Search
Abstract
This paper describes the new version of a method that is capable of protecting automatic speaker verification (ASV) systems from playback attacks. The presented approach uses computer vision techniques, such as the texture feature extraction based on Local Ternary Patterns (LTP), to identify spoofed recordings. Our goal is to make the algorithm independent from the contents of the training set as much as possible; we look for the descriptors that would allow the method to detect attacks performed in an environment entirely different from the training one and with the use of the equipment that differs considerably from the devices that captured the training samples. The final form of our method, based on the previously presented proof of concept, performs significantly better than the reference Textrogram algorithm.
Citations
-
1
CrossRef
-
0
Web of Science
-
1
Scopus
Cite as
Full text
full text is not available in portal
Keywords
Details
- Category:
- Articles
- Type:
- artykuły w czasopismach
- Published in:
-
Advances in Intelligent Systems and Computing
no. 977,
pages 214 - 223,
ISSN: 2194-5357 - Language:
- English
- Publication year:
- 2020
- Bibliographic description:
- Smiatacz M.: Texture Features for the Detection of Playback Attacks: Towards a Robust Solution// Advances in Intelligent Systems and Computing -Vol. 977,iss. Chapter 22 (2020), s.214-223
- DOI:
- Digital Object Identifier (open in new tab) 10.1007/978-3-030-19738-4_22
- Verified by:
- Gdańsk University of Technology
seen 173 times
Recommended for you
Fault detection in the marine engine using a support vector data description method
- K. Wrzask,
- J. Kowalski,
- V. V. Le
- + 2 authors