Disappeared Command: Spoofing Attack On Automatic Speech Recognition Systems with Sound Masking
Sound
2022-06-09 v2 Artificial Intelligence
Audio and Speech Processing
Abstract
The development of deep learning technology has greatly promoted the performance improvement of automatic speech recognition (ASR) technology, which has demonstrated an ability comparable to human hearing in many tasks. Voice interfaces are becoming more and more widely used as input for many applications and smart devices. However, existing research has shown that DNN is easily disturbed by slight disturbances and makes false recognition, which is extremely dangerous for intelligent voice applications controlled by voice.
Cite
@article{arxiv.2204.08977,
title = {Disappeared Command: Spoofing Attack On Automatic Speech Recognition Systems with Sound Masking},
author = {Jinghui Xu and Jifeng Zhu and Yong Yang},
journal= {arXiv preprint arXiv:2204.08977},
year = {2022}
}
Comments
13 pages, 4 figures. arXiv admin note: text overlap with arXiv:1903.10346 by other authors