公开(公告)号：WO2022005661A1

公开(公告)日：2022-01-06

申请号：PCT/US2021/034669

申请日：2021-05-28

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： NECKERMANN, Tom ,  WILSON, Alexander J. ,  REY, Romain Gabriel Paul

IPC: H04M3/56 ,  G10L17/00 ,  H04L12/18 ,  H04N7/00 ,  G10L15/02 ,  G10L17/04 ,  G10L17/16 ,  H04L12/1827 ,  H04L12/1831 ,  H04M2201/38 ,  H04M2201/41 ,  H04M2203/1025 ,  H04M2203/5072 ,  H04M2203/5081 ,  H04M2203/509 ,  H04M3/569

Abstract: Computerized systems are provided for determining an identity of one or more users that use a same audio source, such as a microphone. The identity of one or more users that use a same audio source can based on generating a list of participant candidates who are likely to participate in an associated event, such as a meeting. For instance, embodiments can generate one or more network graphs of a meeting invitee any only voice input samples of the meeting invitee's N closest connections are compared to an utterance to determine the identity of the user associated with the utterance. One or more indicators that identify the users who are using the same audio source, as well as additional information or metadata associated with the identified user can be caused to be presented.

公开(公告)号：WO2021191519A1

公开(公告)日：2021-09-30

申请号：PCT/FR2021/050381

申请日：2021-03-05

Applicant: ORANGE

Inventor： MENON, Bruno ,  TCHOUMI, Paul ,  PRUDON, Didier ,  BELDAME, Mathias

IPC: H04L29/06 ,  G06F21/32 ,  H04L9/32 ,  H04W12/06 ,  H04M3/51 ,  H04M3/493 ,  H04L63/0861 ,  H04L63/0884 ,  H04L9/321 ,  H04L9/3231 ,  H04M2201/41 ,  H04M2203/6054 ,  H04M3/4936 ,  H04M3/5166

Abstract: L'invention concerne un procédé d'authentification d'un utilisateur d'un service sur un terminal de communication, comprenant ce qui suit, au niveau du terminal de communication : - envoyer (S23) à un serveur une requête d'accès audit serveur, ladite requête comprenant un identifiant associé au terminal de communication et un identifiant associé à un service requis dans ledit serveur, - recevoir (S25) en provenance d'un dispositif d'authentification une requête d'authentification demandant à l'utilisateur de prononcer au moins un mot, - communiquer (S26) ledit au moins un mot prononcé par l'utilisateur au dispositif, - ledit au moins un mot prononcé correspondant à une empreinte vocale de l'utilisateur préalablement enregistrée en association avec l'identifiant dudit terminal de communication, accéder (S30a) au service ou recevoir (S29b) en provenance du dispositif une requête d'authentification complémentaire de l'utilisateur.

公开(公告)号：WO2021126444A1

公开(公告)日：2021-06-24

申请号：PCT/US2020/060913

申请日：2020-11-17

Applicant: EDUWORKS CORPORATION

Inventor： ENZINGER, Ewald ,  ROBSON, Robert O.

IPC: H04L29/06 ,  G10L17/00 ,  G10L17/02 ,  G10L17/06 ,  G10L17/18 ,  G10L25/18 ,  G10L25/24 ,  G10L25/30 ,  G10L25/69 ,  H04L63/0861 ,  H04L63/14 ,  H04M1/66 ,  H04M2201/41 ,  H04M3/2281 ,  H04M3/5183

Abstract: Methods and systems are disclosed for detecting threats in voice communications such as telephone calls. Various voice phishing (vishing) detectors detect respective type of threats and can be used or activated individually or in various combinations. A tampering detector utilizes deep scattering spectra and shifted delta cepstra features to detect tampering in the form of voice conversion, speech synthesis, or splicing. A content detector predicts a likelihood that word patterns on an incoming voice signal are indicative of a vishing threat. A spoofing detector authenticates or repudiates a purported speaker based on comparison of voice profiles. The vishing detectors can be provided as an authentication service or embedded in communication equipment. Machine learning and signal processing aspects are disclosed, along with applications to mobile telephony and call centers.