-
1.发明授权Method and apparatus for executing neural network applications on a network of embedded devices 有权用于在嵌入式设备的网络上执行神经网络应用的方法和装置公开(公告)号：US06418423B1
公开(公告)日：2002-07-09
申请号：US09239939
申请日：1999-01-29
IPC分类号： G06N302
CPC分类号： G06N3/10
摘要： Disclosed is a system and a method for combining the computational resources of numerous embedded devices to enable any of them to perform complex tasks like speech recognition or natural language understanding. A distinguished master device communicates with a network of embedded devices, and organizes them as the nodes of a neural network. To each node (embedded device) in the neural network, the master device sends the activation function for that node and the connectivity pattern for that node. The master device sends the inputs for the network to the distinguished input nodes of the network. During computation, each node computes the activation function of all of its inputs and sends its activation to all the nodes to which it needs to send output to. The outputs of the neural network are sent to the master device. Thus, the network of embedded devices can perform any computation (like speech recognition, natural language understanding, etc.) which can be mapped onto a neural network model.
摘要翻译： 公开了一种用于组合许多嵌入式设备的计算资源的系统和方法，以使它们中的任何一个能够执行诸如语音识别或自然语言理解的复杂任务。 杰出的主设备与嵌入式设备的网络通信，并将其组织为神经网络的节点。 对于神经网络中的每个节点（嵌入式设备），主设备发送该节点的激活功能和该节点的连接模式。 主设备将网络的输入发送到网络的不同输入节点。 在计算期间，每个节点计算其所有输入的激活函数，并将其激活发送到需要发送输出的所有节点。 神经网络的输出被发送到主设备。 因此，嵌入式设备的网络可以执行可映射到神经网络模型的任何计算（如语音识别，自然语言理解等）。
-
2.发明授权Method and apparatus for creating speech recognition grammars constrained by counter examples 失效用于创建由计数器示例约束的语音识别语法的方法和装置
公开(公告)号：US5937385A
公开(公告)日：1999-08-10
申请号：US954761
申请日：1997-10-20
CPC分类号： G10L15/193 , G10L15/183
摘要： An automated system generates and revises grammars for speech recognizers in a speech recognition system. Given an initial grammar, expressed in terms of non-terminals in Backus-Naur Form (BNF) notation, a sentence generator generates a list of all sentences accepted by the grammar. From this list, a corpus of inappropriate or irrelevant sentences which are accepted by the grammar (counter-examples) is identified. A grammar revisor program uses the original grammar and the list of counter examples, to generate a pruned list from which a revised grammar is generated. The revision process is iterated several times either concatenating or merging pairs of non-terminals until the revised grammar is deemed satisfactory in that it accepts as legal only relevant sentences. The revised grammar is used by the speech recognizer, thus reducing errors in the overall system.
摘要翻译： 自动化系统生成和修改语音识别系统中语音识别器的语法。 给出一种初始语法，用Backus-Naur表格（BNF）表示法表示非终端语法，一个句子生成器生成语法接受的所有句子的列表。 从该列表中，确定了语法接受的不适当或不相关句子的语料库（反例）。 语法指导程序使用原始语法和计数器示例列表来生成修剪的语法的修剪列表。 修订过程多次重复连接或合并非终端对，直到修改后的语法被认为是令人满意的，因为它只接受合法的相关句子。 修改后的语法由语音识别器使用，从而减少了整个系统的错误。
-
公开(公告)号：US06704394B1
公开(公告)日：2004-03-09
申请号：US09047722
申请日：1998-03-25
IPC分类号： H04M164
CPC分类号： H04M3/533 , H04M2203/2016 , H04M2203/253 , H04M2203/4509
摘要： The invention is directed towards an automated system for extracting voice messages from a voice mail system and for providing unified access to voice mail and electronic mail or voice mail and the internet. For a given user, a voice mail remote access server connects to the user's voice mail system through a telephone or data network, and uses speech recognition and understanding to navigate through the prompts of the voice mail system and extract the user's voice mail. Depending upon the access mechanism preferred by the user, the voice messages are sent as e-mail messages with attachments (audio files) to the user or made accessible to the user's world wide web server or displayed to the user using a stand-alone voice mail player application.
摘要翻译： 本发明涉及一种用于从语音邮件系统提取语音消息并用于提供对语音邮件和电子邮件或语音邮件和互联网的统一访问的自动化系统。 对于给定用户，语音邮件远程访问服务器通过电话或数据网络连接到用户的语音邮件系统，并且使用语音识别和理解来导航语音邮件系统的提示并提取用户的语音邮件。 取决于用户优选的访问机制，语音消息作为具有附件（音频文件）的电子邮件发送给用户或使得用户的万维网服务器可访问或者使用独立语音显示给用户 邮件播放器应用程序。
-
4.发明授权
公开(公告)号：US5649060A
公开(公告)日：1997-07-15
申请号：US547113
申请日：1995-10-23
申请人： Hamed A. Ellozy , Dimitri Kanevsky , Michelle Y. Kim , David Nahamoo , Michael Alan Picheny , Wlodek Wlodzimierz Zadrozny
发明人： Hamed A. Ellozy , Dimitri Kanevsky , Michelle Y. Kim , David Nahamoo , Michael Alan Picheny , Wlodek Wlodzimierz Zadrozny
IPC分类号： G03B31/00 , G06F17/30 , G10L15/00 , G10L15/18 , G10L15/22 , G10L15/26 , G11B27/028 , G11B27/10 , G11B27/28 , H04N5/91 , G10L9/00
CPC分类号： G11B27/28 , G06F17/30746 , G11B27/028 , G11B27/10
摘要： A method of automatically aligning a written transcript with speech in video and audio clips. The disclosed technique involves as a basic component an automatic speech recognizer. The automatic speech recognizer decodes speech (recorded on a tape) and produces a file with a decoded text. This decoded text is then matched with the original written transcript via identification of similar words or clusters of words. The results of this matching is an alignment of the speech with the original transcript. The method can be used (a) to create indexing of video clips, (b) for "teleprompting" (i.e. showing the next portion of text when someone is reading from a television screen), or (c) to enhance editing of a text that was dictated to a stenographer or recorded on a tape for its subsequent textual reproduction by a typist.
摘要翻译： 自动将书面誊本与视频和音频剪辑中的语音对齐的方法。 所公开的技术涉及作为自动语音识别器的基本组件。 自动语音识别器解码语音（记录在磁带上）并产生具有解码文本的文件。 然后，通过识别类似的单词或单词集合，将该解码的文本与原始的书面记录相匹配。 这种匹配的结果是语音与原始誊本的一致。 该方法可用于（a）创建视频剪辑的索引，（b）“电视提示”（即，当有人从电视屏幕读取时显示文本的下一部分），或（c）增强文本的编辑 这是由速记员决定的，或者录制在磁带上，以便打字员随后进行文字复制。
-
5.发明授权Method and apparatus for automatic segregation and routing of signals of different origins by using prototypes 失效通过原型自动分离和路由不同来源的信号的方法和装置公开(公告)号：US06246985B1
公开(公告)日：2001-06-12
申请号：US09137966
申请日：1998-08-20
IPC分类号： H04M3527
CPC分类号： H04L45/00 , H04M3/42 , H04M2203/2066
摘要： A method and apparatus is disclosed for automatic segregation of signals of different origin, using models that statistically characterize a wave signal, more particularly including feature vectors consisting of a plurality of parameters extracted from a data stream of a known type for use in identifying data types by comparison, which can be Hidden Markov Model based methods, thereby enabling automatic data type identification and routing of received data streams to the appropriate destination device, thereby further enabling a user to transmit different data types over the same communication channel without changing communication settings.
摘要翻译： 公开了一种用于自动分离不同来源的信号的方法和装置，使用统计学上表征波信号的模型，更具体地，包括由从用于识别数据类型的已知类型的数据流中提取的多个参数组成的特征向量 通过比较，其可以是基于隐马尔可夫模型的方法，从而使得自动数据类型识别和接收的数据流的路由到适当的目的地设备，从而进一步使得用户能够通过相同的通信信道传输不同的数据类型而不改变通信设置。
-
6.发明授权Method and apparatus utilizing dynamic questioning to provide secure access control 失效利用动态询问提供安全访问控制的方法和设备
公开(公告)号：US5774525A
公开(公告)日：1998-06-30
申请号：US911259
申请日：1997-08-14
CPC分类号： G06F21/40 , G06F21/31 , H04M3/382 , H04M3/493 , G06F2221/2103
摘要： A method and corresponding apparatus utilizes questioning to provide secure access control including the steps of storing information in a database; generating at least one question based upon the information stored in the data base; communicating to the user the generated question(s); receiving a response associated with the question(s), interpreting the response to determine whether the response conforms to the information upon which is based the associated question(s); and outputting an authorization status indicating whether or not the user is authorized for access according to the determination. The question(s) concerns a relationship among portions of information contained in said data base. This feature is advantageous because it protects against an eavesdropper gaining access to the service or facility and provides the capability of generating a relatively large number of different questions from a small data base. Furthermore, the questions asked of the user may be based on dynamic data, which advantageously protects against eavesdroppers gaining access to the service or facility. In addition, the number and/or type of questions generated by the first module may correspond to a security level of the system. The security level may be set by the service or facility, or may be set the system control module according to user input.
摘要翻译： 一种方法和相应的装置利用提问来提供安全的访问控制，包括将信息存储在数据库中的步骤; 基于存储在数据库中的信息生成至少一个问题; 向用户传达所产生的问题; 接收与所述问题相关联的响应，解释所述响应以确定所述响应是否符合基于相关问题的信息; 并且根据该确定输出指示用户是否被授权访问的授权状态。 该问题涉及所述数据库中包含的部分信息之间的关系。 该特征是有利的，因为它防止窃听者获得对服务或设施的访问，并且提供从小数据库生成相对大量不同问题的能力。 此外，用户询问的问题可以基于动态数据，其有利地防止窃听者获得对服务或设施的访问。 此外，第一模块产生的问题的数量和/或类型可以对应于系统的安全级别。 安全级别可以由服务或设施设置，或者可以根据用户输入设置系统控制模块。
-
7.发明授权Non intrusive automatic remote support for freeing overloaded storage in portable devices 有权非侵入式自动远程支持，可在便携式设备中释放超载存储公开(公告)号：US06393470B1
公开(公告)日：2002-05-21
申请号：US09225800
申请日：1999-01-05
IPC分类号： G06F1516
CPC分类号： H04N21/4223 , H04N1/00132 , H04N1/00137 , H04N1/00148 , H04N5/765 , H04N5/772 , H04N7/17318 , H04N21/2743 , H04N21/440263 , H04N21/4424 , H04W28/14
摘要： A non intrusive method for freeing storage of portable devices (such as digital video cameras) when the portable device becomes full. This task is accomplished using a network of servers that communicate via wireless channels with the portable devices (like cameras) within the zones of these servers. That is, if a server detects that a camera (or other device) is near full with stored captured images (data), or meets some other criteria, this server moves stored images (data) to a storage server without interrupting possible owner actions with the camera/device. The owner can download all moved images/data from a storage server to his/her computer after returning to a home/office/hotel. Similar non intrusive services can be provided for other miniature devices with embedded storage that are using by owners during some their activities (like palmtops, tapes, smart phones, wrist watches etc.).
摘要翻译： 当便携式设备变满时，用于释放便携式设备（例如数字摄像机）的存储的非侵入式方法。 该任务通过使用无线信道与这些服务器的区域内的便携式设备（如相机）进行通信的服务器网络来实现。 也就是说，如果服务器检测到摄像机（或其他设备）接近满载存储的捕获图像（数据）或满足某些其他条件，则该服务器将存储的图像（数据）移动到存储服务器，而不会中断可能的所有者操作 相机/设备。 返回家庭/办公室/酒店后，所有者可以将所有移动的图像/数据从存储服务器下载到他/她的计算机。 可以为具有嵌入式存储器的其他微型设备提供类似的非侵入式服务，这些嵌入式存储器在其某些活动期间（如掌上电脑，磁带，智能手机，手表等）由业主使用。
-
公开(公告)号：US06285777B1
公开(公告)日：2001-09-04
申请号：US08978957
申请日：1997-11-26
IPC分类号： G06K900
摘要： A communication system that transmits and receives combinations of paper mail and electronic mail. The communication system permits a user of the system to send an internet message via post mail including the mailing address for delivery. The post mail office forwards the internet message via e-mail to the internet post office that is the closest to the addressee. This post office that is local to the addressee downloads this message, prints a hard copy on a paper, encloses it in an envelop and sends the hard copy to the addressee via usual local mail. The communication system also permits a user of the system to send paper mail to the post office. The post office scans the paper mail and forwards the scanned information data either to the addressee directly via internet or via a post office that is local to the addressee.
-
9.发明授权公开(公告)号：US06912580B1
公开(公告)日：2005-06-28
申请号：US09239109
申请日：1999-01-27
CPC分类号： H04L67/34 , H04L67/04 , H04L67/18 , H04L69/329
摘要： A computer has one or more communication interfaces that determine if one or more client (client devices) is within a range of communication of the computer. The computer also has one or more computer interfaces capable of communicating with one or more of the second computers. The second computers can be at any general location and/or installed as subsystems of other devices. An application process determines from the client signal that the client is within the range of communication and that requests and receives one or more of the application programs through the computer interface from one or more of the second computers at the commuter location. Thus, the application program (and necessary databases) are moved to a next computer as the client moves within the range of communication of this next computer. The application programs/databases can be discarded once the client moves outside of the range of communication of the computer.
摘要翻译： 计算机具有一个或多个通信接口，其确定一个或多个客户机（客户端设备）是否在计算机的通信范围内。 计算机还具有能够与一个或多个第二计算机通信的一个或多个计算机接口。 第二台计算机可以在任何一般位置和/或作为其他设备的子系统安装。 应用处理从客户端信号确定客户端在通信范围内，并且通过来自通勤位置的一个或多个第二计算机的计算机接口请求和接收一个或多个应用程序。 因此，当客户端在该下一台计算机的通信范围内移动时，将应用程序（以及必要的数据库）移动到下一台计算机。 一旦客户端移动到计算机的通信范围之外，应用程序/数据库就可以被丢弃。
-
公开(公告)号：US06236968B1
公开(公告)日：2001-05-22
申请号：US09078807
申请日：1998-05-14
IPC分类号： G10L2100
CPC分类号： G10L17/26 , A61B5/4803 , G06F19/00 , G08B21/06 , G10L15/22
摘要： An automatic dialog system capable of keeping a drive awake while driving during a long trip or one that extends into the late evening. The system carries on a conversation with the driver on various topics utilizing a natural dialog car system. The system includes an automatic speech recognition module, a speech generation module which includes speech synthesis or recorded speech, and possibly dynamically combined speech synthesizer and recorded speech, and a natural language processing module. The natural dialog car system analyzes a driver's answer and the contents of the answer together with his voice patterns to determine if he is alert while driving. The system warns the driver or changes the topic of conversation if the system determines that the driver is about to fall asleep. The system may also detect whether a driver is effected by alcohol or drugs.
摘要翻译： 一种自动对话系统，能够在长时间行驶期间或延迟至深夜的同时保持驱动器的清醒。 系统利用自然对话车系统与驾驶员进行各种话题的交谈。 该系统包括自动语音识别模块，语音生成模块，其包括语音合成或记录语音，以及可能的动态组合语音合成器和记录语音，以及自然语言处理模块。 自然对话车系统分析驾驶员的答案和答案的内容以及他的声音模式，以确定驾驶时是否有警觉。 如果系统确定驾驶员即将入睡，系统会警告驾驶员或更改对话主题。 该系统还可以检测驾驶员是否受酒精或药物影响。
-
-
-
-
-
-
-
-
-
搜索结果
15 条记录 (耗时 0.018 秒)
