知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

6 条记录 (耗时 0.012 秒)

    Method and apparatus for executing a human-machine dialogue in the form of two-sided speech as based on a modular dialogue structure
    1.
    发明授权
    Method and apparatus for executing a human-machine dialogue in the form of two-sided speech as based on a modular dialogue structure 失效
    基于模块对话结构，以双面语言的形式执行人机对话的方法和装置

    公开(公告)号：US6035275A

    公开(公告)日：2000-03-07

    申请号：US005626

    申请日：1998-01-09

    申请人： Holger W. Brode ,  Olaf Schroer ,  Jens F. Marschner ,  Harald Aust ,  Enrique Marti Del Olmo

    发明人： Holger W. Brode ,  Olaf Schroer ,  Jens F. Marschner ,  Harald Aust ,  Enrique Marti Del Olmo

    IPC分类号： G06F3/16 ,  G10L15/00 ,  G10L15/22 ,  G10L3/00

    CPC分类号： G10L15/22

    摘要： In a dialogue structure outputting speech items interrogating an access call while examining subsequently received human speech items for ascertaining an actual transaction instance further outputting speech in accordance with the ascertaining until either attaining a positive transaction result, or otherwise exiting the dialogue in case of failure. In particular, the dialogue is constructed from hierarchically arranged and callable subdialogues constituting respective mutually independent building blocks, which are arranged for generating a particular outcome if a positive result is attained by the subdialogue in question. The subdialogues offer interfaces for mutual coupling with a hierarchically superior subdialogue, so that the overall structure is formed as based on a selection of subdialogues and exclusively based on required partial results by each of the subdialogues in the structure.

    摘要翻译： 在对话结构中，输出询问访问呼叫的语音项目，同时检查随后接收到的人类语音项目，以确定实际的交易实例，根据确定进一步输出语音，直到达到正的交易结果，或者否则在失败的情况下退出对话。 特别地，对话由构成各自相互独立的构建块的分级布置和可呼叫的子对话构成，如果所讨论的小学对象获得了积极的结果，则被配置为产生特定结果。 子目录提供用于与分级上级子对话相互耦合的界面，使得总体结构基于子对话的选择形成，并且仅基于结构中每个子对话的所需部分结果。

    Transaction system based on a bidirectional speech channel by status graph building and problem detection for a human user
    2.
    发明授权
    Transaction system based on a bidirectional speech channel by status graph building and problem detection for a human user 失效
    基于双向语音信道的交易系统，通过状态图构建和人类用户的问题检测

    公开(公告)号：US5860059A

    公开(公告)日：1999-01-12

    申请号：US810778

    申请日：1997-03-05

    申请人： Harald Aust ,  Holger W. Brode ,  Olaf Schroer ,  Jens F. Marschner ,  Erique Marti Del Olmo ,  Ralf Mehlan

    发明人： Harald Aust ,  Holger W. Brode ,  Olaf Schroer ,  Jens F. Marschner ,  Erique Marti Del Olmo ,  Ralf Mehlan

    IPC分类号： G06F3/16 ,  G10L15/18 ,  G10L15/22 ,  H04M3/493 ,  G10L3/02 ,  G10L9/00 ,  G10L5/02

    CPC分类号： H04M3/493 ,  G06F3/16 ,  G10L15/22 ,  G10L15/1815 ,  H04M2201/60

    摘要： A transaction system has machine recognition of speech. It has dialogue control fed by the recognition, and speech generation fed by the dialogue control for outputting question and verifier statements from a repertoire set. A human-machine dialogue is executed until the dialogue control has recognized a viable transaction formulation with a plurality of user-provided slot fillers to specify the transaction. Dialogue control builds a directed and loopless status graph with nodes that each have their own slot filler and associated metric, and are interrelated through logic relations. The building can amend a node's metric and under control of conflict detection or lowering of a particular node's metric, discard the node in question and its filler, including of derived nodes and also of one-to-one derival nodes of the discarded node. A subset of problems is detected for a particular item outputted by the speech generation for ascertaining a particular slot filler, as combined with a subsequent unsatisfactory recognition. Then the speech generation outputs a further question statement for ascertaining the latter slot filler.

    摘要翻译： 交易系统具有机器对语音的识别。 它具有通过识别进行的对话控制，以及由对话控制馈送的语音生成，用于从集合集中输出问题和验证者语句。 执行人机对话，直到对话控件已经识别出具有多个用户提供的插槽填充器的可行交易公式来指定交易。 对话控制构建了一个有针对性的无状态状态图，每个节点都有自己的插槽填充和关联度量，并且通过逻辑关系相互关联。 建筑物可以修改节点的度量，并且在冲突检测或特定节点度量的降低的控制下，丢弃所涉及的节点及其填充物，包括派生节点以及丢弃节点的一对一导出节点。 检测到由语音产生输出的用于确定特定时隙填充器的特定项目的问题的子集，以及随后的不令人满意的识别。 然后，语音生成输出另一个问题陈述，以确定后者的插槽填充。

    System and method for outputting spoken information in response to input speech signals
    5.
    发明授权
    System and method for outputting spoken information in response to input speech signals 失效
    响应于输入语音信号输出口语信息的系统和方法

    公开(公告)号：US5754736A

    公开(公告)日：1998-05-19

    申请号：US526017

    申请日：1995-09-08

    申请人： Harald Aust

    发明人： Harald Aust

    IPC分类号： G06F3/16 ,  G06F17/30 ,  G10L13/00 ,  G10L15/18 ,  G10L5/00

    CPC分类号： G10L15/1822 ,  G10L15/193

    摘要： The invention aims to make an automatic information system suitable for the input of requests which are spoken as naturally as possible and which are not subject to restrictions about which the user must be informed in advance. To this end, the system and the method are subdivided into several, essentially independently operating segments with unambiguous interfaces. A first segment serves for the recognition of words and outputs a word graph. A second segment forms a concept graph from the word graph in that essentially the word graph is searched only for word sequences wherefrom values for a database enquiry can be derived; such word sequences, or also single words, are replaced by concepts in the concept graph. In a further segment the concepts in the concept graph are bridged and gaps between the concepts are filled. A speech model is taken into account for this operation. A stochastic attributed grammar is used to determine the concepts from the word graph and to determine the meaning of the word sequences in the concepts. Because irrelevant filler words in the spoken request are ignored early on, the computational expenditure is comparatively small despite the freely pronounced requests.

    摘要翻译： 本发明旨在使自动信息系统适合输入尽可能自然地说出的请求，并且不受用户事先通知的限制。 为此，系统和方法被细分为几个基本上独立操作的具有明确界面的段。 第一段用于识别单词并输出单词图。 第二段从单词图形成概念图，因为本质上仅针对单词序列搜索单词图，从而可以导出数据库查询的值; 这些单词序列或单个单词被概念图中的概念所替代。 在另一段中，概念图中的概念被桥接，并且填充了概念之间的差距。 在此操作中考虑了语音模型。 随机归因语法用于确定词图中的概念，并确定概念中单词序列的含义。 由于语音请求中的不相关填充词早期被忽略，尽管有自由发出的请求，但计算支出相对较小。

    Method and apparatus for providing a human-machine dialog supportable by operator intervention
    6.
    发明授权
    Method and apparatus for providing a human-machine dialog supportable by operator intervention 失效
    用于提供可由操作员介入支持的人机对话的方法和装置

    公开(公告)号：US5745877A

    公开(公告)日：1998-04-28

    申请号：US587190

    申请日：1996-01-16

    申请人： Aloijsius J. Nijmam ,  Harald Aust ,  Peter Besting ,  Martin Oerder

    发明人： Aloijsius J. Nijmam ,  Harald Aust ,  Peter Besting ,  Martin Oerder

    IPC分类号： G06F3/16 ,  G06Q30/00 ,  G06Q50/00 ,  G09B7/04 ,  G10L15/22 ,  G10L15/28 ,  H04M3/42 ,  G10L5/06

    CPC分类号： G06F3/16 ,  G09B7/04 ,  G10L15/22

    摘要： Successive sections of a computer program of a user interactive system are carried out. A user presents successive verbal items such as answers, to verbal items such as questions presented by the system. Each question corresponds to a respective program section. The user item is recognized and a next machine item is presented, if possible and appropriate. The recognizing is evaluated, and on the basis of the evaluating a progress score is kept. If the progress score attains a particular level, the system enables an operator to intervene in the dialogue in an unobtrusive manner. If a plurality of dialogs are supervised in parallel, the enabling is on the basis of a progress ranking among the dialogs. The intervention may be realized by emulating a user item in the form of speech or in the form of a mechanically entered user item.

    摘要翻译： 执行用户交互系统的计算机程序的连续部分。 用户将诸如答案等连续的语言项目呈现给诸如系统呈现的问题的言语项目。 每个问题对应于相应的程序部分。 识别用户项目，并在可能和适当的情况下呈现下一个机器项目。 评估识别，并在评估进度评分的基础上进行评估。 如果进度得分达到一个特定的水平，系统就能让操作者以不引人注意的方式介入对话。 如果并行地监视多个对话，则启用是基于对话之间的进度排序。 可以通过以语音的形式或以机械输入的用户项的形式来模拟用户项来实现干预。