-
公开(公告)号：US07464031B2
公开(公告)日：2008-12-09
申请号：US10724536
申请日：2003-11-28
申请人： Scott E. Axelrod , Sreeram Viswanath Balakrishnan , Stanley F. Chen , Yuging Gao , Ramesh A. Gopinath , Hong-Kwang Kuo , Benoit Maison , David Nahamoo , Michael Alan Picheny , George A. Saon , Geoffrey G. Zweig
发明人： Scott E. Axelrod , Sreeram Viswanath Balakrishnan , Stanley F. Chen , Yuging Gao , Ramesh A. Gopinath , Hong-Kwang Kuo , Benoit Maison , David Nahamoo , Michael Alan Picheny , George A. Saon , Geoffrey G. Zweig
CPC分类号： G10L15/063 , G10L15/02 , G10L15/14 , G10L2015/085
摘要： In a speech recognition system, the combination of a log-linear model with a multitude of speech features is provided to recognize unknown speech utterances. The speech recognition system models the posterior probability of linguistic units relevant to speech recognition using a log-linear model. The posterior model captures the probability of the linguistic unit given the observed speech features and the parameters of the posterior model. The posterior model may be determined using the probability of the word sequence hypotheses given a multitude of speech features. Log-linear models are used with features derived from sparse or incomplete data. The speech features that are utilized may include asynchronous, overlapping, and statistically non-independent speech features. Not all features used in training need to appear in testing/recognition.
摘要翻译： 在语音识别系统中，提供了具有多个语音特征的对数线性模型的组合来识别未知语音语音。 语音识别系统使用对数线性模型对与语音识别相关的语言单位的后验概率进行建模。 后验模型捕获了语言单位给出观察到的语音特征和后验模型参数的概率。 可以使用给定多个语音特征的单词序列假设的概率来确定后验模型。 对数线性模型与来自稀疏或不完整数据的特征一起使用。 所使用的语音特征可以包括异步，重叠和统计上非独立的语音特征。 培训中使用的并非所有功能都需要出现在测试/识别中。
-
公开(公告)号：US20080312921A1
公开(公告)日：2008-12-18
申请号：US12195123
申请日：2008-08-20
申请人： Scott E. Axelrod , Sreeram Viswanath Balakrishnan , Stanley F. Chen , Yuging Gao , Rameah A. Gopinath , Hong-Kwang Kuo , Benoit Maison , David Nahamoo , Michael Alan Picheny , George A. Saon , Geoffrey G. Zweig
发明人： Scott E. Axelrod , Sreeram Viswanath Balakrishnan , Stanley F. Chen , Yuging Gao , Rameah A. Gopinath , Hong-Kwang Kuo , Benoit Maison , David Nahamoo , Michael Alan Picheny , George A. Saon , Geoffrey G. Zweig
CPC分类号： G10L15/063 , G10L15/02 , G10L15/14 , G10L2015/085
摘要： In a speech recognition system, the combination of a log-linear model with a multitude of speech features is provided to recognize unknown speech utterances. The speech recognition system models the posterior probability of linguistic units relevant to speech recognition using a log-linear model. The posterior model captures the probability of the linguistic unit given the observed speech features and the parameters of the posterior model. The posterior model may be determined using the probability of the word sequence hypotheses given a multitude of speech features. Log-linear models are used with features derived from sparse or incomplete data. The speech features that are utilized may include asynchronous, overlapping, and statistically non-independent speech features. Not all features used in training need to appear in testing/recognition.
摘要翻译： 在语音识别系统中，提供了具有多个语音特征的对数线性模型的组合来识别未知语音语音。 语音识别系统使用对数线性模型对与语音识别相关的语言单位的后验概率进行建模。 后验模型捕获了语言单位给出观察到的语音特征和后验模型参数的概率。 可以使用给定多个语音特征的单词序列假设的概率来确定后验模型。 对数线性模型与来自稀疏或不完整数据的特征一起使用。 所使用的语音特征可以包括异步，重叠和统计上非独立的语音特征。 培训中使用的并非所有功能都需要出现在测试/识别中。
-
公开(公告)号：US20050119885A1
公开(公告)日：2005-06-02
申请号：US10724536
申请日：2003-11-28
申请人： Scott Axelrod , Sreeram Balakrishnan , Stanley Chen , Yuging Gao , Ramesh Gopinath , Hong-Kwang Kuo , Benoit Maison , David Nahamoo , Michael Picheny , George Saon , Geoffrey Zweig
发明人： Scott Axelrod , Sreeram Balakrishnan , Stanley Chen , Yuging Gao , Ramesh Gopinath , Hong-Kwang Kuo , Benoit Maison , David Nahamoo , Michael Picheny , George Saon , Geoffrey Zweig
CPC分类号： G10L15/063 , G10L15/02 , G10L15/14 , G10L2015/085
摘要： In a speech recognition system, the combination of a log-linear model with a multitude of speech features is provided to recognize unknown speech utterances. The speech recognition system models the posterior probability of linguistic units relevant to speech recognition using a log-linear model. The posterior model captures the probability of the linguistic unit given the observed speech features and the parameters of the posterior model. The posterior model may be determined using the probability of the word sequence hypotheses given a multitude of speech features. Log-linear models are used with features derived from sparse or incomplete data. The speech features that are utilized may include asynchronous, overlapping, and statistically non-independent speech features. Not all features used in training need to appear in testing/recognition.
摘要翻译： 在语音识别系统中，提供了具有多个语音特征的对数线性模型的组合来识别未知语音语音。 语音识别系统使用对数线性模型对与语音识别相关的语言单位的后验概率进行建模。 后验模型捕获了语言单位给出观察到的语音特征和后验模型参数的概率。 可以使用给定多个语音特征的单词序列假设的概率来确定后验模型。 对数线性模型与来自稀疏或不完整数据的特征一起使用。 所使用的语音特征可以包括异步，重叠和统计上非独立的语音特征。 培训中使用的并非所有功能都需要出现在测试/识别中。
-
4.发明授权Automatic construction of unique signatures and confusable sets for database access 有权自动构建数据库访问的独特签名和混淆集公开(公告)号：US07251599B2
公开(公告)日：2007-07-31
申请号：US10315411
申请日：2002-12-10
申请人： Benoit Maison , Geoffrey G. Zweig
发明人： Benoit Maison , Geoffrey G. Zweig
IPC分类号： G10L15/02
CPC分类号： G10L15/18
摘要： Methods and arrangements for facilitating database access in speech recognition. A plurality of possible subsequences corresponding to a database entry are ascertained, a record of such subsequences and their correspondence to database entries is created, and either or both of the following are carried out: unique signatures are ascertained via determining whether a subsequence corresponding to a given database entry does not also correspond to at least one other database entry; and/or multiple occurrences of a given subsequence are found, with corresponding database entries being grouped into a confusion set.
摘要翻译： 在语音识别中促进数据库访问的方法和安排。 确定对应于数据库条目的多个可能的子序列，创建这样的子序列的记录及其与数据库条目的对应关系，并执行以下任何一个或两者：唯一签名是通过确定对应于 给定的数据库条目也不对应于至少一个其他数据库条目; 和/或发现给定子序列的多次出现，其中相应的数据库条目被分组成混淆集合。
-
公开(公告)号：US20080243507A1
公开(公告)日：2008-10-02
申请号：US12135397
申请日：2008-06-09
申请人： Ramesh A. Gopinath , Benoit Maison , Brian C. Wu
发明人： Ramesh A. Gopinath , Benoit Maison , Brian C. Wu
IPC分类号： G10L15/18
CPC分类号： G10L15/22 , G10L2015/225
摘要： A user interface, and associated techniques, that permit a fast and efficient way of correcting speech recognition errors, or of diminishing their impact. The user may correct mistakes in a natural way, essentially by repeating the information that was incorrectly recognized previously. Such a mechanism closely approximates what human-to-human dialogue would be in similar circumstances. Such a system fully takes advantage of all the information provided by the user, and on its own estimates the quality of the recognition in order to determine the correct sequence of words in the fewest number of steps.
摘要翻译： 用户界面和相关技术，可以快速有效地纠正语音识别错误或减少其影响。 用户可以以自然的方式纠正错误，主要是通过重复先前未正确识别的信息。 这种机制与近似于类似情况下的人与人之间的对话密切相关。 这样的系统充分利用用户提供的所有信息，并且自己估计识别的质量，以便以最少的步数确定正确的单词序列。
-
公开(公告)号：US07386454B2
公开(公告)日：2008-06-10
申请号：US10210704
申请日：2002-07-31
申请人： Ramesh A. Gopinath , Benoit Maison , Brian C. Wu
发明人： Ramesh A. Gopinath , Benoit Maison , Brian C. Wu
CPC分类号： G10L15/22 , G10L2015/225
摘要： A user interface, and associated techniques, that permit a fast and efficient way of correcting speech recognition errors, or of diminishing their impact. The user may correct mistakes in a natural way, essentially by repeating the information that was incorrectly recognized previously. Such a mechanism closely approximates what human-to-human dialogue would be in similar circumstances. Such a system fully takes advantage of all the information provided by the user, and on its own estimates the quality of the recognition in order to determine the correct sequence of words in the fewest number of steps.
摘要翻译： 用户界面和相关技术，可以快速有效地纠正语音识别错误或减少其影响。 用户可以以自然的方式纠正错误，主要是通过重复先前未正确识别的信息。 这种机制与近似于类似情况下的人与人之间的对话密切相关。 这样的系统充分利用用户提供的所有信息，并且自己估计识别的质量，以便以最少的步数确定正确的单词序列。
-
公开(公告)号：US07702512B2
公开(公告)日：2010-04-20
申请号：US12135397
申请日：2008-06-09
申请人： Ramesh A. Gopinath , Benoit Maison , Brian C. Wu
发明人： Ramesh A. Gopinath , Benoit Maison , Brian C. Wu
CPC分类号： G10L15/22 , G10L2015/225
摘要： A user interface, and associated techniques, that permit a fast and efficient way of correcting speech recognition errors, or of diminishing their impact. The user may correct mistakes in a natural way, essentially by repeating the information that was incorrectly recognized previously. Such a mechanism closely approximates what human-to-human dialogue would be in similar circumstances. Such a system fully takes advantage of all the information provided by the user, and on its own estimates the quality of the recognition in order to determine the correct sequence of words in the fewest number of steps.
摘要翻译： 用户界面和相关技术，可以快速有效地纠正语音识别错误或减少其影响。 用户可以以自然的方式纠正错误，主要是通过重复先前未正确识别的信息。 这种机制与近似于类似情况下的人与人之间的对话密切相关。 这样的系统充分利用用户提供的所有信息，并且自己估计识别的质量，以便以最少的步数确定正确的单词序列。
-
公开(公告)号：US08355920B2
公开(公告)日：2013-01-15
申请号：US12135452
申请日：2008-06-09
申请人： Ramesh A. Gopinath , Benoit Maison , Brian C. Wu
发明人： Ramesh A. Gopinath , Benoit Maison , Brian C. Wu
CPC分类号： G10L15/22 , G10L2015/225
摘要： A user interface, and associated techniques, that permit a fast and efficient way of correcting speech recognition errors, or of diminishing their impact. The user may correct mistakes in a natural way, essentially by repeating the information that was incorrectly recognized previously. Such a mechanism closely approximates what human-to-human dialogue would be in similar circumstances. Such a system fully takes advantage of all the information provided by the user, and on its own estimates the quality of the recognition in order to determine the correct sequence of words in the fewest number of steps.
摘要翻译： 用户界面和相关技术，可以快速有效地纠正语音识别错误或减少其影响。 用户可以以自然的方式纠正错误，主要是通过重复先前未正确识别的信息。 这种机制与近似于类似情况下的人与人之间的对话密切相关。 这样的系统充分利用用户提供的所有信息，并且自己估计识别的质量，以便以最少的步数确定正确的单词序列。
-
公开(公告)号：US20080243514A1
公开(公告)日：2008-10-02
申请号：US12135452
申请日：2008-06-09
申请人： Ramesh A. Gopinath , Benoit Maison , Brian C. Wu
发明人： Ramesh A. Gopinath , Benoit Maison , Brian C. Wu
IPC分类号： G10L21/00
CPC分类号： G10L15/22 , G10L2015/225
摘要： A user interface, and associated techniques, that permit a fast and efficient way of correcting speech recognition errors, or of diminishing their impact. The user may correct mistakes in a natural way, essentially by repeating the information that was incorrectly recognized previously. Such a mechanism closely approximates what human-to-human dialogue would be in similar circumstances. Such a system fully takes advantage of all the information provided by the user, and on its own estimates the quality of the recognition in order to determine the correct sequence of words in the fewest number of steps.
-
公开(公告)号：US07206387B2
公开(公告)日：2007-04-17
申请号：US10645051
申请日：2003-08-21
申请人： Ea-Ee Jan , Benoit Maison , Andrzei Sakrajda
发明人： Ea-Ee Jan , Benoit Maison , Andrzei Sakrajda
IPC分类号： H04M1/64
CPC分类号： H04M3/50 , H04L67/1002 , H04L2012/6443 , H04L2012/6481 , H04M2201/39 , H04M2201/40 , H04M2201/41
摘要： A voice processing system is provided in which sets of engines running on a plurality of servers are configured differently from one another. The sets of engines may be configured to achieve different trade-offs between performance of a task and resources required to perform the task. In the voice processing system, a task routing server is provided that assigns different sets of sub-tasks to different sets of task engines. The number of engines used to perform a task and the number of engines in each set are adjusted. By adjusting the parameters settings for the set of engines based on the type of application, the particular requirements of the application, or the nature and importance of the subtasks, for example, advantages such as improvement of resource utilization and the hardware and software costs reduction may be obtained.
摘要翻译： 提供语音处理系统，其中在多个服务器上运行的引擎组彼此不同地配置。 发动机组可以被配置为在执行任务和执行任务所需的资源之间实现不同的权衡。 在语音处理系统中，提供了将不同的子任务集分配给不同的任务引擎组的任务路由服务器。 调整用于执行任务的引擎数量和每组中的引擎数量。 通过基于应用程序的类型，应用程序的特定要求或子任务的性质和重要性调整引擎集的参数设置，例如资源利用率的提高以及降低硬件和软件成本的优点 可以获得。
-
-
-
-
-
-
-
-
-
搜索结果
22 条记录 (耗时 0.043 秒)
