures against spoofing attacks on ASV systems.”
BackgroundBiologically Inspired Adaptive-Q Filterbanks for Replay Spoofing Attack Detection
Wickramasinghe, B., Eliathamby Ambikairajah, A., & Epps, J. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1535 · Cited by 5
“Auditory based concepts such as constant-Q transform which provides time-frequency resolution similar to that of the auditory system [3] and auditory filterbanks [17] have also been used in replay attack detection systems.”
BackgroundMethodInfluentialIntegration of CQCC and MFCC based Features for Replay Attack Detection
Chaudhari, A., & Shedge, D. (2022) · International Conference on Emerging Smart Computing and Informatics (ESCI) · doi:10.1109/esci53509.2022.9758391 · Cited by 7
Is Audio Spoof Detection Robust to Laundering Attacks?
Ali, H., Subramani, S., Sudhir, S., Varahamurthy, R., & Malik, H. M. A. (2024) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/3658664.3659656 · Cited by 11
“The audio spoof detection methodologies described in Section 3 have predominantly been evaluated on ASVSpoof (2015, 2017, 2019, 2021) datasets [5, 24, 25, 28].”
MethodData augmentation and post selection for improved replay attack detection
Zhao, Y., Togneri, R. B., & Sreeram, V. (2019) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc47483.2019.9023070 · Cited by 5
“Table I shows the statistics of the ASVspoof 2017 2.0 corpus [9].”
BackgroundInfluentialWang, Y., Liu, Y., Gao, P., & Wang, Y. (2021) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1145/3458380.3458426 · Cited by 4
“The detailed parameters of CQCC features are consistent with the baseline [16], while 12 IMFCC coefficients plus the energy term is extracted for each frame, and we have 2 more sets corresponding to the delta and the double delta values, which would combine to give a feature vector of length 39.”
MethodInfluentialLightCvT: Audio Forgery Detection via Fusion of Light CNN and Transformer
Liu, C., Li, J., Duan, J., Shen, H., & Huang, H. (2021) · International Conference on Computing and Pattern Recognition (ICCPR) · doi:10.1145/3497623.3497639 · Cited by 4
“ASVspoof 2019 is an extended version of the previous challenges ASVspoof 2015 [35] and ASVspoof 2017 [36], including two evaluation criteria.”
BackgroundNon-Cepstral Uncertainty Vector for Replay Spoofed Speech Detection
Patil, H. A., Acharya, R., Patil, A. T., & Gupta, P. (2022) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco55093.2022.9909946 · Cited by 4
“0 database, which is based on RedDots database, having a collection of genuine and spoof utterances for several replay sessions and different configurations [17].”
BackgroundLow-Key Shallow Learning Voice Spoofing Detection System
Ali, D., Al–Shareeda, S., & Abdulrahman, N. (2022) · IEEE Middle East and North Africa Communications Conference (MENACOMM) · doi:10.1109/menacomm57252.2022.9998199 · Cited by 4
“According to the ASVspoof2017 challenge, [2], an M = 512 component is sufficient for the scope of voice analysis application [14].”
BackgroundHernández-Nava, C. A., Rincón-García, E. A., Lara-Velázquez, P., de-los-Cobos-Silva, S. G., Andrade, M. Á. G., & Mora-Gutiérrez, R. A. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1740 · Cited by 8
Feature Fusion and Voiceprint-Based Access Control for Wireless Insulin Pump Systems
Ping, Y., Hao, B., Hei, X., Tu, Y., Du, X., & Wu, J. (2019) · IEEE Access · doi:10.1109/access.2019.2937805 · Cited by 5
“0 [52] and purge the evaluation protocol file by removing the file items which do not exist in the Evaluation subset.”
BackgroundAn Adaptive-Q Cochlear Model for Replay Spoofing Detection
Gunendradasan, T., Eliathamby Ambikairajah, A., Epps, J., & Li, H. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-2361 · Cited by 4
“The recent experimental results released on the ASVspoof 2015 and 2017 challenge demonstrate that the replay attack is most difficult to be detected [6], [7].”
MethodResultInvestigating Feature Reduction Strategies for Replay Antispoofing in Voice Biometrics
Mankad, S. H., Garg, S., Patel, M., & Adalja, H. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-34872-4_44 · Cited by 4
Subband Channel Selection using TEO for Replay Spoof Detection in Voice Assistants
Kotta, H., Patil, A. T., Acharya, R., & Patil, H. A. (2020) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · Cited by 8
Robust Multilingual Audio Deepfake Detection Through Hybrid Modeling
Mawalim, C. O., Wang, Y., Adila, A., Okada, S., & Unoki, M. (2025) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/3733102.3736706 · Cited by 4
“One of the most widely adopted benchmark datasets is provided by the ASVspoof Challenge [9, 20, 38, 39, 41].”
Contreras, R. C., Viana, M. S., & Guido, R. C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42508-0_27 · Cited by 3
Data Quality as Predictor of Voice Anti-Spoofing Generalization
Chettri, B., Hautamäki, R. G., Sahidullah, M., & Kinnunen, T. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1180 · Cited by 9
Self-citationWu, Q., Xiong, S., & Zhu, Z. (2021) · IEEE Access · doi:10.1109/access.2021.3098058 · Cited by 3
“It was found that energy information is useful for replay speech detection in the work [21].”
BackgroundMethodConstant-Q Deep Coefficients for Playback Attack Detection
Yang, J., Xu, L., & Bo, R. E. N. (2020) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2019edl8115 · Cited by 3
“ASVspoof 2017 V2 [8] released in 2018, which is constituted by three subsets: training set, development and evaluation set, Table 1 gives some details of ASVspoof 2017 V2.”
BackgroundUsing Multi-Resolution Feature Maps with Convolutional Neural Networks for Anti-Spoofing in ASV
Wang, Q., Lee, K. A., & Koshinaka, T. (2020) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2020-20 · Cited by 4
“ASVspoof 2015 [5] focused on promoting awareness and fostering solutions to spoofing attacks generated from speech synthesis and voice conversion, while ASVspoof 2017 [6] focused on replay attacks.”
BackgroundSelf-citationCross-Teager Energy Cepstral Coefficients for Replay Spoof Detection on Voice Assistants
Acharya, R., Kotta, H., Patil, A. T., & Patil, H. A. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414847 · Cited by 4
An Investigation about the Scalability of the Spoofing Detection System
Suthokumar, G., Sriskandaraja, K., Sethu, V., Wijenayake, C. A., & Ambikairajah, E. (2018) · International Conference on Information and Automation for Sustainability (ICIAfS) · doi:10.1109/iciafs.2018.8913369 · Cited by 6
“0 database [20] was released early this year as a subsequent version of original ASV Spoof 2017 Challenge database version 1.”
Voice Liveness Detection KYC Project: Distinguishing Genuine and Spoofed Voices Using Deep Learning
Eyidogan, B., Özsoy, G., Khatamino, P., Avvad, B., Şen, E., & Kumlu, D. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.02.261 · Cited by 2
Improved Processing of LP-residual Information for Detection of Replay Signals
Dutta, K., Singh, M., & Pati, D. (2019) · IEEE India Conference · doi:10.1109/indicon47234.2019.9030321 · Cited by 2
Comparative study of data augmentation methods for fake audio detection
Park, K., & Kwak, I. (2023) · Korean Journal of Applied Statistics · doi:10.5351/kjas.2023.36.2.101 · Cited by 2
Spoofed Speech Detection with Weighted Phase Features and Convolutional Networks
Dişken, G. (2022) · Archives of Acoustics · doi:10.24425/aoa.2022.141648 · Cited by 2
“The version 1.0 data includes data anomalies such as zero-valued samples and silence periods, which affects the detection performance ( Delgado et al ., 2018).”
InfluentialChaudhari, A., Shedge, D., Bairagi, V. K., & Nanthaamornphong, A. (2024) · Symmetry · doi:10.3390/sym16070788 · Cited by 2
“Afterwards, ASVspoof 2017 version 2.0 was made available, with certain meta-data modi fi cations [2].”
BackgroundMethodInfluentialContreras, R. C., Heck, G. L., Viana, M. S., Bongarti, M. A. D. S., Zamani, H., & Guido, R. C. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-7181-3_20 · Cited by 3
A Supervised Learning Classifier for Replayed Voice Attack Detection
Abdulrahman, N., Al–Shareeda, S., & Ali, D. (2022) · International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT) · doi:10.1109/3ict56508.2022.9990744 · Cited by 2
Replay spoofing countermeasures using high spectro-temporal resolution features
Alluri, K. N. R. K. R., & Vuppala, A. K. (2019) · International Journal of Speech Technology · doi:10.1007/s10772-019-09602-z · Cited by 2
“Several studies conducted on AVspoof data-set are reported in (Korshunov et al. 2016; Korshu-nov and Marcel 2016; Todisco et al. 2017; Paul et al. 2017; Alluri et al. 2017a) and on ASVspoof 2017 are reported in (Font et al. 2017; Patil et al. 2017; Alluri et al. 2017b; Cai et al. 2017; Chen et al.…”
BackgroundMethodResultInfluentialAn analysis of speaker dependent models in replay detection
Suthokumar, G., Sriskandaraja, K., Sethu, V., Ambikairajah, E., & Li, H. (2020) · APSIPA Transactions on Signal and Information Processing · doi:10.1017/atsip.2020.9 · Cited by 7
An adaptive transmission line cochlear model based front-end for replay attack detection
Gunendradasan, T., Eliathamby Ambikairajah, A., Epps, J., Sethu, V., & Li, H. (2021) · Speech Communication · doi:10.1016/j.specom.2021.06.004 · Cited by 2
Smartphone Audio Replay Attacks Dataset
Mandalapu, H., Ramachandra, R., & Busch, C. (2021) · International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf50991.2021.9465096 · Cited by 2
Chaudhari, A., & Shedge, D. K. (2021) · International Conference for Emerging Technology (INCET) · doi:10.1109/incet51464.2021.9456331 · Cited by 2
“TABLE II: The details of ASVspoof version 2 database [18], [24], [25]”
BackgroundMankad, S. H., Garg, S., Patel, V., & Patwa, N. (2023) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-023-04684-9 · Cited by 2
“Three approaches are implemented to perform this multi-class classification: (i) naive approach (ii) threat based approach, motivated from Delgado et al. (2018) (iii) agglomerative clustering based approach.”
InfluentialChaudhari, A. A., Shedge, D. K., & Bairagi, V. K. (2023) · International Journal of Electrical and Electronics Engineering · doi:10.14445/23488379/ijeee-v10i10p112 · Cited by 2
“As mentioned in [34], natural statements are replayed and recorded using various diverse devices and acoustic environments for obtaining spoofed utterances.”
BackgroundMethodInfluentialDiscriminate Natural versus Loudspeaker Emitted Speech
Le, T., Gilberton, P., & Duong, N. Q. K. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683227 · Cited by 2
Robust Spoofed Speech Detection with Denoised I-vectors
Dişken, G. (2023) · GAZI UNIVERSITY JOURNAL OF SCIENCE · doi:10.35378/gujs.1062788 · Cited by 1
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
Significance of Quadrature and In-Phase Components for Synthetic Spoofed Speech Detection
Gupta, P., Chodingala, P. K., & Patil, H. A. (2022) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipaasc55919.2022.9980241 · Cited by 2
“In order to address the vulnerabilities of ASV systems, several challenges were organized during INTERSPEECH in 2015, 2017, 2019, and 2021 [2], [3], [4], [5].”
BackgroundNoise-Robust Spoofed Speech Detection Using Discriminative Autoencoder
Dişken, G., & TÜFEKCİ, Z. (2023) · Celal Bayar Üniversitesi Fen Bilimleri Dergisi · doi:10.18466/cbayarfbe.1132319 · Cited by 1
Linear Prediction Networks for Residual based Replay Speech Detection
Veesa, S., Badugu, V. K., & Singh, M. (2025) · IEEE India Council International Subsections Conference (INDISCON) · doi:10.1109/indiscon66021.2025.11254201 · Cited by 1
“[ 19] baseline and Graph frequency cepstral coefficients(GFCC) GFCC+GMM (10.96”
InfluentialOn The Role of Room Acoustics in Audio Presentation Attack Detection
Gaubitch, N. D., & Looney, D. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448243 · Cited by 3
“Interestingly, it was observed in [2] that features based on the frame-level log-energy greatly improved PAD performance.”
BackgroundFake Speech Detection in Domain Variability Scenario
N, R. S. T., Agarwal, A., & Prasanna, S. R. M. (2024) · National Conference on Communications · doi:10.1109/ncc60321.2024.10485922 · Cited by 1
Improving Voice Spoofing Detection Through Extensive Analysis of Multicepstral Feature Reduction
de Souza, L. M., Guido, R. C., Contreras, R. C., Viana, M. S., & Bongarti, M. A. D. S. (2025) · Sensors · doi:10.3390/s25154821 · Cited by 5
“The dataset adopted for the experiments is the second edition of ASVspoof 2017 [58], which comprises a diverse collection of genuine and spoofed utterances.”
Speech Demodulation-based Techniques for Replay and Presentation Attack Detection
Kamble, M. R., Sai, P. A. K., Krishna, M. V. S., Patil, A. T., Acharya, R., & Patil, H. A. (2019) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc47483.2019.9023046 · Cited by 1
“The detailed statistics of the database is given in [9], [36], [37].”
BackgroundChadha, A. N., Abdullah, A. B., & Angeline, L. (2021) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2021.0120894 · Cited by 3
“Furthermore, the CFCCIF, CQCC based features were also proposed; out of which CQCCs are considered to outperform in the ASV Spoof 2017 challenge [13], [14].”
MethodBharath, K. P., Mathew, D., Naidu, R. C., & Rajesh Kumar, M. (2021) · Innovations in Power and Advanced Computing Technologies (i-PACT) · doi:10.1109/i-pact52855.2021.9696930 · Cited by 1
Leveraging Kalmogorov-Arnold Networks for Voice Liveness Detection in Anti-Spoofing SystemsPreprint
Shah, A. J., & Kamble, M. R. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5379668 · Cited by 1
Cheng, Z., & Jiang, Y. (2020) · International Conference on Computer Communication and Network Security (CCNS) · doi:10.1109/ccns50731.2020.00023
Spectral Root Features for Replay Spoof Detection in Voice Assistants
Patil, A. T., Kotta, H., Acharya, R., & Patil, H. A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87802-3_46
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
Improving Computational Efficiency of Voice Anti-Spoofing Models
Yang, J., Xia, B., Bailey, J., Gong, Y., Templeton, J. M., & Poellabauer, C. (2023) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass58611.2023.00014
“All experiments were conducted using the ASVspoof2017 Challenge 2.0 dataset [33].”
MethodInfluentialMulti-environment Audio Dataset Using RPi-Based Sound Logger
Govilkar, G., Shaikh, K. B. T., & Gopalkrishnan, N. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-48774-3_6
INCREASING ROBUSTNESS OF I-VECTORS VIA MASKING: A CASE STUDY IN SYNTHETIC SPEECH DETECTION
Aydın, B., & Dişken, G. (2024) · Uludağ University Journal of The Faculty of Engineering · doi:10.17482/uumfd.1311113
“Once the i-vector is extracted, various compensation and dimensionality reduction techniques such as within-class covariance normalization (WCCN), linear discriminant analysis (LDA), and length normalization can be applied ((Dehak et al., 2011), (Delgado et al. 2018)).”
MethodEPTLENet: Replay Attack Detection with Efficient Parameter Transfer Learning Based on ERes2Net
Qian, Q., Kuang, Y.-L., & Yue, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5606-3_35
What's the Real: A Novel Design Philosophy for Robust AI-Synthesized Voice Detection
Xuan, H., Liu, X., Tan, Y., Liu, G., Li, S., Niu, W., Zhou, R., & Zhou, X. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681100 · Cited by 2
“In 2019, Kaneko et al. [21] proposed CycleGAN-VC2, which optimizes the adversarial loss and discriminator based on CycleGAN-VC.”
Contreras, R. C., Campanharo, A. F., Viana, M. S., Bongarti, M. A. D. S., & Guido, R. C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-84356-3_19
Wang, T., Borsdorf, M., Zhang, Q., Xu, L., & Shao, X. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5252047
An Efficient Voice Replay Antispoofing Method
Aljasem, M., Javed, A., Abouheaf, M., & Mayyas, M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-1758-6_16
MT-EPTNet: Multi-task Acoustic Scene Classification with Efficient Parameter Tuning
Qian, Q., Yue, Y., Kuang, Y., Wang, H., Cui, Y., Wu, B., Ran, L., & Wang, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6599-0_17
$\beta$-Order Energy-Weighting Modulation on Spectral Bins for Replay Speech Detection
Yang, J., You, C. H., & Das, R. K. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3587454
“In this subsection, we are to discuss the application of energy information in the feature extraction for RSD by comparing our proposed EW modulation features with traditional energy-appended features [34].”
InfluentialModified Heterogeneous Auto-Similarities of Characteristic for Voice Spoofing Attack Detection
Meriem, F., Mokdad, F., Karima, A. S., & Naima, E.-K. (2025) · International Conference on Electronics, Energy and Measurement (IC2EM) · doi:10.1109/ic2em63689.2025.11101037
“Unlike the post-evaluation CQCC baseline system [15] which employs Cepstral Mean Variance Normalization (CMVN), our baseline implementation excludes this normalization technique.”
Venaik, U., Kushwaha, A., Nabeel Koya, A., & Shah, R. R. (2025) · doi:10.1145/3746265.3759675 · Cited by 4
“However, the rapid rise of text-to-speech (TTS) and voice conversion technologies has revealed new vulnerabilities in these systems [41], motivating research on audio-based spoof detection through the ASVspoof challenges [8, 10, 36, 44].”
AI Speaks, but does it Feel? Detecting Synthetic Voices with Emotional Cues
Bhardwaj, N., & Sankar, M. S. A. (2025) · IEEE International Conference on System Engineering and Technology (ICSET) · doi:10.1109/icset65917.2025.11283688
“The ASVspoof challenge, launched in 2015 and held again in 2021 and 2023, aims to advance research in spoofing detection and countermeasures [8], [9].”
MultiSiFer: Detecting Multiple-Speaker Fake Voice Without Speaker-Irrelative Features
Liu, X., Xuan, H., Yu, Z., Zhang, Z., Fei, Q., & Zhou, Q. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3648834
“The works [7], [8], [9], [10] show that the ASVspoof datasets [11], [12], [13], which are the most widely used datasets in fake voice detection, have a serious data feature distribution flaw.”
A Hybrid EMD-CQCC Based Features for Replay Attack Detection
Fahad, M. S., Ranjan, A., Kumari, A., Deepak, A., Ahmad, K., & Kumar, S. (2025) · International Conference on Cognitive, Green and Ubiquitous Computing (IC-CGU) · doi:10.1109/ic-cgu67042.2025.11337996
“The ASVspoof 2017 Version 2 dataset, introduced as part of the ASVspoof Challenge 2017 [3], is employed in this study.”
Secure, efficient automatic speaker verification for embedded applications
Valenti, G. (2019) · theses.fr (ABES) · doi:10.70675/29594222z8f7dz4a52za585z03b3ff50ea21
-Combining Liveness Detection and Fusion Method for Multimodal Face and Voice Biometrics Recognition
Christianto, A., & Kusuma, G. P. (2026) · International Conference on Intelligent Engineering and Next-Gen Healthcare Systems (IEHNS) · doi:10.1109/iehns68708.2026.11606907
“The face biometrics are obtained from the CASIA-FASD dataset [14] with the combination of voice biometrics obtained from the ASVSpoof-2017 dataset [15].”
LP Residual based Extended Residual Constant Q Cepstral Coefficients for Replay Speech Detection
Veesa, S., Badugu, V. K., & Singh, M. (2026) · IEEE International Conference on Instrumentation (INSTCon) · doi:10.1109/instcon69741.2026.11691684
“All three features extraction methods involves CQT based cepstral processing configuration provided in the study [21].”
Influential
Metadata
- Authors
- Delgado, H., Todisco, M., Sahidullah, M., Evans, N., Kinnunen, T., Lee, K. A., & Yamagishi, J.
- Affiliations
- EURECOM (FR)
- Institut national de recherche en sciences et technologies du numérique (FR)
- University of Eastern Finland (FI)
- NEC (Japan) (JP)
- National Institute of Informatics (JP)
- ORCID
- Venue
- The Speaker and Language Recognition Workshop (Odyssey 2018)
- Publisher
- ISCA
- Published
- 2018-06-26
- Pages
- 296-303
- OpenAlex
- W2807325376
- Cited by
- 178
- References
- 26
- Citations by year
- 2026: 2 · 2025: 17 · 2024: 15 · 2023: 20 · 2022: 18 · 2021: 27 · 2020: 31 · 2019: 34 · 2018: 14
- FWCI
- 10.78
- Type
- conference paper
- Language
- en
- Open access
- green
- inria.hal.science
- Licence
- other-oa
- Locations
- The Speaker and Language Recognition Workshop (Odyssey) (publishedVersion)
- HAL (submittedVersion, other-oa)
- Graduate School and Research Center in Digital Science (EURECOM) (submittedVersion)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, other-oa)
- 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
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.