A Kernel Density Estimation Based Loss Function and its Application to ASV-Spoofing Detection
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Biometric systems are exposed to spoofing attacks which may compromise their security, and voice biometrics, also known as automatic speaker verification (ASV), is no exception. Replay, synthesis and voice conversion attacks cause false acceptances that can be detected by anti-spoofing systems. Recently, deep neural networks (DNNs) which extract embedding vectors have shown superior performance than conventional systems in both ASV and anti-spoofing tasks. In this work, we develop a new concept of loss function for training DNNs which is based on kernel density estimation (KDE) techniques. The proposed loss functions estimate the probability density function (pdf) of every training class in each mini-batch, and compute a log likelihood matrix between the embedding vectors and pdfs of all training classes within the mini-batch in order to obtain the KDE-based loss. To evaluate our proposal for spoofing detection, experiments were carried out on the recent ASVspoof 2019 corpus, including both logical and physical access scenarios. The experimental results show that training a DNN based anti-spoofing system with our proposed loss functions clearly outperforms the performance of the same system being trained with other well-known loss functions. Moreover, the results also show that the proposed loss functions are effective for different types of neural network architectures.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00482 · Cited by 7,781 · cited 1×
“In our preliminary experiments we evaluated the cosface [50], arcface [51] and sphereface [24] versions of the additive margin loss.”
MethodCosFace: Large Margin Cosine Loss for Deep Face Recognition
Wang, H., Wang, Y., Zhou, Z., Ji, X., Gong, D., Zhou, J., Li, Z., & Liu, W. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00552 · Cited by 3,034
ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection
Todisco, M., Wang, X., Vestman, V., Sahidullah, M., Delgado, H., Nautsch, A., Yamagishi, J., Evans, N., Kinnunen, T., & Lee, K. A. (2019) · arXiv · doi:10.48550/arxiv.1904.05441 · Cited by 688 · cited 8×
“As can be seen, our proposed systems outperform the baseline anti-spoofing systems released with this database (CQCC + GMM and LFCC + GMM), as well as the other top performing single systems (presented to the ASVspoof 2019 Challenge [8]) and our previous GRCNN [47], in both the LA and PA scenarios.”
BackgroundMethodResultInfluentialASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection
Todisco, M., Wang, X., Vestman, V., Sahidullah, M., Delgado, H., Nautsch, A., Yamagishi, J., Evans, N., Kinnunen, T. H., & Lee, K. A. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2249 · Cited by 687
Spoofing 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
The 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
Audio 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
Kinnunen, T., Lee, K. A., Delgado, H., Evans, N., Todisco, M., Sahidullah, M., Yamagishi, J., & Reynolds, D. A. (2018) · The Speaker and Language Recognition Workshop (Odyssey 2018) · doi:10.21437/odyssey.2018-44 · Cited by 198
Cited by
Replay and Synthetic Speech Detection with Res2Net Architecture
Li, X., Li, N., Weng, C., Liu, X., Su, D., Yu, D., & Meng, H. (2021) · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp39728.2021.9413828 · Cited by 186
“To construct generalized countermeasures, existing efforts may be divided into three categories: feature engineering [11, 12], system modeling [13–15] and loss criteria [16].”
BackgroundA conformer-based classifier for variable-length utterance processing in anti-spoofing
Rosello, E., Gomez-Alanis, A., Gomez, A. M., & Peinado, A. (2023) · INTERSPEECH 2023 · doi:10.21437/interspeech.2023-1820 · Cited by 47
“These challenges highlight the importance of developing technologies that are robust to different types of attacks and environmental conditions, with deep neural networks (DNNs) being the most effective approach [7, 8, 9, 10, 11, 12].”
BackgroundSelf-citationTan, C. B., Hijazi, M. H. A., Khamis, N., Nohuddin, P. N. E. B., Zainol, Z., Coenen, F., & Gani, A. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11235-x · Cited by 40
“From recent works, it is found that deep learning classifiers such as DNN [120], RNN [30], and CNN [88] are capable of automatic feature abstraction in which more informative features can be identified.”
BackgroundXue, J., Fan, C., Lv, Z., Tao, J., Yi, J., Zheng, C., Wen, Z., Yuan, M., & Shao, S. (2022) · Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia · doi:10.1145/3552466.3556526 · Cited by 40
An Empirical Study on Channel Effects for Synthetic Voice Spoofing Countermeasure Systems
(2021) · doi:10.21437/interspeech.2021-1820 · Cited by 30
Metadata
- Authors
- Gomez-Alanis, A., Gonzalez-Lopez, J. A., & Peinado, A. M.
- Venue
- IEEE Access
- Published
- 2020
- Volume
- 8
- Pages
- 108530-108543
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W3034598492
- Cited by
- 35
- References
- 9
- FWCI
- 2.84
- Type
- journal article
- Language
- en
- Open access
- gold
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.