Resmax: Detecting voice spoofing attacks with residual network and max feature map

Il Youp Kwak; Sungsu Kwag; Junhee Lee; Jun Ho Huh; Choong Hoon Lee; Youngbae Jeon; Jeonghwan Hwang; Ji Won Yoon

doi:10.1109/ICPR48806.2021.9412165

Resmax: Detecting voice spoofing attacks with residual network and max feature map

Il Youp Kwak, Sungsu Kwag, Junhee Lee, Jun Ho Huh, Choong Hoon Lee, Youngbae Jeon, Jeonghwan Hwang, Ji Won Yoon

School of Cybersecurity

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

9 Citations (Scopus)

Abstract

The “2019 Automatic Speaker Verification Spoofing And Countermeasures Challenge” (ASVspoof) competition aimed to facilitate the design of highly accurate voice spoofing attack detection systems. the competition did not emphasize model complexity and latency requirements; such constraints are strict and integral in real-world deployment. Hence, most of the top performing solutions from the competition all used an ensemble approach, and combined multiple complex deep learning models to maximize detection accuracy - this kind of approach would sit uneasily with real-world deployment constraints. To design a lightweight system, we combined the notions of skip connection (from ResNet) and max feature map (from Light CNN), and evaluated the accuracy of the system using the ASVspoof 2019 dataset. With an optimized constant Q transform (CQT) feature, our single model achieved a replay attack detection equal error rate (EER) of 0.37% on the evaluation set, surpassing the top ensemble system from the competition that achieved an EER of 0.39%.

Original language	English
Title of host publication	Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	4837-4844
Number of pages	8
ISBN (Electronic)	9781728188089
DOIs	https://doi.org/10.1109/ICPR48806.2021.9412165
Publication status	Published - 2020
Event	25th International Conference on Pattern Recognition, ICPR 2020 - Virtual, Milan, Italy Duration: 2021 Jan 10 → 2021 Jan 15

Publication series

Name	Proceedings - International Conference on Pattern Recognition
ISSN (Print)	1051-4651

Conference

Conference	25th International Conference on Pattern Recognition, ICPR 2020
Country/Territory	Italy
City	Virtual, Milan
Period	21/1/10 → 21/1/15

Bibliographical note

Funding Information:
Acknowledgment This work was conducted at Samsung Research. The authors would like to thank Samsung Research Security Team for the helpful discussions. IK was supported by the National Research Foundation of Korea(NRF) grant funded by Ministry of Science and ICT (2020R1C1C1A01013020)

Funding Information:
This work was conducted at Samsung Research. The authors would like to thank Samsung Research Security Team for the helpful discussions. IK was supported by the National Research Foundation of Korea(NRF) grant funded by Ministry of Science and ICT (2020R1C1C1A01013020)

Publisher Copyright:
© 2020 IEEE

Keywords

Voice assistant security
Voice presentation attack detection
Voice spoofing attack
Voice synthesis attack

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Access to Document

10.1109/ICPR48806.2021.9412165

Cite this

Kwak, I. Y., Kwag, S., Lee, J., Huh, J. H., Lee, C. H., Jeon, Y., Hwang, J., & Yoon, J. W. (2020). Resmax: Detecting voice spoofing attacks with residual network and max feature map. In Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition (pp. 4837-4844). Article 9412165 (Proceedings - International Conference on Pattern Recognition). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR48806.2021.9412165

Resmax: Detecting voice spoofing attacks with residual network and max feature map. / Kwak, Il Youp; Kwag, Sungsu; Lee, Junhee et al.
Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition. Institute of Electrical and Electronics Engineers Inc., 2020. p. 4837-4844 9412165 (Proceedings - International Conference on Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kwak, IY, Kwag, S, Lee, J, Huh, JH, Lee, CH, Jeon, Y, Hwang, J & Yoon, JW 2020, Resmax: Detecting voice spoofing attacks with residual network and max feature map. in Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition., 9412165, Proceedings - International Conference on Pattern Recognition, Institute of Electrical and Electronics Engineers Inc., pp. 4837-4844, 25th International Conference on Pattern Recognition, ICPR 2020, Virtual, Milan, Italy, 21/1/10. https://doi.org/10.1109/ICPR48806.2021.9412165

Kwak IY, Kwag S, Lee J, Huh JH, Lee CH, Jeon Y et al. Resmax: Detecting voice spoofing attacks with residual network and max feature map. In Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition. Institute of Electrical and Electronics Engineers Inc. 2020. p. 4837-4844. 9412165. (Proceedings - International Conference on Pattern Recognition). doi: 10.1109/ICPR48806.2021.9412165

@inproceedings{55c65067ea874a948b7c70b07e211d68,

title = "Resmax: Detecting voice spoofing attacks with residual network and max feature map",

abstract = "The “2019 Automatic Speaker Verification Spoofing And Countermeasures Challenge” (ASVspoof) competition aimed to facilitate the design of highly accurate voice spoofing attack detection systems. the competition did not emphasize model complexity and latency requirements; such constraints are strict and integral in real-world deployment. Hence, most of the top performing solutions from the competition all used an ensemble approach, and combined multiple complex deep learning models to maximize detection accuracy - this kind of approach would sit uneasily with real-world deployment constraints. To design a lightweight system, we combined the notions of skip connection (from ResNet) and max feature map (from Light CNN), and evaluated the accuracy of the system using the ASVspoof 2019 dataset. With an optimized constant Q transform (CQT) feature, our single model achieved a replay attack detection equal error rate (EER) of 0.37% on the evaluation set, surpassing the top ensemble system from the competition that achieved an EER of 0.39%.",

keywords = "Voice assistant security, Voice presentation attack detection, Voice spoofing attack, Voice synthesis attack",

author = "Kwak, {Il Youp} and Sungsu Kwag and Junhee Lee and Huh, {Jun Ho} and Lee, {Choong Hoon} and Youngbae Jeon and Jeonghwan Hwang and Yoon, {Ji Won}",

note = "Funding Information: Acknowledgment This work was conducted at Samsung Research. The authors would like to thank Samsung Research Security Team for the helpful discussions. IK was supported by the National Research Foundation of Korea(NRF) grant funded by Ministry of Science and ICT (2020R1C1C1A01013020) Funding Information: This work was conducted at Samsung Research. The authors would like to thank Samsung Research Security Team for the helpful discussions. IK was supported by the National Research Foundation of Korea(NRF) grant funded by Ministry of Science and ICT (2020R1C1C1A01013020) Publisher Copyright: {\textcopyright} 2020 IEEE; 25th International Conference on Pattern Recognition, ICPR 2020 ; Conference date: 10-01-2021 Through 15-01-2021",

year = "2020",

doi = "10.1109/ICPR48806.2021.9412165",

language = "English",

series = "Proceedings - International Conference on Pattern Recognition",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "4837--4844",

booktitle = "Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition",

}

TY - GEN

T1 - Resmax

T2 - 25th International Conference on Pattern Recognition, ICPR 2020

AU - Kwak, Il Youp

AU - Kwag, Sungsu

AU - Lee, Junhee

AU - Huh, Jun Ho

AU - Lee, Choong Hoon

AU - Jeon, Youngbae

AU - Hwang, Jeonghwan

AU - Yoon, Ji Won

N1 - Funding Information: Acknowledgment This work was conducted at Samsung Research. The authors would like to thank Samsung Research Security Team for the helpful discussions. IK was supported by the National Research Foundation of Korea(NRF) grant funded by Ministry of Science and ICT (2020R1C1C1A01013020) Funding Information: This work was conducted at Samsung Research. The authors would like to thank Samsung Research Security Team for the helpful discussions. IK was supported by the National Research Foundation of Korea(NRF) grant funded by Ministry of Science and ICT (2020R1C1C1A01013020) Publisher Copyright: © 2020 IEEE

PY - 2020

Y1 - 2020

N2 - The “2019 Automatic Speaker Verification Spoofing And Countermeasures Challenge” (ASVspoof) competition aimed to facilitate the design of highly accurate voice spoofing attack detection systems. the competition did not emphasize model complexity and latency requirements; such constraints are strict and integral in real-world deployment. Hence, most of the top performing solutions from the competition all used an ensemble approach, and combined multiple complex deep learning models to maximize detection accuracy - this kind of approach would sit uneasily with real-world deployment constraints. To design a lightweight system, we combined the notions of skip connection (from ResNet) and max feature map (from Light CNN), and evaluated the accuracy of the system using the ASVspoof 2019 dataset. With an optimized constant Q transform (CQT) feature, our single model achieved a replay attack detection equal error rate (EER) of 0.37% on the evaluation set, surpassing the top ensemble system from the competition that achieved an EER of 0.39%.

AB - The “2019 Automatic Speaker Verification Spoofing And Countermeasures Challenge” (ASVspoof) competition aimed to facilitate the design of highly accurate voice spoofing attack detection systems. the competition did not emphasize model complexity and latency requirements; such constraints are strict and integral in real-world deployment. Hence, most of the top performing solutions from the competition all used an ensemble approach, and combined multiple complex deep learning models to maximize detection accuracy - this kind of approach would sit uneasily with real-world deployment constraints. To design a lightweight system, we combined the notions of skip connection (from ResNet) and max feature map (from Light CNN), and evaluated the accuracy of the system using the ASVspoof 2019 dataset. With an optimized constant Q transform (CQT) feature, our single model achieved a replay attack detection equal error rate (EER) of 0.37% on the evaluation set, surpassing the top ensemble system from the competition that achieved an EER of 0.39%.

KW - Voice assistant security

KW - Voice presentation attack detection

KW - Voice spoofing attack

KW - Voice synthesis attack

UR - http://www.scopus.com/inward/record.url?scp=85110423250&partnerID=8YFLogxK

U2 - 10.1109/ICPR48806.2021.9412165

DO - 10.1109/ICPR48806.2021.9412165

M3 - Conference contribution

AN - SCOPUS:85110423250

T3 - Proceedings - International Conference on Pattern Recognition

SP - 4837

EP - 4844

BT - Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 10 January 2021 through 15 January 2021

ER -

Resmax: Detecting voice spoofing attacks with residual network and max feature map

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this