CoChat

An Investigation of Deep-Learning Frameworks for Speaker Verification Antispoofing

Zhang, Chunlei, Yu, Chengzhu, Hansen, John H. L. · 2017 · IEEE Journal of Selected Topics in Signal Processing
Cited by 122

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/jstsp.2016.2647199

Cites

11 of 11 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Research works printed but not linked: 38

  1. 10.1109/TIFS.2015.2398817 · DOI · Paper page
  2. chen, 0, Robust deep feature for spoofing detection—The SJTU system for ASVspoof 2015 challenge, Proc INTERSPEECH, 2097
  3. khoury, 0, Introducing i-vectors for joint anti-spoofing and speaker verification, Proc INTERSPEECH
  4. alam, 0, Development of crim system for the automatic speaker verification spoofing and countermeasures challenge 2015, Proc INTERSPEECH, 2072
  5. patel, 0, Combining evidences from mel cepstral, cochlear filter cepstral and instantaneous frequency features for detection of natural vs. spoofed speech, Proc INTERSPEECH, 2062
  6. montavon, 0, Deep learning for spoken language identification, Proc NIPS Workshop Deep Learn Speech Recogn Relat Applicat, 1
  7. 10.1109/TASLP.2014.2339736 · DOI · Paper page
  8. 10.1109/MSP.2012.2205597 · DOI · Paper page
  9. 10.1109/ICASSP.2016.7472636 · DOI
  10. 10.1016/j.specom.2007.07.006 · DOI
  11. 10.1109/ICASSP.2013.6639067 · DOI
  12. xiao, 0, Spoofing speech detection using high dimensional magnitude and phase features: The NTU approach for ASVspoof 2015 challenge, Proc INTERSPEECH, 2052
  13. 10.1109/BTAS.2013.6712706 · DOI · Paper page
  14. matrouf, 2005, Effect of impostor speech transformation on automatic speaker recognition, Biometrics on the Internet, 37
  15. 10.1109/TPAMI.2006.244 · DOI · Paper page
  16. chingovska, 0, On the effectiveness of local binary patterns in face anti-spoofing, Proc IEEE Int Conf Biometrics Special Interest Group, 1
  17. 10.1109/ICASSP.2013.6639151 · DOI · Paper page
  18. hanilçi, 0, Classifiers for synthetic speech detection: A comparison, Proc INTERSPEECH
  19. 10.21437/Odyssey.2016-41 · DOI · Paper page
  20. 10.1109/BTAS.2015.7358783 · DOI · Paper page
  21. 10.1109/ICASSP.2016.7472652 · DOI · Paper page
  22. alegre, 0, Re-assessing the threat of replay spoofing attacks against automatic speaker verification, Proc IEEE Int Conf Biometrics Special Interest Group, 1
  23. 10.1109/APSIPA.2014.7041636 · DOI
  24. 10.1109/TASL.2012.2201472 · DOI · Paper page
  25. hautamäki, 0, I-vectors meet imitators: On vulnerability of speaker verification systems against voice mimicry, Proc INTERSPEECH, 930
  26. wu, 0, Detecting converted speech and natural speech for anti-spoofing attack in speaker recognition, Proc INTERSPEECH, 1700
  27. 10.1109/ICASSP.2015.7178810 · DOI
  28. 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
  29. 10.1109/ICASSP.2014.6853887 · DOI · Paper page
  30. 10.1109/TASLP.2014.2352154 · DOI
  31. 10.1109/BIOSIG.2016.7736933 · DOI
  32. 10.1109/ICASSP.1999.759801 · DOI
  33. 10.1109/ICASSP.2013.6639154 · DOI
  34. 2016, Information Technology Biometrics Presentation Attack Detection I J S Biometrics DIS 30107-1
  35. srivastava, 2014, Dropout: A simple way to prevent neural networks from overfitting, J Mach Learn Res, 15, 1929
  36. wester, 0, Human vs machine spoofing detection on wideband and narrowband data, Proc ISCA Interspeech
  37. zhang, 0, I-vector based physical task stress detection with different fusion strategies, Proc INTERSPEECH
  38. glorot, 0, Deep sparse rectifier neural networks, Proc 14th Int Conf Artif Intell Statist, 15, 315

Cited by

See all 122

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.