公开(公告)号：EP2723036B1

公开(公告)日：2018-11-21

申请号：EP13189531.0

申请日：2013-10-21

Applicant: Verint Systems Ltd.

Inventor： Hazzani, Gideon ,  Ariav, Yoav

IPC: H04L29/06 ,  H04W12/02 ,  H04M3/22 ,  H04W4/02 ,  G10L17/00

CPC classification number: H04M3/2281 ,  H04L63/0428 ,  H04L63/0442 ,  H04L63/308 ,  H04M2201/41 ,  H04M2242/12 ,  H04M2242/30 ,  H04W4/025 ,  H04W12/02 ,  H04W12/04

Abstract: Methods and systems for monitoring, analyzing and acting upon voice calls in communication networks. An identification system receives monitored voice calls that are conducted in a communication network. Some of the monitored voice calls may be conducted by target individuals who are predefined as suspects. In order to maintain user privacy, the system selects and retains only voice calls that are suspected of being conducted by predefined targets. The techniques disclosed herein are particularly advantageous in scenarios where the network identifiers of the terminal used by the target are not known, or where the target uses public communication devices. In accordance with the disclosure, content-based identifiers such as speaker recognition or keyword matching are used.

公开(公告)号：EP3158719A1

公开(公告)日：2017-04-26

申请号：EP15731282.8

申请日：2015-06-18

Applicant: Katia SA

Inventor： WINKLER, Maxime

IPC: H04M3/436 ,  H04M3/42

CPC classification number: H04M3/436 ,  G06N99/005 ,  H04L63/0861 ,  H04L63/10 ,  H04M3/42059 ,  H04M3/42102 ,  H04M3/4211 ,  H04M2201/41

Abstract: Method of filtering undesirable incoming telephone calls, in which a decision to block a call or to transmit it is based both on the caller's number and on analysis of the caller's voice.

Abstract translation: 过滤不希望的来电的方法，其中阻止呼叫或发送呼叫的决定既基于呼叫者号码又基于呼叫者语音的分析。

公开(公告)号：EP2663977A4

公开(公告)日：2016-12-28

申请号：EP12734541

申请日：2012-01-09

Applicant: GARCIA WILSON A ,  SAMUEL GARFIELD

Inventor： GARCIA WILSON A ,  SAMUEL GARFIELD

IPC: G10L17/00 ,  G06Q20/40 ,  G07C9/00 ,  G10L17/04 ,  H04L9/32 ,  H04M3/493

CPC classification number: H04L9/3231 ,  G06Q20/40145 ,  G07C9/00158 ,  G07C9/00166 ,  G07C2209/02 ,  G10L17/04 ,  H04L2463/102 ,  H04M3/4936 ,  H04M3/5183 ,  H04M2201/41 ,  H04M2203/6054

公开(公告)号：EP2913822B1

公开(公告)日：2016-12-07

申请号：EP15155688.3

申请日：2015-02-19

Applicant: Nokia Technologies OY

Inventor： Lönnfors, Mikko ,  Rainisto, Roope

IPC: G10L17/04 ,  G10L15/18

CPC classification number: G10L17/04 ,  G10L15/1822 ,  G10L15/26 ,  H04M3/56 ,  H04M3/569 ,  H04M2201/41 ,  H04M2250/74

公开(公告)号：EP3001662A3

公开(公告)日：2016-08-17

申请号：EP15182074.3

申请日：2015-08-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： KIM, Seung-min ,  NA, Jeong-shan ,  LEE, Dai-boong ,  LEE, Min-hyuk

IPC: H04M3/56

CPC classification number: G10L15/26 ,  H04M3/56 ,  H04M2201/40 ,  H04M2201/41 ,  H04N1/00352 ,  H04N7/147 ,  H04N7/15

Abstract: A conference proceeding apparatus a conference proceeding method for advancing a conference are provided. The conference proceeding apparatus includes an interface configured to receive an input, a display configured to display subjects of a conference in response to the interface receiving an input to start the conference, and a voice recognizer configured to recognize voices of participants of the conference. The conference proceeding apparatus further includes a voice-text converter configured to convert the recognized voices into texts, and a controller configured to register, in a record of the conference, the converted texts corresponding to the subjects.

公开(公告)号：EP2840767A1

公开(公告)日：2015-02-25

申请号：EP14178020.5

申请日：2014-07-22

Applicant: Nuance Communications, Inc.

Inventor： Sharp, Robert Douglas

IPC: H04M3/42

CPC classification number: G10L17/00 ,  G10L17/04 ,  G10L17/22 ,  H04M3/42042 ,  H04M3/42068 ,  H04M2201/41 ,  H04M2203/6045 ,  H04M2203/6054 ,  H04M2203/6081

Abstract: A method of enabling speaker identification, the method comprising receiving an identifier, the identifier having a limited number of potential speakers associated with it, processing speech data received from a speaker, and when the speaker is recognized, tagging a speaker and displaying a speaker identity. The method further comprises, when the speaker is not recognized, prompting an associate to identify the speaker.

Abstract translation: 一种使扬声器识别的方法，所述方法包括接收标识符，所述标识符具有与其相关联的有限数量的潜在扬声器，处理从扬声器接收的语音数据，以及当所述扬声器被识别时，标记扬声器并显示扬声器身份 。 该方法还包括：当扬声器不被识别时，提示联络人识别扬声器。

公开(公告)号：EP2769541A1

公开(公告)日：2014-08-27

申请号：EP11776094.2

申请日：2011-10-18

Applicant: Unify GmbH & Co. KG

Inventor： BRIESKORN, Jürgen

IPC: H04N7/15

CPC classification number: H04L12/1822 ,  H04L12/1831 ,  H04M3/42221 ,  H04M3/567 ,  H04M3/569 ,  H04M2201/41 ,  H04N7/147 ,  H04N7/152

Abstract: A method for providing data produced in a conference, in which voice signals from participants in the conference are mixed in a conference bridge, comprises provision of a time base that runs concurrently over the duration of the conference and setup of automatic identification of each participant when this participant speaks in the conference. The method also comprises capture of conversation contribution by each speaking participant to a conversation by the participants which is conducted during the conference as speaking time associated with each speaking participant at the conference, association of a time stamp with the speaking time, and production of statistical data by virtue of statistical evaluation of the speaking times of the participants.

公开(公告)号：EP2692106A2

公开(公告)日：2014-02-05

申请号：EP12714466.5

申请日：2012-03-30

Applicant: Qualcomm Incorporated

Inventor： JOHNSGARD, Todd J. ,  SIU, Ta-yan ,  SHI, Guangming

IPC: H04L29/06

CPC classification number: H04L63/0861 ,  G07C9/00158 ,  G10L17/00 ,  H04M1/67 ,  H04M2201/41 ,  H04M2203/6045 ,  H04M2203/6054 ,  H04R25/55 ,  H04W12/12 ,  H04W88/02

Abstract: Disclosed is an apparatus, system, and method to continuously authenticate a user of a mobile device. The mobile device includes a user interface, a transceiver, a microphone, and processor. The processor continuously samples a user's voice from the microphone during a call by obtaining voice snippets on a pre-defined periodic basis or on a random basis. The processor further compares the sampled voice from the microphone to a stored voice to authenticate a valid user, wherein if the sampled voice matches the stored voice for a valid user, functionality of the mobile device continues. On the other hand, if the sampled voice does not match the stored voice for a valid user, functionality of the mobile device is locked.

公开(公告)号：EP2663977A2

公开(公告)日：2013-11-20

申请号：EP12734541.1

申请日：2012-01-09

Applicant: Garcia, Wilson A. ,  Samuel, Garfield

Inventor： Garcia, Wilson A. ,  Samuel, Garfield

IPC: G10L17/00 ,  H04L9/32

CPC classification number: H04L9/3231 ,  G06Q20/40145 ,  G07C9/00158 ,  G07C9/00166 ,  G07C2209/02 ,  G10L17/04 ,  H04L2463/102 ,  H04M3/4936 ,  H04M3/5183 ,  H04M2201/41 ,  H04M2203/6054

Abstract: The natural biometric enrolment system describes a methodology and associated apparatus for extracting spoken biometric voiceprint data from user/enrollee such a way that the natural course of live agent verification is used to mask what has typically been an automated interactive voice response task. The natural biometric enrolment system also provide the capability to synchronize agent location and agent identification such that tradition CTI systems integration is not required; this being achieved with a bidirectional and dual verification process wherein both agent and caller voiceprints are matched in a common database and software control is used to match the telephone caller with an enrolment and verification widget located at the agent desktop. Further, such an enrollment/verification widget can be used by the agent to make human judgment notations in that cause the system to a) have better scoring for enrolment and verification; b) record notations reflecting the live agent confidence regarding the user's validity, or c) trigger a PIN reset for fraudulent callers in native or third party systems.

Abstract translation: 自然生物识别注册系统描述了一种用于从用户/登记者提取口语生物识别声纹数据的方法和相关装置，使得使用现场代理验证的自然过程来屏蔽通常是自动交互式语音响应任务的方式。 自然生物识别注册系统还提供同步代理位置和代理识别的能力，以便不需要传统的CTI系统集成; 这通过双向和双重验证过程来实现，其中代理和呼叫者声纹在通用数据库中匹配，并且软件控制用于将电话呼叫者与位于代理台式机的登记和验证小部件相匹配。 此外，代理人可以使用这样的注册/验证小部件来制作人为的判断符号，这导致系统a）对注册和验证有更好的评分; b）记录反映用户有效性的现场代理信心的记录，或c）触发本地或第三方系统中的欺诈呼叫者的PIN重置。

公开(公告)号：EP2622832A1

公开(公告)日：2013-08-07

申请号：EP11764835.2

申请日：2011-09-27

Applicant: British Telecommunications Public Limited Company

Inventor： PAWLEWSKI, Mark

IPC: H04M3/22 ,  G10L15/26

CPC classification number: H04M3/2281 ,  G10L15/26 ,  H04M3/436 ,  H04M2201/41 ,  H04M2203/6027

Abstract: Fraudulent callers that masquerade as legitimate callers in order to discover details of bank accounts or other accounts are an increasing problem. In order to detect possible fraudsters and preventing them from obtaining such details a method and system is proposed that transform the recorded speech of a batch of incoming calls to strings of phonemes or text. Thereafter similar speech patterns, such as distinct similar phrases or wording, in the recorded speech are determined and calls having similar speech patterns, and preferably also similar acoustic properties, are grouped together and identified as being from the same fraudulent caller. Transactions initiated by the fraudulent caller can as a result be stopped and preferably a voiceprint of the fraudulent caller's speech is generated and stored in a database for further use.