公开(公告)号：EP1854271A2

公开(公告)日：2007-11-14

申请号：EP06740513.4

申请日：2006-04-05

Applicant: MICROSOFT CORPORATION

Inventor： PARKER, Cameron, J.

IPC: H04M3/42

CPC classification number: H04M3/56 ,  H04M3/563 ,  H04M2201/38 ,  H04M2201/41 ,  H04M2203/5054

Abstract: A method and system for identifying conference participants who dial in to a telephone conference of an electronic conference that includes a web conference is provided. To identify a conference participant, a conference system displays to a user the names of those conference participants who have not yet been associated with a telephone line of the telephone conference. The conference system plays to the user the identification announcement of a conference participant who is not yet associated with a telephone line. When the user hears the identification announcement, the user recognizes the name of the conference participant and selects the name of that conference participant from the displayed names. The conference system can then associate that conference participant with the telephone line associated with the identification announcement that was played to the user.

公开(公告)号：EP1798945A1

公开(公告)日：2007-06-20

申请号：EP06024688.1

申请日：2006-11-29

Applicant: Alcatel Lucent

Inventor： Wengrovitz, Michael S. ,  Gupta, Siddhartha

IPC: H04M3/56

CPC classification number: H04M3/56 ,  G10L15/26 ,  H04M2201/40 ,  H04M2201/41 ,  H04M2201/60 ,  H04N7/155

Abstract: A system for enabling controlled application of derived who-is-speaking indications related to activity of participants to a live multiparty communications conference or recorded outputs. The system includes a first node hosting a conference bridging switch, software or a combination thereof, having multiple conference input channels; a second node having data access to at least an output signal port of the conference bridging switch, software, or a combination thereof, and a software application distributed wholly to the first or second node, or in parts to the first and second node. The application is used to apply the who is speaking indications to output communications, data files, or data streams, forwarded to one of, a select potion of, or combination of, the conference participants, non-participant third parties, and one or more storage facilities.

Abstract translation: 一种能够将派生的与会人员的活动有关的现场指示用于实时多方通信会议或记录的输出的系统。 该系统包括承载会议桥接交换机的第一节点，具有多个会议输入信道的软件或其组合; 第二节点，具有对会议桥接交换机，软件或其组合的至少输出信号端口的数据访问，以及完全分配给第一或第二节点的软件应用程序，或部分分配给第一和第二节点。 该应用程序用于应用谁在说明指示来输出通信，数据文件或数据流，转发给会议参与者，非参与者第三方和一个或多个的选择部分或组合的一个 储存设施。

公开(公告)号：EP1771999A2

公开(公告)日：2007-04-11

申请号：EP05775329.5

申请日：2005-07-28

Applicant: SBC Knowledge Ventures L.P.

Inventor： NOVACK, Brian M. ,  MADSEN, Daniel Larry ,  THOMPSON, Timothy R.

IPC: H04M1/66 ,  H04M1/64 ,  H04L12/66

CPC classification number: H04L63/0861 ,  G06F21/32 ,  G06Q20/40145 ,  H04M3/38 ,  H04M7/006 ,  H04M7/0078 ,  H04M2201/41 ,  H04M2203/6045 ,  H04W12/02 ,  H04W12/06 ,  H04W12/08

Abstract: A system (200) is provided for verifying an identity of a calling party. The system includes a storage (210) that stores voice sample information in association with information that idetifies an individual. The system also includes a receiver (221) that receives, from a communications platform (150/152/154) called by the calling party, a request to authenticate the identity of the calling party as the individual, using a digital audio sample packetized according to voice over internet protocol and obtained from the calling party during the call. Additionally, the system includes a processor (223) that compares the digital audio sample to the voice sample information to authenticate the identity of the calling party as the individual.

公开(公告)号：EP1592282A4

公开(公告)日：2006-08-09

申请号：EP04708849

申请日：2004-02-06

Applicant: NIPPON TELEGRAPH & TELEPHONE

Inventor： KOBAYASHI K ,  FURUYA K

IPC: G10L11/02 ,  G10L21/02 ,  H04R3/00 ,  H03H17/02 ,  H03H21/00 ,  H04B3/20 ,  H04M1/60

CPC classification number: H04M3/56 ,  G10L21/0364 ,  G10L25/78 ,  G10L2021/02166 ,  H04M2201/41 ,  H04R3/005

Abstract: When a speech section is detected by a state judging section (14), the positions of the sound sources(91 to 9K) are determined by a sound source position detecting section (15). A covariance matrix of the received sound signal is determined correspondingly to each sound source by a covariance matrix calculating section (17) and stored in a covariance matrix storage section (18) correspondingly to the sound source. The levels of the collected sounds from the sound sources are deduced from the covariance matrices by a collected sound level deducing section (19). The filter factors are determined from the deduced collected sound levels and the covariance matrices by a filter factor calculating section (21) so that the output level may be a predetermined value. The determined filter factors are assigned to filters (121 to 12M). The received sound signals from the microphones are processed by means of the filters, and the results of the processings are added by an adder (13) and outputted as a speech transmission signal. Thus, irrespective of the positions of the sound sources, a speech transmission signal of desired level can be generated.

公开(公告)号：EP1571815A2

公开(公告)日：2005-09-07

申请号：EP05012139.1

申请日：1997-05-30

Applicant: WorldVoice Inc.

Inventor： Finnigan, Paul F.

IPC: H04M3/50

CPC classification number: H04M3/53366 ,  G10L17/00 ,  H04M3/42042 ,  H04M3/42059 ,  H04M3/42093 ,  H04M3/42102 ,  H04M3/487 ,  H04M3/533 ,  H04M3/53325 ,  H04M3/53383 ,  H04M2201/40 ,  H04M2201/41

Abstract: Authentication of voice message recipient network addresses employs generating (102) and storing (104) a "network file" that includes "voice clips" and associated network addresses that are extracted from voice messages received across a network (10) from voice message systems (16, 18). A voice clip is the first one to three seconds of voice extracted from each received voice message. Over time, the network file will grow to contain multiple voice clips and associated network voice message addresses. When a voice message originator subsequently enters a recipient's network address (106), the originating voice message system searches (114) the network file for the network address, retrieves the associated voice clip (116), and plays it for the voice message originator to authenticate the recipient's network address. Voice authentication of a voice message originator entails encoding (134) into a "voice print file", original voice clips and associated network addresses received from positively identified voice message originators. Thereafter, when a questionable voice message is received (138), the voice message system extracts a new voice clip (142), generates a new voice print (144), and compares it with the original voice print associated with the voice message address (148). If the voice prints are substantially the same, the received voice message is annotated with an "authenticating" message (150).

Abstract translation: 语音消息接收网络地址的认证采用生成（102）并存储（104）包括“语音剪辑”的相关网络地址和从网络（10）从语音消息系统接收的语音消息中提取的相关网络地址的“网络文件” 16，18）。 语音剪辑是从每个接收到的语音消息中提取的第一个到三秒的语音。 随着时间的推移，网络文件将增长到包含多个语音片段和相关联的网络语音消息地址。 当语音消息发起者随后进入接收者的网络地址（106）时，始发语音消息系统搜索网络文件（114）网络地址，检索相关联的语音剪辑（116），并将其播放给语音消息发起者 验证收件人的网络地址。 语音消息发起者的语音认证需要编码（134）到“语音打印文件”，从主动识别的语音消息发起者接收的原始语音片段和相关联的网络地址。 此后，当接收到有问题的语音消息（138）时，语音消息系统提取新的语音剪辑（142），生成新的语音打印（144），并将其与与语音消息地址相关联的原始语音打印（ 148）。 如果语音打印基本上相同，则接收的语音消息用“认证”消息（150）注释。

公开(公告)号：EP1447794A1

公开(公告)日：2004-08-18

申请号：EP03002679.3

申请日：2003-02-12

Applicant: Kuebler, Hans, Dr.

Inventor： Kuebler, Hans, Dr.

IPC: G10L17/00

CPC classification number: G10L17/22 ,  H04M3/385 ,  H04M3/4938 ,  H04M2201/41

Abstract: Die Benutzung eines Telefons als Zugangsterminal zum Intranet/Internet mittels der Sprachkommunikation ist einerseits sehr komfortabel, eröffnet jedoch andererseits auch neue Möglichkeiten des unbefugten Zugriffs. Dieser kann insbesondere dadurch entstehen, dass eine Session de facto unterbrochen wird, die aufgebaute Verbindung zu dem/den Server(n) jedoch nicht, sodass die bestehende Einwahl mit der Autorisierung bestehen bleibt. Dies kann insbesondere bei der Spracheingabe geschehen, da es durchaus sinnvoll erscheint, diese Art des Zugriffs auf das Intranet/Internet auch dann zu benutzen, wenn zuzüglich am Schreibtisch Akten bearbeitet werden z. B., sodass der Nutzer nicht immer sich im klaren ist, ob der Zugang noch aktiv ist oder nicht.
Die Erfindung ermöglicht nun kontinuierlich oder in unregelmäßigen oder auch regelmäßigen zeitlichen Abständen die Authentisierung der Person dadurch zu überprüfen, dass ― erfindungsgemäß ― das Profil der Sprache der bedienenden Person mit dem spezifischen gespeicherten Profil der Person verglichen wird, die unter der Anmeldung sich autorisiert hat. Dies setzt jedoch voraus, dass das System der Spracheingabe mit personenspezifischen Sprachprofilen arbeitet.

Abstract translation: 通过语音识别方法认证连接到网络，特别是基于IP的网络的用户的方法。 根据该方法，用户的语音被连续地，定期地或随机地检查，以确定接收到的语音相对于最初授权和识别的说话者是否已经发生了重大变化。 支票用于语音检查或验证。

公开(公告)号：EP1381210A1

公开(公告)日：2004-01-14

申请号：EP03014585.8

申请日：2003-07-08

Applicant: ALCATEL

Inventor： Mani, Babu V.

IPC: H04M3/42 ,  H04M3/38

CPC classification number: H04M3/42 ,  G10L17/00 ,  H04M3/38 ,  H04M2201/41 ,  H04M2203/6054

Abstract: A method for identifying a caller based on voice recognition is provided that includes receiving call data from a communication device through a communication network. The call data comprises voice data for a user of the communication device. A search is performed for an identifying data match based on the terminal identification data. A voice recognition system is activated when an identifying data match is found and uniquely identifies a terminal. A search is performed for a first voice pattern match with the voice recognition system based on the call data. A user identifier corresponding to the first voice pattern is provided to the communication network when the first voice pattern match is found, the user identifier operable to identify the user of the communication device.

Abstract translation: 提供了一种基于语音识别来识别呼叫者的方法，其包括通过通信网络从通信设备接收呼叫数据。 呼叫数据包括用于通信设备的用户的语音数据。 基于终端识别数据进行识别数据匹配的搜索。 当找到识别数据匹配并唯一地识别终端时，语音识别系统被激活。 基于呼叫数据，执行与语音识别系统的第一语音模式匹配的搜索。 当发现第一语音模式匹配时，将与第一语音模式对应的用户标识符提供给通信网络，该用户标识符用于识别通信设备的用户。

公开(公告)号：EP0846395B1

公开(公告)日：2002-10-09

申请号：EP96924297.3

申请日：1996-06-27

Applicant: AT&T Corp.

Inventor： BRUNO, Richard, F. ,  GIBBON, David, C. ,  KATSEFF, Howard, P. ,  MARKOWITZ, Robert, E. ,  ROBINSON, Bethany, S. ,  SHAHRARAY, Behzad ,  STUNTEBECK, Peter, H. ,  WEBER, Roy, P.

IPC: H04N7/15

CPC classification number: H04M3/42221 ,  H04M3/567 ,  H04M2201/41 ,  H04N7/142 ,  H04N7/147 ,  H04N7/15 ,  H04N7/152

Abstract: A method and apparatus for recording and indexing audio information exchanged during an audio conference call, or video, audio and data information exchanged during a multimedia conference. For a multimedia conference, the method and apparatus utilize the voice activated switching functionality of a multipoint control unit (MCU) (26) to provide a video signal, which is input to the MCU (26) from a workstation from which an audio signal is detected, to each of the other workstations participating in the conference. A workstation and/or participant-identifying signal generated by the multipoint control unit (26) is stored, together or in correspondence with the audio signal and video information, for subsequent ready retrieval of the stored multimedia information. For an audio conference, a computer (32') is connected to an audio bridge (44) for recording the audio information along with an identification signal for correlating each conference participant with that participant's statements.

公开(公告)号：EP0823701A2

公开(公告)日：1998-02-11

申请号：EP97305924.9

申请日：1997-08-05

Applicant: Gammalink Corporation

Inventor： Fromm, Laurence J.

IPC: G10L5/06 ,  G10L7/08 ,  G10L9/06 ,  G10L9/18

CPC classification number: G06Q20/40145 ,  G06Q20/40 ,  G10L17/00 ,  H04M3/385 ,  H04M3/493 ,  H04M7/12 ,  H04M2201/40 ,  H04M2201/41

Abstract: A technique for verifying a user's voice prior to permitting the user to conduct a business transaction over a data network is disclosed. An order is received via the data network, and a voice verification unit is contacted to (i) access a prestored voice print, (ii) obtain a present voice sample from the consumer desiring the transaction and compare said present voice sample to the prestored voice sample, and (iii) issue a signal indicating whether or not the voice correctly verifies or not.

Abstract translation: 公开了一种用于在允许用户通过数据网络进行业务交易之前验证用户的语音的技术。 经由数据网络接收订单，并且接触语音验证单元（i）访问预存的语音打印，（ii）从想要交易的消费者获得当前语音样本，并将所述当前语音样本与预存的语音进行比较 样本，（iii）发出一个信号，指示语音是否正确验证。

公开(公告)号：EP0598469A2

公开(公告)日：1994-05-25

申请号：EP93303061.1

申请日：1993-04-20

Applicant: Dunlevy, Daniel P.

Inventor： Dunlevy, Daniel P.

IPC: G07F7/10 ,  G06F15/30

CPC classification number: G06Q20/04 ,  G06Q20/389 ,  G06Q20/403 ,  G07C9/00087 ,  G10L17/22 ,  H04M3/385 ,  H04M15/00 ,  H04M2201/41

Abstract: The INTERACTIVE CREDIT CARD FRAUD CONTROL PROCESS system utilizes a computer with telephone interface, memory, voice recognition software and hardware, and an information archive and retrieval process. A computer program (10) is used to automatically and electronically control the determination of the caller as the authorized credit card holder, or conversely an unauthorized perpetrator attempting to make a credit card transaction. The telephone interface is connected to a telephone line and the caller dials a number that connects the caller with the present invention (12), which then captures certain information about the incoming call (14 & 16) and creates a permanent Record Stamp (18) of the call to which transactional information is added as the call progresses. The caller is asked question prompts, and the system receives voice and touch tone responses from the caller from which the system determines if a VoicePrint is applicable (20). The caller responses are managed by the present invention in a method that determines if the caller is the authorized credit card holder, and if the caller is not the authorized credit card holder the present invention captures information that can lead to the capture and conviction of the caller as a credit card fraud felon. The present invention uses the caller's spoken voice print of the card holder's name as one of the determining factors to determine if the caller is the authorized credit card holder (22). The VoicePrint, included in a claim in the present invention, uniquely and positively identifies a single person, and therefore becomes a valuable tool and evidence in the apprehension and conviction of perpetrators of credit card fraud. With a VoicePrint of the authorized credit card holder on file, the present invention prevents any other person except approved persons from making credit card transactions with that card number. Even without the VoicePrint, the control process is highly effective in limiting fraud risk and the present invention creates a VoicePrint of the caller, ties that identifier to the Record Stamp, and can thereafter identify that person as the person who was the caller. Additional claims relate to using the present invention for security and access control, including the gathering of positive identifying evidence of perpetrators.

Abstract translation: 交互式信用卡欺诈控制过程系统利用具有电话接口，存储器，语音识别软件和硬件的计算机以及信息归档和检索过程。 计算机程序（10）用于自动和电子地控制作为授权信用卡持有者的呼叫者的确定，或者相反地，试图进行信用卡交易的未经授权的肇事者。 电话接口连接到电话线路，呼叫方拨打将呼叫者连接到本发明（12）的号码，然后本发明（12）捕获有关来话呼叫（14和16）的某些信息，并创建一个永久记录邮票（18） 在呼叫进行时添加事务信息的呼叫。 呼叫者被询问提示，系统接收来自呼叫者的语音和触摸音响应，系统确定VoicePrint是否适用（20）。 呼叫者响应由本发明以一种方法来管理，该方法确定呼叫者是否是授权的信用卡持有者，如果呼叫者不是授权的信用卡持有者，则本发明捕获可导致捕获和定罪的信息 来电者作为信用卡诈骗重罪。 本发明使用呼叫者的持卡人姓名的语音打印作为决定因素之一来确定呼叫者是否是授权的信用卡持有人（22）。 包含在本发明的权利要求中的VoicePrint独特且积极地识别了一个人，因此成为信用卡欺诈者的担心和定罪的宝贵工具和证据。 通过授权的信用卡持有者的VoicePrint的文件，本发明防止任何其他人除了获得批准的人员与该卡号进行信用卡交易。 即使没有VoicePrint，控制过程在限制欺诈风险方面也是非常有效的，本发明创建了呼叫者的VoicePrint，将该标识符与记录戳相关联，并且此后可以将该人称为作为呼叫者的人。 附加权利要求涉及将本发明用于安全和访问控制，包括收集肇事者的积极确定证据。