一种语音会议纪要的分类方法、设备和系统

    公开(公告)号:WO2014082445A1

    公开(公告)日:2014-06-05

    申请号:PCT/CN2013/078598

    申请日:2013-07-01

    Inventor: 詹五洲

    Abstract: 一种语音会议纪要的分类方法、设备和系统,能够将会场中的语音数据按照说话人的方位分别进行声纹识别,提高了声纹识别准确率,进而提高了语音会议纪要分类的可靠性。其方法为:根据会场的音频数据进行声源定位,以获取音频数据所对应的声源的方位,并将声源的方位写入音频数据的附加域信息,再将语音激活标志写入附加域信息,而后将音频数据打包成音频码流,并将音频码流和音频码流的附加域信息发送至录播服务器,以使得录播服务器根据附加域信息对音频数据进行分类,将音频数据所对应的声源的方位对应的参会者身份写入音频码流的附加域信息中。

    CALLER IDENTIFICATION FOR MISSED CALLS
    213.
    发明申请
    CALLER IDENTIFICATION FOR MISSED CALLS 审中-公开
    错误呼叫的呼叫者识别

    公开(公告)号:WO2013003033A1

    公开(公告)日:2013-01-03

    申请号:PCT/US2012/042121

    申请日:2012-06-13

    Abstract: Methods and devices are provided for identifying a caller after receiving a missed call from a calling device (502) that is not associated with the caller. An exemplary method involves obtaining (204) an audio message from the caller, recognizing (208) the caller as being a first contact of the called individual by matching (206) an audio sample associated with the first contact to at least a portion of the audio message, and graphically indicating (210) an association between the first contact and the missed call after recognizing the first contact as the caller.

    Abstract translation: 提供方法和设备用于在从与呼叫者不相关联的呼叫设备(502)接收到未接来电之后识别呼叫者。 一个示例性的方法涉及从呼叫者获得(204)音频消息,通过将与第一接触相关联的音频样本(206)与第一接触相关联的音频样本(206)识别(208)呼叫者作为被呼叫个体的第一接触, 音频消息,并且在识别出第一联系人作为呼叫者之后图形地指示(210)第一联系人和未接来电的关联。

    SPEECH COMPARISON
    214.
    发明申请
    SPEECH COMPARISON 审中-公开
    语音比较

    公开(公告)号:WO2012042200A1

    公开(公告)日:2012-04-05

    申请号:PCT/GB2011/001399

    申请日:2011-09-27

    Inventor: PAWLEWSKI, Mark

    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.

    Abstract translation: 为了发现银行帐户或其他账户的细节,虚伪的呼叫者伪装成合法的呼叫者是一个越来越多的问题。 为了检测可能的欺诈者并阻止他们获得这样的细节,提出了将一批来电的记录语音转换成音素或文本字符串的方法和系统。 此后,确定记录的语音中类似的语音模式,例如不同的类似的短语或措词,并且具有相似的语音模式,并且优选地也是类似的声学特性的呼叫被分组在一起并被识别为来自相同的欺诈呼叫者。 可以停止由欺诈性呼叫者发起的交易,并且优选地生成欺诈性呼叫者语音的声纹并存储在数据库中以供进一步使用。

    CORRELATING CALL LOG FILES USING VOICE PRINTS
    215.
    发明申请
    CORRELATING CALL LOG FILES USING VOICE PRINTS 审中-公开
    使用语音打印机调用日志文件

    公开(公告)号:WO2011047914A1

    公开(公告)日:2011-04-28

    申请号:PCT/EP2010/062692

    申请日:2010-08-31

    CPC classification number: H04M3/42221 H04M3/2218 H04M3/5175 H04M2201/41

    Abstract: A system is presented for logging and recording a call to a call network. The system comprises a voice print logic for generating a voice print of a caller who is making a call to a call network. A telecom routing switch generates a correlated telecom router switch log file by appending the voice print of the caller to a telecom router switch log file for the call. A telecom software system generates a correlated telecom software system log file by appending the voice print of the caller to a telecom software system log file for the call. A contact center agent generates a correlated contact center agent log file by appending the voice print of the caller to a contact center agent log file for the call. The voice print is utilized to retrieve and to consolidate the correlated telecom router switch log file, the correlated telecom software system log file, and the correlated contact center agent log file into a single correlated file for the call.

    Abstract translation: 提出了一种用于记录和记录呼叫到呼叫网络的系统。 该系统包括用于生成正在呼叫呼叫​​网络的呼叫者的语音打印的语音打印逻辑。 电信路由交换机通过将呼叫者的语音打印附加到用于呼叫的电信路由器交换机日志文件来生成相关的电信路由器交换机日志文件。 电信软件系统通过将呼叫者的语音打印附加到用于呼叫的电信软件系统日志文件来生成相关的电信软件系统日志文件。 联络中心代理通过将呼叫者的语音打印附加到呼叫的联络中心代理日志文件来生成相关的联络中心代理日志文件。 语音打印用于检索并将相关的电信路由器交换机日志文件,相关的电信软件系统日志文件和相关的联络中心代理日志文件合并到用于该呼叫的单个相关文件中。

    METHOD AND SYSTEM FOR LOCALIZING AND AUTHENTICATING A PERSON
    216.
    发明申请
    METHOD AND SYSTEM FOR LOCALIZING AND AUTHENTICATING A PERSON 审中-公开
    用于本地化和认证人员的方法和系统

    公开(公告)号:WO2009135517A1

    公开(公告)日:2009-11-12

    申请号:PCT/EP2008/003768

    申请日:2008-05-09

    Abstract: The present invention refers to a method for localizing a person comprising the steps carried out in a computing system (1) : determining (20) the localization of a telecommunication means (3, 6, 8) or determining a telecommunication means (3, 6, 8) at a specific location; this can be implemented using ANI or calling number received and a database to look up address of a fixed telephone, for a cellular device, cell-ID or triangulation can be used; receiving (21) a voice utterance of a person by the telecommunications means; and verifying (22) the identity of that person based on the received voice utterance using biometric voice data (speech, speaker recognition). Further the invention relates to a corresponding system and computer readable medium.

    Abstract translation: 本发明涉及一种用于定位人的方法,包括在计算系统(1)中执行的步骤:确定(20)电信装置(3,6,8)的定位或确定电信装置(3,6 ,8)在特定位置; 这可以使用ANI或接收到的主叫号码来实现,并且可以使用数据库来查找固定电话的地址,对于蜂窝设备,小区ID或三角测量; 接收(21)电讯手段对某人的发声; 以及使用生物特征语音数据(语音,说话者识别),基于所接收的语音话语来验证(22)该人的身份。 此外,本发明涉及相应的系统和计算机可读介质。

    METHOD AND SYSTEM FOR ADDING A CALLER IN A BLOCKED LIST
    217.
    发明申请
    METHOD AND SYSTEM FOR ADDING A CALLER IN A BLOCKED LIST 审中-公开
    用于在阻塞列表中添加呼叫者的方法和系统

    公开(公告)号:WO2009067356A1

    公开(公告)日:2009-05-28

    申请号:PCT/US2008/083095

    申请日:2008-11-11

    Abstract: A method and system for adding a caller (102) in a blocked list is provided. The blocked list is stored at a communication server (104). The method includes receiving (604) a call from the caller (102) at a communication device (108). Further, the method includes receiving (606) a set of inputs at the communication device (108) in response to the call. The set of inputs includes a set of instructions to add the caller (102) in the blocked list. Furthermore, the method includes transmitting (608) a call termination request to the communication server (104). The call termination request includes the set of instructions to add the caller (102) in the blocked list. Transmission of the call termination request initiates addition of the caller (102) in the blocked list at the communication server (104).

    Abstract translation: 提供了一种在被阻止的列表中添加呼叫者(102)的方法和系统。 阻塞列表存储在通信服务器(104)。 该方法包括在通信设备(108)处接收(604)来自呼叫者(102)的呼叫(604)。 此外,该方法包括响应于该呼叫在通信设备(108)处接收(606)一组输入。 该组输入包括一组用于将呼叫者(102)添加到阻塞列表中的指令。 此外,该方法包括向通信服务器(104)发送(608)呼叫终止请求。 呼叫终止请求包括将呼叫者(102)添加到阻塞列表中的一组指令。 呼叫终止请求的发送在通信服务器(104)发起阻塞列表中的呼叫者(102)的添加。

    METHOD AND DEVICE FOR THE CONTROL OF A USER'S ACCESS TO A SERVICE PROVIDED IN A DATA NETWORK
    218.
    发明申请
    METHOD AND DEVICE FOR THE CONTROL OF A USER'S ACCESS TO A SERVICE PROVIDED IN A DATA NETWORK 审中-公开
    方法和设备用于控制用户访问一个中提供的数据网络服务

    公开(公告)号:WO2008116858A3

    公开(公告)日:2009-05-07

    申请号:PCT/EP2008053468

    申请日:2008-03-25

    CPC classification number: H04L63/0861 H04M3/38 H04M3/493 H04M2201/41

    Abstract: The invention relates to a method for the control of a user's access to a service provided in a data network for the purpose of protecting user data stored in a database of the service from unauthorized access, said method comprising: Inputting a speech sample of the user into a user's data terminal in a VoIP session, said data terminal being connected at least temporarily to the data network, processing the user's speech sample in a first processing step using a dedicated client implemented in the user's data terminal for the purpose of obtaining a preprocessed speech sample or current voice profile of the user, additional processing of the preprocessed speech sample or current voice profile in a second processing step, including a comparison step of the current voice profile to an initial voice profile stored in a database, and outputting an access control signal to allow or deny access to the service, taking into account the results of the comparison step.

    Abstract translation: 一种用于控制在一个数据网络服务提供给保护存储的用户数据对在所述服务的数据的基础上的未授权访问的服务的用户访问的方法,该方法包括:在VoIP会话输入用户的声音样本到用户数据终端包括至少 暂时连接到数据网络,处理在第一处理步骤中,用户的语音样本,使用专用客户端在用户终端中实现,以获得预处理的语音样本,或者用户的实际语音简档,其进一步处理该预处理的语音样本或 在第二处理步骤中的ktuellen语音简档,包括当前语音配置文件与存储在数据库中的初始语音简档进行比较;以及授予或接入至d的拒绝输出的访问控制信号的步骤的 的服务,考虑到比较步骤的结果。

    METHOD AND SYSTEM FOR ASSOCIATING A CONFERENCE PARTICIPANT WITH A TELEPHONE CALL
    219.
    发明申请
    METHOD AND SYSTEM FOR ASSOCIATING A CONFERENCE PARTICIPANT WITH A TELEPHONE CALL 审中-公开
    与电话会议的会议参与者相关联的方法和系统

    公开(公告)号:WO2006118734A3

    公开(公告)日:2009-05-07

    申请号:PCT/US2006012554

    申请日:2006-04-05

    Applicant: MICROSOFT CORP

    Inventor: PARKER CAMERON J

    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.

    Abstract translation: 提供了一种用于识别参加包括网络会议的电子会议的电话会议的会议参与者的方法和系统。 为了识别会议参与者,会议系统向用户显示尚未与电话会议的电话线路相关联的那些会议参与者的姓名。 会议系统向用户播放尚未与电话线相关联的会议参与者的识别通知。 当用户听到识别通知时,用户识别会议参与者的姓名,并从显示的名称中选择该会议参与者的姓名。 然后,会议系统可以将该会议参与者与与播放的识别通知相关联的电话线路与用户相关联。

    DIGITALES VERFAHREN UND ANORDNUNG ZUR AUTHENTIFIZIERUNG EINES NUTZERS EINES TELEKOMMUNIKATIONS- BZW. DATENNETZES
    220.
    发明申请
    DIGITALES VERFAHREN UND ANORDNUNG ZUR AUTHENTIFIZIERUNG EINES NUTZERS EINES TELEKOMMUNIKATIONS- BZW. DATENNETZES 审中-公开
    用于认证的电信的用户数字化方法以及系统或 数据网络

    公开(公告)号:WO2008098839A1

    公开(公告)日:2008-08-21

    申请号:PCT/EP2008/051117

    申请日:2008-01-30

    Abstract: Digitales Verfahren zur Authentifizierung eines Nutzers eines Telekommunikations- bzw. Datennetzes für einen Zugriff zu geschützten Daten oder einer einem definierten Nutzerkreis vorbehaltenen Leistung oder für die Verwendung aktuell durch den Nutzer eingegebener Daten, wobei eine aktuell bei einem Zugriffs-Versuch durch den Nutzer an einem Telekommunikations- oder VoIP-Endgerät eingesprochene Sprachprobe einer Stimmanalyseeinrichtung zugeführt und hierin ein aktuelles Stimmprofil errechnet und dieses in einer Stimmprofil-Vergleichereinheit mit einem vorgespeicherten initialen Stimmprofil verglichen und im Ansprechen auf ein positives Vergleichsergebnis der Nutzer authentifiziert und ein den Zugriff freigebendes erstes Steuersignal, jedoch im Ansprechen auf ein negatives Vergleichsergebnis ein den Zugriff sperrendes oder eine Ersatz-Authentifizierungsprozedur triggerndes zweites Steuersignal erzeugt wird.

    Abstract translation: 用于认证通信或数据网络的用户访问受保护的数据或一个保留的一组已定义的用户的性能或用于由用户输入数据中的使用的电流,数字方法,其中在由所述用户的访问尝试的电信的电流 语音分析装置供给或VoIP终端eingesprochene语音样本和本文计算是当前语音简档,该声纹比较单元与一个预先存储的初始声纹和认证响应于肯定的比较结果,在用户和访问释放第一控制信号,而在响应 - 负比较结果,接入阻断或替换认证过程triggerndes产生第二控制信号。

Patent Agency Ranking