METHOD FOR DETECTING AN AUDIO ADVERSARIAL ATTACK WITH RESPECT TO A VOICE INPUT PROCESSED BY AN AUTOMATIC SPEECH RECOGNITION SYSTEM, CORRESPONDING DEVICE, COMPUTER PROGRAM PRODUCT AND COMPUTER-READABLE CARRIER MEDIUM

摘要

The disclosure relates to a method and device for detecting an audio adversarial attack with respect to a voice input (VI) processed by an automatic speech recognition system (ASR). The method includes: obtaining (12) a transcript (T) resulting from the processing, by the automatic speech recognition system, of an input audio signal of a voice input; converting (13) the transcript (T) into a synthesized audio signal (SAS); extracting (15, 15'), from the input audio signal and from the synthesized audio signal, acoustic features and converting them into sequences of feature vectors (sFV1, sFV2); computing (17) a dynamic time warping distance (D) between the sequences of converted features vectors; and delivering (18) a piece of data representative of a detection of an audio adversarial attack, as a function of a result of a comparison between the dynamic time warping distance and a predetermined threshold.