公开(公告)号：WO2005122462A1

公开(公告)日：2005-12-22

申请号：PCT/US2005/018180

申请日：2005-05-23

Applicant: MATSUSHITA ELECTRIC INDUSTRIAL CO., LTD ,  PEARSON, Steven ,  CONTOLINI, Matteo

Inventor： PEARSON, Steven ,  CONTOLINI, Matteo

IPC: H04L9/00

CPC classification number: H04M3/385 ,  G06Q20/32 ,  G06Q20/341 ,  G06Q20/4014 ,  G06Q20/40145 ,  G07C9/00087 ,  G07C2009/00095 ,  G07F7/1008 ,  G10L17/24 ,  H04M1/66 ,  H04M2201/41 ,  H04M2250/12 ,  H04M2250/74

Abstract: A portable device, such as a cellular telephone, engages the user in a challenge-response sequence that is based on recognition of the user's utterance and also upon verification of the user's speech patterns or voiceprint. The challenge-response protocol presents the user with an unexpected challenge word, which the user is then requested to respond to. The system maintains a secure data store of challenge words which it adapts and augments as the user makes use of the portable device. The portable device provides the user with a convenient, single access point through which he or she can authenticate with a variety of disparate secure devices ranging from door locks, ATM machines, financial institutions and third-party business associates.

Abstract translation: 诸如蜂窝电话之类的便携式设备使用户能够基于对用户话语的识别以及验证用户的语音模式或声纹的挑战响应序列。 挑战 - 响应协议向用户呈现一个意想不到的挑战字，然后用户被要求响应。 系统维护挑战词的安全数据存储，当用户利用便携式设备时，它会适应并增强。 便携式设备向用户提供方便的单个接入点，通过该接入点，他或她可以从门锁，ATM机，金融机构和第三方业务伙伴等各种不同的安全设备进行认证。

公开(公告)号：WO2004095811A2

公开(公告)日：2004-11-04

申请号：PCT/US2004008892

申请日：2004-03-24

Applicant: METRO ONE TELECOMMUNICATIONS

Inventor： TIMMINS TIMOTHY A ,  MILLER JOHN S ,  BAKER NATHAN B ,  HUEY CHRISTOPHER A ,  LJUBICICH PHILIP A

IPC: H04M3/487 ,  H04M3/493 ,  H04M

CPC classification number: H04M3/4878 ,  H04M3/42068 ,  H04M3/4931 ,  H04M2201/41

Abstract: In communications systems where multiple users may be associated with the same account, the voiceprint of a user is used to identify a profile of the user, facilitating identification of the user's preferences without requesting additional information from the user. The system may also monitor messages played to individual users, to control the playing of the messages to users. Calls made by users associated with the same account may be allocated to the caller initiating the call in bills, based on voiceprints. Voiceprints may be collected for use in deriving voiceprint samples during registration of a user with the system and during conversations between the user and the system. A voiceprint comparison threshold may be set based on the type of phone calling the system, to compensate for noise. Changes in phone numbers and/or addresses of users are monitored and the threshold is adjusted if changes are found.

Abstract translation: 在多个用户可能与同一帐户相关联的通信系统中，用户的声纹用于识别用户的简档，便于识别用户的偏好而不需要用户的附加信息。 该系统还可以监视对各个用户播放的消息，以控制向用户播放消息。 基于声波纹的用户可以将与同一帐户相关联的用户的呼叫分配给呼叫者发起账单。 可以收集Voiceprint用于在用户与系统注册期间以及在用户与系统之间的对话期间导出声纹样本。 可以基于呼叫系统的电话的类型来设置声纹比较阈值，以补偿噪声。 监控用户的电话号码和/或地址的更改，如果发现更改，则调整阈值。

公开(公告)号：WO2003075540A2

公开(公告)日：2003-09-12

申请号：PCT/US2003/005880

申请日：2003-02-26

Applicant: HEWLETT-PACKARD COMPANY

Inventor： ARMINGTON, John, P. ,  HO, Purdy, P.

IPC: H04L29/06

CPC classification number: H04L63/0838 ,  G06F21/32 ,  G06F21/42 ,  G10L17/00 ,  H04L9/3215 ,  H04L9/3226 ,  H04L9/3231 ,  H04L9/3271 ,  H04L63/0861 ,  H04L63/18 ,  H04L2209/08 ,  H04L2209/56 ,  H04M3/385 ,  H04M2201/41

Abstract: An improved authentication system utilizes multi-factor user authentication. In an exemplary embodiment, one authentication factor is the user's speech pattern, and another authentication factor is a one-time passcode. The speech pattern and the passcode may be provided via voice portal and/or browser input. The speech pattern is routed to a speaker verification subsystem, while the passcode is routed to a passcode validation subsystem. Many other combinations of input types are also possible. For heightened security, the two (or more) authentication factors are preferably, although not necessarily, provided over differing communication channels (i.e., they are out-of-band with respect to each other). If a user is authenticated by the multi-factor process, he is given access to one or more desired secured applications. Policy and authentication procedures may be abstracted from the applications to allow a single sign-on across multiple applications.

Abstract translation: 改进的认证系统利用多因素用户认证。 在示例性实施例中，一个认证因素是用户的语音模式，另一个认证因素是一次性密码。 语音模式和密码可以经由语音门户和/或浏览器输入来提供。 语音模式被路由到扬声器验证子系统，而密码被路由到密码验证子系统。 输入类型的许多其他组合也是可能的。 为了提高安全性，两个（或多个）认证因素优选地，尽管不一定是通过不同的通信信道提供的（即它们相对于彼此是带外的）。 如果用户被多因素过程认证，则可以访问一个或多个所需的安全应用程序。 可以从应用程序中抽象出策略和身份验证过程，以便跨多个应用程序进行单一登录。

公开(公告)号：WO1996008907A2

公开(公告)日：1996-03-21

申请号：PCT/IB1995001017

申请日：1995-09-18

Applicant: MCI COMMUNICATIONS CORPORATION

Inventor： MCI COMMUNICATIONS CORPORATION ,  JORDAN, David, P.

IPC: H04M01/66

CPC classification number: H04M15/47 ,  H04M3/2218 ,  H04M3/38 ,  H04M3/382 ,  H04M3/385 ,  H04M3/42 ,  H04M7/00 ,  H04M2201/40 ,  H04M2201/41 ,  H04M2203/6027 ,  H04M2215/0148

Abstract: The present invention advanced voice application system takes advantage of information, or attributes, built into a telecommunications network to determine the risk that a call is a fraudulent call in a voice recognition and verification system. To achieve this end, information relating to the telecommunications network is stored in a database as various risk factors. Thus, depending on the type of risk factors associated with a particular call, the risk assigned to that call can be raised or lowered so that the network would not reject a valid caller even though the voice pattern of the caller does not match exactly with the prestored enrolled voice print of the caller. Such risk assessment allows the management of the network to tighten the security of the system without overburdening the caller with questions and also permits calls to be completed for valid subscribers that otherwise would have been rejected. Past calling history may be added to the database as it relates to the different risk factors so that constantly updated risk factors may be used for further assessing whether a call is to be completed.

Abstract translation: 本发明的高级语音应用系统利用内置于电信网络中的信息或属性来确定呼叫是语音识别和验证系统中的欺诈呼叫的风险。 为了实现这一目的，与电信网络有关的信息作为各种危险因素存储在数据库中。 因此，根据与特定呼叫相关联的风险因素的类型，可以提高或降低分配给该呼叫的风险，使得网络不会拒绝有效的呼叫者，即使呼叫者的语音模式与 预先登记的来电者的语音打印。 这种风险评估允许网络的管理收紧系统的安全性，而不会对呼叫者产生负担，同时也允许为有效用户完成呼叫，否则将被拒绝。 过去的电话记录可能会被添加到数据库中，因为它与不同的风险因素有关，因此不断更新的风险因素可用于进一步评估呼叫是否要完成。

公开(公告)号：WO2018144472A1

公开(公告)日：2018-08-09

申请号：PCT/US2018/015991

申请日：2018-01-30

Applicant: GLOBAL TEL*LINK CORPORATION

Inventor： VOLKART, Mitch

IPC: G10L15/18 ,  G10L15/26 ,  G10L17/00

CPC classification number: H04M3/2281 ,  G06F17/2765 ,  H04M3/387 ,  H04M2201/41

Abstract: A centralized and robust threat assessment tool is disclosed to perform comprehensive analysis of previously-stored and subsequent communication data, activity data, and other relevant information relating to inmates within a controlled environment facility. As part of the analysis, the system detects certain keywords and key interactions with the dataset in order to identify particular criminal proclivities of the inmate. Based on the identified proclivities, the system assigns threat scores to inmate that represents a relative likelihood that the inmate will carry out or be drawn to certain threats and/or criminal activities. This analysis provides a predictive tool for assessing an inmate's ability to rehabilitate. Based on the analysis, remedial measures can be taken in order to correct an inmate's trajectory within the controlled environment and increase the likelihood of successful rehabilitation, as well as to prevent potential criminal acts.

公开(公告)号：WO2016071248A1

公开(公告)日：2016-05-12

申请号：PCT/EP2015/075366

申请日：2015-11-02

Applicant: AMICIMI BVBA

Inventor： DAUWE, Stefaan Benedicte Emiel Jacqueline ,  VAN QUICKENBORNE, Frederic Guy Hélène ,  ECK, Robert Nils

IPC: H04M1/725 ,  H04M3/38 ,  G08B25/01 ,  H04M3/51

CPC classification number: H04M3/385 ,  G08B25/001 ,  H04M1/7253 ,  H04M1/72541 ,  H04M3/5116 ,  H04M2201/41 ,  H04M2242/04

Abstract: The invention relates to a method comprising the steps of: - (a) storing data by means of storage means; - (b) receiving input with a sensor of a communication device. The method further comprises of - determining with comparing means in response to an emergency signal an outcome of a comparison of the received input to at least a part of the stored data; and - determining subject to the outcome whether communication means of the communication device must be activated so as to make contact with an alarm responder.

Abstract translation: 本发明涉及一种方法，包括以下步骤： - （a）通过存储装置存储数据; - （b）用通信设备的传感器接收输入。 所述方法还包括以下步骤：响应于紧急信号，通过比较装置确定所接收的输入与存储的数据的至少一部分的比较结果; 以及 - 决定是否必须激活通信装置的通信装置，以便与报警响应者联系。

公开(公告)号：WO2015024413A1

公开(公告)日：2015-02-26

申请号：PCT/CN2014/080651

申请日：2014-06-24

Applicant: 中兴通讯股份有限公司

Inventor： 王建欢

IPC: H04N7/15

CPC classification number: G10L17/00 ,  G10L15/26 ,  H04L12/1831 ,  H04M3/567 ,  H04M2201/40 ,  H04M2201/41 ,  H04N7/155

Abstract: 一种会议纪要的提取方法及装置，该方法包括：获取从视频会议信号中采集的音频信号，并将音频信号转化为文本；从音频信号中通过声纹识别技术标识各个发言者的身份，并将发言者与文本中的相应内容进行关联，形成会议纪要。借助于上述技术方案，能够在会议纪要中向用户清楚的展示在会议中的发言者和其发言的内容。

公开(公告)号：WO2012135681A2

公开(公告)日：2012-10-04

申请号：PCT/US2012/031551

申请日：2012-03-30

Applicant: QUALCOMM Incorporated ,  JOHNSGARD, Todd J. ,  SIU, Ta-yan ,  SHI, Guangming

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 users 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.

Abstract translation: 公开了一种用于连续认证移动设备的用户的装置，系统和方法。 移动设备包括用户界面，收发器，麦克风和处理器。 在通话期间，处理器通过在预定义的周期性基础上或随机地获取语音片段，连续地从麦克风采样用户声音。 处理器还将来自麦克风的采样语音与存储的语音进行比较，以验证有效用户，其中如果采样的语音与有效用户的所存储的语音匹配，移动设备的功能将继续进行。 另一方面，如果采样语音与有效用户的存储语音不匹配，则移动设备的功能被锁定。

公开(公告)号：WO2009153581A1

公开(公告)日：2009-12-23

申请号：PCT/GB2009/001564

申请日：2009-06-19

Applicant: NEWVOICEMEDIA LTD ,  PICKERING, Richard ,  MOUSSALLI, Joseph ,  UNITT, Ashley

Inventor： PICKERING, Richard ,  MOUSSALLI, Joseph ,  UNITT, Ashley

IPC: H04M3/51 ,  G10L15/22 ,  G10L15/28 ,  G10L17/00

CPC classification number: H04M3/5175 ,  G10L15/22 ,  G10L15/30 ,  G10L17/00 ,  H04M3/42068 ,  H04M3/42221 ,  H04M3/5183 ,  H04M2201/41 ,  H04M2203/357

Abstract: One embodiment of the invention provides a computer-implemented method of handling a telephone call. The method comprises monitoring a conversation between an agent and a customer on a telephone line as part of the telephone call to extract the audio signal therefrom. Real-time voice analytics are performed on the extracted audio signal while the telephone call is in progress. The results from the voice analytics are then passed to a computer-telephony integration system responsible for the call for use by the computer-telephony integration system for determining future handling of the call.

Abstract translation: 本发明的一个实施例提供了一种处理电话呼叫的计算机实现的方法。 该方法包括在电话线路上监视代理和客户之间的会话，作为电话呼叫的一部分以从中提取音频信号。 当电话呼叫进行时，对所提取的音频信号执行实时语音分析。 然后将语音分析的结果传递到计算机电话集成系统，该系统负责计算机电话集成系统的呼叫以确定呼叫的未来处理。

公开(公告)号：WO2009042105A1

公开(公告)日：2009-04-02

申请号：PCT/US2008/010998

申请日：2008-09-23

Applicant: SIEMENS COMMUNICATIONS, INC. ,  CASPI, Rami ,  BEYDA, William, J.

Inventor： CASPI, Rami ,  BEYDA, William, J.

IPC: H04M3/56 ,  H04M3/38

CPC classification number: H04M3/568 ,  H04M3/385 ,  H04M3/387 ,  H04M2201/18 ,  H04M2201/38 ,  H04M2201/41 ,  H04M2203/6045 ,  H04M2242/30

Abstract: A method includes receiving audio electronic business card data during a conference; comparing said audio electronic business card data with voices of conference speakers to confirm identities of said speakers; performing an acoustic triangulation to determine a position of speakers; correlating a position of said speakers with said identities; and displaying locations of said speakers.

Abstract translation: 一种方法包括在会议期间接收音频电子名片数据; 将所述音频电子名片数据与会议扬声器的声音进行比较，以确认所述扬声器的身份; 执行声学三角测量以确定扬声器的位置; 将所述扬声器的位置与所述身份相关联; 并显示所述扬声器的位置。