公开(公告)号：US5963903A

公开(公告)日：1999-10-05

申请号：US673435

申请日：1996-06-28

申请人： Hsiao-Wuen Hon ,  Xuedong D. Huang ,  Mei-Yuh Hwang ,  Li Jiang ,  Yun-Cheng Ju ,  Milind V. Mahajan ,  Michael J. Rozak

发明人： Hsiao-Wuen Hon ,  Xuedong D. Huang ,  Mei-Yuh Hwang ,  Li Jiang ,  Yun-Cheng Ju ,  Milind V. Mahajan ,  Michael J. Rozak

IPC分类号： G10L15/02 ,  G10L15/06 ,  G10L15/14 ,  G10L5/04

CPC分类号： G10L15/063 ,  G10L2015/0635

摘要： A method and system for dynamically selecting words for training a speech recognition system. The speech recognition system models each phoneme using a hidden Markov model and represents each word as a sequence of phonemes. The training system ranks each phoneme for each frame according to the probability that the corresponding codeword will be spoken as part of the phoneme. The training system collects spoken utterances for which the corresponding word is known. The training system then aligns the codewords of each utterance with the phoneme that it is recognized to be part of. The training system then calculates an average rank for each phoneme using the aligned codewords for the aligned frames. Finally, the training system selects words for training that contain phonemes with a low rank.

摘要翻译： 一种用于动态选择用于训练语音识别系统的单词的方法和系统。 语音识别系统使用隐马尔科夫模型对每个音素进行建模，并将每个单词表示为音素序列。 训练系统根据将相应的码字作为音素的一部分被说出的概率，对每个帧的每个音素进行排序。 训练系统收集对应词语已知的口语说话。 然后，训练系统将每个话语的码字与被认为是其一部分的音素对齐。 训练系统然后使用对齐的帧的对齐码字来计算每个音素的平均等级。 最后，训练系统选择包含低等级音素的训练词。

公开(公告)号：US5829000A

公开(公告)日：1998-10-27

申请号：US741696

申请日：1996-10-31

申请人： Xuedong D. Huang ,  Hsiao-Wuen Hon ,  Li Jiang

发明人： Xuedong D. Huang ,  Hsiao-Wuen Hon ,  Li Jiang

IPC分类号： G10L15/06 ,  G10L15/22 ,  G01L5/06

CPC分类号： G10L15/22

摘要： A method and system for editing words that have been misrecognized. The system allows a speaker to specify a number of alternative words to be displayed in a correction window by resizing the correction window. The system also displays the words in the correction window in alphabetical order. A preferred system eliminates the possibility, when a misrecognized word is respoken, that the respoken utterance will be again recognized as the same misrecognized word. This elimination occurs based on the probabilities of alternative words associated with both the misrecognized utterance and the respoken utterance. The system, when operating with a word processor, allows the speaker to specify the amount of speech that is buffered before transferring to the word processor. The system also uses a word correction metaphor or a phrase correction metaphor.

摘要翻译： 用于编辑错误识别的单词的方法和系统。 该系统允许扬声器通过调整校正窗口的大小来指定要在校正窗口中显示的替代单词的数量。 系统还会按字母顺序显示校正窗口中的单词。 一个首选的系统消除了当一个错误识别的话被重申时，这个可重复发音将被再次被认为是同一个错误识别的单词的可能性。 这种消除是基于与错误识别的话语和呼出话语相关联的替代词的概率。 当使用文字处理器进行操作时，该系统允许扬声器指定在传送到文字处理器之前缓冲的语音量。 该系统还使用单词修正隐喻或短语校正隐喻。

公开(公告)号：US6076056A

公开(公告)日：2000-06-13

申请号：US934622

申请日：1997-09-19

申请人： Xuedong D. Huang ,  Fileno A. Alleva ,  Li Jiang ,  Mei-Yuh Hwang

发明人： Xuedong D. Huang ,  Fileno A. Alleva ,  Li Jiang ,  Mei-Yuh Hwang

IPC分类号： G10L15/02 ,  G10L15/04 ,  G10L15/06 ,  G10L15/08 ,  G10L15/14 ,  G10L15/28

CPC分类号： G10L15/08 ,  G10L15/05

摘要： Speech recognition is performed by receiving isolated speech training data indicative of a plurality of discretely spoken training words, and receiving continuous speech training data indicative of a plurality of continuously spoken training words. A plurality of speech unit models is trained based on the isolated speech training data and the continuous speech training data. Speech is recognized based on the speech unit models trained.

摘要翻译： 通过接收指示多个离散讲话的训练词的孤立语音训练数据，以及接收指示多个连续讲话的训练词的连续语音训练数据来执行语音识别。 基于孤立语音训练数据和连续语音训练数据来训练多个语音单元模型。 基于训练的语音单元模型识别语音。

公开(公告)号：US5933804A

公开(公告)日：1999-08-03

申请号：US833916

申请日：1997-04-10

申请人： Xuedong D. Huang ,  Michael J. Rozak ,  Li Jiang

发明人： Xuedong D. Huang ,  Michael J. Rozak ,  Li Jiang

IPC分类号： G06F3/16 ,  G10L13/00 ,  G10L15/06 ,  G10L15/22 ,  G10L15/28 ,  G10L5/06 ,  G10L5/02

CPC分类号： G10L15/063 ,  G10L2015/0638

摘要： A speech recognition system is extensible in that new terms may be added to a list of terms that are recognized by the speech recognition system. The speech recognition system provides audio feedback when new terms are added so that a user may hear how the system expects the word to be pronounced. The user may then accept the pronunciation or provide his own pronunciation. The user may also selectively change the pronunciation of words to avoid misrecognitions by the system. The system may provide appropriate user interface elements for enabling a user to change the pronunciation of words. The system may also include intelligence for automatically changing the pronunciation of words used in recognition based upon empirically derived information.

摘要翻译： 语音识别系统是可扩展的，因为可以将新术语添加到由语音识别系统识别的术语列表中。 当添加新术语时，语音识别系统提供音频反馈，使得用户可以听到系统如何预期该单词被发音。 用户可以接受发音或提供自己的发音。 用户还可以选择性地改变单词的发音，以避免系统误认识。 系统可以提供适当的用户界面元素，以使用户能够改变单词的发音。 该系统还可以包括基于经验导出的信息来自动改变识别中使用的单词的发音的智能。

公开(公告)号：US20050203739A1

公开(公告)日：2005-09-15

申请号：US10797358

申请日：2004-03-10

申请人： Mei-Yuh Hwang ,  Li Jiang

发明人： Mei-Yuh Hwang ,  Li Jiang

IPC分类号： G10L13/06 ,  G10L13/08 ,  G06K9/00

CPC分类号： G10L13/08

摘要： A method and apparatus are provided for segmenting words into component parts. Under the invention, mutual information scores for pairs of graphoneme units found in a set of words are determined. Each graphoneme unit includes at least one letter. The graphoneme units of one pair of graphoneme units are combined based on the mutual information score. This forms a new graphoneme unit. Under one aspect of the invention, a syllable n-gram model is trained based on words that have been segmented into syllables using mutual information. The syllable n-gram model is used to segment a phonetic representation of a new word into syllables. Similarly, an inventory of morphemes is formed using mutual information and a morpheme n-gram is trained that can be used to segment a new word into a sequence of morphemes.

摘要翻译： 提供了一种用于将单词分割成组成部分的方法和装置。 根据本发明，确定在一组单词中发现的一对图形单元的互信息得分。 每个图形单元至少包含一个字母。 基于相互信息得分组合一对图形单元的图形单位。 这形成一个新的图形单元。 在本发明的一个方面，使用相互信息将已经被分段成音节的单词训练在一个音节的n-gram模型上。 音节n-gram模型用于将新词的语音表示分割成音节。 类似地，使用相互信息形成语素的清单，并且训练语素n-gram，其可以用于将新单词分割成语素序列。

公开(公告)号：US07693715B2

公开(公告)日：2010-04-06

申请号：US10797358

申请日：2004-03-10

申请人： Mei-Yuh Hwang ,  Li Jiang

发明人： Mei-Yuh Hwang ,  Li Jiang

IPC分类号： G10L15/04

CPC分类号： G10L13/08

摘要： A method and apparatus are provided for segmenting words into component parts. Under the invention, mutual information scores for pairs of graphoneme units found in a set of words are determined. Each graphoneme unit includes at least one letter. The graphoneme units of one pair of graphoneme units are combined based on the mutual information score. This forms a new graphoneme unit. Under one aspect of the invention, a syllable n-gram model is trained based on words that have been segmented into syllables using mutual information. The syllable n-gram model is used to segment a phonetic representation of a new word into syllables. Similarly, an inventory of morphemes is formed using mutual information and a morpheme n-gram is trained that can be used to segment a new word into a sequence of morphemes.

摘要翻译： 提供了一种用于将单词分割成组成部分的方法和装置。 根据本发明，确定在一组单词中发现的一对图形单元的互信息得分。 每个图形单元至少包含一个字母。 基于相互信息得分组合一对图形单元的图形单位。 这形成一个新的图形单元。 在本发明的一个方面，使用相互信息将已经被分段成音节的单词训练在一个音节的n-gram模型上。 音节n-gram模型用于将新词的语音表示分割成音节。 类似地，使用相互信息形成语素的清单，并且训练语素n-gram，其可以用于将新单词分割成语素序列。

公开(公告)号：US09811850B2

公开(公告)日：2017-11-07

申请号：US13441898

申请日：2012-04-08

申请人： Steven William Macbeth ,  Michael William O'Connor ,  Zhaowei Charlie Jiang ,  Michael Van Snellenberg ,  Li Jiang ,  Shajib Sadhukha ,  Amit Kumar

发明人： Steven William Macbeth ,  Michael William O'Connor ,  Zhaowei Charlie Jiang ,  Michael Van Snellenberg ,  Li Jiang ,  Shajib Sadhukha ,  Amit Kumar

IPC分类号： G06F17/30 ,  G06Q30/06 ,  G06Q50/10 ,  G06Q30/02

CPC分类号： G06Q30/0631 ,  G06F17/30864 ,  G06F17/30867 ,  G06F17/30991 ,  G06Q30/0256 ,  G06Q30/0627 ,  G06Q50/10

摘要： Among other things, one or more techniques and/or systems are provided for facilitating the completion of a user task. That is, user intent (e.g., intentions of a user to perform a user task) may be identified. The user intent may comprise an entity (e.g., a movie entity) and/or an action (e.g., an order movie tickets action) that the user wants to perform on the entity. A provider list may be created based upon one or more providers capable of performing the action on the entity (e.g., a movie application may be capable of performing the order movie tickets action on the movie entity). Providers may be dynamically selected for inclusion within the provider list at run-time. For example, an open market of providers may be maintained (e.g., providers may be added, removed, and/or updated over time), such that providers may be selected from the open market to complete user tasks.

公开(公告)号：US20160377754A1

公开(公告)日：2016-12-29

申请号：US14748737

申请日：2015-06-24

申请人： Mayank Malik ,  John DeSantis ,  Fuju Chen ,  Li Jiang ,  Saijin Huang ,  John A. Best

发明人： Mayank Malik ,  John DeSantis ,  Fuju Chen ,  Li Jiang ,  Saijin Huang ,  John A. Best

IPC分类号： G01V1/34 ,  G01V13/00 ,  G01V1/30

CPC分类号： G01V1/40

摘要： Desirable completion zones can be identified using closure stress in combination with one or more other attributes such as porosity. One computer-based well placement method includes using the computer to: process a seismic data volume to map the spatial distribution of a seismic-based CSS attribute; acquire logs from one or more boreholes in the subsurface region; derive from the logs a relationship between CSS and a minimum in-situ stress; apply the relationship to the CSS attribute map to produce a landing map that highlights desirable completion zones; and place one or more wells in the desirable completion zones. The borehole logs may include direct measurements of minimum in-situ stress (acquired via microfracture testing), sonic tool measurements of P-wave and S-wave velocity, and density tool measurements of bulk formation density.

摘要翻译： 可以使用闭合应力与一个或多个其它属性（例如孔隙率）组合来确定期望的完井区域。 一种基于计算机的井位置方法包括使用该计算机：处理地震数据量以映射基于地震的CSS属性的空间分布; 从地下区域的一个或多个钻孔采集原木; 从日志中得出CSS与最小原位应力之间的关系; 将关系应用于CSS属性映射，以生成突出显示所需完成区域的着陆映射; 并将一个或多个井放置在所需的完井区。 钻孔测井可以包括直接测量最小原位应力（通过微裂缝测试获得），P波和S波速度的声波工具测量以及体积地层密度的密度测量。

公开(公告)号：US09034651B2

公开(公告)日：2015-05-19

申请号：US12820363

申请日：2010-06-22

申请人： Li Jiang ,  Timothy Gareth John Jones ,  Andrew Meredith ,  Markus Pagels ,  Amilra Prasanna De Silva

发明人： Li Jiang ,  Timothy Gareth John Jones ,  Andrew Meredith ,  Markus Pagels ,  Amilra Prasanna De Silva

IPC分类号： G01N15/06 ,  E21B47/10 ,  G01N17/00 ,  G01N33/18

CPC分类号： E21B47/10 ,  G01N17/008 ,  G01N33/1853 ,  Y10T436/21 ,  Y10T436/25 ,  Y10T436/25375 ,  Y10T436/255

摘要： This invention relates to methods and apparatus for determination of ion concentrations, particularly in downhole water from hydrocarbon wells, aquifers etc. It is useful in a wide range of applications, including predicting the formation of scale and fingerprinting waters from different sources. More particularly, the invention relates to the use of ligands whose electronic configuration is altered by the binding of the scaling ions within a water sample. These alterations are detected electrochemically by applying varying potential to electrodes and measuring current flow as potential is varied, from which is derived the concentration of scaling ions in the fluid.

摘要翻译： 本发明涉及用于测定离子浓度的方法和装置，特别是在来自烃井，含水层等的井下水中。它在广泛的应用中是有用的，包括预测来自不同来源的水垢和指纹图谱的形成。 更具体地，本发明涉及配体的用途，其配体通过水样中的结垢离子而改变。 通过对电极施加变化的电位并且随着电位变化来测量电流而电化学地检测这些变化，从而导出流体中结垢离子的浓度。

公开(公告)号：US08908084B2

公开(公告)日：2014-12-09

申请号：US13663578

申请日：2012-10-30

申请人： Chih-Kuang Chang ,  Li Jiang ,  Zhong-Kui Yuan ,  Xiao-Guang Xue ,  Dong-Hai Li

发明人： Chih-Kuang Chang ,  Li Jiang ,  Zhong-Kui Yuan ,  Xiao-Guang Xue ,  Dong-Hai Li

IPC分类号： G03B13/00 ,  H04N5/232

CPC分类号： G01B11/00 ,  G01B11/026 ,  G01B11/03 ,  G01B2210/50

摘要： In an electronic device, an image point A on an image of an object is selected. A spectral confocal sensor is controlled to move to a position above a measuring point A′ on the object, where the measuring point A′ corresponds to the image point A, and a Z-coordinate of the measuring point A′ is computed using the spectral confocal sensor. A focal position of the measuring point A′ is computed according to the Z-coordinate of the measuring point A′, and a CCD lens is controlled to move to the focal position. The Z-coordinate of the measuring point A′ is stored into a storage unit of the electronic device.

摘要翻译： 在电子设备中，选择对象的图像上的图像点A. 控制光谱共焦传感器移动到物体上的测量点A'上方的位置，其中测量点A'对应于图像点A，并且使用光谱计算测量点A'的Z坐标 共焦传感器 根据测量点A'的Z坐标来计算测量点A'的焦点位置，并且控制CCD透镜移动到焦点位置。 测量点A'的Z坐标被存储在电子设备的存储单元中。