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

US06073096A Speaker adaptation system and method based on class-specific pre-clustering training speakers 失效
标题翻译：基于类特定的前聚类训练讲话者的演讲人适应系统和方法
公开(公告)号：US06073096A
公开(公告)日：2000-06-06
申请号：US18350
申请日：1998-02-04
申请人： Yuqing Gao , Mukund Padmanabhan , Michael Alan Picheny
发明人： Yuqing Gao , Mukund Padmanabhan , Michael Alan Picheny
IPC分类号： G10L15/07 , G10L15/06
CPC分类号： G10L15/07
摘要： A method of speech recognition, in accordance with the present invention includes the steps of grouping acoustics to form classes based on acoustic features, clustering training speakers by the classes to provide class-specific cluster systems, selecting from the cluster systems, a subset of cluster systems closest to adaptation data from a test speaker, transforming the subset of cluster systems to bring the subset of cluster systems closer to the test speaker based on the adaptation data to form adapted cluster systems and combining the adapted cluster systems to create a speaker adapted system for decoding speech from the test speaker. System and methods for building speech recognition systems as well as adapting speaker systems for class-specific speaker clusters are included.
摘要翻译：根据本发明的语音识别方法包括以下步骤：基于声学特征对声学进行分组以形成类别，由类别聚类训练讲话者以提供特定类别的集群系统，从集群系统中选择集群的子集最接近来自测试说话者的自适应数据的系统，基于适配数据来改变集群系统的子集以使集群系统的子集更靠近测试说话者，以形成适应的集群系统，并组合适应的集群系统以创建一个说话者适配系统用于解码来自测试扬声器的语音。包括构建语音识别系统的系统和方法以及适用于类特定扬声器群的扬声器系统。

2. 发明授权

US07610191B2 Method for fast semi-automatic semantic annotation 有权
标题翻译：快速半自动语义注释方法
公开(公告)号：US07610191B2
公开(公告)日：2009-10-27
申请号：US10959523
申请日：2004-10-06
申请人： Yuqing Gao , Michael Alan Picheny , Ruhi Sarikaya
发明人： Yuqing Gao , Michael Alan Picheny , Ruhi Sarikaya
IPC分类号： G06F17/27
CPC分类号： G06F17/271 , G06F17/2755
摘要： A method, apparatus and computer instructions is provided for fast semi-automatic semantic annotation. Given a limited annotated corpus, the present invention assigns a tag and a label to each word of the next limited annotated corpus using a parser engine, a similarity engine, and a SVM engine. A rover then combines the parse trees from the three engines and annotates the next chunk of limited annotated corpus with confidence, such that the efforts required for human annotation is reduced.
摘要翻译：提供了一种用于快速半自动语义注释的方法，装置和计算机指令。给定有限的注释语料库，本发明使用解析器引擎，相似性引擎和SVM引擎为下一个有限注释语料库的每个单词分配标签和标签。然后，流动站组合来自三个引擎的解析树，并自信地注释下一批有限注释语料库，从而减少人体注释所需的努力。

3. 发明授权

US07996211B2 Method and apparatus for fast semi-automatic semantic annotation 有权
标题翻译：快速半自动语义注释的方法和装置
公开(公告)号：US07996211B2
公开(公告)日：2011-08-09
申请号：US12123778
申请日：2008-05-20
申请人： Yuqing Gao , Michael Alan Picheny , Ruhi Sarikaya
发明人： Yuqing Gao , Michael Alan Picheny , Ruhi Sarikaya
IPC分类号： G06F17/27
CPC分类号： G06F17/271 , G06F17/2755
摘要： A method, apparatus and computer instructions is provided for fast semi-automatic semantic annotation. Given a limited annotated corpus, the present invention assigns a tag and a label to each word of the next limited annotated corpus using a parser engine, a similarity engine, and a SVM engine. A rover then combines the parse trees from the three engines and annotates the next chunk of limited annotated corpus with confidence, such that the efforts required for human annotation is reduced.
摘要翻译：提供了一种用于快速半自动语义注释的方法，装置和计算机指令。给定有限的注释语料库，本发明使用解析器引擎，相似性引擎和SVM引擎向下一个有限注释语料库的每个单词分配标签和标签。然后，流动站组合来自三个引擎的解析树，并自信地注释下一批有限注释语料库，从而减少人体注释所需的努力。

4. 发明授权

US06850888B1 Methods and apparatus for training a pattern recognition system using maximal rank likelihood as an optimization function 失效
标题翻译：使用最大秩可能性作为优化函数训练模式识别系统的方法和装置
公开(公告)号：US06850888B1
公开(公告)日：2005-02-01
申请号：US09680706
申请日：2000-10-06
申请人： Yuqing Gao , Yongxin Li , Michael Alan Picheny
发明人： Yuqing Gao , Yongxin Li , Michael Alan Picheny
IPC分类号： G10L15/14 , G10L15/00
CPC分类号： G10L15/144
摘要： A method and apparatus are disclosed for training a pattern recognition system, such as a speech recognition system, using an improved objective function. The concept of rank likelihood, previously applied only to the decding process, is applied in a novel manner to the parameter estimation of the training phase of a pattern recognition system. The disclosed objective function is based on a pseudo-rank likelihood that not only maximizes the likelihood of an observation for the correct class, but also minimizes the likelihoods of the observation for all other classes, such that the discrimination between classes is maximized. A training process is disclosed that utilizes the pseudo-rank likelihood objective function to identify model parameters that will result in a pattern recognizer with the lowest possible recognition error rate. The discrete nature of the rank-based rank likelihood objective function is transformed to allow the parameter estimations to be optimized during the training phase.
摘要翻译：公开了一种使用改进的目标函数来训练诸如语音识别系统的模式识别系统的方法和装置。先前仅适用于解码处理的等级似然性的概念以新颖的方式应用于模式识别系统的训练阶段的参数估计。所公开的目标函数基于伪秩可能性，其不仅使对正确类的观察的可能性最大化，而且使对所有其他类的观察的可能性最小化，使得类之间的区分最大化。公开了一种训练过程，其利用伪秩似然度目标函数来识别将产生具有最低可能识别错误率的模式识别器的模型参数。转换基于秩的等级似然目标函数的离散性质，以便在训练阶段优化参数估计。

5. 发明授权

US08869119B2 Preferential execution of method calls in hybrid systems 有权
公开(公告)号：US08869119B2
公开(公告)日：2014-10-21
申请号：US13616417
申请日：2012-09-14
申请人： Michael H. Dawson , Parijat Dube , Liana L. Fong , Yuqing Gao , Xavier R. Guerin , Michel H. T. Hack , Megumi Ito , Graeme Johnson , Nai K. Ling , Yanbin Liu , Xiaoqiao Meng , Pramod B. Nagaraja , Seetharami R. Seelam , Wei Tan , Li Zhang
发明人： Michael H. Dawson , Parijat Dube , Liana L. Fong , Yuqing Gao , Xavier R. Guerin , Michel H. T. Hack , Megumi Ito , Graeme Johnson , Nai K. Ling , Yanbin Liu , Xiaoqiao Meng , Pramod B. Nagaraja , Seetharami R. Seelam , Wei Tan , Li Zhang
IPC分类号： G06F9/44
CPC分类号： G06F9/5027 , G06F9/548 , G06F2209/501 , G06F2209/509 , G06F2209/542 , G06F2209/549 , Y02D10/22
摘要： Affinity-based preferential call technique, in one aspect, may improve performance of distributed applications in a hybrid system having heterogeneous platforms. A segment of code in a program being executed on a processor may be intercepted or trapped in runtime. A platform is selected in the hybrid system for executing said segment of code, the platform determined to run the segment of code with best efficiency among a plurality of platforms in the hybrid system. The segment of code is dynamically executed on the selected platform determined to run the segment of code with best efficiency.

6. 发明授权

US08768699B2 Techniques for aiding speech-to-speech translation 有权
标题翻译：帮助语音到语音翻译的技术
公开(公告)号：US08768699B2
公开(公告)日：2014-07-01
申请号：US12760934
申请日：2010-04-15
申请人： Yuqing Gao , Hong-Kwang Jeff Kuo , Bowen Zhou
发明人： Yuqing Gao , Hong-Kwang Jeff Kuo , Bowen Zhou
IPC分类号： G10L15/04
CPC分类号： G06F17/2827 , G10L15/26
摘要： Techniques for assisting in translation are provided. A speech recognition hypothesis is obtained, corresponding to a source language utterance. Information retrieval is performed on a supplemental database, based on a situational context, to obtain at least one word string that is related to the source language utterance. The speech recognition hypothesis and the word string are then formatted for display to a user, to facilitate an appropriate selection by the user for translation.
摘要翻译：提供协助翻译的技巧。获得语音识别假设，对应于源语言发音。基于情境语境在辅助数据库上执行信息检索，以获得与源语言话语相关的至少一个字串。然后，将语音识别假设和字串格式化以供用户显示，以便于用户适当地选择用于翻译。

7. 发明申请

US20130239128A1 PREFERENTIAL EXECUTION OF METHOD CALLS IN HYBRID SYSTEMS 有权
标题翻译：混合系统中方法调用的优先执行
公开(公告)号：US20130239128A1
公开(公告)日：2013-09-12
申请号：US13616417
申请日：2012-09-14
申请人： Michael H. Dawson , Parijat Dube , Liana L. Fong , Yuqing Gao , Xavier R. Guerin , Michel H. T. Hack , Megumi Ito , Graeme Johnson , Nai K. Ling , Yanbin Liu , Xiaoqiao Meng , Pramod B. Nagaraja , Seetharami R. Seelam , Wei Tan , Li Zhang
发明人： Michael H. Dawson , Parijat Dube , Liana L. Fong , Yuqing Gao , Xavier R. Guerin , Michel H. T. Hack , Megumi Ito , Graeme Johnson , Nai K. Ling , Yanbin Liu , Xiaoqiao Meng , Pramod B. Nagaraja , Seetharami R. Seelam , Wei Tan , Li Zhang
IPC分类号： G06F9/46
CPC分类号： G06F9/5027 , G06F9/548 , G06F2209/501 , G06F2209/509 , G06F2209/542 , G06F2209/549 , Y02D10/22
摘要： Affinity-based preferential call technique, in one aspect, may improve performance of distributed applications in a hybrid system having heterogeneous platforms. A segment of code in a program being executed on a processor may be intercepted or trapped in runtime. A platform is selected in the hybrid system for executing said segment of code, the platform determined to run the segment of code with best efficiency among a plurality of platforms in the hybrid system. The segment of code is dynamically executed on the selected platform determined to run the segment of code with best efficiency.
摘要翻译：基于亲和度的优惠呼叫技术在一个方面可以提高具有异构平台的混合系统中的分布式应用的性能。在处理器上执行的程序中的一段代码可能在运行时被拦截或被捕获。在混合系统中选择用于执行所述代码段的平台，所述平台被确定为以混合系统中的多个平台中的最佳效率运行代码段。在所选择的平台上动态地执行代码段，以确保以最佳效率运行代码段。

8. 发明申请

US20080077393A1 VIRTUAL KEYBOARD ADAPTATION FOR MULTILINGUAL INPUT 审中-公开
标题翻译：虚拟键盘适应多输入
公开(公告)号：US20080077393A1
公开(公告)日：2008-03-27
申请号：US11680870
申请日：2007-03-01
申请人： Yuqing Gao , Liang Gu , Timothy Mathes , Lazkin Tahir , Wei Zhang
发明人： Yuqing Gao , Liang Gu , Timothy Mathes , Lazkin Tahir , Wei Zhang
IPC分类号： G06F17/20
CPC分类号： G06F17/275 , G06F3/018 , G06F3/0236
摘要： Techniques for adapting a virtual keyboard for multilingual input are disclosed. By way of example, a method of adapting a virtual keyboard for multilingual input includes the steps of detecting an input language and displaying a virtual keyboard corresponding to the input language upon detection of the input language. The identifying step may include automatic identification of an input language, such as by one or more language recognition modules, or it may include manual selection of an input language and activation of at least one language recognition module operative to recognize at least the input language upon selection of the input language.
摘要翻译：公开了适用于多语言输入的虚拟键盘的技术。作为示例，适用于多语言输入的虚拟键盘的方法包括以下步骤：检测输入语言并在检测到输入语言时显示与输入语言相对应的虚拟键盘。识别步骤可以包括诸如通过一个或多个语言识别模块的输入语言的自动识别，或者可以包括对输入语言的手动选择以及至少一个语言识别模块的激活，该至少一个语言识别模块至少可以识别输入语言选择输入语言。

9. 发明申请

US20080046229A1 Disfluency detection for a speech-to-speech translation system using phrase-level machine translation with weighted finite state transducers 有权
标题翻译：使用带加权有限状态传感器的短语级机器翻译的语音到语音翻译系统的差异检测
公开(公告)号：US20080046229A1
公开(公告)日：2008-02-21
申请号：US11506981
申请日：2006-08-19
申请人： Sameer Raj Maskey , Yuqing Gao , Bowen Zhou
发明人： Sameer Raj Maskey , Yuqing Gao , Bowen Zhou
IPC分类号： G06F17/28
CPC分类号： G06F17/2775
摘要： A computer-implemented method for creating a disfluency translation lattice includes providing a plurality of weighted finite state transducers including a translation model, a language model, and a phrase segmentation model as input, performing a cascaded composition of the weighted finite state transducers to create a disfluency translation lattice, and storing the disfluency translation lattice to a computer-readable media.
摘要翻译：用于创建不相容性转换格子的计算机实现的方法包括提供包括翻译模型，语言模型和短语分割模型的多个加权有限状态换能器作为输入，执行加权有限状态换能器的级联组合以创建不清晰度转换格子，并将不清晰度转换格架存储到计算机可读介质。

10. 发明申请

US20060195321A1 Natural language system and method based on unisolated performance metric 有权
公开(公告)号：US20060195321A1
公开(公告)日：2006-08-31
申请号：US11067819
申请日：2005-02-28
申请人： Sabine Deligne , Yuqing Gao , Vaibhava Goel , Hong-Kwang Kuo , Cheng Wu
发明人： Sabine Deligne , Yuqing Gao , Vaibhava Goel , Hong-Kwang Kuo , Cheng Wu
IPC分类号： G10L15/18
CPC分类号： G10L15/18 , G10L15/065
摘要： A natural language business system and method is developed to understand the underlying meaning of a person's speech, such as during a transaction with the business system. The system includes a speech recognition engine, and action classification engine, and a control module. The control module causes the system to execute an inventive method wherein the speech recognition and action classification models may be recursively optimized on an unisolated performance metric that is pertinent to the overall performance of the natural language business system, as opposed to the isolated model-specific criteria previously employed.

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