公开(公告)号：US20140328473A1

公开(公告)日：2014-11-06

申请号：US14336855

申请日：2014-07-21

Applicant: AT&T Intellectual Property I, L.P.

Inventor： David L. Dunmire ,  Jeff P. Clark ,  Brian M. Novack

IPC: H04M3/42

CPC classification number: H04M3/42059 ,  G10L17/02 ,  H04L63/0861 ,  H04M2201/405 ,  H04M2201/41 ,  H04M2203/60

Abstract: A disclosed method of authenticating a telephone caller includes receiving an authentication request for the telephone caller that includes a voice recording of the caller and household information indicative of a household, creating a first voice pattern based on the voice recording of the caller, retrieving a second voice pattern using at least some of the household information, comparing the two voice patterns, and transmitting information indicative of the results of the comparison. The transmitted information may include information that the telephone caller is authenticated, is not authenticated, or that the comparison results were inconclusive. The method may include monitoring telephone calls with the household, and if it is determined that a voice on at least some of the telephone calls is associated with the household, creating the second voice pattern based on the voice, and associating the second voice pattern to the household. The method may further include disassociating the second voice pattern from the household if it is determined that a change of household has occurred.

Abstract translation: 公开的认证电话呼叫者的方法包括：接收对包括呼叫者的语音记录和指示家庭的家庭信息的电话呼叫者的认证请求，基于呼叫者的语音记录创建第一语音模式，检索第二个 使用至少一些家庭信息的语音模式，比较两种语音模式，以及发送指示比较结果的信息。 所发送的信息可以包括电话呼叫者被认证，未认证的信息，或者比较结果不确定。 该方法可以包括监视与家庭的电话呼叫，并且如果确定至少一些电话呼叫中的语音与家庭相关联，则基于语音创建第二语音模式，并将第二语音模式与 家庭。 如果确定已经发生家庭变更，该方法还可以包括将第二语音模式与家庭分离。

公开(公告)号：US08787866B2

公开(公告)日：2014-07-22

申请号：US11189294

申请日：2005-07-26

Applicant: Roberto Battaglini ,  Brian Patrick Singer

Inventor： Roberto Battaglini ,  Brian Patrick Singer

IPC: H04M3/00

CPC classification number: H04M1/19 ,  G10L15/22 ,  G10L17/04 ,  G10L17/06 ,  G10L25/84 ,  G10L2015/223 ,  H04M1/247 ,  H04M1/6008 ,  H04M1/6033 ,  H04M2201/405 ,  H04M2203/258 ,  H04M2250/74

Abstract: System, method and program for controlling a mute function on a telephone device. While the mute function is active, sound reaching a telephone or other communication device is sensed, and a determination is made if the sound includes a word. If so, an alarm is activated to alert a user that the mute function is active. If not, the alarm is not activated. In accordance with an optional feature of the present invention, speech recognition software is trained to recognize the voice or speech pattern of a specific user, and the alarm is activated only if the word was spoken by the specific user.

Abstract translation: 用于控制电话设备上的静音功能的系统，方法和程序。 当静音功能被激活时，感测达到电话或其他通信设备的声音，并且确定声音是否包括一个单词。 如果是这样，则激活警报来提醒用户静音功能处于活动状态。 如果没有，则报警不被激活。 根据本发明的可选特征，语音识别软件被训练以识别特定用户的语音或语音模式，并且仅当该特定用户说出该单词时才激活该报警。

公开(公告)号：US08787535B2

公开(公告)日：2014-07-22

申请号：US12022855

申请日：2008-01-30

Applicant: David L. Dunmire ,  Jeff P. Clark ,  Brian M. Novack

Inventor： David L. Dunmire ,  Jeff P. Clark ,  Brian M. Novack

IPC: H04M1/64

CPC classification number: H04M3/42059 ,  G10L17/02 ,  H04L63/0861 ,  H04M2201/405 ,  H04M2201/41 ,  H04M2203/60

Abstract: A disclosed method of authenticating a telephone caller includes receiving an authentication request for the telephone caller that includes a voice recording of the caller and household information indicative of a household, creating a first voice pattern based on the voice recording of the caller, retrieving a second voice pattern using at least some of the household information, comparing the two voice patterns, and transmitting information indicative of the results of the comparison. The transmitted information may include information that the telephone caller is authenticated, is not authenticated, or that the comparison results were inconclusive. The method may include monitoring telephone calls with the household, and if it is determined that a voice on at least some of the telephone calls is associated with the household, creating the second voice pattern based on the voice, and associating the second voice pattern to the household. The method may further include disassociating the second voice pattern from the household if it is determined that a change of household has occurred.

Abstract translation: 公开的认证电话呼叫者的方法包括：接收对包括呼叫者的语音记录和指示家庭的家庭信息的电话呼叫者的认证请求，基于呼叫者的语音记录创建第一语音模式，检索第二个 使用至少一些家庭信息的语音模式，比较两种语音模式，以及发送指示比较结果的信息。 所发送的信息可以包括电话呼叫者被认证，未认证的信息，或者比较结果不确定。 该方法可以包括监视与家庭的电话呼叫，并且如果确定至少一些电话呼叫中的语音与家庭相关联，则基于语音创建第二语音模式，并将第二语音模式与 家庭。 如果确定已经发生家庭变更，该方法还可以包括将第二语音模式与家庭分离。

公开(公告)号：US08019387B2

公开(公告)日：2011-09-13

申请号：US12326753

申请日：2008-12-02

Applicant: Bernard F. Bareis ,  Peter J. Foster ,  Thomas B. Schalk

Inventor： Bernard F. Bareis ,  Peter J. Foster ,  Thomas B. Schalk

IPC: H04B1/38

CPC classification number: H04W4/18 ,  H04B7/18567 ,  H04M3/42204 ,  H04M3/4936 ,  H04M11/10 ,  H04M2201/40 ,  H04M2201/405 ,  H04W4/00 ,  H04W88/18

Abstract: Voice activated dialing is described for use in a mobile telecommunications system. A voice input is received from a wireless network user. A telephone number to be dialed is determined by using speaker independent speech recognition to interpret a string of spoken digits in the voice input to determine the telephone number, or using speaker dependent speech recognition to interpret a spoken word in the voice input to determine the telephone number. A telephone call is then initiated by dialing the telephone number.

Abstract translation: 语音激活拨号被描述为用于移动电信系统。 从无线网络用户接收语音输入。 要拨打的电话号码通过使用与讲话者无关的语音识别来解释语音输入中的一串口头数字来确定电话号码，或者使用说话者依赖语音识别来解释语音输入中的口语单词以确定电话 数。 然后通过拨打电话号码开始电话呼叫。

公开(公告)号：US07551944B2

公开(公告)日：2009-06-23

申请号：US10308653

申请日：2002-12-03

Applicant: Bernard F. Bareis ,  Thomas B. Schalk ,  Peter J. Foster

Inventor： Bernard F. Bareis ,  Thomas B. Schalk ,  Peter J. Foster

IPC: H04B1/38

CPC classification number: H04W4/18 ,  H04B7/18567 ,  H04M3/42204 ,  H04M3/4936 ,  H04M11/10 ,  H04M2201/40 ,  H04M2201/405 ,  H04W4/00 ,  H04W88/18

Abstract: An advanced telecommunications system is provided for the recognizing of spoken commands over a cellular telephone, satellite telephone, or personal communications network. In the cellular application, for example, a Speech Recognition System interconnects either internally with or as an external peripheral to a cellular telecommunications switch. The Speech Recognition System includes an administrative subsystem, a call processing subsystem, a speaker-dependent recognition subsystem, a speaker-independent recognition subsystem, and a data storage subsystem. The Speech Recognition System also allows for increased efficiency in the cellular telephone network by integrating with the switch or switches as a shared resource. The administrative subsystem of the Speech Recognition System is used to keep statistical logs of pertinent call information. Pre-recorded instructional messages are stored in the memory of the call processing subsystem for instructing a user on his or her progress in using the system. The speaker-independent recognition subsystem allows the user to interact with the system employing non-user specific functions. User specific functions are controlled with the speaker-dependent recognition subsystem. User specific attributes collected by the recognition subsystems are stored in the data storage subsystem.

公开(公告)号：US20080133235A1

公开(公告)日：2008-06-05

申请号：US11949346

申请日：2007-12-03

Applicant: Laurent SIMONEAU ,  Pascal Soucy

Inventor： Laurent SIMONEAU ,  Pascal Soucy

IPC: G10L15/00

CPC classification number: H04M3/4936 ,  G10L15/183 ,  G10L15/197 ,  H04M3/53333 ,  H04M2201/405

Abstract: A method and a related system to index voicemail documents by training a language model for a speaker or group of speakers by using existing emails and contact information on available repositories.

Abstract translation: 通过使用现有电子邮件和可用存储库的联系信息，通过为扬声器或扬声器组训练语言模型来索引语音邮件文档的方法和相关系统。

公开(公告)号：US06704405B1

公开(公告)日：2004-03-09

申请号：US09823997

申请日：2001-04-03

Applicant: Robert D. Farris ,  Alexander I. McAllister ,  Michael J. Strauss

Inventor： Robert D. Farris ,  Alexander I. McAllister ,  Michael J. Strauss

IPC: H04M100

CPC classification number: H04M3/42017 ,  H04M3/2281 ,  H04M3/38 ,  H04M3/382 ,  H04M3/385 ,  H04M3/42 ,  H04M3/42059 ,  H04M3/42068 ,  H04M3/42102 ,  H04M3/4211 ,  H04M3/42229 ,  H04M3/533 ,  H04M3/53383 ,  H04M7/06 ,  H04M7/12 ,  H04M2201/40 ,  H04M2201/405 ,  H04M2207/12 ,  H04Q3/0029 ,  H04Q3/0045

Abstract: An intelligent telephone network provides personalized communication services based on a voice identification of the subscriber. The network executes a speech processing operation to identify the person or a party that the person is calling as a known subscriber. The network can provide personalized services to several subscribers sharing a common line. For incoming calls to such a line, the network executes an interactive procedure to determine from the caller which subscriber is being called. If the line is free, the switch applies distinctive ringing. If the line is in use, the switching office uses the profile of the identified subscriber to provide a distinctive call waiting tone or a voice message over the line. The tone or voice message indicates to the party using the line that there is a call waiting and specifically identifies the called subscriber.

Abstract translation: 智能电话网络基于用户的语音识别提供个性化通信服务。 网络执行语音处理操作以识别该人正在呼叫的人或一方作为已知用户。 网络可以为共享一条通用线路的多个用户提供个性化服务。 对于对这种线路的呼入，网络执行交互过程以从呼叫者确定正在呼叫哪个用户。 如果该线路是空闲的话，该交换机应用独特的振铃。 如果该线路正在使用中，则交换局使用所识别的用户的配置文件来提供独特的呼叫等待音或语音消息。 音调或语音消息向使用线路的一方指示有呼叫等待并具体标识被叫用户。

公开(公告)号：US20020163999A1

公开(公告)日：2002-11-07

申请号：US10124659

申请日：2002-04-17

Inventor： Robert D. Farris ,  Alexander I. McAllister ,  Michael J. Strauss

IPC: H04M001/64 ,  H04M003/42

CPC classification number: H04M3/42017 ,  H04M3/2281 ,  H04M3/38 ,  H04M3/382 ,  H04M3/385 ,  H04M3/42 ,  H04M3/42059 ,  H04M3/42068 ,  H04M3/42102 ,  H04M3/4211 ,  H04M3/42229 ,  H04M3/533 ,  H04M3/53383 ,  H04M7/06 ,  H04M7/12 ,  H04M2201/40 ,  H04M2201/405 ,  H04M2207/12 ,  H04Q3/0029 ,  H04Q3/0045

Abstract: An intelligent telephone network provides personalized communication services based on a voice identification of the subscriber. Specifically, when a person requests a service, the network executes a speech processing operation, to identify the person or a party that the person is calling as a known subscriber. One or more switching offices of the network utilize profile data associated with the identified subscriber to control services. The personalized service applies both to incoming and outgoing calls. The network can provide the personalized services to several subscribers sharing a common line. For incoming calls to such a line, the network executes an interactive procedure to determine from the caller which subscriber she is calling. If the line is free, the switch applies distinctive ringing. If the line is in use, the switch uses the profile of the identified subscriber to provide a distinctive call waiting tone or a voice message over the line. The tone or voice message indicates to the party using the line that there is a call waiting and specifically identifies the called subscriber. For outgoing calls, the network utilizes a voice verification procedure to identify the actual subscriber. The subscriber's profile controls network processing of the call, including the provision of personal subscriber identification for caller ID, both on ringing calls and with call waiting alert signals.

Abstract translation: 智能电话网络基于用户的语音识别提供个性化通信服务。 具体地说，当人请求服务时，网络执行语音处理操作，以识别该人正在呼叫的人或一方为已知用户。 网络的一个或多个交换局利用与所识别的用户相关联的简档数据来控制服务。 个性化服务既适用于来电和去电。 网络可以为共享共同线路的多个用户提供个性化服务。 对于这样一条线路的呼入，网络执行一个交互过程，以从呼叫者确定她正在呼叫哪个用户。 如果该线路是空闲的话，该交换机应用独特的振铃。 如果线路正在使用中，则交换机使用所识别的用户的配置文件来提供一个独特的呼叫等待音或语音消息。 音调或语音消息向使用线路的一方指示有呼叫等待并具体标识被叫用户。 对于拨出电话，网络利用语音验证程序来识别实际的用户。 用户的配置文件控制呼叫的网络处理，包括在呼叫呼叫​​和呼叫等待警报信号上提供呼叫者ID的个人用户标识。

公开(公告)号：US20010054085A1

公开(公告)日：2001-12-20

申请号：US09777406

申请日：2001-02-06

Inventor： Alexander Kurganov

IPC: G06F015/16

CPC classification number: H04M3/4938 ,  G06F3/167 ,  G06F17/30769 ,  G06F17/30861 ,  G10L13/08 ,  G10L15/02 ,  G10L15/06 ,  G10L15/08 ,  G10L15/22 ,  G10L15/26 ,  G10L17/24 ,  G10L25/54 ,  G10L2015/223 ,  H04L29/0809 ,  H04L67/02 ,  H04M2201/39 ,  H04M2201/40 ,  H04M2201/405 ,  H04M2207/40

Abstract: The present invention relates to a system for retrieving information from a network such as the Internet. A user creates a user-defined record in a database that identifies an information source, such as a web site, containing information of interest to the user. This record identifies the location of the information source and also contains a recognition grammar based upon a speech command assigned by the user. Upon receiving the speech command from the user that is described within the recognition grammar, a network interface system accesses the information source and retrieves the information requested by the user.

Abstract translation: 本发明涉及一种用于从诸如因特网的网络检索信息的系统。 用户在数据库中创建用户定义的记录，该记录标识包含用户感兴趣的信息的信息源（例如网站）。 该记录识别信息源的位置，并且还包含基于用户分配的语音命令的识别语法。 在接收到在识别语法中描述的用户的语音命令之后，网络接口系统访问信息源并检索用户请求的信息。

公开(公告)号：US6167119A

公开(公告)日：2000-12-26

申请号：US006033

申请日：1998-01-12

Applicant: Dale L. Bartholomew ,  Robert D. Farris ,  Alexander I. McAllister ,  Michael J. Strauss

Inventor： Dale L. Bartholomew ,  Robert D. Farris ,  Alexander I. McAllister ,  Michael J. Strauss

IPC: H04M3/22 ,  H04M3/38 ,  H04M3/42 ,  H04M3/533 ,  H04M7/12 ,  H04Q3/00

CPC classification number: H04M3/38 ,  H04M3/2281 ,  H04M3/382 ,  H04M3/385 ,  H04M3/42 ,  H04M3/42017 ,  H04M3/42059 ,  H04M3/42068 ,  H04M3/42102 ,  H04M3/4211 ,  H04M3/42229 ,  H04M3/533 ,  H04M3/53383 ,  H04M7/06 ,  H04M7/12 ,  H04M2201/40 ,  H04M2201/405 ,  H04M2207/12 ,  H04Q3/0029 ,  H04Q3/0045

Abstract: An intelligent telephone network provides personalized communication services based on subscriber prescribed double speech signal processing of utterances of both calling and answering parties on a subscriber line having multiple subscribers with a single directory number. Specifically, when one of the multiple subscribers has personalized voice mail service and a busy/no answer call is received, the network uses speech processing of an utterance of the calling party to identify a customer service profile of the called party in the terminating switch. This contains instructions inviting storage of a voice message left by the caller. Upon the subscriber going off-hook, the customer profile of the subscriber line is installed in the switch. The subscriber transmits an utterance and the personalized customer profile of the subscriber is identified by a virtual office equipment number and the profile installed in the switch. The subscriber may then retrieve the stored message.

Abstract translation: 智能电话网络基于在具有单个目录号码的多个订户的用户线上的呼叫和应答方的话语的用户规定的双语言信号处理来提供个性化通信服务。 具体地，当多个用户中的一个具有个性化语音邮件服务并且接收到忙/不应答呼叫时，网络使用主叫方的话语的语音处理来识别终止交换机中被叫方的客户服务简档。 这包含邀请​​存储呼叫者留下的语音消息的指令。 当用户摘机时，用户线路的客户资料安装在交换机中。 用户发送话语，并且用户的个性化客户简档由虚拟办公室设备号码和安装在交换机中的简档来标识。 订户然后可以检索存储的消息。