-
公开(公告)号：US06889219B2
公开(公告)日：2005-05-03
申请号：US10054051
申请日：2002-01-22
申请人： Mark E. Epstein , Jerome L. Quinn
发明人： Mark E. Epstein , Jerome L. Quinn
CPC分类号： G06N5/025
摘要： A method of tuning a decision network can include a series of steps. The steps can include identifying a deviation between a correct interpretation of a data item and an incorrect interpretation of the data item. In a decision network including a hierarchical set of nodes and leaves, a path of traversed nodes in the decision network resulting in the deviation can be determined. The nodes can correspond to queries. A measure of goodness at a node in the path can be calculated using at least one new query as a replacement for an existing query to determine whether the measure of goodness improves using the new query compared to the old query. If the measure of goodness improves, at least one new query can be selected and the decision network can be regrown from the node down through the leaves using the at least one new query at the node.
摘要翻译： 调整决策网络的方法可以包括一系列步骤。 这些步骤可以包括识别数据项的正确解释与数据项的不正确解释之间的偏差。 在包括节点和树叶的分级集合的决策网络中，可以确定导致偏差的决策网络中遍历节点的路径。 节点可以对应于查询。 可以使用至少一个新查询作为现有查询的替代来计算路径中的节点的良好度量，以确定与旧查询相比，使用新查询是否改善了度量。 如果善意度提高，则可以选择至少一个新查询，并且可以使用该节点处的至少一个新查询从节点向下再循环决策网络。
-
2.发明授权Integrated development tool for building a natural language understanding application 有权用于构建自然语言理解应用程序的集成开发工具公开(公告)号：US07191119B2
公开(公告)日：2007-03-13
申请号：US10140522
申请日：2002-05-07
申请人： Mark E. Epstein , Sharon B. Jones , Robert T. Ward
发明人： Mark E. Epstein , Sharon B. Jones , Robert T. Ward
IPC分类号： G06F17/21
CPC分类号： G06F17/2785 , G06F17/271 , G06F17/2775
摘要： A method of developing natural language understanding (NLU) applications can include determining NLU interpretation information from an NLU training corpus of text using a multi-pass processing technique. The alteration of one pass automatically can alter an input for a subsequent pass. The NLU interpretation information can specify an interpretation of at least part of the NLU training corpus of text. The NLU interpretation information can be stored in a database, and selected items of the NLU interpretation information can be presented in a graphical editor. User specified edits also can be received in the graphical editor.
摘要翻译： 开发自然语言理解（NLU）应用的方法可以包括使用多遍处理技术从NLU训练语料库确定NLU解释信息。 自动更改一次通过可以更改后续通过的输入。 NLU解释信息可以指定至少部分NLU训练语料库的解释。 NLU解释信息可以存储在数据库中，并且可以在图形编辑器中呈现NLU解释信息的选定项目。 用户指定的编辑也可以在图形编辑器中接收。
-
3.发明授权公开(公告)号：US07039579B2
公开(公告)日：2006-05-02
申请号：US09952974
申请日：2001-09-14
CPC分类号： G06F17/2775 , G10L15/183 , G10L15/197
摘要： A Monte Carlo method for use with natural language understanding and speech recognition language models can include a series of steps. The steps can include identifying at least one phrase embedded in a body of text wherein the phrase can belong to a phrase class. An additional attribute corresponding to the identified phrase can be determined. The body of text can be copied and the identified phrase can be replaced with a different phrase selected from a plurality of phrases. The different phrase can belong to the phrase class and correspond to the attribute.
-
4.发明授权Bi-directional natural language system for interfacing with multiple back-end applications 有权用于与多个后端应用程序进行连接的双向自然语言系统公开(公告)号：US07254539B2
公开(公告)日：2007-08-07
申请号：US10178807
申请日：2002-06-24
IPC分类号： G10L15/00
CPC分类号： H04M3/4936 , G10L15/1822 , Y10S707/99934
摘要： A system and method for servicing natural language requests with a plurality of remote host systems. The system utilizes a computer program that comprises: (1) an input system for inputting an NL command; (2) a translation system that extracts a request from the NL command and stores the request in a host-independent format; and (3) a routing system for servicing the request, wherein the routing system comprises a mechanism for selecting a host, for converting the request into a host dependent directive, and for forwarding the directive to the selected host. The system may further include a speech recognition system, a local data source for servicing the NL command, templates for converting the request into the host dependent directive, a heuristic for selecting the host, and an output system for obtaining and outputting the response.
摘要翻译： 一种用于利用多个远程主机系统来服务自然语言请求的系统和方法。 该系统利用计算机程序，其包括：（1）用于输入NL命令的输入系统; （2）翻译系统，其从NL命令中提取请求并将请求存储在与主机无关的格式中; 以及（3）用于对所述请求进行服务的路由系统，其中所述路由系统包括用于选择主机的机制，用于将所述请求转换为主机相关指令，以及将所述指令转发到所选主机。 该系统还可以包括语音识别系统，用于服务NL命令的本地数据源，用于将请求转换为主机相关指令的模板，用于选择主机的启发式，以及用于获得和输出响应的输出系统。
-
5.发明授权公开(公告)号：US06845356B1
公开(公告)日：2005-01-18
申请号：US09773172
申请日：2001-01-31
申请人： Mark E. Epstein
发明人： Mark E. Epstein
摘要： A method for processing dual tone multi-frequency signals for use with a natural language understanding system can include several steps. The step of determining whether a audio input signal is a dual tone multi-frequency signal or a human speech signal can be included. If the audio input signal is determined to be a dual tone multi-frequency signal, the audio input signal can be converted to at least one text equivalent. Also, the step of providing the at least one text equivalent to a natural language understanding system can be included. The natural language understanding system can determine a meaning from the text equivalent.
摘要翻译： 一种用于处理与自然语言理解系统一起使用的双音多频信号的方法可以包括几个步骤。 可以包括确定音频输入信号是双音多频信号还是人语音信号的步骤。 如果音频输入信号被确定为双音多频信号，则音频输入信号可被转换为至少一个文本等价物。 此外，可以包括提供与自然语言理解系统相当的至少一个文本的步骤。 自然语言理解系统可以从文本中确定一个含义。
-
公开(公告)号：US5522011A
公开(公告)日：1996-05-28
申请号：US127392
申请日：1993-09-27
CPC分类号： G10L19/038
摘要： A speech coding apparatus and method uses classification rules to code an utterance while consuming fewer computing resources. The value of at least one feature of an utterance is measured during each of a series of successive time intervals to produce a series of feature vector signals representing the feature values. The classification rules comprise at least first and second sets of classification rules. The first set of classification rules map each feature vector signal from a set of all possible feature vector signals to exactly one of at least two disjoint subsets of feature vector signals. The second set of classification rules map each feature vector signal in a subset of feature vector signals to exactly one of at least two different classes of prototype vector signals. Each class contains a plurality of prototype vector signals. According to the classification rules, a first feature vector signal is mapped to a first class of prototype vector signals. The closeness of the feature value of the first feature vector signal is compared to the parameter values of only the prototype vector signals in the first class of prototype vector signals to obtain prototype match scores for the first feature vector signal and each prototype vector signal in the first class. At least the identification value of at least the prototype vector signal having the best prototype match score is output as a coded utterance representation signal of the first feature vector signal.
摘要翻译： 语音编码装置和方法使用分类规则来编码话语，同时消耗更少的计算资源。 在一系列连续时间间隔的每一个期间测量话音的至少一个特征的值，以产生表示特征值的一系列特征向量信号。 分类规则至少包括第一组和第二组分类规则。 第一组分类规则将来自一组所有可能特征向量信号的每个特征向量信号映射到特征向量信号的至少两个不相交子集中的一个。 第二组分类规则将特征向量信号的子集中的每个特征向量信号精确地映射到至少两个不同类型的原型矢量信号中的一个。 每个类都包含多个原型矢量信号。 根据分类规则，将第一特征向量信号映射到第一类原型矢量信号。 将第一特征向量信号的特征值的接近度与仅第一类原型矢量信号中的原型矢量信号的参数值进行比较，以获得第一特征向量信号的原型匹配分数和 一等课 至少具有最佳原型匹配分数的原型矢量信号的识别值被输出为第一特征向量信号的编码话音表示信号。
-
7.发明授权
公开(公告)号：US5293451A
公开(公告)日：1994-03-08
申请号：US602020
申请日：1990-10-23
CPC分类号： G10L15/063 , G10L15/144
摘要： A method and apparatus for modeling words based on match scores representing (a) the closeness of a match between probabilistic word models and the acoustic features of at least two utterances, and (b) the closeness of a match between word models and the spelling of the word. A match score is calculated for a selection set of one or more probabilistic word models. A match score is also calculated for an expansion set comprising the probabilistic word models in the selection set and one probabilistic word model from a candidate set. If the expansion set match score improves the selection set match score by a selected nonzero threshold value, the word is modelled with the word models in the expansion set. If the expansion set match score does not improve the selection set match score by the selected nonzero threshold value, the word is modelled with the words in the selection set.
摘要翻译： 一种用于基于匹配分数对词进行建模的方法和装置，其表示（a）概率词模型与至少两个话语的声学特征之间的匹配的接近度，以及（b）词模型与拼写之间的匹配的接近度 这个单词。 对于一个或多个概率词模型的选择集计算匹配分数。 还对包括选择集合中的概率词模型和来自候选集合的一个概率词模型的扩展集合计算匹配分数。 如果扩展集匹配分数通过选择的非零阈值改善了选择集匹配分数，则该词用扩展集合中的单词模型建模。 如果扩展集匹配得分没有通过选择的非零阈值改善选择集合匹配分数，则用该选择集中的单词建模该单词。
-
8.发明授权Method and apparatus for embedding grammars in a natural language understanding (NLU) statistical parser 失效在自然语言理解（NLU）统计解析器中嵌入语法的方法和装置公开(公告)号：US06983239B1
公开(公告)日：2006-01-03
申请号：US09696764
申请日：2000-10-25
申请人： Mark E. Epstein
发明人： Mark E. Epstein
IPC分类号： G06F17/27
CPC分类号： G06F17/271 , G06F17/2715 , G06F17/274 , G10L15/193
摘要： A method and system for use in a natural language understanding system for including grammars within a statistical parser. The method involves a series of steps. The invention receives a text input. The invention applies a first context free grammar to the text input to determine substrings and corresponding parse trees, wherein the substrings and corresponding parse trees further correspond to the first context free grammar. Additionally, the invention can examine each possible substring using an inventory of queries corresponding to the CFG.
摘要翻译： 用于在统计解析器中包含语法的自然语言理解系统中使用的方法和系统。 该方法涉及一系列步骤。 本发明接收文本输入。 本发明将第一上下文无关语法应用于文本输入以确定子串和相应的解析树，其中所述子串和相应的解析树进一步对应于第一语境自由语法。 此外，本发明可以使用与CFG相对应的查询的清单来检查每个可能的子串。
-
9.发明授权Method and apparatus for providing multiple output channels in a microphone 失效用于在麦克风中提供多个输出通道的方法和装置公开(公告)号：US06959095B2
公开(公告)日：2005-10-25
申请号：US09927690
申请日：2001-08-10
申请人： Raimo Bakis , Mark E. Epstein
发明人： Raimo Bakis , Mark E. Epstein
IPC分类号： H04R3/00
CPC分类号： H04R3/00
摘要： Methods and apparatus for providing multiple output channels in a microphone. More particularly, provision is made for an arrangement wherein a single microphone is adapted to produce one or more different audio outputs depending upon characteristics of a speaker or user of the microphone while facilitating a high degree of accuracy in the recognition of the user or speaker by the arrangement. The microphone is adapted to produce one or more different audio streams or outputs depending upon the speaker presently using the microphone. In effect, this can be readily implemented by a main user or speaker, such as an interviewer on a radio or TV talk show, or any speaker in a conference room, intending to control the audio output streams by suitably activating a button or switch.
摘要翻译： 用于在麦克风中提供多个输出通道的方法和装置。 更具体地，提供了一种布置，其中单个麦克风适于根据麦克风的扬声器或用户的特性产生一个或多个不同的音频输出，同时便于用户或扬声器的识别中的高度准确度 安排。 麦克风适于根据目前使用麦克风的扬声器产生一个或多个不同的音频流或输出。 实际上，这可以容易地由诸如无线电或电视谈话节目上的访问者或会议室中的任何扬声器的主要用户或扬声器实现，旨在通过适当地激活按钮或开关来控制音频输出流。
-
10.发明授权Creating a hierarchical tree of language models for a dialog system based on prompt and dialog context 有权基于提示和对话框上下文创建对话系统的语言模型层次树公开(公告)号：US06754626B2
公开(公告)日：2004-06-22
申请号：US09798655
申请日：2001-03-01
申请人： Mark E. Epstein
发明人： Mark E. Epstein
IPC分类号： G10L1526
CPC分类号： G10L15/197 , G10L15/183
摘要： The invention disclosed herein concerns a method of converting speech to text using a hierarchy of contextual models. The hierarchy of contextual models can be statistically smoothed into a language model. The method can include processing text with a plurality of contextual models. Each one of the plurality of contextual models can correspond to a node in a hierarchy of the plurality of contextual models. Also included can be identifying at least one of the contextual models relating to the text and processing subsequent user spoken utterances with the identified at least one contextual model.
摘要翻译： 本文公开的发明涉及使用上下文模型的层次将语音转换为文本的方法。 语境模型的层次结构可以被统计学平滑化为语言模型。 该方法可以包括用多个上下文模型处理文本。 多个上下文模型中的每一个可以对应于多个上下文模型的层次结构中的节点。 还包括可以识别与文本相关的上下文模型中的至少一个以及使用所识别的至少一个上下文模型来处理随后的用户口语话语。
-
-
-
-
-
-
-
-
-
搜索结果
16 条记录 (耗时 0.018 秒)