CoChat

Generalized end-to-end detection of spoofing attacks to automatic speaker recognizers

Monteiro, João, Alam, Jahangir, Falk, Tiago H. · 2020 · Computer Speech & Language
Cited by 62

The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.

Abstract

As automatic speaker recognizer systems become mainstream, voice spoofing attacks are on the rise. Common attack strategies include replay, the use of text-to-speech synthesis, and voice conversion systems. While previously-proposed end-to-end detection frameworks have shown to be effective in spotting attacks for one particular spoofing strategy, they have relied on different models, architectures, and speech representations, depending on the spoofing strategy. In practice, however, one does not have a priori information regarding the strategy an attacker might employ to fool a speaker recognizer, thus it is necessary to devise approaches which are able to detect attacks regardless of the strategy employed to generate them. In this work, we introduce an end-to-end ensemble based approach such that two models – previously shown to perform well on each considered attack strategy – are trained jointly, while a third model learns how to mix their outputs yielding a single score. Experimental results with replay and text-to-speech/voice conversion attacks show the proposed ensemble method achieving similar or superior performance when compared to systems specialized on each spoofing strategy separately.

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 · 10.1016/j.csl.2020.101096

Cites

14 of 14 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: 20

  1. Bai, S., Kolter, J. Z., Koltun, V., 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv:1803.01271. · arXiv
  2. Bartlett, P. L., Helmbold, D. P., Long, P. M., 2018. Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks. arXiv:1802.06093. · DOI
  3. Ganin, 2016, Domain-adversarial training of neural networks, J. Mach. Learn. Res., 17
  4. Goodfellow, I. J., Shlens, J., Szegedy, C., 2014. Explaining and harnessing adversarial examples. arXiv:1412.6572. · arXiv
  5. Hardt, M., Ma, T., 2016. Identity matters in deep learning. arXiv:1611.04231. · arXiv
  6. He, 2009, Learning from imbalanced data, IEEE Trans. Knowl. Data Eng., 21, 1263, 10.1109/TKDE.2008.239 · DOI · Paper page
  7. Kingma, D. P., Ba, J., 2014. Adam: a method for stochastic optimization. arXiv:1412.6980. · arXiv
  8. Kinnunen, 2010, An overview of text-independent speaker recognition: from features to supervectors, Speech Commun., 52, 12, 10.1016/j.specom.2009.08.009 · DOI · Paper page
  9. Li, C., Ma, X., Jiang, B., Li, X., Zhang, X., Liu, X., Cao, Y., Kannan, A., Zhu, Z., 2017. Deep speaker: an end-to-end neural speaker embedding system. arXiv:1705.02304. · arXiv
  10. Mirza, M., Osindero, S., 2014. Conditional generative adversarial nets. arXiv:1411.1784. · arXiv
  11. Monteiro, 2019, Residual convolutional neural network with attentive feature pooling for end-to-end language identification from short-duration speech, Comput. Speech Lang., 58, 364, 10.1016/j.csl.2019.05.006 · DOI
  12. Reynolds, 2000, Speaker verification using adapted Gaussian mixture models, Digit. Signal Process., 10, 19, 10.1006/dspr.1999.0361 · DOI · Paper page
  13. Rohdin, J., Silnova, A., Diez, M., Plchot, O., Matejka, P., Burget, L., 2017. End-to-end DNN based speaker recognition inspired by I-vector and PLDA. arXiv:1710.02369. · DOI
  14. Todisco, 2016, A new feature for automatic speaker verification anti-spoofing: constant q cepstral coefficients, vol. 25, 249
  15. van den Oord, A., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., Kavukcuoglu, K., Wavenet: a generative model for raw audio. In: 9th ISCA Speech Synthesis Workshop, pp. 125–125.
  16. Weninger, F., Andrés-Ferrer, J., Li, X., Zhan, P., 2019. Listen, attend, spell and adapt: speaker adapted sequence-to-sequence asr. arXiv:1907.04916. · DOI
  17. Wu, 2018, A light CNN for deep face representation with noisy labels, IEEE Trans. Inf. Forensics Secur., 13, 2884, 10.1109/TIFS.2018.2833032 · DOI · Paper page
  18. Xue, 2014, Fast adaptation of deep neural network based on discriminant codes for speech recognition, IEEE/ACM Trans. Audio Speech Lang. Process., 22, 1713, 10.1109/TASLP.2014.2346313 · DOI · Paper page
  19. Zeinali, H., Wang, S., Silnova, A., Matějka, P., Plchot, O., 2019. But system description to voxceleb speaker recognition challenge 2019. arXiv:1910.12592. · arXiv
  20. Zhu, 2004, Product of power spectrum and group delay function for speech recognition, vol. 1, I

Cited by

See all 62

Metadata

Authors
Monteiro, J., Alam, J., & Falk, T. H.
Venue
Computer Speech & Language
Publisher
Elsevier BV
Published
2020-09
Volume
63
Pages
101096
ISSN
0885-2308 (ISSN-L)
OpenAlex
W3017138616
Cited by
62
References
14
FWCI
4.26
Type
journal article
Language
en
Open access
closed
Licence
  • www.elsevier.com/tdm/userlicense/1.0/ (tdm)
  • www.elsevier.com/legal/tdmrep-license (tdm)
Funders
Natural Sciences and Engineering Research Council of Canada

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.