专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明授权

US07424675B2 Language input architecture for converting one text form to another text form with tolerance to spelling typographical and conversion errors 失效
标题翻译：用于将一种文本形式转换为另一种文本形式的语言输入架构，具有拼写排印和转换错误的容错能力
公开(公告)号：US07424675B2
公开(公告)日：2008-09-09
申请号：US10951307
申请日：2004-09-27
申请人： Kai-Fu Lee , Zheng Chen , Jian Han
发明人： Kai-Fu Lee , Zheng Chen , Jian Han
IPC分类号： G06F17/00
CPC分类号： G06F17/273 , G06F17/2223 , G06F17/2715 , G06F17/2818 , G06F17/2863
摘要： A language input architecture converts input strings of phonetic text to an output string of language text. The language input architecture has a search engine, one or more typing models, a language model, and one or more lexicons for different languages. The typing model is configured to generate a list of probable typing candidates that may be substituted for the input string based on probabilities of how likely each of the candidate strings was incorrectly entered as the input string. The language model provides probable conversion strings for each of the typing candidates based on probabilities of how likely a probable conversion output string represents the candidate string. The search engine combines the probabilities of the typing and language models to find the most probable conversion string that represents a converted form of the input string.
摘要翻译：语言输入架构将语音文本的输入字符串转换为语言文本的输出字符串。语言输入体系结构具有搜索引擎，一个或多个输入模型，语言模型以及用于不同语言的一个或多个词典。打字模型被配置为基于每个候选字符串被错误地输入作为输入字符串的可能性的概率来生成可替代输入字符串的可能的输入候选的列表。语言模型基于可能的转换输出字符串表示候选字符串的可能性的概率，为每个输入候选提供可能的转换字符串。搜索引擎结合了打字和语言模型的概率，以找到表示输入字符串的转换形式的最可能的转换字符串。

12. 发明申请

US20050086590A1 Language input architecture for converting one text form to another text form with tolerance to spelling, typographical, and conversion errors 失效
标题翻译：语言输入架构，用于将一种文本形式转换为另一种文本形式，具有拼写，排版和转换错误的容错能力
公开(公告)号：US20050086590A1
公开(公告)日：2005-04-21
申请号：US10970438
申请日：2004-10-21
申请人： Kai-Fu Lee , Zheng Chen , Jian Han
发明人： Kai-Fu Lee , Zheng Chen , Jian Han
IPC分类号： G06F17/21 , G06F17/22 , G06F17/27 , G06F17/28 , G06F15/00
CPC分类号： G06F17/273 , G06F17/2223 , G06F17/2715 , G06F17/2818 , G06F17/2863
摘要： A language input architecture converts input strings of phonetic text (e.g., Chinese Pinyin) to an output string of language text (e.g., Chinese Hanzi) in a manner that minimizes typographical errors and conversion errors that occur during conversion from the phonetic text to the language text. The language input architecture has a search engine, one or more typing models, a language model, and one or more lexicons for different languages. Each typing model is trained on real data, and learns probabilities of typing errors. The typing model is configured to generate a list of probable typing candidates that may be substituted for the input string based on probabilities of how likely each of the candidate strings was incorrectly entered as the input string. The probable typing candidates may be stored in a database. The language model provides probable conversion strings for each of the typing candidates based on probabilities of how likely a probable conversion output string represents the candidate string. The search engine combines the probabilities of the typing and language models to find the most probable conversion string that represents a converted form of the input string. By generating typing candidates and then using the associated conversion strings to replace the input string, the architecture eliminates many common typographical errors. When multiple typing models are employed, the architecture can automatically distinguish among multiple languages without requiring mode switching for entry of the different languages.
摘要翻译：语言输入架构将语音文本的输入字符串（例如中文拼音）转换为语言文本的输出字符串（例如汉字），以最小化从语音文本转换为语言的排版错误和转换错误文本。语言输入体系结构具有搜索引擎，一个或多个输入模型，语言模型以及用于不同语言的一个或多个词典。每个打字模型都对真实数据进行培训，并学习打字错误的可能性。打字模型被配置为基于每个候选字符串被错误地输入作为输入字符串的可能性的概率来生成可替代输入字符串的可能的输入候选的列表。可能的打字候选人可以存储在数据库中。语言模型基于可能的转换输出字符串表示候选字符串的可能性的概率，为每个输入候选提供可能的转换字符串。搜索引擎结合了打字和语言模型的概率，以找到表示输入字符串的转换形式的最可能的转换字符串。通过生成打字候选人，然后使用关联的转换字符串来替换输入字符串，该架构消除了许多常见的打印错误。当采用多种类型模型时，架构可以自动区分多种语言，而不需要为不同语言的输入进行模式切换。

13. 发明申请

US20050044495A1 Language input architecture for converting one text form to another text form with tolerance to spelling typographical and conversion errors 失效
标题翻译：用于将一种文本形式转换为另一种文本形式的语言输入架构，具有拼写排印和转换错误的容错能力
公开(公告)号：US20050044495A1
公开(公告)日：2005-02-24
申请号：US10951307
申请日：2004-09-27
申请人： Kai-Fu Lee , Zheng Chen , Jian Han
发明人： Kai-Fu Lee , Zheng Chen , Jian Han
IPC分类号： G06F17/21 , G06F17/22 , G06F17/27 , G06F17/28 , G06F15/00
CPC分类号： G06F17/273 , G06F17/2223 , G06F17/2715 , G06F17/2818 , G06F17/2863
摘要： A language input architecture converts input strings of phonetic text to an output string of language text. The language input architecture has a search engine, one or more typing models, a language model, and one or more lexicons for different languages. The typing model is configured to generate a list of probable typing candidates that may be substituted for the input string based on probabilities of how likely each of the candidate strings was incorrectly entered as the input string. The language model provides probable conversion strings for each of the typing candidates based on probabilities of how likely a probable conversion output string represents the candidate string. The search engine combines the probabilities of the typing and language models to find the most probable conversion string that represents a converted form of the input string.
摘要翻译：语言输入架构将语音文本的输入字符串转换为语言文本的输出字符串。语言输入体系结构具有搜索引擎，一个或多个输入模型，语言模型以及用于不同语言的一个或多个词典。打字模型被配置为基于每个候选字符串被错误地输入作为输入字符串的可能性的概率来生成可替代输入字符串的可能的输入候选的列表。语言模型基于可能的转换输出字符串表示候选字符串的可能性的概率，为每个输入候选提供可能的转换字符串。搜索引擎结合了打字和语言模型的概率，以找到表示输入字符串的转换形式的最可能的转换字符串。

14. 发明授权

US5734791A Rapid tree-based method for vector quantization 失效
标题翻译：用于矢量量化的快速基于树的方法
公开(公告)号：US5734791A
公开(公告)日：1998-03-31
申请号：US999354
申请日：1992-12-31
申请人： Alejandro Acero , Kai-Fu Lee , Yen-Lu Chow
发明人： Alejandro Acero , Kai-Fu Lee , Yen-Lu Chow
IPC分类号： G10L19/02 , G10L3/02
CPC分类号： G10L19/038
摘要： The branching decision for each node in a vector quantization (VQ) binary tree is made by a simple comparison of a pre-selected element of the candidate vector with a stored threshold resulting in a binary decision for reaching the next lower level. Each node has a preassigned element and threshold value. Conventional centroid distance training techniques (such as LBG and k-means) are used to establish code-book indices corresponding to a set of VQ centroids. The set of training vectors are used a second time to select a vector element and threshold value at each node that approximately splits the data evenly. After processing the training vectors through the binary tree using threshold decisions, a histogram is generated for each code-book index that represents the number of times a training vector belonging to a given index set appeared at each index. The final quantization is accomplished by processing and then selecting the nearest centroid belonging to that histogram. Accuracy comparable to that achieved by conventional binary tree VQ is realized but with almost a full magnitude increase in processing speed.
摘要翻译：矢量量化（VQ）二叉树中的每个节点的分支决定是通过将候选矢量的预先选择的元素与存储的阈值进行简单比较而得到的，从而产生用于达到下一较低级别的二进制决定。每个节点具有预分配的元素和阈值。传统的质心距离训练技术（如LBG和k-means）用于建立与一组VQ质心相对应的代码簿索引。训练矢量集合被用于第二次在每个节点选择一个向量元素和阈值，每个节点大致分割数据。在通过使用阈值判定的二进制树处理训练向量之后，针对代表每个索引处出现的给定索引集的训练向量的次数的每个代码簿索引生成直方图。最后量化通过处理然后选择属于该直方图的最近质心来实现。实现与常规二叉树VQ实现的精度相当的精度，但处理速度几乎提高了一个全面的幅度。

15. 发明授权

US07403888B1 Language input user interface 有权
标题翻译：语言输入用户界面
公开(公告)号：US07403888B1
公开(公告)日：2008-07-22
申请号：US09606811
申请日：2000-06-28
申请人： Jian Wang , Gao Zhang , Jian Han , Zheng Chen , Xianoning Ling , Kai-Fu Lee
发明人： Jian Wang , Gao Zhang , Jian Han , Zheng Chen , Xianoning Ling , Kai-Fu Lee
IPC分类号： G10L11/00
CPC分类号： G06F17/27 , G06F3/018 , G06F17/273 , G06F17/2775 , G06F17/2863 , G10L15/187
摘要： A language input architecture receives input text (e.g., phonetic text of a character-based language) entered by a user from an input device (e.g., keyboard, voice recognition). The input text is converted to an output text (e.g., written language text of a character-based language). The language input architecture has a user interface that displays the output text and unconverted input text in line with one another. As the input text is converted, it is replaced in the UI with the converted output text. In addition to this in-line input feature, the UI enables in-place editing or error correction without requiring the user to switch modes from an entry mode to an edit mode. To assist with this in-place editing, the UI presents pop-up windows containing the phonetic text from which the output text was converted as well as first and second candidate lists that contain small and large sets of alternative candidates that might be used to replace the current output text. The language input user interface also allows a user to enter a mixed text of different languages.
摘要翻译：语言输入架构从输入设备（例如，键盘，语音识别）接收用户输入的输入文本（例如，基于字符的语言的语音文本）。输入文本被转换为输出文本（例如，基于字符的语言的书面语言文本）。语言输入架构具有用于显示输出文本和未转换的输入文本的用户界面。当输入文本被转换时，它将在UI中被替换为转换的输出文本。除了这种在线输入功能之外，UI还可以进行就地编辑或纠错，而无需用户将模式从入门模式切换到编辑模式。为了协助进行就地编辑，用户界面将显示弹出窗口，其中包含输出文本被转换的语音文本以及第一个和第二个候选列表，其中包含可用于替换的小组和大组替代候选项当前的输出文本。语言输入用户界面还允许用户输入不同语言的混合文本。

16. 发明申请

US20050060138A1 Language conversion and display 审中-公开
标题翻译：语言转换和显示
公开(公告)号：US20050060138A1
公开(公告)日：2005-03-17
申请号：US10898407
申请日：2004-07-23
申请人： Jian Wang , Gao Zhang , Jian Han , Zheng Chen , Xianoning Ling , Kai-Fu Lee
发明人： Jian Wang , Gao Zhang , Jian Han , Zheng Chen , Xianoning Ling , Kai-Fu Lee
IPC分类号： G06F17/22 , G06F3/00 , G06F3/01 , G06F3/048 , G06F17/21 , G06F17/27 , G06F17/28 , G10L15/18 , G06F17/20
CPC分类号： G06F17/27 , G06F3/018 , G06F17/273 , G06F17/2775 , G06F17/2863 , G10L15/187
摘要： A language input architecture receives input text (e.g., phonetic text of a character-based language) entered by a user from an input device (e.g., keyboard, voice recognition). The input text is converted to an output text (e.g., written language text of a character-based language). The language input architecture has a user interface that displays the output text and unconverted input text in line with one another. As the input text is converted, it is replaced in the UI with the converted output text. In addition to this in-line input feature, the UI enables in-place editing or error correction without requiring the user to switch modes from an entry mode to an edit mode. To assist with this in-place editing, the UI presents pop-up windows containing the phonetic text from which the output text was converted as well as first and second candidate lists that contain small and large sets of alternative candidates that might be used to replace the current output text. The language input user interface also allows a user to enter a mixed text of different languages.
摘要翻译：语言输入架构从输入设备（例如，键盘，语音识别）接收用户输入的输入文本（例如，基于字符的语言的语音文本）。输入文本被转换为输出文本（例如，基于字符的语言的书面语言文本）。语言输入架构具有用于显示输出文本和未转换的输入文本的用户界面。当输入文本被转换时，它将在UI中被替换为转换的输出文本。除了这种在线输入功能之外，UI还可以进行就地编辑或纠错，而无需用户将模式从入门模式切换到编辑模式。为了协助进行就地编辑，用户界面将显示弹出窗口，其中包含输出文本被转换的语音文本以及第一个和第二个候选列表，其中包含可用于替换的小组和大组替代候选项当前的输出文本。语言输入用户界面还允许用户输入不同语言的混合文本。

17. 发明授权

US5757964A System and method for automatic subcharacter unit and lexicon generation for handwriting recognition 失效
标题翻译：用于手写识别的自动子字符单元和词典生成的系统和方法
公开(公告)号：US5757964A
公开(公告)日：1998-05-26
申请号：US901989
申请日：1997-07-29
申请人： Kai-Fu Lee , Yen-Lu Chow , Kamil Grajski
发明人： Kai-Fu Lee , Yen-Lu Chow , Kamil Grajski
IPC分类号： G06K9/62 , G06K9/72
CPC分类号： G06K9/6297 , G06K9/6255
摘要： A system for automatic subcharacter unit and lexicon generation for handwriting recognition comprises a processing unit, a handwriting input device, and a memory wherein a segmentation unit, a subcharacter generation unit, a lexicon unit, and a modeling unit reside. The segmentation unit generates feature vectors corresponding to sample characters. The subcharacter generation unit clusters feature vectors and assigns each feature vector associated with a given cluster an identical label. The lexicon unit constructs a lexical graph for each character in a character set. The modeling unit generates a Hidden Markov Model for each set of identically-labeled feature vectors. After a first set of lexical graphs and Hidden Markov Models have been created, the subcharacter generation unit determines for each feature vector which Hidden Markov Model produces a highest likelihood value. The subcharacter generation unit relabels each feature vector according to the highest likelihood value, after which the lexicon unit and the modeling unit generate a new set of lexical graphs and a new set of Hidden Markov models, respectively. The feature vector relabeling, lexicon generation, and Hidden Markov Model generation are performed iteratively until a convergence criterion is met. The final set of Hidden Markov Model model parameters provide a set of subcharacter units for handwriting recognition, where the subcharacter units are derived from information inherent in the sample characters themselves.
摘要翻译：用于手写识别的自动子字符单元和词典生成的系统包括处理单元，手写输入装置和存储器，其中存在分割单元，子字符生成单元，词典单元和建模单元。分割单元生成与采样字符对应的特征矢量。子字符生成单元簇特征向量并且将与给定簇相关联的每个特征向量分配给相同的标签。词典单元为字符集中的每个字符构成一个词汇图。建模单元为每组相同标记的特征向量生成隐马尔科夫模型。在创建了第一组词汇图和隐马尔科夫模型之后，子字符生成单元为每个特征向量确定隐马尔可夫模型产生最高似然值。子字符生成单元根据最高似然值重新标记每个特征向量，之后词法单元和建模单元分别生成一组新的词法图和一组新的隐马尔可夫模型。迭代地执行特征向量重新标记，词法生成和隐马尔科夫模型生成，直到满足收敛标准。最后一组隐马尔可夫模型参数提供了一组用于手写识别的子字符单元，其中子字符单元是从样本字符本身固有的信息导出的。

18. 发明授权

US5602960A Continuous mandarin chinese speech recognition system having an integrated tone classifier 失效
标题翻译：连续汉语中文语音识别系统具有综合音分类器
公开(公告)号：US5602960A
公开(公告)日：1997-02-11
申请号：US316257
申请日：1994-09-30
申请人： Hsiao-Wuen Hon , Yen-Lu Chow , Kai-Fu Lee
发明人： Hsiao-Wuen Hon , Yen-Lu Chow , Kai-Fu Lee
IPC分类号： G10L15/02 , G10L15/04 , G10L15/18 , G10L3/02
CPC分类号： G10L15/04 , G10L25/15
摘要： A speech recognition system for continuous Mandarin Chinese speech comprises a microphone, an A/D converter, a syllable recognition system, an integrated tone classifier, and a confidence score augmentor. The syllable recognition system generates N-best theories with initial confidence scores. The integrated tone classifier has a pitch estimator to estimate the pitch of the input once and a long-term tone analyzer to segment the estimated pitch according to the syllables of each of the N-best theories. The long-term tone analyzer performs long-term tonal analysis on the segmented, estimated pitch and generates a long-term tonal confidence signal. The confidence score augmentor receives the initial confidence scores and the long-term tonal confidence signals, modifies each initial confidence score according to the corresponding long-term tonal confidence signal, re-ranks the N-best theories according to the augmented confidence scores, and outputs the N-best theories.
摘要翻译：用于连续汉语普通话的语音识别系统包括麦克风，A / D转换器，音节识别系统，集成音分类器和置信分数增强器。音节识别系统产生具有初始置信分数的N最佳理论。综合音分类器具有估计输入音高的音调估计器和一个长期音调分析器，以根据每个N最佳理论的音节来分段估计音高。长期音调分析仪对分段估计音高进行长期色调分析，并产生长期色调置信度信号。信心分数增强器接收初始置信度分数和长期音调信号，根据相应的长期音调信号信号修改每个初始置信度分数，根据增强的置信度得分重新排列N最佳理论; 输出N最好的理论。

19. 发明授权

US5535305A Sub-partitioned vector quantization of probability density functions 失效
标题翻译：概率密度函数的子分割矢量量化
公开(公告)号：US5535305A
公开(公告)日：1996-07-09
申请号：US999293
申请日：1992-12-31
申请人： Alejandro Acero , Yen-Lu Chow , Kai-Fu Lee
发明人： Alejandro Acero , Yen-Lu Chow , Kai-Fu Lee
IPC分类号： G06K9/62 , G10L15/02 , G10L15/14 , G10L5/06
CPC分类号： G10L15/144 , G06K9/6217
摘要： A speech recognition memory compression method and apparatus subpartitions probability density function (pdf) space along the hidden Markov model (HMM) index into packets of typically 4 to 8 log-pdf values. Vector quantization techniques are applied using a logarithmic distance metric and a probability weighted logarithmic probability space for the splitting of clusters. Experimental results indicate a significant reduction in memory can be obtained with little increase in overall speech recognition error.
摘要翻译：一种将隐马尔可夫模型（HMM）索引的语音识别存储器压缩方法和装置子分类概率密度函数（pdf）空间通常为4到8个log-pdf值的分组。使用对数距离度量和用于分割簇的概率加权对数概率空间来应用矢量量化技术。实验结果表明，在语音识别总误差增加很小的情况下可以显着降低记忆。

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