公开(公告)号：US07136461B1

公开(公告)日：2006-11-14

申请号：US09785223

申请日：2001-02-16

申请人： Loren Swingle ,  Craig L. Reding ,  John Reformato ,  Jayant M. Naik ,  Robert C. Baruch

发明人： Loren Swingle ,  Craig L. Reding ,  John Reformato ,  Jayant M. Naik ,  Robert C. Baruch

IPC分类号： H04M11/00

CPC分类号： H04M3/53333 ,  H04L51/00 ,  H04M3/533 ,  H04M3/53325 ,  H04M3/53383 ,  H04M2203/4509 ,  H04M2203/4536

摘要： Methods and apparatus for controlling and retrieving messages from multiple voice mail systems used by a single individual are described. A voice messaging retrieval and forwarding (VMRAF) system checks a subscriber's voice message systems for messages, retrieves the messages and forwards them to the subscriber as attachments to E-mail files. E-mail replay messages are used to control deleting of the messages from the original systems. Prompt messages played to callers by different voice messaging systems before they leave a message can be updated automatically. This is done by indicating to the VMRAF system when one or more prompt messages are to be updated and which messages, from a set of prerecorded messages, are to be loaded into the voice message systems to replace the existing prompt messages. Accordingly, the VMRAF system facilities message retrieval and the updating of prompt messages, e.g., on a preselected schedule or at preselected times.

摘要翻译： 描述了用于控制和检索由单个个人使用的多个语音邮件系统的消息的方法和装置。 语音消息检索和转发（VMRAF）系统检查订户的语音消息系统的消息，检索消息并将其转发给用户作为电子邮件文件的附件。 电子邮件回放消息用于控制从原始系统删除消息。 不同语音留言系统在呼叫者离开消息之前播放的提示消息可以自动更新。 这是通过向VMRAF系统指示要更新一个或多个提示消息，并且从一组预先记录的消息中将哪些消息加载到语音消息系统中以替换现有的提示消息。 因此，VMRAF系统设施消息检索和即时消息的更新，例如，以预选的时间表或预选的时间。

公开(公告)号：US07609822B2

公开(公告)日：2009-10-27

申请号：US11548423

申请日：2006-10-11

申请人： Loren Swingle ,  Craig L. Reding ,  John Reformato ,  Jayant M. Naik ,  Robert C. Baruch

发明人： Loren Swingle ,  Craig L. Reding ,  John Reformato ,  Jayant M. Naik ,  Robert C. Baruch

IPC分类号： H04M1/64

CPC分类号： H04M3/53333 ,  H04L51/00 ,  H04M3/533 ,  H04M3/53325 ,  H04M3/53383 ,  H04M2203/4509 ,  H04M2203/4536

摘要： Methods and apparatus for controlling and retrieving messages from multiple voice mail systems used by a single individual are described. A voice messaging retrieval and forwarding (VMRAF) system checks a subscriber's voice message systems for messages, retrieves the messages and forwards them to the subscriber as attachments to E-mail files. E-mail replay messages are used to control deleting of the messages from the original systems. Prompt messages played to callers by different voice messaging systems before they leave a message can be updated automatically. This is done by indicating to the VMRAF system when one or more prompt messages are to be updated and which messages, from a set of prerecorded messages, are to be loaded into the voice message systems to replace the existing prompt messages. Accordingly, the VMRAF system facilities message retrieval and the updating of prompt messages, e.g., on a preselected schedule or at preselected times.

摘要翻译： 描述了用于控制和检索由单个个人使用的多个语音邮件系统的消息的方法和装置。 语音消息检索和转发（VMRAF）系统检查订户的语音消息系统的消息，检索消息并将其转发给用户作为电子邮件文件的附件。 电子邮件回放消息用于控制从原始系统删除消息。 不同语音留言系统在呼叫者离开消息之前播放的提示消息可以自动更新。 这是通过向VMRAF系统指示要更新一个或多个提示消息，并且从一组预先记录的消息中将哪些消息加载到语音消息系统中以替换现有的提示消息。 因此，VMRAF系统设施消息检索和即时消息的更新，例如，以预选的时间表或预选的时间。

公开(公告)号：US07254220B1

公开(公告)日：2007-08-07

申请号：US09828679

申请日：2001-04-06

申请人： Craig L. Reding ,  John R. Reformato ,  Jayant M. Naik

发明人： Craig L. Reding ,  John R. Reformato ,  Jayant M. Naik

IPC分类号： H04M1/64

CPC分类号： H04M3/537 ,  H04M3/533 ,  H04M2203/253 ,  H04M2203/4536

摘要： SMDI messages are used by the SMDI message server to generate either E-mail notifications of received messages which are forwarded to a user of the VMS or to supply VMS message status information to a voice message retrieval and forwarding system using IP messaging instead of SMDI FSK or PSK signaling. SMDI messages between a stored program controlled switching system, e.g., C.O. switch, and a voice message system are monitored by the SMDI message server of the present invention, e.g., by inserting a Tee into the SMDI link between the C.O. switch and VMS. The SMDI message server uses the directory number information and/or a message line identifier included in a received SMDI message to identify a subscriber or voice message retrieval and forwarding system which should be notified of the received SMDI message information.

摘要翻译： SMDI消息服务器使用SMDI消息来生成被转发给VMS的用户的所接收消息的电子邮件通知，或者使用IP消息而不是SMDI FSK向语音消息检索和转发系统提供VMS消息状态信息 或PSK信令。 存储的程序控制的交换系统（例如C.O.）之间的SMDI消息。 交换机，并且语音消息系统由本发明的SMDI消息服务器监视，例如通过将Tee插入到C.O.之间的SMDI链路中。 开关和VMS。 SMDI消息服务器使用包含在所接收的SMDI消息中的目录号码信息和/或消息行标识符来标识应该被通知接收的SMDI消息信息的用户或语音消息检索和转发系统。

公开(公告)号：US06963633B1

公开(公告)日：2005-11-08

申请号：US09609585

申请日：2000-06-30

申请人： William F. Diede ,  Kay L. Bechtel ,  Eugene Lubchenko ,  Scott Alexander McAlily ,  Jayant M. Naik ,  Barry Paul Pershan ,  John Reformato

发明人： William F. Diede ,  Kay L. Bechtel ,  Eugene Lubchenko ,  Scott Alexander McAlily ,  Jayant M. Naik ,  Barry Paul Pershan ,  John Reformato

IPC分类号： G10L15/06 ,  G10L15/26 ,  H04M1/64 ,  H04M3/42 ,  H04M3/493

CPC分类号： H04M3/42204 ,  G10L15/06 ,  G10L15/26 ,  H04M3/4931 ,  H04M7/12 ,  H04M2207/45

摘要： Methods and apparatus for implementing communication services such as voice dialing services are described. In one Centrex based voice dialing embodiment, voice dialing service subscribers are given access to personal voice dialing records including calling entries via the Internet as well as via telephone connections. Each calling entry normally includes the name and, optionally nickname, of a party to be called. It also includes one or more telephone numbers associated with each name. Different telephone number identifies, e.g. locations, can be associated with different names. A user can create or update entries in a voice dialing directory using text conveyed over the Internet or speech supplied via a telephone connection. In order to facilitate updating and maintenance of voice dialing directories over the Internet speaker independent (SI) speech recognition models are used. When a calling entry is created via the Internet the text of the name is processed to generate a corresponding speech recognition model there from. When an entry is created via speech obtained over the telephone, a speech recognition model is generated from the speech and a text name is generated is generated using speech to text technology. To avoid having to hang-up and initiate a new voice dialing call the outcome of a voice dialing call is monitored and the subscriber is provided the opportunity to initiate another call using voice dialing if the first call did not complete successfully e.g., goes unanswered.

摘要翻译： 描述用于实现诸如语音拨号服务的通信服务的方法和装置。 在一个基于Centrex的语音拨号实施例中，语音拨号服务用户被允许访问个人语音拨号记录，包括通过因特网的呼叫条目以及通过电话连接。 每个呼叫条目通常包括要呼叫的一方的名称和（可选的昵称）。 它还包括与每个名称相关联的一个或多个电话号码。 不同的电话号码标识，例如 位置，可以与不同的名称相关联。 用户可以使用通过因特网传送的文本或通过电话连接提供的语音来创建或更新语音拨号目录中的条目。 为了便于通过互联网扬声器独立（SI）语音识别模型更新和维护语音拨号目录。 当通过因特网创建呼叫条目时，处理该名称的文本以从中产生相应的语音识别模型。 当通过电话获得的语音创建条目时，从语音生成语音识别模型，并且使用语音到文本技术生成文本名称。 为了避免挂起并发起新的语音拨号呼叫，监视语音拨号呼叫的结果，并且如果第一呼叫没有成功地完成，则向用户提供利用语音拨号发起另一个呼叫的机会，例如，未被应答。

公开(公告)号：US06744861B1

公开(公告)日：2004-06-01

申请号：US09609018

申请日：2000-06-30

申请人： Barry Paul Pershan ,  Kay L. Bechtel ,  William F. Diede ,  Euguene Lubchenko ,  Scott Alexander McAliley ,  Jayant M. Naik ,  John Reformato

发明人： Barry Paul Pershan ,  Kay L. Bechtel ,  William F. Diede ,  Euguene Lubchenko ,  Scott Alexander McAliley ,  Jayant M. Naik ,  John Reformato

IPC分类号： H04M164

CPC分类号： H04M1/271 ,  H04M3/44 ,  H04M3/4931 ,  H04Q3/0029

摘要： Methods and apparatus for implementing communication services such as voice dialing services are described. In one Centrex based voice dialing embodiment, voice dialing service subscribers are given access to personal voice dialing records including calling entries via the Internet as well as via telephone connections. Each calling entry normally includes the name and, optionally nickname, of a party to be called. It also includes one or more telephone numbers associated with each name. Different telephone number identifies, e.g. locations, can be associated with different names. A user can create or update entries in a voice dialing directory using text conveyed over the Internet or speech supplied via a telephone connection. In order to facilitate updating and maintenance of voice dialing directories over the Internet speaker independent (SI) speech recognition models are used. When a calling entry is created via the Internet the text of the name is processed to generate a corresponding speech recognition model there from. When an entry is created via speech obtained over the telephone, a speech recognition model is generated from the speech and a text name is generated is generated using speech to text technology. To avoid having to hang-up and initiate a new voice dialing call the outcome of a voice dialing call is monitored and the subscriber is provided the opportunity to initiate another call using voice dialing if the first call did not complete successfully e.g., goes unanswered.

摘要翻译： 描述用于实现诸如语音拨号服务的通信服务的方法和装置。 在一个基于Centrex的语音拨号实施例中，语音拨号服务用户被允许访问个人语音拨号记录，包括通过因特网的呼叫条目以及通过电话连接。 每个呼叫条目通常包括要呼叫的一方的名称和（可选的昵称）。 它还包括与每个名称相关联的一个或多个电话号码。 不同的电话号码标识，例如 位置，可以与不同的名称相关联。 用户可以使用通过因特网传送的文本或通过电话连接提供的语音来创建或更新语音拨号目录中的条目。 为了便于通过互联网扬声器独立（SI）语音识别模型更新和维护语音拨号目录。 当通过因特网创建呼叫条目时，处理该名称的文本以从中产生相应的语音识别模型。 当通过电话获得的语音创建条目时，从语音生成语音识别模型，并且使用语音到文本技术生成文本名称。 为了避免挂起并发起新的语音拨号呼叫，监视语音拨号呼叫的结果，并且如果第一呼叫没有成功地完成，则向用户提供利用语音拨号发起另一个呼叫的机会，例如，未被应答。

公开(公告)号：US06650738B1

公开(公告)日：2003-11-18

申请号：US09608405

申请日：2000-06-30

申请人： Barry Paul Pershan ,  Kay L. Bechtel ,  William F. Diede ,  Euguene Lubchenko ,  Scott Alexander McAlily ,  Jayant M. Naik ,  John Reformato

发明人： Barry Paul Pershan ,  Kay L. Bechtel ,  William F. Diede ,  Euguene Lubchenko ,  Scott Alexander McAlily ,  Jayant M. Naik ,  John Reformato

IPC分类号： H04M164

CPC分类号： H04M1/271 ,  H04M3/44 ,  H04M3/4931 ,  H04Q3/0029

摘要： Methods and apparatus for implementing communication services such as voice dialing services are described. In one Centrex based voice dialing embodiment, voice dialing service subscribers are given access to personal voice dialing records including calling entries via the Internet as well as via telephone connections. Each calling entry normally includes the name and, optionally nickname, of a party to be called. It also includes one or more telephone numbers associated with each name. Different telephone number identifies, e.g. locations, can be associated with different names. A user can create or update entries in a voice dialing directory using text conveyed over the Internet or speech supplied via a telephone connection. In order to facilitate updating and maintenance of voice dialing directories over the Internet speaker independent (SI) speech recognition models are used. When a calling entry is created via the Internet the text of the name is processed to generate a corresponding speech recognition model there from. When an entry is created via speech obtained over the telephone, a speech recognition model is generated from the speech and a text name is generated is generated using speech to text technology. To avoid having to hang-up and initiate a new voice dialing call the outcome of a voice dialing call is monitored and the subscriber is provided the opportunity to initiate another call using voice dialing if the first call did not complete successfully e.g., goes unanswered.

摘要翻译： 描述用于实现诸如语音拨号服务的通信服务的方法和装置。 在一个基于Centrex的语音拨号实施例中，语音拨号服务用户被允许访问个人语音拨号记录，包括通过因特网的呼叫条目以及通过电话连接。 每个呼叫条目通常包括要呼叫的一方的名称和（可选的昵称）。 它还包括与每个名称相关联的一个或多个电话号码。 不同的电话号码标识，例如 位置，可以与不同的名称相关联。 用户可以使用通过因特网传送的文本或通过电话连接提供的语音来创建或更新语音拨号目录中的条目。 为了便于通过互联网扬声器独立（SI）语音识别模型更新和维护语音拨号目录。 当通过因特网创建呼叫条目时，处理该名称的文本以从中产生相应的语音识别模型。 当通过电话获得的语音创建条目时，从语音生成语音识别模型，并且使用语音到文本技术生成文本名称。 为了避免挂起并发起新的语音拨号呼叫，监视语音拨号呼叫的结果，并且如果第一呼叫没有成功地完成，则向用户提供利用语音拨号发起另一个呼叫的机会，例如，未被应答。

公开(公告)号：US06690772B1

公开(公告)日：2004-02-10

申请号：US09608884

申请日：2000-06-30

申请人： Jayant M. Naik ,  Kay L. Bechtel ,  William F. Diede ,  Eugene Lubchenko ,  Scott Alexander McAlily ,  Barry Paul Pershan ,  John Reformato

发明人： Jayant M. Naik ,  Kay L. Bechtel ,  William F. Diede ,  Eugene Lubchenko ,  Scott Alexander McAlily ,  Barry Paul Pershan ,  John Reformato

IPC分类号： H04M342

CPC分类号： H04M3/42204 ,  H04M3/4931 ,  H04Q3/0029

摘要： Methods and apparatus for implementing communication services such as voice dialing services are described. In one Centrex based voice dialing embodiment, voice dialing service subscribers are given access to personal voice dialing records including calling entries via the Internet as well as via telephone connections. Each calling entry normally includes the name and, optionally nickname, of a party to be called. It also includes one or more telephone numbers associated with each name. Different telephone number identifies, e.g. locations, can be associated with different names. A user can create or update entries in a voice dialing directory using text conveyed over the Internet or speech supplied via a telephone connection. In order to facilitate updating and maintenance of voice dialing directories over the Internet speaker independent (SI) speech recognition models are used. When a calling entry is created via the Internet the text of the name is processed to generate a corresponding speech recognition model there from. When an entry is created via speech obtained over the telephone, a speech recognition model is generated from the speech and a text name is generated is generated using speech to text technology. To avoid having to hang-up and initiate a new voice dialing call the outcome of a voice dialing call is monitored and the subscriber is provided the opportunity to initiate another call using voice dialing if the first call did not complete successfully e.g., goes unanswered.

摘要翻译： 描述用于实现诸如语音拨号服务的通信服务的方法和装置。 在一个基于Centrex的语音拨号实施例中，语音拨号服务用户被允许访问个人语音拨号记录，包括通过因特网的呼叫条目以及通过电话连接。 每个呼叫条目通常包括要呼叫的一方的名称和（可选的昵称）。 它还包括与每个名称相关联的一个或多个电话号码。 不同的电话号码标识，例如 位置，可以与不同的名称相关联。 用户可以使用通过因特网传送的文本或通过电话连接提供的语音来创建或更新语音拨号目录中的条目。 为了便于通过互联网扬声器独立（SI）语音识别模型更新和维护语音拨号目录。 当通过因特网创建呼叫条目时，处理该名称的文本以从中产生相应的语音识别模型。 当通过电话获得的语音创建条目时，从语音生成语音识别模型，并且使用语音到文本技术生成文本名称。 为了避免挂起并发起新的语音拨号呼叫，监视语音拨号呼叫的结果，并且如果第一呼叫没有成功地完成，则向用户提供利用语音拨号发起另一个呼叫的机会，例如，未被应答。

公开(公告)号：US5832063A

公开(公告)日：1998-11-03

申请号：US904920

申请日：1997-08-01

申请人： George J. Vysotsky ,  Ayman O. Asadi ,  David M. Lubensky ,  Vijay R. Raman ,  Jayant M. Naik

发明人： George J. Vysotsky ,  Ayman O. Asadi ,  David M. Lubensky ,  Vijay R. Raman ,  Jayant M. Naik

IPC分类号： G10L15/00 ,  G10L15/06 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L15/28 ,  H04M3/42 ,  H04M3/44 ,  G10L9/08 ,  H04M1/30 ,  H04M1/66

CPC分类号： H04M1/271 ,  G10L15/065 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L15/34 ,  H04M3/42204 ,  H04M3/44 ,  G10L2015/088 ,  H04M2201/40 ,  H04M3/42

摘要： Methods and apparatus for activating telephone services in response to speech are described. A directory including names is maintained for each customer. A speaker dependent speech template and a telephone number for each name, is maintained as part of each customer's directory. Speaker independent speech templates are used for recognizing commands. The present invention has the advantage of permitting a customer to place a call by speaking a person's name which serves as a destination identifier without having to speak an additional command or steering word to place the call. This is achieved by treating the receipt of a spoken name in the absence of a command as an implicit command to place a call. Explicit speaker independent commands are used to invoke features or services other than call placement. Speaker independent and speaker dependent speech recognition are performed on a customer's speech in parallel. An arbiter is used to decide which function or service should be performed when an apparent conflict arises as a result of both the speaker dependent and speaker independent speech recognition step outputs. Stochastic grammars, word spotting and/or out-of-vocabulary rejection are used as part of the speech recognition process to provide a user friendly interface which permits the use of spontaneous speech. Voice verification is performed on a selective basis where security is of concern.

公开(公告)号：US09218128B1

公开(公告)日：2015-12-22

申请号：US12394508

申请日：2009-02-27

申请人： Matthew John Yuschik ,  Cordell Amos Coy ,  Jayant M. Naik ,  Karthik Narayanaswami ,  Ajay Warrier

发明人： Matthew John Yuschik ,  Cordell Amos Coy ,  Jayant M. Naik ,  Karthik Narayanaswami ,  Ajay Warrier

IPC分类号： G06F3/00 ,  G06F3/0489 ,  G06F9/44 ,  G09B9/00 ,  G06N99/00 ,  G09B5/00 ,  G09B5/06 ,  H04M3/51 ,  G09B19/00

CPC分类号： G06F3/0481 ,  G06F3/04895 ,  G06F9/453 ,  G06N99/005 ,  G09B5/00 ,  G09B5/06 ,  G09B9/00 ,  G09B19/0053 ,  H04M3/493 ,  H04M3/5175 ,  H04M3/5183 ,  H04M2201/42 ,  H04M2203/252 ,  H04M2203/357 ,  H04M2203/403

摘要： Training for a multimodal user interface may be organized into a plurality of modules. In embodiment, modules may include data corresponding to a “Push to Talk” tool, a set of data corresponding to navigation through a graphic user interface via voice input, and a set of data corresponding to entering data into a graphic user interface via voice input. Such training may be implemented in a variety of manners, including those which utilize data stored on a computer readable medium. Also, the structure and content of training may be streamlined and directed towards teaching a user to operate a multimodal user interface in an adequate manner. The structure and content of training may be configured to work in conjunction with the operation of a multimodal user interface being used in a real-time setting.

摘要翻译： 多模式用户界面的训练可以被组织成多个模块。 在实施例中，模块可以包括对应于“一键通”工具的数据，对应于通过语音输入通过图形用户界面的导航的一组数据，以及对应于经由语音输入将数据输入图形用户界面的一组数据 。 这样的训练可以以各种方式来实现，包括利用存储在计算机可读介质上的数据的方式。 此外，训练的结构和内容可以被简化并且旨在教导用户以适当的方式操作多模态用户界面。 可以将训练的结构和内容配置为与在实时设置中使用的多模式用户界面的操作一起工作。

公开(公告)号：USRE38101E1

公开(公告)日：2003-04-29

申请号：US09505103

申请日：2000-02-16

申请人： George J. Vysotsky ,  Ayman O. Asadi ,  David M. Lubensky ,  Vijay R. Raman ,  Jayant M. Naik

发明人： George J. Vysotsky ,  Ayman O. Asadi ,  David M. Lubensky ,  Vijay R. Raman ,  Jayant M. Naik

IPC分类号： G10L908

CPC分类号： H04M1/271 ,  G10L15/065 ,  G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L15/34 ,  G10L2015/088 ,  G10L2015/223 ,  H04M3/42 ,  H04M3/42204 ,  H04M3/44 ,  H04M2201/40

摘要： Methods and apparatus for activating telephone services in response to speech are described. A directory including names is maintained for each customer. A speaker dependent speech template and a telephone number for each name, is maintained as part of each customer's directory. Speaker independent speech templates are used for recognizing commands. The present invention has the advantage of permitting a customer to place a call by speaking a person's name which serves as a destination identifier without having to speak an additional command or steering word to place the call. This is achieved by treating the receipt of a spoken name in the absence of a command as an implicit command to place a call. Explicit speaker independent commands are used to invoke features or services other than call placement. Speaker independent and speaker dependent speech recognition are performed on a customer's speech in parallel. An arbiter is used to decide which function or service should be performed when an apparent conflict arises as a result of both the speaker dependent and speaker independent speech recognition step outputs. Stochastic grammars, word spotting and/or out-of-vocabulary rejection are used as part of the speech recognition process to provide a user friendly interface which permits the use of spontaneous speech. Voice verification is performed on a selective basis where security is of concern.

摘要翻译： 描述了响应于语音激活电话服务的方法和装置。 为每个客户维护包含名称的目录。 每个名字的说话者依赖语音模板和电话号码都作为每个客户目录的一部分进行维护。 扬声器独立语音模板用于识别命令。 本发明的优点在于，允许客户通过说出作为目的地标识符的人的姓名来进行呼叫，而不用说另外的命令或指导词来进行呼叫。 这是通过在没有命令的情况下处理接收到口语名称作为发出呼叫的隐式命令来实现的。 独立于显示扬声器的命令用于调用除呼叫位置之外的功能或服务。 扬声器独立和扬声器相关语音识别是在客户演讲中并行执行的。 当由于说话人依赖和说话者独立的语音识别步骤输出而产生明显的冲突时，仲裁器用于决定应该执行哪个功能或服务。 语音识别过程的一部分使用随机语法，单词发音和/或超出词汇拒绝，以提供允许使用自发语音的用户友好界面。 语音验证是在安全性受到关注的基础上进行的。