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.

翻译：深层学习技术的发展极大地促进了自动语音识别技术的性能改进,这证明在很多任务中具有与人听力相当的能力,语音接口正日益被广泛用作许多应用程序和智能装置的投入,然而,现有研究表明,DNN很容易受到轻微干扰的干扰,并作出虚假识别,这对由声音控制的智能语音应用程序极为危险。