An Investigation of Deep-Learning Frameworks for Speaker Verification Antispoofing
The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
In this study, we explore the use of deep-learning approaches for spoofing detection in speaker verification. Most spoofing detection systems that have achieved recent success employ hand-craft features with specific spoofing prior knowledge, which may limit the feasibility to unseen spoofing attacks. We aim to investigate the genuine-spoofing discriminative ability from the back-end stage, utilizing recent advancements in deep-learning research. In this paper, alternative network architectures are exploited to target spoofed speech. Based on this analysis, a novel spoofing detection system, which simultaneously employs convolutional neural networks (CNNs) and recurrent neural networks (RNNs) is proposed. In this framework, CNN is treated as a convolutional feature extractor applied on the speech input. On top of the CNN processed output, recurrent networks are employed to capture long-term dependencies across the time domain. Novel features including Teager energy operator critical band autocorrelation envelope, perceptual minimum variance distortionless response, and a more general spectrogram are also investigated as inputs to our proposed deep-learning frameworks. Experiments using the ASVspoof 2015 Corpus show that the integrated CNN-RNN framework achieves state-of-the-art single-system performance. The addition of score-level fusion further improves system robustness. A detailed analysis shows that our proposed approach can potentially compensate for the issue due to short duration test utterances, which is also an issue in the evaluation corpus.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“, Deep neural networks(DNNs), Convolutional Neural networks (CNNs) and Recurrent Neural Networks (RNNs)) for spoofing detection [34]– [37].”
BackgroundFront-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
Speaker 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
Self-citationSpoofing 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 7×
“The most common and effective strategy is to build a stand-alone spoofing detection system before the speaker verification system [2], [6].”
BackgroundMethodInfluentialNonlinear feature based classification of speech under stress.
Zhou, G., Hansen, J. H. L., & Kaiser, J. F. (2001) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.905995 · Cited by 409
Self-citationA comparison of features for synthetic speech detection
Sahidullah, M., Kinnunen, T., & Hanilçi, C. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-472 · Cited by 382
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
“Preventing replay attacks on speaker verification systems,”
Villalba, J., & Lleida, E. (2011) · 2011 Carnahan Conference on Security Technology · doi:10.1109/ccst.2011.6095943 · Cited by 108 · cited 1×
“Previous studies have shown that the false acceptance rate of state-of-the-art speaker verification systems has been significantly increased with replayed speech, impersonation, synthesized speech, voice conversion and artificial signals as spoofing attacks [2], [6], [11]–[17].”
BackgroundSpoofing detection with DNN and one-class SVM for the ASVspoof 2015 challenge
Villalba, J., Miguel, A., Ortega, A., & Lleida, E. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-468 · Cited by 72
Alegre, F., Vipperla, R., & Evans, N. (2012) · Interspeech 2012 · doi:10.21437/interspeech.2012-462 · Cited by 43 · cited 1×
“Previous studies have shown that the false acceptance rate of state-of-the-art speaker verification systems has been significantly increased with replayed speech, impersonation, synthesized speech, voice conversion and artificial signals as spoofing attacks [2], [6], [11]–[17].”
Background
Research works printed but not linked: 38
- 10.1109/TIFS.2015.2398817 · DOI · Paper page
- chen, 0, Robust deep feature for spoofing detection—The SJTU system for ASVspoof 2015 challenge, Proc INTERSPEECH, 2097
- khoury, 0, Introducing i-vectors for joint anti-spoofing and speaker verification, Proc INTERSPEECH
- alam, 0, Development of crim system for the automatic speaker verification spoofing and countermeasures challenge 2015, Proc INTERSPEECH, 2072
- patel, 0, Combining evidences from mel cepstral, cochlear filter cepstral and instantaneous frequency features for detection of natural vs. spoofed speech, Proc INTERSPEECH, 2062
- montavon, 0, Deep learning for spoken language identification, Proc NIPS Workshop Deep Learn Speech Recogn Relat Applicat, 1
- 10.1109/TASLP.2014.2339736 · DOI · Paper page
- 10.1109/MSP.2012.2205597 · DOI · Paper page
- 10.1109/ICASSP.2016.7472636 · DOI
- 10.1016/j.specom.2007.07.006 · DOI
- 10.1109/ICASSP.2013.6639067 · DOI
- xiao, 0, Spoofing speech detection using high dimensional magnitude and phase features: The NTU approach for ASVspoof 2015 challenge, Proc INTERSPEECH, 2052
- 10.1109/BTAS.2013.6712706 · DOI · Paper page
- matrouf, 2005, Effect of impostor speech transformation on automatic speaker recognition, Biometrics on the Internet, 37
- 10.1109/TPAMI.2006.244 · DOI · Paper page
- chingovska, 0, On the effectiveness of local binary patterns in face anti-spoofing, Proc IEEE Int Conf Biometrics Special Interest Group, 1
- 10.1109/ICASSP.2013.6639151 · DOI · Paper page
- hanilçi, 0, Classifiers for synthetic speech detection: A comparison, Proc INTERSPEECH
- 10.21437/Odyssey.2016-41 · DOI · Paper page
- 10.1109/BTAS.2015.7358783 · DOI · Paper page
- 10.1109/ICASSP.2016.7472652 · DOI · Paper page
- alegre, 0, Re-assessing the threat of replay spoofing attacks against automatic speaker verification, Proc IEEE Int Conf Biometrics Special Interest Group, 1
- 10.1109/APSIPA.2014.7041636 · DOI
- 10.1109/TASL.2012.2201472 · DOI · Paper page
- hautamäki, 0, I-vectors meet imitators: On vulnerability of speaker verification systems against voice mimicry, Proc INTERSPEECH, 930
- wu, 0, Detecting converted speech and natural speech for anti-spoofing attack in speaker recognition, Proc INTERSPEECH, 1700
- 10.1109/ICASSP.2015.7178810 · DOI
- wu, 0, A study on spoofing attack in state-of-the-art speaker verification: The telephone speech case, Proc Asia-Pacific Signal Inf Proc Assoc Annu Summit Conf, 1
- 10.1109/ICASSP.2014.6853887 · DOI · Paper page
- 10.1109/TASLP.2014.2352154 · DOI
- 10.1109/BIOSIG.2016.7736933 · DOI
- 10.1109/ICASSP.1999.759801 · DOI
- 10.1109/ICASSP.2013.6639154 · DOI
- 2016, Information Technology Biometrics Presentation Attack Detection I J S Biometrics DIS 30107-1
- srivastava, 2014, Dropout: A simple way to prevent neural networks from overfitting, J Mach Learn Res, 15, 1929
- wester, 0, Human vs machine spoofing detection on wideband and narrowband data, Proc ISCA Interspeech
- zhang, 0, I-vector based physical task stress detection with different fusion strategies, Proc INTERSPEECH
- glorot, 0, Deep sparse rectifier neural networks, Proc 14th Int Conf Artif Intell Statist, 15, 315
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
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
A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection
Wang, X., & Yamagishi, J. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-702 · Cited by 137
A deep learning framework for audio deepfake detection
Khochare, J., Joshi, C., Yenarkar, B., Suratkar, S., & Kazi, F. (2022) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-021-06297-w · Cited by 135
Evaluation 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
Metadata
- Authors
- Zhang, C., Yu, C., & Hansen, J. H. L.
- Venue
- IEEE Journal of Selected Topics in Signal Processing
- Published
- 2017-06
- Volume
- 11
- Issue
- 4
- Pages
- 684-694
- ISSN
- 1932-4553 (ISSN-L)
- 1941-0484
- OpenAlex
- W2576165910
- Cited by
- 122
- References
- 11
- FWCI
- 8.36
- Type
- journal article
- Language
- en
- Open access
- closed
- Funders
- Air Force Research Laboratory (FA8750-15-1-0205)
- University of Texas at Dallas
- Distinguished University Chair in Telecommunications Engineering
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.