-
公开(公告)号：WO2022083969A1
公开(公告)日：2022-04-28
申请号：PCT/EP2021/076248
申请日：2021-09-23
Applicant: THOMSON LICENSING
Inventor： NADEAU, Pascal , GILBERTON, Philippe , GAUTIER, Eric , DELAUNAY, Christophe
Abstract: 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.
-
公开(公告)号：WO2022083968A1
公开(公告)日：2022-04-28
申请号：PCT/EP2021/076240
申请日：2021-09-23
Applicant: THOMSON LICENSING
Inventor： NADEAU, Pascal , GILBERTON, Philippe , GAUTIER, Eric , DELAUNAY, Christophe
Abstract: The disclosure relates to a method and device for detecting an audio adversarial attack with respect to a voice command (VC) processed by an automatic speech recognition system (ASR). The method is implemented by a detection device connected to the automatic speech recognition system. The method includes: obtaining (11) an audio signal associated with the voice command; performing (12) a phonetic transcription of the audio signal, according to a phonetic transcription scheme, delivering a first character string (CS1); obtaining (13) a transcript resulting from the processing, by the automatic speech recognition system, of the audio signal; performing (14) a phonetic transcription of the transcript, according to the phonetic transcription scheme, delivering a second character string (CS2); computing (15) a similarity score (SS) between the first character string (CS1) and the second character string (CS2); and delivering (16) a piece of data representative of a detection of an audio adversarial attack, as a function of a result of a comparison between the similarity score (SS) and a predetermined threshold.
-
公开(公告)号：WO2018095911A1
公开(公告)日：2018-05-31
申请号：PCT/EP2017/079936
申请日：2017-11-21
Applicant: THOMSON LICENSING
Inventor： LOUZIR, Ali , KUMAR, Rupesh , NADEAU, Pascal , MINARD, Philippe
Abstract: Apparatus (300, 400) and method (600) for passive remote control are provided. The apparatus (300) includes at least two radio-frequency identification (RFID) tag devices (330_1, 330_2, 330_N, 430_1, 430_2) each operable to transmit a signal when activated and a first switch coupled to the at least two RFID tag devices (310_1, 310_2, 310_K, 410_1) and operable to activate the at least two RFID tag devices when the first switch is in a first switch state, said first switch being a first key identified by RFID tag information of the at least two RFID tag devices. Apparatus (110) and method (700) for receiving RFID signals are also provided.
-
-
Search Results
3
records
(took 0.039 seconds)
