Channel pattern noise based playback attack detection algorithm for speaker recognition
The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
This paper proposes a channel pattern noise based approach to guard speaker recognition system against playback attacks. For each recording under investigation, the channel pattern noise severs as a unique channel identification fingerprint. Denoising filter and statistical frames are applied to extract channel pattern noise, and 6 Legendre coefficients and 6 statistical features are extracted. SVM is used to train channel noise model to judge whether the input speech is an authentic or a playback recording. The experimental results indicate that, with the designed playback detector, the equal error rate of speaker recognition system is reduced by 30%.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Hermansky, H., & Morgan, N. (1994) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.326616 · Cited by 1,808 · cited 1×
“The low frequency component is mainly the effect of convolution noise intro duced by channel noise [9].”
BackgroundTheory and Applications of Digital Speech Processing
Rabiner, L. R., & Schafer, R. W. (2010) · Medical Entomology and Zoology · Cited by 579
Kersta, L. G. (1962) · Nature · doi:10.1038/1961253a0 · Cited by 204 · cited 3×
“T he concept of voiceprint was firstly presented by Kersta for speaker recognition in 1962 in Nature [1].”
BackgroundInfluentialPohlmann, K. C. (1985) · Cited by 148
Vulnerability of speaker verification to voice mimicking
Lau, Y. W., Wagner, M., & Tran, D. (2005) · Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004. · doi:10.1109/isimp.2004.1434021 · Cited by 128 · cited 2×
“Two common security problems for speaker recognition systems are voice mimicking [3] and playback attack [4].”
BackgroundMornington-West, A. (1998) · Elsevier eBooks · doi:10.1016/b978-0-08-054564-6.50008-2 · Cited by 68
Score normalization in playback attack detection
Shang, W., & Stevenson, M. (2010) · 2010 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2010.5495503 · Cited by 58
Language Identification Using Pitch Contour Information
Lin, C.-Y., & Wang, H.-C. (2006) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2005.1415185 · Cited by 57 · cited 1×
“Legendre polynomials are a set of orthogonal basis, and this technique of approximation by Legendre polynomials has been successfully applied in language identification and other engineering applications [10].”
MethodSubband or cepstral domain filtering for recognition of Lombard and channel-distorted speech
Hanson, B. A., & Applebaum, T. H. (1993) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1993.319235 · Cited by 30 · cited 1×
“Channel noise is all along with speech signals and varies slowly [7].”
BackgroundPrevention of impostors entering speaker recognition systems
Zheng, F. (2008) · Journal of Tsinghua University(Science and Technology) · Cited by 6
Research works printed but not linked: 1
- lipeng, 2008, Pre-vention of impostors entering speaker recognition sys-tems, Journal of Tsinghua University, 48, 699
Cited by
Items 101–102 of 102
Bekiryazıcı, Ş., Hanilçi, C., & Ozcan, N. (2025) · Gümüşhane Üniversitesi Fen Bilimleri Enstitüsü Dergisi · doi:10.17714/gumusfenbil.1695733
Splicing detection and localization for speech deepfakes using audio novelty
Salvi, D., Castelli, F., Negroni, V., Bestagini, P., & Tubaro, S. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104888
Metadata
- Authors
- Wang, Z.-F., Wei, G., & He, Q.-H.
- Affiliations
- South China University of Technology (CN)
- ORCID
- Wei, Gang
- Venue
- 2011 International Conference on Machine Learning and Cybernetics
- Publisher
- IEEE
- Published
- 2011-07
- Pages
- 1708-1713
- OpenAlex
- W2114376863
- Cited by
- 101
- References
- 11
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 5 · 2023: 12 · 2022: 6 · 2021: 6 · 2020: 9 · 2019: 14 · 2018: 13 · 2017: 15 · 2016: 7 · 2015: 6 · 2014: 4
- FWCI
- 1.00
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Machine Learning and Cybernetics (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Keywords
- speaker recognition, replay attacks, Legendre coefficients, statistical features, support vector machine, anti-spoofing
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.