公开(公告)号：US5602960A

公开(公告)日：1997-02-11

申请号：US316257

申请日：1994-09-30

Applicant: Hsiao-Wuen Hon ,  Yen-Lu Chow ,  Kai-Fu Lee

Inventor： Hsiao-Wuen Hon ,  Yen-Lu Chow ,  Kai-Fu Lee

IPC: G10L15/02 ,  G10L15/04 ,  G10L15/18 ,  G10L3/02

CPC classification number: G10L15/04 ,  G10L25/15

Abstract: 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.

Abstract translation: 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。

公开(公告)号：US5617486A

公开(公告)日：1997-04-01

申请号：US563256

申请日：1995-11-27

Applicant: Yen-Lu Chow ,  Peter V. deSouza ,  Adam B. Fineberg ,  Hsiao-Wuen Hon

Inventor： Yen-Lu Chow ,  Peter V. deSouza ,  Adam B. Fineberg ,  Hsiao-Wuen Hon

IPC: G06K9/00 ,  G10L15/06 ,  G10L15/14

CPC classification number: G10L15/07 ,  G06K9/00154 ,  G10L15/063 ,  G10L15/144 ,  G10L2015/0635

Abstract: A pattern recognition system which continuously adapts reference patterns to more effectively recognize input data from a given source. The input data is converted to a set or series of observed vectors and is compared to a set of Markov Models. The closest matching Model is determined and is recognized as being the input data. Reference vectors which are associated with the selected Model are compared to the observed vectors and updated ("adapted") to better represent or match the observed vectors. This updating method retains the value of these observed vectors in a set of accumulation vectors in order to base future adaptations on a broader data set. When updating, the system also may factor in the values corresponding to neighboring reference vectors that are acoustically similar if the data set from the single reference vector is insufficient for an accurate calculation. Every reference vector is updated after every input; thus reference vectors neighboring an updated reference vector may also be updated. The updated reference vectors are then stored by the computer system for use in recognizing subsequent inputs.

Abstract translation: 一种模式识别系统，其连续地适应参考模式以更有效地识别来自给定源的输入数据。 将输入数据转换为一组或一系列观测向量，并将其与一组马尔科夫模型进行比较。 确定最接近的匹配模型，并将其识别为输入数据。 将与所选模型相关联的参考向量与观察到的向量进行比较并更新（“适应”）以更好地表示或匹配观察到的向量。 这种更新方法将这些观测向量的值保留在一组累积向量中，以便将未来的适应基础放在更广泛的数据集上。 当更新时，如果来自单个参考矢量的数据集不足以进行准确的计算，则系统还可以考虑与相邻参考矢量相对应的值，该参考矢量在声学上类似。 每个参考矢量在每次输入后更新; 因此也可以更新与更新的参考矢量相邻的参考矢量。 然后，更新的参考向量由计算机系统存储以用于识别后续输入。

公开(公告)号：US5832428A

公开(公告)日：1998-11-03

申请号：US538828

申请日：1995-10-04

Applicant: Yen-Lu Chow ,  Hsiao-Wuen Hon

Inventor： Yen-Lu Chow ,  Hsiao-Wuen Hon

IPC: G10L15/00 ,  G10L15/06 ,  G10L15/18 ,  G10L5/06 ,  G10L9/00

CPC classification number: G10L15/063 ,  G10L15/1815 ,  G10L15/19 ,  G10L15/183

Abstract: A method of constructing a language model for a phrase-based search in a speech recognition system and an apparatus for constructing and/or searching through the language model. The method includes the step of separating a plurality of phrases into a plurality of words in a prefix word, body word, and suffix word structure. Each of the phrases has a body word and optionally a prefix word and a suffix word. The words are grouped into a plurality of prefix word classes, a plurality of body word classes, and a plurality of suffix word classes in accordance with a set of predetermined linguistic rules. Each of the respective prefix, body, and suffix word classes includes a number of prefix words of same category, a number of body words of same category, and a number of suffix words of same category, respectively. The prefix, body, and suffix word classes are then interconnected together according to the predetermined linguistic rules. A method of organizing a phrase search based on the above-described prefix/body/suffix language model is also described. The words in each of the prefix, body, and suffix classes are organized into a lexical tree structure. A phrase start lexical tree structure is then created for the words of all the prefix classes and the body classes having a word which can start one of the plurality of phrases while still maintaining connections of these prefix and body classes within the language model.

Abstract translation: 一种在语音识别系统中构建用于基于短语的搜索的语言模型的方法以及用于通过语言模型构建和/或搜索的装置。 该方法包括将多个短语分离成前缀字，正文和后缀词结构中的多个单词的步骤。 每个短语都有一个正文词和可选的前缀词和一个后缀词。 这些字根据一组预定语言规则分组成多个前缀词类，多个体词类和多个后缀词类。 各个前缀，正文和后缀词类中的每一个分别包括相同类别的多个前缀词，相同类别的正文字数，以及相同类别的多个后缀词。 然后，前缀，正文和后缀词类根据预定的语言规则互连在一起。 还描述了基于上述前缀/主体/后缀语言模型来组织短语搜索的方法。 每个前缀，正文和后缀类中的单词被组织成词法树结构。 然后，针对所有前缀类和具有单词的主体类创建短语开始词法树结构，该单词可以开始多个短语中的一个，同时仍然保持语言模型内的这些前缀和身体类的连接。

公开(公告)号：US5852801A

公开(公告)日：1998-12-22

申请号：US538919

申请日：1995-10-04

Applicant: Hsiao-Wuen Hon ,  Yen-Lu Chow

Inventor： Hsiao-Wuen Hon ,  Yen-Lu Chow

IPC: G10L15/18 ,  G10L15/22 ,  G01L5/06

CPC classification number: G10L15/22 ,  G10L15/18 ,  G10L15/183 ,  G10L15/197

Abstract: A method for reducing recognition errors in a speech recognition system that has a user interface, which instructs the user to invoke a new word acquisition module upon a predetermined condition, and that improves the recognition accuracy for poorly recognized words. The user interface of the present invention suggests to a user which unrecognized words may be new words that should be added to the recognition program lexicon. The user interface advises the user to enter words into a new word lexicon that fails to present themselves in an alternative word list for two consecutive tries. A method to improve the recognition accuracy for poorly recognized words via language model adaptation is also provided by the present invention. The present invention increases the unigram probability of an unrecognized word in proportion to the score difference between the unrecognized word and the top one word to guarantee recognition of the same word in a subsequent try. In the event that the score of unrecognized word is unknown (i.e., not in the alternative word list), the present invention increases the unigram probability of the unrecognized word in proportion to the difference between the top one word score and the smallest score in the alternative list.

Abstract translation: 一种用于减少具有用户界面的语音识别系统中的识别错误的方法，所述用户界面指示用户在预定条件下调用新的单词获取模块，并且提高了对于较差识别字词的识别精度。 本发明的用户界面向用户建议未被识别的单词可以是应被添加到识别程序词典的新单词。 用户界面建议用户将单词输入到一个新的单词词典中，这个单词词典不能在两个连续的尝试中呈现出一个替代单词列表。 通过本发明也提供了通过语言模型适应来提高对于识别不良的词的识别精度的方法。 本发明增加与未被识别的单词和前一个单词之间的分数差成比例的未被识别的单词的单字概率，以保证在随后的尝试中识别相同的单词。 在无法识别的词的得分未知（即，不在替代词表中）的情况下，本发明将不识别词的单词概率与第一个单词得分和最小分数之间的差成比例增加 替代清单

公开(公告)号：US08326785B2

公开(公告)日：2012-12-04

申请号：US12241078

申请日：2008-09-30

Applicant: Cheng Niu ,  Ming Zhou ,  Hsiao-Wuen Hon

Inventor： Cheng Niu ,  Ming Zhou ,  Hsiao-Wuen Hon

IPC: G06F17/00 ,  G06F17/20 ,  G06F7/00 ,  G06F17/30 ,  G06N5/00

CPC classification number: G06F17/30675

Abstract: A classifier is built to rank documents of different languages found in a query based at least in part on similarity to other documents and the relevance of those other documents to the query. A joint ranking model, e.g., based upon a Boltzmann machine, is used to represent the content similarity among documents, and to help determine joint relevance probability for a set of documents. The relevant documents of one language are thus leveraged to improve the relevance estimation for documents of different languages. In one aspect, a hidden layer of units (neurons) represents clusters (corresponding to relevant topics) among the retrieved documents, with an output layer representing the relevant documents and their features, and edges representing a relationship between clusters and documents.

Abstract translation: 构建分类器至少部分地基于与其他文档的相似性以及这些其他文档与查询的相关性来对查询中发现的不同语言的文档进行排序。 联合排名模型，例如基于玻尔兹曼（Boltzmann）机器，用于表示文档之间的内容相似性，并且帮助确定一组文档的联合相关概率。 因此，利用一种语言的相关文件来改进不同语言文件的相关性估计。 在一个方面，隐藏的单位（神经元）表示检索的文档中的集群（对应于相关主题），输出层表示相关文档及其特征，边缘表示集群和文档之间的关系。

公开(公告)号：US07574348B2

公开(公告)日：2009-08-11

申请号：US11177136

申请日：2005-07-08

Applicant: Hsiao-Wuen Hon ,  Jianfeng Gao ,  Ming Zhou

Inventor： Hsiao-Wuen Hon ,  Jianfeng Gao ,  Ming Zhou

IPC: G06F17/27

CPC classification number: G06F17/274 ,  Y10S707/99933 ,  Y10S707/99936

Abstract: A sentence is accessed and at least one query is generated based on the sentence. At least one query can be compared to text within a collection of documents, for example using a web search engine. Collocation errors in the sentence can be detected and/or corrected based on the comparison of the at least one query and the text within the collection of documents.

Abstract translation: 访问一个句子，并且基于该句子生成至少一个查询。 至少可以将一个查询与文档集合中的文本进行比较，例如使用Web搜索引擎。 可以基于至少一个查询与文档集合内的文本的比较来检测和/或修正该句子中的配置错误。

公开(公告)号：US20080133444A1

公开(公告)日：2008-06-05

申请号：US11633788

申请日：2006-12-05

Applicant: Jianfeng Gao ,  William B. Dolan ,  Hsiao-Wuen Hon ,  Ming Zhou

Inventor： Jianfeng Gao ,  William B. Dolan ,  Hsiao-Wuen Hon ,  Ming Zhou

IPC: G06N7/02 ,  G06F17/30 ,  G06F3/048

CPC classification number: G06F17/3061 ,  G06F17/273 ,  G06F17/277 ,  G06F17/2845

Abstract: Collocation errors can be automatically proofed using local and network-based corpora, including the Web. For example, according to one illustrative method, one or more collocations from a text sample are compared with a corpus such as the content of the Web. The collocations are identified for whether they are disfavored in the corpus. Indications are provided via an output device of whether the collocations are disfavored in the corpus. Additional steps may then be taken such as searching for and providing potentially proper word collocations via a user output.

Abstract translation: 可以使用本地和基于网络的语料库（包括Web）自动验证并置错误。 例如，根据一个说明性方法，将来自文本样本的一个或多个并置与诸如Web的内容的语料库进行比较。 识别他们是否在语料库中不利的搭配。 通过输出设备提供指示是否在语料库中不匹配。 然后可以采取额外的步骤，例如通过用户输出搜索并提供潜在的适当的单词搭配。

公开(公告)号：US20050203934A1

公开(公告)日：2005-09-15

申请号：US10796644

申请日：2004-03-09

Applicant: Scott Meredith ,  Peter Leonard ,  Hsiao-Wuen Hon

Inventor： Scott Meredith ,  Peter Leonard ,  Hsiao-Wuen Hon

IPC: G06F12/00 ,  G06F17/30 ,  H03M7/30 ,  G06F17/00

CPC classification number: H03M7/30

Abstract: A method and apparatus for compressing query logs is provided. Multiple levels of user-specifiable compression include character-based compression, token-based compression, and subsumption. An efficient method for performing subsumption is also provided. The compressed query logs are then used to train a statistical process such as a help function for a computer operating system.

Abstract translation: 提供了一种用于压缩查询日志的方法和装置。 用户可指定压缩的多个级别包括基于字符的压缩，基于令牌的压缩和包含。 还提供了一种执行包含的有效方法。 然后，压缩的查询日志用于训练诸如用于计算机操作系统的帮助功能的统计过程。

公开(公告)号：US20050033713A1

公开(公告)日：2005-02-10

申请号：US10887058

申请日：2004-07-08

Applicant: Aravind Bala ,  Andrew McGlinchey ,  Saikat Sen ,  James Jacoby ,  Hsiao-Wuen Hon

Inventor： Aravind Bala ,  Andrew McGlinchey ,  Saikat Sen ,  James Jacoby ,  Hsiao-Wuen Hon

IPC: G06F3/048 ,  G06F3/00 ,  G06F3/033 ,  G06F3/14 ,  G06F9/00 ,  G06F9/06 ,  G06F9/44 ,  G06F17/00 ,  G06F17/30 ,  G06N5/02 ,  G06N5/04 ,  G09G5/00

CPC classification number: G06F17/2881 ,  G06F9/453

Abstract: A text generator automatically generating a text document based on the actions of an author on a user interface. To generate the text document the author activates a recording component. The recording component records the author's actions on the user interface. Based on the recorded actions, a text generation component searches a text database and identifies an entry that matches the author's recorded actions. This text is then combined to form a text document, which provides instruction or other information to a user. During the process of generating the text document, the text can be edited using an editor as desired, such as to enhance the comprehensibility of the document.

Abstract translation: 文本生成器根据作者在用户界面上的动作自动生成文本文档。 要生成文本文档，作者激活录制组件。 录音组件将作者的动作记录在用户界面上。 基于记录的动作，文本生成组件搜索文本数据库并识别与作者记录的动作相匹配的条目。 然后将该文本组合以形成文本文档，其向用户提供指令或其他信息。 在生成文本文档的过程中，可以使用编辑器根据需要编辑文本，以增强文档的可理解性。

公开(公告)号：US5884261A

公开(公告)日：1999-03-16

申请号：US271639

申请日：1994-07-07

Applicant: Peter V. de Souza ,  Adam B. Fineberg ,  Hsiao-Wuen Hon ,  Baosheng Yuan

Inventor： Peter V. de Souza ,  Adam B. Fineberg ,  Hsiao-Wuen Hon ,  Baosheng Yuan

IPC: G10L11/04 ,  G10L15/02 ,  G10L15/14 ,  G10L15/18 ,  G10L9/00

CPC classification number: G10L15/144 ,  G10L25/15 ,  G10L25/90

Abstract: Tone-sensitive acoustic models are generated by first generating acoustic vectors which represent the input data. The input data is separated into multiple frames and an acoustic vector is generated for each frame which represents the input data over its corresponding frame. A tone-sensitive parameter is then generated for each of the frames which indicates the tone of the input data at its corresponding frame. Tone-sensitive parameters are generated in accordance with two embodiments. First, a pitch detector may be used to calculate a pitch for each of the frames. If a pitch cannot be detected for a particular frame, then a pitch is created for that frame based on the pitch values of surrounding frames. Second, the cross covariance between the autocorrelation coefficients for each frame and its successive frame may be generated and used as the tone-sensitive parameter. Feature vectors are then created for each frame by appending the tone-sensitive parameter for a frame to the acoustic vector for the same frame. Then, using these feature vectors, acoustic models are created which represent the input data.

Abstract translation: 通过首先产生表示输入数据的声矢量来产生音调敏感的声学模型。 输入数据被分成多个帧，并且为代表其对应帧上的输入数据的每个帧生成声向量。 然后，对于指示在其对应帧处的输入数据的音调的每个帧，生成对音调敏感的参数。 根据两个实施例产生音敏参数。 首先，可以使用音调检测器来计算每个帧的音调。 如果对于特定帧不能检测到音调，则基于周围帧的音调值创建针对该帧的音高。 其次，可以生成每个帧及其连续帧的自相关系数之间的交叉协方差，并将其用作音调敏感参数。 然后通过将帧的音调敏感参数附加到相同帧的声矢量来为每个帧创建特征向量。 然后，使用这些特征向量，创建表示输入数据的声学模型。