With the improvement of deep fake technology, the problem of detecting fabricated audio has become significant. Modern approaches have certain shortcomings that do not allow their implementation in existing vehicles. The article is devoted to the creation of a unique approach to the analysis of audio data to detect the fact of contextual falsification of information. The proposed solution is based on a complex combination of recurrent and convolutional neural networks. The results of the research conducted on a self-created data set related to operational information dedicated to Russia’s invasion of Ukraine, and a comparison with existing approaches, assert the high efficiency of the proposed solution and the possibility of its further implementation as part of an unmanned systems.
Using RCNN to Indentify the Fake Audio Information
22.10.2024
2363194 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Preprocessed Faster RCNN for Vehicle Detection
IEEE | 2018
|Improved Faster RCNN for Traffic Sign Detection*
IEEE | 2020
|Robustness of Mask-RCNN at High Ambiguous Environments
IEEE | 2022
|