公开(公告)号：US06731307B1

公开(公告)日：2004-05-04

申请号：US09699577

申请日：2000-10-30

申请人： Hugo J. Strubbe ,  Larry J. Eshelman ,  Srinivas Gutta ,  John Milanski

发明人： Hugo J. Strubbe ,  Larry J. Eshelman ,  Srinivas Gutta ,  John Milanski

IPC分类号： G10L1522

CPC分类号： H04N21/466 ,  G06N3/004 ,  G10L15/22 ,  G10L17/26

摘要： An interaction simulator uses computer vision, and inputs of other modalities, to analyze the user's mental state and/or personality. The mental state and/or personality are classified and this information used to guide conversation and other interaction. In a chatterbot embodiment, the substance of the conversation may be altered in response to the mental state and/or personality class, for example, by changing the topic of conversation to a favorite subject when the user is sad or by telling a joke when the user is in a good mood.

摘要翻译： 交互模拟器使用计算机视觉和其他模式的输入来分析用户的精神状态和/或个性。 精神状态和/或个性被分类，这些信息用于指导对话和其他交互。 在喋喋不休的实施例中，对话的实质可以响应于精神状态和/或个性等级而被改变，例如，当用户悲伤时通过将对话主题改变为最喜欢的对象，或者当 用户心情很好

公开(公告)号：US06615178B1

公开(公告)日：2003-09-02

申请号：US09673470

申请日：2000-10-17

申请人： Kazuhiko Tajima

发明人： Kazuhiko Tajima

IPC分类号： G10L1522

CPC分类号： G06F17/2705 ,  G06F17/271 ,  G06F17/2735 ,  G06F17/274 ,  G06F17/2765 ,  G06F17/2785 ,  G06F17/2872 ,  G10L15/1815 ,  G10L15/19

摘要： The learning history memory 9 controls, based on the accumulated learning history, the word dictionary memory 6, semantic/syntactic analysis grammar memory 7, and a correction information memory 13 to limit the syntactic/semantic language structure and range of vocabulary, which are not used frequently. Then, the speech recognition collator 4 collates the feature vector with information, having high priority within the limited range, in the word dictionary memory 6 and semantic/syntactic analysis grammar memory 7 to recognize the speech.

摘要翻译： 学习历史存储器9基于积累的学习历史来控制词典存储器6，语义/句法分析语法存储器7和校正信息存储器13，以限制不是的语义/语义语言结构和词汇范围 频繁使用 然后，语音识别整理器4将特征矢量与有限范围内具有高优先级的信息整合在单词辞典存储器6和语义/句法分析语法存储器7中，以识别语音。

公开(公告)号：US06615175B1

公开(公告)日：2003-09-02

申请号：US09330101

申请日：1999-06-10

申请人： Robert F. Gazdzinski

发明人： Robert F. Gazdzinski

IPC分类号： G10L1522

CPC分类号： B66B1/3415 ,  B66B1/34 ,  B66B1/3453 ,  B66B1/468 ,  B66B3/006 ,  B66B3/008 ,  B66B2201/4615 ,  B66B2201/463 ,  B66B2201/4646 ,  B66B2201/4676 ,  G10L15/26

摘要： An information and control system for personnel transport devices. In one embodiment, the information and control system is coupled to the elevator system of a building, and includes a touch panel input device, a flat panel display having a touch sensitive screen, and speech recognition and synthesis systems serving each elevator car. The speech recognition and synthesis systems and input device(s) are operatively coupled to a processor and storage devices having a plurality of different types of data stored thereon. Each elevator car is also a client connected to a LAN, WAN, intranet, or Internet, and capable of exchanging data with and retrieving data therefrom. Functions performed by the information and control system include a voice-actuated building directory, download of selected data to personal electronic devices (PEDs), monitoring of areas adjacent to the elevator car on destination floors, and control of lighting and security monitoring in selectable areas of destination floors. The system is also optionally fitted with an RFID interrogator/reader capable of recognizing RFID tags carried by passengers on the elevator, thereby granting access to various controlled locations automatically after password authentication. The RFID system also allows the authenticated passenger(s) to control utilities such as lighting and HVAC within specific zones on their destination floors. The information and control system is also optionally equipped with an occupancy estimating sub-system which allows elevator cars to bypass calling floors when their capacity is reached or exceeded.

摘要翻译： 人员运输装置信息和控制系统。 在一个实施例中，信息和控制系统耦合到建筑物的电梯系统，并且包括触摸面板输入设备，具有触敏屏幕的平板显示器以及为每个电梯轿厢服务的语音识别和综合系统。 语音识别和合成系统和输入设备可操作地耦合到具有存储在其上的多种不同类型的数据的处理器和存储设备。 每个电梯轿厢也是连接到局域网，广域网，内联网或互联网的客户端，并且能够与数据交换数据并从中检索数据。 由信息和控制系统执行的功能包括语音建立目录，将所选择的数据下载到个人电子设备（PED），监视目的地楼层上的电梯轿厢邻近区域，以及控制可选区域中的照明和安全监控 的目的地楼层。 该系统还可选配有能够识别乘客在电梯上携带的RFID标签的RFID询问器/读取器，从而在密码认证之后自动访问各种受控位置。 RFID系统还允许经过身份验证的乘客在其目的地楼层的特定区域内控制诸如照明和HVAC之类的实用工具。 信息和控制系统还可选地配备有占用估计子系统，其允许电梯轿厢在达到或超过其容量时绕过呼叫楼层。

公开(公告)号：US06505162B1

公开(公告)日：2003-01-07

申请号：US09426275

申请日：1999-10-25

申请人： Huei-Ming Wang ,  Yi-Chung Lin ,  Tung-Hui Chiang

发明人： Huei-Ming Wang ,  Yi-Chung Lin ,  Tung-Hui Chiang

IPC分类号： G10L1522

CPC分类号： G10L15/22

摘要： A portable dialogue management system includes a dialogue manager and a hierarchical task description table. The hierarchical task description table has a plurality of base tables connected with a hierarchical structure. Each base table defines the strategy of a sub-dialogue and stores the dialogue states, a number of domain parameters, and a plurality of response actions corresponding to each dialogue state. The dialogue manager manages the dialogue state of a dialogue system, determines the dialogue state and executes the appropriate response action. Because the domain knowledge is defined in the hierarchical task description table and the dialogue manager is not dependent on the application domain, the dialogue management system is easily portable to different applications. A stack may also be used to push in or pop up a dialogue state so that dialogues of multiple purposes can be accomplished.

摘要翻译： 便携式对话管理系统包括对话管理器和分级任务描述表。 分级任务描述表具有与分层结构连接的多个基表。 每个基表定义子对话的策略，并存储对话状态，多个域参数以及对应于每个对话状态的多个响应动作。 对话管理器管理对话系统的对话状态，确定对话状态并执行适当的响应动作。 由于领域知识在分层任务描述表中定义，对话管理器不依赖于应用领域，对话管理系统可以轻松地移植到不同的应用中。 也可以使用堆栈来推入或弹出对话状态，从而可以实现多种目的的对话。

公开(公告)号：US06408272B1

公开(公告)日：2002-06-18

申请号：US09290508

申请日：1999-04-12

申请人： George M. White ,  James J. Buteau ,  Glen E. Shires ,  Kevin J. Surace ,  Steven Markman

发明人： George M. White ,  James J. Buteau ,  Glen E. Shires ,  Kevin J. Surace ,  Steven Markman

IPC分类号： G10L1522

CPC分类号： G10L15/30

摘要： A distributed voice user interface system includes a local device which receives speech input issued from a user. Such speech input may specify a command or a request by the user. The local device performs preliminary processing of the speech input and determines whether it is able to respond to the command or request by itself. If not, the local device initiates communication with a remote system for further processing of the speech input.

摘要翻译： 分布式语音用户接口系统包括接收从用户发出的语音输入的本地设备。 这样的语音输入可以指定用户的命令或请求。 本地设备执行语音输入的初步处理，并确定是否能够自己对命令或请求作出响应。 如果不是，则本地设备发起与远程系统的通信，以进一步处理语音输入。

公开(公告)号：US06389398B1

公开(公告)日：2002-05-14

申请号：US09338890

申请日：1999-06-23

申请人： Paul C. Lustgarten ,  Thomas Clavin Cannon, Jr.

发明人： Paul C. Lustgarten ,  Thomas Clavin Cannon, Jr.

IPC分类号： G10L1522

CPC分类号： G10L15/22

摘要： An IVR system for an information network and method for storing and executing user queries stored on the network so that such queries do not have to be re-entered each time a user wants to access information from or execute a transaction on the network. The system can also be programmed to automatically execute the query at a predetermined time or times, and deliver information retrieved from the network and/or confirmation of the execution of a transaction on the network to the user in a format specified by the user.

摘要翻译： 一种用于信息网络的IVR系统和用于存储和执行存储在网络上的用户查询的方法，使得每当用户想要从网络上访问信息或执行交易时，不需要重新输入这些查询。 该系统还可以被编程为在预定的时间或时间自动执行查询，并且以网络指定的格式将从网络检索的信息和/或将网络上的交易的执行确认递送给用户。

公开(公告)号：US06345253B1

公开(公告)日：2002-02-05

申请号：US09335627

申请日：1999-06-18

申请人： Mahesh Viswanathan

发明人： Mahesh Viswanathan

IPC分类号： G10L1522

CPC分类号： G06F17/30746 ,  G10L15/26 ,  G10L17/00

摘要： An audio retrieval system and method are provided for augmenting the transcription of an audio file with one or more alternate word or phrase choices, such as next-best guesses for each word or phrase, in addition to the best word sequence identified by the transcription process. The audio retrieval system can utilize a primary index file containing the best identified words and/or phrases for each portion of the input audio stream and a supplemental index file containing alternative choices for each word or phrase in the transcript. The present invention allows words that are incorrectly transcribed during speech recognition to be identified in response to a textual query by searching the supplemental index files. During an indexing process, the list of alternative word or phrase choices provided by the speech recognition system are collected to produce a set of supplemental index files. During a retrieval process, the user-specified textual query is matched against the primary and supplemental indexes derived from the transcribed audio to identify relevant documents. An objective ranking function scales matches found in the supplemental index file(s) using a predefined scaling factor, or a value reflecting the confidence value of the corresponding alternative choice as identified by the speech recognition system.

摘要翻译： 提供音频检索系统和方法，用于增加具有一个或多个替代词或短语选择的音频文件的转录，例如除了由转录过程识别的最佳词序列之外的每个单词或短语的下一个最佳猜测 。 音频检索系统可以利用包含输入音频流的每个部分的最佳识别词和/或短语的主索引文件，以及包含转录中的每个单词或短语的替代选择的补充索引文件。 本发明允许通过搜索补充索引文件来响应于文本查询来识别在语音识别期间错误地转录的单词。 在索引过程中，收集由语音识别系统提供的备选词或短语选择的列表，以产生一组补充索引文件。 在检索过程中，用户指定的文本查询与从转录音频导出的主要和补充索引进行匹配，以识别相关文档。 客观排序功能使用预定义的缩放因子来缩放在补充索引文件中找到的匹配，或反映由语音识别系统识别的对应的替代选择的置信度的值。

公开(公告)号：US06338035B1

公开(公告)日：2002-01-08

申请号：US09220769

申请日：1998-12-28

申请人： Ichiro Mori

发明人： Ichiro Mori

IPC分类号： G10L1522

CPC分类号： G10L15/22

摘要： A voice-input document creation system which reduces correction times to a wrongly-recognized input to ensure input efficiency. The system has a determination means for comparing the feature content of a newest voice input extracted by a feature extracting module with a feature content of an immediately preceding voice input to determine if the newest voice input is a correction to the immediately preceding voice input. When a first-time correction is received, the system displays a list of all output candidates for the immediately preceding voice input stored in a second memory. When a second-time correction is received, the system stores the output candidates for the newest voice input into a third memory and, at the same time, displays the output candidates; at this time, the system neither displays nor stores in the third memory those output candidates displayed upon the first-time correction.

摘要翻译： 一种语音输入文档创建系统，其将错误识别输入的校正时间减少，以确保输入效率。 该系统具有用于将由特征提取模块提取的最新语音输入的特征内容与紧接在前的语音输入的特征内容进行比较的确定装置，以确定最新的语音输入是否是对前一个语音输入的校正。 当接收到第一次校正时，系统显示存储在第二存储器中的紧接在前的语音输入的所有输出候选的列表。 当接收到第二次校正时，系统将用于最新语音输入的输出候选存储到第三存储器中，同时显示输出候选; 此时，在第一次修正时，系统既不显示也不存储在第三存储器中显示这些输出候补。

公开(公告)号：US06292782B1

公开(公告)日：2001-09-18

申请号：US08709584

申请日：1996-09-09

申请人： William Edward Weideman

发明人： William Edward Weideman

IPC分类号： G10L1522

CPC分类号： G06Q20/425 ,  G07C9/00158 ,  G10L15/142 ,  G10L17/24 ,  G10L2015/025

摘要： A system and apparatus for using speech recognition and verification to provide secure and authorized data transmissions between networked computer systems is provided. The system includes first and second network computer systems wherein a request for a transaction by user of the first computer system causes the user to be prompted to enter a spoken identifier such as a credit card number, PIN number or password. This spoken identifier is converted from speech data into speech feature data using either a resident software application or a downloaded application from the second computer system. The speech feature data is transmitted to the second computer system wherein speech recognition and verification engines identify the spoken identifier and determine whether or not the user who spoke the identifier is properly associated with the spoken identifier. Upon successful completion of this recognition and verification process, the requested transaction is completed.

摘要翻译： 提供了一种用于使用语音识别和验证在联网的计算机系统之间提供安全和授权的数据传输的系统和装置。 该系统包括第一和第二网络计算机系统，其中第一计算机系统的用户对交易的请求使得用户被提示输入诸如信用卡号码，PIN号或密码的口语标识符。 该语音标识符使用驻留的软件应用或来自第二计算机系统的下载的应用从语音数据转换成语音特征数据。 语音特征数据被发送到第二计算机系统，其中语音识别和验证引擎识别语音标识符并且确定说出标识符的用户是否与语音标识符正确地相关联。 成功完成此识别和验证过程后，所请求的交易完成。

公开(公告)号：US06269337B1

公开(公告)日：2001-07-31

申请号：US09122124

申请日：1998-07-24

申请人： Martha Desmond ,  Karrie Jo Hanson ,  Bethany Scott Robinson ,  David G. Unger ,  Michael Chris Varley

发明人： Martha Desmond ,  Karrie Jo Hanson ,  Bethany Scott Robinson ,  David G. Unger ,  Michael Chris Varley

IPC分类号： G10L1522

CPC分类号： H04M3/4931 ,  H04M3/4933 ,  H04M7/12 ,  H04M2201/60

摘要： An operator receives a request for directory information about a listed party over a telephone connection. It is then determined if enhanced directory information for the listed party is available in an enhanced information database. The enhanced directory information associated with the listed party is retrieved, from the enhanced information database, as a script that incorporates the enhanced directory information. The enhanced directory information can then be provided using the script. The enhanced directory information can be stored, for example, on a Web server that is updated by the listed party and the information can be transferred using a Phone Markup Language script.

摘要翻译： 操作者通过电话连接接收关于被列出方的目录信息的请求。 然后，确定增强型信息数据库中是否提供了列出方的增强目录信息。 从增强信息数据库中检索与列出的方相关联的增强目录信息，作为包含增强目录信息的脚本。 然后可以使用脚本提供增强的目录信息。 增强目录信息可以存储在例如被列出方更新的Web服务器上，并且可以使用电话标记语言脚本传送信息。