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.
Authors
Additional information
- DOI
- Digital Object Identifier link open in new tab 10.1007/978-3-030-19738-4_22
- Category
- Publikacja w czasopiśmie
- Type
- artykuły w czasopismach
- Language
- angielski
- Publication year
- 2020
