公开(公告)号：US07349527B2

公开(公告)日：2008-03-25

申请号：US10769137

申请日：2004-01-30

Applicant: Sherif Yacoub ,  Steven J. Simske ,  Xiaofan Lin ,  Francois Vincent

Inventor： Sherif Yacoub ,  Steven J. Simske ,  Xiaofan Lin ,  Francois Vincent

IPC: H04M1/64

CPC classification number: H04M3/4936 ,  G10L15/26 ,  H04M3/5166 ,  H04M2201/41

Abstract: A system and method for extracting demographic information from a contact is disclosed. The method discloses: initiating a dialog between a contact and a call handling system; selecting a set of demographic characteristics; assigning a set of acoustic confidence scores; assigning a set of substantive confidence scores; combining the acoustic and substantive confidence scores; and tailoring information presented to the contact using the set of combined confidence scores. The system discloses: an Interactive Voice Response module for initiating a dialog between a contact and a call handling system, and selecting a set of demographic characteristics; an acoustic classifier for assigning a set of acoustic confidence scores; a substantive classifier for assigning a set of substantive confidence scores; and a data combiner for combining the acoustic and substantive confidence scores. The Interactive Voice Response module also tailors information presented to the contact using the set of combined confidence scores.

Abstract translation: 公开了一种从联系人中提取人口统计信息的系统和方法。 该方法公开：在联系人和呼叫处理系统之间发起对话; 选择一组人口特征; 分配一组声信心得分; 分配一组实质信心分数; 结合声学和实质的信心得分; 并使用一组组合的置信分数来裁剪提供给联系人的信息。 该系统公开了一种交互式语音响应模块，用于启动联系人和呼叫处理系统之间的对话，并且选择一组人口特征; 声分类器，用于分配一组声信心分数; 用于分配一组实质信心分数的实质分类器; 以及用于组合声学和实质可信度得分的数据组合器。 交互式语音应答模块还使用组合的置信分数来定制呈现给联系人的信息。

公开(公告)号：US20070274293A1

公开(公告)日：2007-11-29

申请号：US11441519

申请日：2006-05-26

Applicant: Scott C. Forbes

Inventor： Scott C. Forbes

IPC: H04L12/66

CPC classification number: H04L63/08 ,  H04L63/0823 ,  H04L63/0861 ,  H04L65/1083 ,  H04M3/42221 ,  H04M7/006 ,  H04M2201/41

Abstract: Generally described, the present invention is directed to a method and system that provides the ability to record and store a digital conversation exchanged among mutually agreed parties in a specified archive database. In some instances, content of a digital conversations may be stored (e.g., for legal and/or medical purposes) along with the authenticity of those conversations. Parties who are involved in the digital conversation can authenticate and associate themselves with the conversation. The authentication may be integrated or bound with the digital conversation so that the digital conversation can be stored with a proof of authenticity in the specified archive database. The stored conversation may be retrieved by the parties or any entity with a delegation from the party for reviewing the conversation, or incorporating new information into the stored conversation.

Abstract translation: 通常描述，本发明涉及一种方法和系统，其提供在指定的归档数据库中记录和存储在相互同意的方之间交换的数字对话的能力。 在某些情况下，可以存储数字对话的内容（例如，用于合法和/或医疗目的）以及那些会话的真实性。 参与数字对话的各方可以对会话进行身份验证和关联。 认证可以与数字会话集成或绑定，以便可以在指定的归档数据库中存储具有真实性证明的数字会话。 所存储的对话可以由双方或具有来自该方的授权的任何实体检索以查看对话，或者将新信息合并到存储的对话中。

公开(公告)号：US20070263823A1

公开(公告)日：2007-11-15

申请号：US11393685

申请日：2006-03-31

Applicant: Teemu Jalava ,  Jussi Virolainen

Inventor： Teemu Jalava ,  Jussi Virolainen

IPC: H04M3/42

CPC classification number: H04M3/56 ,  H04M3/387 ,  H04M3/568 ,  H04M2201/41 ,  H04M2207/18

Abstract: Techniques for positioning participants of a conference call in a three dimensional (3D) audio space are described. Aspects of a system for positioning include a client component that extracts speech frames of a currently speaking participant of a conference call from a transmission signal. A speech analysis component determines a voice fingerprint of the currently speaking participant based upon any of a number of factors, such as a pitch value of the participant. A control component determines a category position of the currently speaking participant in a three dimensional audio space based upon the voice fingerprint. An audio engine outputs audio signals of the speech frame based upon the determined category position of the currently speaking participant. The category position of one or more participants may be changed as new participants are added to the conference call.

Abstract translation: 描述用于在三维（3D）音频空间中定位电话会议的参与者的技术。 用于定位的系统的方面包括从传输信号提取会议呼叫的当前会话的参与者的语音帧的客户端组件。 语音分析组件基于诸如参与者的音调值的多个因素中的任何一个来确定当前说话的参与者的语音指纹。 控制组件基于语音指纹确定三维音频空间中当前讲话的参与者的类别位置。 音频引擎基于当前说话的参与者的确定的类别位置来输出语音帧的音频信号。 一个或多个参与者的类别位置可以随着新的参与者被添加到电话会议而改变。

公开(公告)号：US07206387B2

公开(公告)日：2007-04-17

申请号：US10645051

申请日：2003-08-21

Applicant: Ea-Ee Jan ,  Benoit Maison ,  Andrzei Sakrajda

Inventor： Ea-Ee Jan ,  Benoit Maison ,  Andrzei Sakrajda

IPC: H04M1/64

CPC classification number: H04M3/50 ,  H04L67/1002 ,  H04L2012/6443 ,  H04L2012/6481 ,  H04M2201/39 ,  H04M2201/40 ,  H04M2201/41

Abstract: A voice processing system is provided in which sets of engines running on a plurality of servers are configured differently from one another. The sets of engines may be configured to achieve different trade-offs between performance of a task and resources required to perform the task. In the voice processing system, a task routing server is provided that assigns different sets of sub-tasks to different sets of task engines. The number of engines used to perform a task and the number of engines in each set are adjusted. By adjusting the parameters settings for the set of engines based on the type of application, the particular requirements of the application, or the nature and importance of the subtasks, for example, advantages such as improvement of resource utilization and the hardware and software costs reduction may be obtained.

Abstract translation: 提供语音处理系统，其中在多个服务器上运行的引擎组彼此不同地配置。 发动机组可以被配置为在执行任务和执行任务所需的资源之间实现不同的权衡。 在语音处理系统中，提供了将不同的子任务集分配给不同的任务引擎组的任务路由服务器。 调整用于执行任务的引擎数量和每组中的引擎数量。 通过基于应用程序的类型，应用程序的特定要求或子任务的性质和重要性调整引擎集的参数设置，例如资源利用率的提高以及降低硬件和软件成本的优点 可以获得。

公开(公告)号：US20070071206A1

公开(公告)日：2007-03-29

申请号：US11475541

申请日：2006-06-26

Applicant: Jay Gainsboro ,  Lee Weinstein

Inventor： Jay Gainsboro ,  Lee Weinstein

IPC: H04M9/00 ,  H04M1/60

CPC classification number: G10L25/63 ,  G10L15/1807 ,  G10L17/00 ,  G10L21/12 ,  H04M3/2281 ,  H04M2201/41

Abstract: A multi-party conversation analyzer and logger uses a variety of techniques including spectrographic voice analysis, absolute loudness measurements, directional microphones, and telephonic directional separation to determine the number of parties who take part in a conversation, and segment the conversation by speaking party. In one aspect, the invention monitors telephone conversations in real time to detect conditions of interest (for instance, calls to non-allowed parties or calls of a prohibited nature from prison inmates). In another aspect, automated prosody measurement algorithms are used in conjunction with speaker segmentation to extract emotional content of the speech of participants within a particular conversation, and speaker interactions and emotions are displayed in graphical form. A conversation database is generated which contains conversation recordings, and derived data such as transcription text, derived emotions, alert conditions, and correctness probabilities associated with derived data. Investigative tools allow flexible queries of the conversation database.

Abstract translation: 多方会话分析器和记录器使用各种技术，包括光谱语音分析，绝对响度测量，定向麦克风和电话方向分离，以确定参与对话的各方数量，并通过会话分割对话。 一方面，本发明实时监控电话对话以检测感兴趣的情况（例如，对不允许的当事人的呼叫或被监禁的囚犯的被禁止的呼叫）。 在另一方面，自动化韵律测量算法与说话者分割结合使用以提取特定对话内的参与者的言语的情感内容，并且以图形形式显示说话人的交互和情绪。 生成会话数据库，其中包含会话记录，以及衍生数据，如转录文本，派生情绪，警报条件以及与派生数据相关联的正确性概率。 调查工具允许会话数据库的灵活查询。

公开(公告)号：US20070025538A1

公开(公告)日：2007-02-01

申请号：US11179347

申请日：2005-07-11

Applicant: Petri Jarske ,  Jussi Virolainen

Inventor： Petri Jarske ,  Jussi Virolainen

IPC: H04M3/42

CPC classification number: H04M3/56 ,  H04M1/6016 ,  H04M2201/41

Abstract: A method for distinguishing speakers in a conference call of a plurality of participants, in which method speech frames of the conference call are received in a receiving unit, which speech frames include encoded speech parameters. At least one parameter of the received speech frames is examined in an audio codec of the receiving unit, and the speech frames are classified to belong to one of the participants, the classification being carried out according to differences in the examined at least one speech parameter. These functions may be carried out in a speaker identification block, which is applicable in various positions of a teleconferencing processing chain. Finally, a spatialization effect is created in a terminal reproducing the audio signal according to notified differences by placing the participants at distinct positions in an acoustical space of the audio signal.

Abstract translation: 一种用于区分多个参与者的电话会议中的扬声器的方法，其中在接收单元中接收会议呼叫的语音帧，哪些语音帧包括编码语音参数。 在接收单元的音频编解码器中检查接收到的语音帧的至少一个参数，并且将语音帧分类为属于其中一个参与者，根据所检查的至少一个语音参数的差异进行分类 。 这些功能可以在可应用于电话会议处理链的各种位置的扬声器识别块中进行。 最后，通过将参与者放置在音频信号的声音空间中的不同位置，根据所通知的差异在终端再生音频信号的终端中产生空间化效果。

公开(公告)号：US20060245566A1

公开(公告)日：2006-11-02

申请号：US11120648

申请日：2005-05-02

Applicant: Cameron Parker

Inventor： Cameron Parker

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.

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。

公开(公告)号：US20060188076A1

公开(公告)日：2006-08-24

申请号：US11065682

申请日：2005-02-24

Applicant: Neil Isenberg

Inventor： Neil Isenberg

IPC: H04M1/64

CPC classification number: H04M3/385 ,  H04M3/42042 ,  H04M2201/41

Abstract: A voiceprint of a calling party, and identifying information, are obtained during a call. One or more voiceprint samples stored in association with the identifying information are selected, and the calling party's identity is verified based on a comparison of the voiceprint to at least one of the selected voiceprint samples. For example, the voiceprint samples may be derived from a verbal utterance by the calling party before the call, mixed with different background noises likely corrupting the calling party's utterance during the call. If the comparison fails to determine the calling party's identity, an attempt to verify the calling party's identity is made based on additional information received during the call. In another example, if the calling party's identity is verified based on the additional information, the voiceprint may be stored in association with the identifying information as a voiceprint sample for use in future verification of the calling party's identity.

Abstract translation: 呼叫期间获得呼叫方的声纹和识别信息。 选择与识别信息相关联地存储的一个或多个声纹样本，并且基于声波纹与至少一个选定的声纹样本之间的比较来验证主叫方的身份。 例如，声调样本可以来自主叫方在呼叫之前的口头发音，混合不同的背景噪声可能会在呼叫期间破坏主叫方的话语。 如果比较未能确定主叫方的身份，则根据呼叫期间接收到的附加信息进行验证主叫方身份的尝试。 在另一示例中，如果主叫方的身份基于附加信息被验证，则可以将声纹作为声纹样本与识别信息相关联地存储，以供将来验证主叫方身份。

公开(公告)号：US07006605B1

公开(公告)日：2006-02-28

申请号：US10352848

申请日：2003-01-27

Applicant: Sanford J. Morganstein ,  Sergey Zaks

Inventor： Sanford J. Morganstein ,  Sergey Zaks

IPC: H04M1/64 ,  H04M11/00

CPC classification number: G10L17/005 ,  G06F21/32 ,  G10L17/00 ,  G10L17/22 ,  H04M3/2281 ,  H04M3/229 ,  H04M3/38 ,  H04M3/382 ,  H04M3/385 ,  H04M3/387 ,  H04M3/42 ,  H04M3/42042 ,  H04M3/42059 ,  H04M2201/40 ,  H04M2201/41 ,  H04M2242/22 ,  H04Q3/72 ,  H04Q2213/13003 ,  H04Q2213/1305 ,  H04Q2213/13091 ,  H04Q2213/13093 ,  H04Q2213/13095 ,  H04Q2213/13103 ,  H04Q2213/13141 ,  H04Q2213/13175 ,  H04Q2213/13204 ,  H04Q2213/13271 ,  H04Q2213/13282 ,  H04Q2213/13353

Abstract: In one embodiment, a system authenticates a caller before providing the caller with access to one or more secured resources. Identification and verification data is stored during system enrollment of known persons. A processing system, in a current call initiated by a caller and prior to identification of the caller, receives voice-based information for the caller including a digital representation of a telephone number spoken by the caller in the current call, the received information including voice-based identification information and voice-based verification information for the caller. The processing system automatically compares the received identification information and the received verification information for the caller with the stored identification and verification data for known persons, respectively, to uniquely identify and verify the identity of the caller as a particular known person. The processing system authenticates the caller for access to the one or more secured resources in response.

公开(公告)号：US06931113B2

公开(公告)日：2005-08-16

申请号：US10290683

申请日：2002-11-08

Applicant: William Charles Gormley Ortel

Inventor： William Charles Gormley Ortel

IPC: H04M1/64 ,  H04M3/42 ,  H04M3/56

CPC classification number: H04M3/56 ,  H04M3/567 ,  H04M2201/38 ,  H04M2201/41

Abstract: There is provided a system for facilitating a conference call. The system includes a module to generate a real-time voiceprint from a voice input of a participant in the conference call, and a module to provide information indicative of the participant based on the real-time voiceprint.

Abstract translation: 提供了一种便于电话会议的系统。 该系统包括用于从会议呼叫中的参与者的语音输入生成实时声纹的模块，以及用于基于实时声纹提供指示参与者的信息的模块。