The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
ASVspoof 2017 Version 2.0: meta-data analysis and baseline enhancements
Open accessAbstract
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 The paper contains as-yet unpublished meta-data which describes recording and playback devices and acoustic environments.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-citationA Statistical Significance Test for Person Authentication
Samy Bengio, A., & Mariéthoz, J. (2004) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 182
Spoofing and countermeasures for automatic speaker verification
Evans, N., Kinnunen, T., & Yamagishi, J. (2013) · Interspeech 2013 · doi:10.21437/interspeech.2013-288 · Cited by 160 · cited 1×
“The research community has also reacted to concerns regarding the vulnerability of ASV technology to spoofing [3], also know as presentation attacks [4], namely attempts by fraudsters to interfere with the normal operation of an ASV system using specially crafted speech signals.”
BackgroundSelf-citationA study on replay attack and anti-spoofing for text-dependent speaker verification
Wu, Z., Gao, S., Cling, E. S., & Li, H. (2014) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2014.7041636 · Cited by 149 · cited 1×
“The later are intended to simulate replay spoofing attacks [9, 10].”
BackgroundThe reddots data collection for speaker recognition
Lee, K. A., Larcher, A., Wang, G., Kenny, P., Brümmer, N., Leeuwen, D. V., Aronowitz, H., Kockmann, M., Vaquero, C., Ma, B., et al. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-95 · Cited by 136 · cited 3×
“These mostly involve periods of silence, or zerovalued samples that are present in the original RedDots data [7].”
BackgroundInfluentialSelf-citationKinnunen, 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 · cited 3×
“A total of 57% of replay utterances were collected by four participants of the EU Horizon 2020-funded OCTAVE project(5) (see [8]) while the remaining 43% were collected by other contributors.”
BackgroundSelf-citationReplay Attack Detection Using DNN for Channel Discrimination
Nagarsheth, P., Khoury, E., Patil, K., & Garland, M. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-1377 · Cited by 112 · cited 1×
“[21, 22, 23, 24], all of which relate to replay detection within the scope of ASVspoof 2017.”
BackgroundFont, R., Espín, J. M., & Cano, M. J. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-450 · Cited by 109 · cited 1×
“[21, 22, 23, 24], all of which relate to replay detection within the scope of ASVspoof 2017.”
BackgroundRe-assessing the threat of replay spoofing attacks against automatic speaker verification
Alegre, F., Janicki, A., & Evans, N. (2014) · Graduate School and Research Center in Digital Science (EURECOM) · Cited by 80
Self-citationSchörkhuber, C., Klapuri, A. P., Holighaus, N., & Dörfler, M. (2014) · Cited by 77
Li, H., Hansen, J. H. L., Bonastre, J.-F., Marcel, S., Mason, J. S. D., & Eliathamby Ambikairajah, A. (2013) · Interspeech (USB) · doi:10.21437/interspeech.2013-472 · Cited by 70 · cited 1×
“While frame-level energy coefficients are used extensively in a multitude of different speech-related tasks [17, 18, 19], they have not been applied extensively to spoofing detection problem in the context of the ASVspoof challenge.”
BackgroundEnsemble Learning for Countermeasure of Audio Replay Spoofing Attack in ASVspoof2017
Ji, Z., Li, Z., Li, P., An, M., Gao, S., Wu, D., & Faru, Z. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-1246 · Cited by 45 · cited 1×
“[21, 22, 23, 24], all of which relate to replay detection within the scope of ASVspoof 2017.”
BackgroundSemi-supervised speech activity detection with an application to automatic speaker verification
Sholokhov, A., Sahidullah, M., & Kinnunen, T. (2017) · Computer Speech & Language · doi:10.1016/j.csl.2017.07.005 · Cited by 42 · cited 1×
“Also included are 95% confidence intervals calculated using the methodology explained in [25], and using the specific configuration described in [26].”
MethodSelf-citationDelgado, H., Todisco, M., Sahidullah, M., Sarkar, A. K., Evans, N., Kinnunen, T., & Tan, Z. (2016) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2016.7846262 · Cited by 40
Self-citationA Deeper Look at Gaussian Mixture Model Based Anti-Spoofing Systems
Chettri, B., & Sturm, B. L. T. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461467 · Cited by 33
Front-End Factor Analysis For Speaker Verification
Curelaru, F. (2018) · International Conference on Communications (COMM) · doi:10.1109/iccomm.2018.8453731 · Cited by 31 · cited 3×
“We have also investigated the performance of an alternative i-vector approach [18].”
Information technology. Biometric presentation attack detection
(2016) · BSI Standards · doi:10.3403/30255472 · Cited by 20
Cited by
ASVspoof 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
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
Personal Voice Assistant Security and Privacy—A Survey
Cheng, P., & Roedig, U. (2022) · Proceedings of the IEEE · doi:10.1109/jproc.2022.3153167 · Cited by 122
The Attacker’s Perspective on Automatic Speaker Verification: An Overview
Das, R. K., Tian, X., Kinnunen, T., & Li, H. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-1052 · Cited by 99
Self-citation
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.