CoChat

Graph Attention Networks for Anti-Spoofing

Open access
Tak, Hemlata, Jung, Jee-weon, Patino, Jose, Todisco, Massimiliano, Evans, Nicholas · 2021 · Interspeech 2021

The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.

Abstract

The cues needed to detect spoofing attacks against automatic speaker verification are often located in specific spectral sub-bands or temporal segments. Previous works show the potential to learn these using either spectral or temporal self-attention mechanisms but not the relationships between neighbouring sub-bands or segments. This paper reports our use of graph attention networks (GATs) to model these relationships and to improve spoofing detection performance. GATs leverage a self-attention mechanism over graph structured data to model the data manifold and the relationships between nodes. Our graph is constructed from representations produced by a ResNet. Nodes in the graph represent information either in specific sub-bands or temporal segments. Experiments performed on the ASVspoof 2019 logical access database show that our GAT-based model with temporal attention outperforms all of our baseline single systems. Furthermore, GAT-based systems are complementary to a set of existing systems. The fusion of GAT-based models with more conventional countermeasures delivers a 47% relative improvement in performance compared to the best performing single GAT system.

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 · 10.21437/interspeech.2021-993

Cites

43 of 43 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Proposed GAT approach to anti-spoofing. Frequency-masked, high-resolution log-linear filterbank (LFB) features extracted from an input utterance are fed to a ResNet-18 network to extract high-level representations. The ResNet-18 feature map output is used to construct a graph with nodes 𝑛 after averaging across time, (spectral attention, GAT-S ) or frequency (temporal attention, GAT-T ). We use a GAT layer followed by projection and readout to predict whether the input utterance is bona fide or spoofed.
Figure 1 Proposed GAT approach to anti-spoofing. Frequency-masked, high-resolution log-linear filterbank (LFB) features extracted from an input utterance are fed to a ResNet-18 network to extract high-level representations. The ResNet-18 feature map output is used to construct a graph with nodes 𝑛 after averaging across time, (spectral attention, GAT-S ) or frequency (temporal attention, GAT-T ). We use a GAT layer followed by projection and readout to predict whether the input utterance is bona fide or spoofed.CC-BY · From the PDF

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

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

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

Show all 43 references

Research works printed but not linked: 3

  1. [1]1. A. Nautsch, X. Wang, N. Evans, T. Kinnunen, V. Vestman, M. Todisco, H. Delgado, M. Sahidullah, J. Yamagishi, and K. A. Lee, "Asvspoof 2019: spoofing countermeasures for the detec- tion of synthesized, converted and replayed speech," IEEE Trans- actions on Biometrics, Behavior, and Identity Science (TIBOM), 2021.
  2. [12]12. C.-I. Lai, N. Chen, J. Villalba, and N. Dehak, "Assert: Anti- spoofing with squeeze-excitation and residual networks," in Proc. Interspeech, 2019.
  3. [21]21. J.-w. Jung, S.-b. Kim, H.-j. Shim, J.-h. Kim, and H.-J. Yu, "Im- proved RawNet with Filter-wise Rescaling for Text-independent Speaker Verification using Raw Waveforms," in Proc. INTER- SPEECH, 2020, pp. 1496-1500.

Cited by

See all 79

Metadata

Authors
Tak, H., Jung, J.-W., Patino, J., Todisco, M., & Evans, N.
Affiliations
  • EURECOM (FR)
  • Seoul National University (KR)
Venue
Interspeech 2021
Publisher
ISCA
Published
2021-08-30
Pages
2356-2360
ISSN
2308-457X (ISSN-L)
OpenAlex
W3146788459
Cited by
79
References
41
Citations by year
2026: 11 · 2025: 21 · 2024: 19 · 2023: 15 · 2022: 11 · 2021: 2
FWCI
5.43
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Interspeech (USB) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Funders
  • Agence Nationale de la Recherche
  • Japan Science and Technology Agency
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
graph attention networks, anti-spoofing, speaker verification, ASVspoof 2019, temporal attention, model fusion, speaker verification security

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Graph Attention Networks for Anti-Spoofing. https://app.cochat.ai/papers/10.21437/interspeech.2021-993
The paper
Tak, H., Jung, J.-W., Patino, J., Todisco, M., & Evans, N. (2021). Graph Attention Networks for Anti-Spoofing. Interspeech 2021. https://doi.org/10.21437/interspeech.2021-993

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.