The DOI matches its Crossref record.
Robust Bayesian and Light Neural Networks for Voice Spoofing Detection
Abstract
We present a replay attack detection system consisting of two convolutional neural network models. The first model consists of a small Bayesian neural network, motivated by the hypothesis that Bayesian models are robust to overfitting. The second one uses a bigger architecture, LCNN, extended with several regularization techniques to improve generalization. Our experiments, considering both size of the networks and use of the Bayesian approach, indicated that smaller networks are sufficient to achieve competitive results. To better estimate the performance against unseen spoofing methods, the final models were selected using novel Attack-Out Cross-Validation. In this procedure each model was tested on a subset of data containing not only previously unseen speakers, but also unseen spoofing attacks. The system was submitted to ASVspoof 2019 challenge’s PA condition and achieved a t-DCF score of 0.0219 and EER of 0.88% on the evaluation dataset, which is a 10 times relative improvement over the baseline.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Neural networks (as well as other machine learning models) applied to the DeepFake detection problem are particularly prone to two common issues - generalization and stability.”
From Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection (2022) · cites this paper as [17]
Citations
Cites
Still being checked.
Cited by
Nautsch, A., Wang, X., Evans, N., Kinnunen, T. H., Vestman, V., Todisco, M., Delgado, H., Sahidullah, M., Yamagishi, J., & Lee, K. A. (2021) · IEEE Transactions on Biometrics, Behavior, and Identity Science · doi:10.1109/tbiom.2021.3059479 · Cited by 185
Deep Audio-visual Learning: A Survey
Zhu, H., Luo, M., Wang, R., Zheng, A., & He, R. (2021) · Machine Intelligence Research · doi:10.1007/s11633-021-1293-0 · Cited by 195
Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection
Kawa, P., Plata, M., & Syga, P. (2022) · Interspeech 2022 · doi:10.21437/interspeech.2022-10078 · Cited by 33
“In [17], authors proposed attack–out cross–validation procedure for replay attacks and split training and testing subsets with respect to microphone distance and replay–device quality.”
BackgroundSelf-citationA robust voice spoofing detection system using novel CLS-LBP features and LSTM
Dawood, H., Saleem, S., Hassan, F., & Javed, A. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2022.02.024 · Cited by 31
Stop Deceiving! An Effective Defense Scheme Against Voice Impersonation Attacks on Smart Devices
Huang, W., Tang, W., Jiang, H., Luo, J., & Zhang, Y. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3110588 · Cited by 28
Chettri, B., Kinnunen, T., & Benetos, E. (2020) · Computer Speech & Language · doi:10.1016/j.csl.2020.101092 · Cited by 27
FMFCC-A: A Challenging Mandarin Dataset for Synthetic Speech Detection
Zhang, Z., Gu, Y., Yi, X., & Zhao, X. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-95398-0_9 · Cited by 24
Deep learning countermeasures for detecting replay speech attacks: a review
Veesa, S., & Singh, M. (2024) · International Journal of Speech Technology · doi:10.1007/s10772-024-10163-z · Cited by 13
Discriminative features based on modified log magnitude spectrum for playback speech detection
Yang, J., Xu, L., Ren, B., & Ji, Y. (2020) · EURASIP Journal on Audio Speech and Music Processing · doi:10.1186/s13636-020-00173-5 · Cited by 10
Recognizing Voice Spoofing Attacks via Acoustic Nonlinearity Dissection for Mobile Devices
Huang, W., Tang, W., Jiang, H., & Zhang, Y. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3411791 · Cited by 8
Audio verification in forensic investigation using light deep neural network
Al-Shakarchy, N. D., Abdullah, Z. N., Alameen, Z. M., & Harjan, Z. A. (2024) · International Journal of Information Technology · doi:10.1007/s41870-024-01812-2 · Cited by 9
Spoofed Speech Detection with Weighted Phase Features and Convolutional Networks
Dişken, G. (2022) · Archives of Acoustics · doi:10.24425/aoa.2022.141648 · Cited by 2
Generalized Replay Spoofing Countermeasure Based on Combining Local Subclassification Models
Altuwayjiri, S. M., Bchir, O., & Ismail, M. M. B. (2022) · Applied Sciences · doi:10.3390/app122211742 · Cited by 2
Automatic Speech Verification Spoofing DetectionPreprint
Mo, S., Wang, H., Ren, P., & Chi, T.-C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.08095 · Cited by 1
Metadata
- Authors
- Białobrzeski, R., Kośmider, M., Matuszewski, M., Plata, M., & Rakowski, A.
- Venue
- Interspeech 2019
- Publisher
- ISCA
- Published
- 2019-09-15
- Pages
- 1028-1032
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2972728673
- Cited by
- 14
- References
- 0
- Citations by year
- 2024: 3 · 2022: 5 · 2021: 3 · 2020: 3
- FWCI
- 1.05
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Interspeech (USB) (publishedVersion)
- 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 › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- voice spoofing detection, voice spoofing, Bayesian neural networks, lightweight neural networks, robustness, 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
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.
