专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US6073097A Speech recognition system which selects one of a plurality of vocabulary models 失效
标题翻译：选择多个词汇模型中的一个的语音识别系统
公开(公告)号：US6073097A
公开(公告)日：2000-06-06
申请号：US882811
申请日：1997-06-26
申请人： Joel M. Gould , Jed M. Roberts , James K. Baker
发明人： Joel M. Gould , Jed M. Roberts , James K. Baker
IPC分类号： G09B19/04 , G10L15/06 , G10L15/18 , G10L15/22 , G10L15/26 , G10L15/28 , G10L9/00
CPC分类号： G10L15/063 , G09B19/04 , G10L15/18 , G10L15/22 , G10L15/285 , G10L15/1815 , G10L2015/0631 , G10L2015/0638
摘要： A word recognition system can: respond to the input of a character string from a user by limiting the words it will recognize to words having a related, but not necessarily the same, string; score signals generated after a user has been prompted to generate a given word against words other than the prompted word to determine if the signal should be used to train the prompted word; vary the number of signals a user is prompted to generate to train a given word as a function of how well the training signals score against each other or prior models for the prompted word; create a new acoustic model of a phrase by concatenating prior acoustic models of the words in the phrase; obtain information from another program running on the same computer, such as its commands or the context of text being entered into it, and use that information to vary which words it can recognize; determine which program unit, such as an application program or dialog box, currently has input focus on its computer and create a vocabulary state associated with that program unit into which vocabulary words which will be made active when that program group has the focus can be put; detect the available computational resources and alter the instructions it executes in response; test if its ability to respond to voice input has been shut off without user confirmation, and, if so, turn that ability back on and prompt the user to confirm if that ability is to be turned off; store both a first and a second set of models for individual vocabulary words and enable a user to selectively cause the recognizer to disregard the second set of models for a selected word; and/or score a signal representing a given word against models for that word from different word model sets to select which model should be used for future recognition.
摘要翻译：字识别系统可以：通过将其将识别的字限制为具有相关但不一定相同的字符串的字符来响应来自用户的字符串的输入; 在用户被提示以产生除提示词之外的单词产生给定单词以产生的得分信号，以确定该信号是否应用于训练所提示词; 改变用户被提示产生的信号的数量，以训练给定的单词，作为训练信号相对于提示的单词相对得分或先前的模型的程度的函数; 通过连接短语中的单词的先前的声学模型来创建短语的新的声学模型; 从在同一台计算机上运行的另一个程序获取信息，例如其命令或输入文本的上下文，并使用该信息来改变其可识别的单词; 确定哪个程序单元（例如应用程序或对话框）当前在其计算机上具有输入焦点，并创建与该程序单元相关联的词汇状态，当该程序组具有焦点时，可以使用将被激活的词汇单词 ; 检测可用的计算资源并改变其响应执行的指令; 测试其响应语音输入的能力是否已被关闭而无需用户确认，如果是，请重新启动该功能，并提示用户确认该功能是否被关闭; 存储用于单个词汇单词的第一和第二模型集合，并且使用户能够选择性地使识别器忽略所选择的单词的第二组模型; 和/或从不同的单词模型集合得到表示给定单词的信号与该单词的模型，以选择哪个模型应用于将来的识别。

2. 发明授权

US5920836A Word recognition system using language context at current cursor position to affect recognition probabilities 无效
标题翻译： Word识别系统使用当前光标位置的语言环境来影响识别概率
公开(公告)号：US5920836A
公开(公告)日：1999-07-06
申请号：US882813
申请日：1997-06-26
申请人： Joel M. Gould , Frank J. McGrath
发明人： Joel M. Gould , Frank J. McGrath
IPC分类号： G09B19/04 , G10L15/06 , G10L15/18 , G10L15/22 , G10L15/26 , G10L15/28 , G10L9/00
CPC分类号： G10L15/063 , G09B19/04 , G10L15/18 , G10L15/22 , G10L15/285 , G10L15/1815 , G10L2015/0631 , G10L2015/0638
摘要： A computerized system performs word recognition. It does pattern matching to select which vocabulary words appears, according to the pattern matching, to most probably correspond to word signals it seeks to recognize. It produces an output corresponding to the vocabulary words selected at a movable cursor position in a body of text. The system improves its recognition by obtaining information about the linguistic context of the current cursor position in the body of text and using that information to vary the probability of which one or more words is selected by its pattern matching. The pattern matching can be speech recognition performed on signals representing the sound of spoken words. In some embodiments, the word recognition is executed on a computer system capable of running multiple programs at once; the recognized word is output to another program for insertion at a cursor position in that other program; and the linguistic context information is obtained from data structures created by the other program.
摘要翻译：计算机化系统执行字识别。根据模式匹配，它进行模式匹配以选择哪个词汇单词出现，最可能对应于它寻求识别的单词信号。它产生对应于在文本主体中的可移动光标位置处选择的词汇单词的输出。该系统通过获取关于文本正文中当前光标位置的语言上下文的信息来改善其识别，并且使用该信息来改变通过其模式匹配来选择一个或多个单词的概率。模式匹配可以是对表示口语的声音的信号执行的语音识别。在一些实施例中，在能够一次运行多个程序的计算机系统上执行单词识别; 将识别的字输出到另一个程序，以插入该另一程序中的光标位置; 并且语言上下文信息从由另一程序创建的数据结构获得。

3. 发明授权

US5850627A Apparatuses and methods for training and operating speech recognition systems 失效
标题翻译：用于训练和操作语音识别系统的装置和方法
公开(公告)号：US5850627A
公开(公告)日：1998-12-15
申请号：US883297
申请日：1997-06-26
申请人： Joel M. Gould , Elizabeth E. Steele , Frank J. McGrath , Steven D. Squires , Peter S. Heitman , Joel W. Parke , Dean G. Sturtevant , Jed M. Roberts , James K. Baker
发明人： Joel M. Gould , Elizabeth E. Steele , Frank J. McGrath , Steven D. Squires , Peter S. Heitman , Joel W. Parke , Dean G. Sturtevant , Jed M. Roberts , James K. Baker
IPC分类号： G09B19/04 , G10L15/06 , G10L15/18 , G10L15/22 , G10L15/26 , G10L15/28 , G10L7/08
CPC分类号： G10L15/063 , G09B19/04 , G10L15/18 , G10L15/22 , G10L15/285 , G10L15/1815 , G10L2015/0631 , G10L2015/0638
摘要： A word recognition system can: respond to the input of a character string from a user by limiting the words it will recognize to words having a related, but not necessarily the same, string; score signals generated after a user has been prompted to generate a given word against words other than the prompted word to determine if the signal should be used to train the prompted word; vary the number of signals a user is prompted to generate to train a given word as a function of how well the training signals score against each other or prior models for the prompted word; create a new acoustic model of a phrase by concatenating prior acoustic models of the words in the phrase; obtain information from another program running on the same computer, such as its commands or the context of text being entered into it, and use that information to vary which words it can recognize; determine which program unit, such as an application program or dialog box, currently has input focus on its computer and create a vocabulary state associated with that program unit into which vocabulary words which will be made active when that program group has the focus can be put; detect the available computational resources and alter the instructions it executes in response; test if its ability to respond to voice input has been shut off without user confirmation, and, if so, turn that ability back on and prompt the user to confirm if that ability is to be turned off; store both a first and a second set of models for individual vocabulary words and enable a user to selectively cause the recognizer to disregard the second set of models for a selected word; and/or score a signal representing a given word against models for that word from different word model sets to select which model should be used for future recognition.
摘要翻译：字识别系统可以：通过将其将识别的字限制为具有相关但不一定相同的字符串的字符来响应来自用户的字符串的输入; 在用户被提示以产生除提示词之外的单词产生给定单词以产生的得分信号，以确定该信号是否应用于训练所提示词; 改变用户被提示产生的信号的数量，以训练给定的单词，作为训练信号相对于提示的单词相对得分或先前的模型的程度的函数; 通过连接短语中的单词的先前的声学模型来创建短语的新的声学模型; 从在同一台计算机上运行的另一个程序获取信息，例如其命令或输入文本的上下文，并使用该信息来改变其可识别的单词; 确定哪个程序单元（例如应用程序或对话框）当前在其计算机上具有输入焦点，并创建与该程序单元相关联的词汇状态，当该程序组具有焦点时，可以使用将被激活的词汇单词 ; 检测可用的计算资源并改变其响应执行的指令; 测试其响应语音输入的能力是否已被关闭而无需用户确认，如果是，请重新启动该功能，并提示用户确认该功能是否被关闭; 存储用于单个词汇单词的第一和第二模型集合，并且使用户能够选择性地使识别器忽略所选择的单词的第二组模型; 和/或从不同的单词模型集合得到表示给定单词的信号与该单词的模型，以选择哪个模型应用于将来的识别。

4. 发明授权

US5818423A Voice controlled cursor movement 失效
标题翻译：语音控制光标移动
公开(公告)号：US5818423A
公开(公告)日：1998-10-06
申请号：US912751
申请日：1997-08-18
申请人： Patri J. Pugliese , Joel M. Gould
发明人： Patri J. Pugliese , Joel M. Gould
IPC分类号： G06F3/033 , G06F3/048 , G06F3/16 , G09G5/08
CPC分类号： G06F3/16 , G06F3/04812 , G06F3/04842
摘要： An element (e.g., a location pointer in a windowed graphical user interface) shown on a computer display is moved toward a target position. A user's input is recognized which identifies a subregion of the display in which the target position is located. The element is moved discontinuously to a location within the identified subregion. Then a next user's input is recognized which identifies a sub-subregion of the subregion of the display in which the target position is located. The element is moved discontinuously to a location within the identified sub-subregion. In another aspect, an element is dragged between two locations on a computer display. User commands are accepted which indicate the two locations. Then the element is dragged between them. The user commands identify a sequence of discontinuous jumps for moving the element to the indicated location.
摘要翻译：在计算机显示器上显示的元素（例如，窗口化的图形用户界面中的位置指针）向目标位置移动。识别用户的输入，其识别目标位置所在的显示器的子区域。该元素不连续地移动到所识别的子区域内的位置。然后，识别下一个用户的输入，其识别目标位置所在的显示器的子区域的子子区域。该元件不连续地移动到所识别的子子区域内的位置。在另一方面，元件被拖动在计算机显示器上的两个位置之间。接受用户命令表示两个位置。然后元素在它们之间被拖动。用户命令识别用于将元件移动到指示位置的不连续跳跃序列。

5. 发明授权

US5799279A Continuous speech recognition of text and commands 失效
公开(公告)号：US5799279A
公开(公告)日：1998-08-25
申请号：US559207
申请日：1995-11-13
申请人： Joel M. Gould , Jonathan H. Young
发明人： Joel M. Gould , Jonathan H. Young
IPC分类号： G10L15/22 , G10L15/26 , G10L5/02 , G10L5/06 , G10L9/00
CPC分类号： G10L15/26 , G10L15/22
摘要： In a method for use in recognizing continuous speech, signals are accepted corresponding to interspersed speech elements including text elements corresponding to text to be recognized and command elements corresponding to commands to be executed. The elements are recognized. The recognized elements are acted on in a manner which depends on whether they represent text or commands.

6. 发明授权

US5359594A Power-saving full duplex nodal communications systems 失效
标题翻译：省电全双工节点通信系统
公开(公告)号：US5359594A
公开(公告)日：1994-10-25
申请号：US884538
申请日：1992-05-15
申请人： Joel M. Gould , Neal M. Lackritz
发明人： Joel M. Gould , Neal M. Lackritz
IPC分类号： G06F1/32 , H04L1/24 , H04L5/14 , H04L29/06 , H04L29/14 , H04J3/02
CPC分类号： G06F1/3215 , H04L1/24 , H04L29/06 , H04L5/14 , H04L5/1461
摘要： An inter-nodal communication system employs full duplex transmission links to connect asynchronously operating nodes. Links between nodes are quiesced to a no-current flow state in the absence of message traffic. The system employs a communication protocol that incorporates time-outs which (1) enable a broken link to be detected at the inception of a message and (2) prevent a receiver from listening to a link which has been quiesced by a transmitter at the other end of a link that is shutting-off. All synchronization messages in the inter-nodal communication network are carried by data links and no additional communication wires are required.
摘要翻译：节点间通信系统采用全双工传输链路来连接异步操作节点。在没有消息流量的情况下，节点之间的链路停顿到无电流流状态。该系统采用包含超时的通信协议，其中（1）在消息开始时能够检测到断开的链路，并且（2）防止接收机收听另一个发射机已经停顿的链路结束关闭的链接。节点间通信网络中的所有同步消息由数据链路承载，不需要额外的通信线路。

7. 发明授权

US06912498B2 Error correction in speech recognition by correcting text around selected area 有权
标题翻译：通过对所选区域的文本进行校正来进行语音识别中的纠错
公开(公告)号：US06912498B2
公开(公告)日：2005-06-28
申请号：US09845769
申请日：2001-05-02
申请人： Daniell Stevens , Robert Roth , Joel M. Gould , Michael J. Newman , Dean Sturtevant , Charles E. Ingold , David Abrahams , Allan Gold
发明人： Daniell Stevens , Robert Roth , Joel M. Gould , Michael J. Newman , Dean Sturtevant , Charles E. Ingold , David Abrahams , Allan Gold
IPC分类号： G10L15/22 , G10L15/04
CPC分类号： G10L15/22 , G10L2015/0631
摘要： Correcting incorrect text associated with recognition errors in computer-implemented speech recognition includes receiving a selection of a word from a recognized utterance. The selection indicates a bound of a portion of the recognized utterance to be corrected. A first recognition correction is produced based on a comparison between a first alternative transcript and the recognized utterance. A second recognition correction is produced based on a comparison between a second alternative transcript and the recognized utterance. The duration of the first recognition correction differs from the duration of the second recognition correction. A portion of the recognition result that is replaced with one of the first recognition correction and the second recognition correction. includes at one bound a word indicated by the selection and extends for the duration of the one of the first recognition correction and the second recognition correction with which the portion is replaced.
摘要翻译：校正与计算机实现的语音识别中的识别错误相关联的错误文本包括从识别的话语中接收单词的选择。选择表示被校正的话语的一部分的界限。基于第一替代誊本与识别的话语之间的比较来产生第一识别校正。基于第二替代誊本与识别的话语之间的比较来产生第二识别校正。第一识别校正的持续时间与第二识别校正的持续时间不同。识别结果的一部分被替换为第一识别校正和第二识别校正之一。在一个边界处包含由选择指示的单词，并且在第一识别校正和第二识别校正中的一个的持续时间内延伸部分被替换。

8. 发明授权

US06839669B1 Performing actions identified in recognized speech 有权
标题翻译：在公认的演讲中确定的行动
公开(公告)号：US06839669B1
公开(公告)日：2005-01-04
申请号：US09432155
申请日：1999-06-10
申请人： Joel M. Gould , Paul G. Bamberg , Charles E. Ingold , Kenneth J. Bayse , Michael L. Elkins , Roger L. Matus , Eric Fieleke
发明人： Joel M. Gould , Paul G. Bamberg , Charles E. Ingold , Kenneth J. Bayse , Michael L. Elkins , Roger L. Matus , Eric Fieleke
IPC分类号： G10L15/22 , G10L21/00
CPC分类号： G10L15/22
摘要： A computer is used to perform recorded actions. The computer receives recorded spoken utterances of actions. The computer then performs speech recognition on the recorded spoken utterances to generate texts of the actions. The computer then parses the texts to determine properties of the actions. After parsing the texts, permits the user to indicate that the user has reviewed one or more actions. The computer then automatically carries out the actions indicated as having been reviewed by the user.
摘要翻译：计算机用于执行记录动作。计算机接收记录的言语说话动作。然后，计算机对记录的话音进行语音识别，以生成动作的文本。然后，计算机解析文本以确定动作的属性。在解析文本之后，允许用户指示用户已经审查了一个或多个动作。然后，计算机自动执行指示为已经由用户审查的动作。

9. 发明授权

US06424943B1 Non-interactive enrollment in speech recognition 有权
标题翻译：语音识别中非互动式录入
公开(公告)号：US06424943B1
公开(公告)日：2002-07-23
申请号：US09624210
申请日：2000-07-24
申请人： Stefan Sherwood , David Wilsberg Parmenter , Joel M. Gould , Toffee A. Albina , Allan Gold
发明人： Stefan Sherwood , David Wilsberg Parmenter , Joel M. Gould , Toffee A. Albina , Allan Gold
IPC分类号： G10L1506
CPC分类号： G10L15/063 , G10L2015/0638
摘要： A computer enrolls a user in a speech recognition system by obtaining data representing a user's speech, the speech including multiple user utterances and generally corresponding to an enrollment text, and analyzing acoustic content of data corresponding to a user utterance. The computer determines, based on the analysis, whether the user utterance matches a portion of the enrollment text. If so, the computer uses the acoustic content of the user utterance to update acoustic models corresponding to the portion of the enrollment text. The computer may determine that the user utterance matches a portion of the enrollment text even when the user has skipped or repeated words of the enrollment text.
摘要翻译：计算机通过获取表示用户言语的数据，包括多个用户话语的语音，并且通常对应于登记文本，并且分析与用户话语相对应的数据的声音内容，将用户注册到语音识别系统中。计算机基于分析确定用户话语是否匹配登记文本的一部分。如果是这样，则计算机使用用户话语的声音内容来更新对应于登记文本部分的声学模型。即使用户已经跳过或重复登记文本的单词，计算机也可以确定用户话语与登记文本的一部分相匹配。

10. 发明授权

US6163768A Non-interactive enrollment in speech recognition 失效
公开(公告)号：US6163768A
公开(公告)日：2000-12-19
申请号：US94609
申请日：1998-06-15
申请人： Stefan Sherwood , David Wilsberg Parmenter , Joel M. Gould , Toffee A. Albina , Allan Gold
发明人： Stefan Sherwood , David Wilsberg Parmenter , Joel M. Gould , Toffee A. Albina , Allan Gold
IPC分类号： G10L15/06 , G10L15/04 , G10L15/26
CPC分类号： G10L15/063 , G10L2015/0638
摘要： A computer enrolls a user in a speech recognition system by obtaining data representing a user's speech, the speech including multiple user utterances and generally corresponding to an enrollment text, and analyzing acoustic content of data corresponding to a user utterance. The computer determines, based on the analysis, whether the user utterance matches a portion of the enrollment text. If so, the computer uses the acoustic content of the user utterance to update acoustic models corresponding to the portion of the enrollment text. The computer may determine that the user utterance matches a portion of the enrollment text even when the user has skipped or repeated words of the enrollment text.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式