公开(公告)号：US08370159B2

公开(公告)日：2013-02-05

申请号：US11120983

申请日：2005-05-04

申请人： Jaewon Lee ,  Jeongmi Cho ,  Kwangil Hwang ,  Yongbeom Lee ,  Jeongsu Kim

发明人： Jaewon Lee ,  Jeongmi Cho ,  Kwangil Hwang ,  Yongbeom Lee ,  Jeongsu Kim

IPC分类号： G10L21/00

CPC分类号： G10L15/08 ,  G10L15/30 ,  G10L15/32

摘要： A multi-layered speech recognition apparatus and method, the apparatus includes a client checking whether the client recognizes the speech using a characteristic of speech to be recognized and recognizing the speech or transmitting the characteristic of the speech according to a checked result; and first through N-th servers, wherein the first server checks whether the first server recognizes the speech using the characteristic of the speech transmitted from the client, and recognizes the speech or transmits the characteristic according to a checked result, and wherein an n-th (2≦n≦N) server checks whether the n-th server recognizes the speech using the characteristic of the speech transmitted from an (n−1)-th server, and recognizes the speech or transmits the characteristic according to a checked result.

摘要翻译： 一种多层语音识别装置和方法，所述装置包括：客户端，根据检查结果，使用要识别的语音特征识别语音，识别语音，或者发送语音的特征; 以及第一至第N服务器，其中第一服务器使用从客户端发送的语音的特征来检查第一服务器是否识别语音，并且根据检查结果识别语音或发送特性，并且其中， （2＆nlE; n＆nlE; N）服务器检查第n个服务器是否使用从第（n-1）个服务器发送的语音的特征识别语音，并且根据检查结果识别语音或发送特性 。

公开(公告)号：US20060080105A1

公开(公告)日：2006-04-13

申请号：US11120983

申请日：2005-05-04

申请人： Jaewon Lee ,  Jeongmi Cho ,  Kwangil Hwang ,  Yongbeom Lee ,  Jeongsu Kim

发明人： Jaewon Lee ,  Jeongmi Cho ,  Kwangil Hwang ,  Yongbeom Lee ,  Jeongsu Kim

IPC分类号： G10L21/00

CPC分类号： G10L15/08 ,  G10L15/30 ,  G10L15/32

摘要： A multi-layered speech recognition apparatus and method, the apparatus includes a client checking whether the client recognizes the speech using a characteristic of speech to be recognized and recognizing the speech or transmitting the characteristic of the speech according to a checked result; and first through N-th servers, wherein the first server checks whether the first server recognizes the speech using the characteristic of the speech transmitted from the client, and recognizes the speech or transmits the characteristic according to a checked result, and wherein an n-th (2≦n≦N) server checks whether the n-th server recognizes the speech using the characteristic of the speech transmitted from an (n−1)-th server, and recognizes the speech or transmits the characteristic according to a checked result.

摘要翻译： 一种多层语音识别装置和方法，所述装置包括：客户端，根据检查结果，使用要识别的语音特征识别语音，识别语音，或者发送语音的特征; 以及第一至第N服务器，其中第一服务器使用从客户端发送的语音的特征来检查第一服务器是否识别语音，并且根据检查结果识别语音或发送特性，并且其中， 服务器检查第n个服务器是否使用从第（n-1）个服务器发送的语音的特征识别语音，并且识别语音或者根据 检查结果。

公开(公告)号：US08380517B2

公开(公告)日：2013-02-19

申请号：US13478656

申请日：2012-05-23

申请人： Jaewon Lee ,  Jeongmi Cho ,  Kwangil Hwang ,  Yongbeom Lee ,  Jeongsu Kim

发明人： Jaewon Lee ,  Jeongmi Cho ,  Kwangil Hwang ,  Yongbeom Lee ,  Jeongsu Kim

IPC分类号： G10L21/00

CPC分类号： G10L15/08 ,  G10L15/30 ,  G10L15/32

摘要： A multi-layered speech recognition apparatus and method, the apparatus includes a client checking whether the client recognizes the speech using a characteristic of speech to be recognized and recognizing the speech or transmitting the characteristic of the speech according to a checked result; and first through N-th servers, wherein the first server checks whether the first server recognizes the speech using the characteristic of the speech transmitted from the client, and recognizes the speech or transmits the characteristic according to a checked result, and wherein an n-th (2≦n≦N) server checks whether the n-th server recognizes the speech using the characteristic of the speech transmitted from an (n−1)-th server, and recognizes the speech or transmits the characteristic according to a checked result.

公开(公告)号：US07603274B2

公开(公告)日：2009-10-13

申请号：US11263826

申请日：2005-11-02

申请人： Kwangil Hwang

发明人： Kwangil Hwang

IPC分类号： G10L17/00 ,  G10L15/00 ,  G10L15/04

CPC分类号： G10L15/02 ,  G06K9/00496 ,  G10L15/142

摘要： A method and apparatus for determining the possibility of pattern recognition of time series signal independent of a pattern recognition ratio is provided. The method for determining the possibility of pattern recognition of time series signal includes extracting a time forward feature and a time reversed feature from an input signal having a time series pattern, generating time forward alignment and time reversed alignment by using the time forward feature and the time reversed feature, comparing the time forward alignment with the time reversed alignment to compute a likelihood of pattern recognition, and determining that the input signal can be recognized if the likelihood is larger than a predetermined threshold value. The possibility of the pattern recognition of the whole system can be determined, independent of the pattern recognition capability of each of the pattern recognition models, by extracting the patterns from the time series signal by using the plurality of the pattern recognition models and then obtaining the likelihood between the patterns to compare the likelihood with the threshold value. In addition, the pattern recognition can be performed in the non-limited environment.

摘要翻译： 提供一种用于确定与模式识别率无关的时间序列信号的模式识别的可能性的方法和装置。 用于确定时间序列信号的模式识别的可能性的方法包括从具有时间序列模式的输入信号中提取时间向前特征和时间反转特征，通过使用时间向前特征产生时间向前对准和时间反向对准，以及 时间反转特征，将时间向前对准与时间反向对准进行比较，以计算模式识别的可能性，以及如果似然率大于预定阈值，则确定可以识别输入信号。 通过使用多个模式识别模型从时间序列信号中提取模式，可以独立于每个模式识别模型的模式识别能力来确定整个系统的模式识别的可能性，然后获得 将可能性与阈值进行比较的模式之间的似然性。 此外，可以在非限制环境中执行模式识别。

公开(公告)号：US20060173686A1

公开(公告)日：2006-08-03

申请号：US11344163

申请日：2006-02-01

申请人： Kwangil Hwang

发明人： Kwangil Hwang

IPC分类号： G10L15/18

CPC分类号： G10L15/19 ,  G10L15/06 ,  G10L15/183

摘要： A method, apparatus, and medium for generating a grammar network for speech recognition and a dialogue speech recognition are provided. A method, apparatus, and medium for employing the same are provided. The apparatus for generating a grammar network for speech recognition includes: a dialogue history storage unit storing a dialogue history between a system and a user; a semantic map formed by clustering words forming each dialogue sentence included in a dialogue sentence corpus depending on semantic correlation, and generating a first candidate group formed of a plurality of words having the semantic correlation extracted for each word forming a dialogue sentence provided from the dialogue history storage unit; a sound map formed by clustering words forming each dialogue sentence included in the dialogue sentence corpus depending on acoustic similarity, and generating a second candidate group formed of a plurality of words having an acoustic similarity extracted for each word forming the dialogue sentence provided from the dialogue history storage unit and each word of the first candidate group; and a grammar network construction unit constructing a grammar network by combining the first candidate group and the second candidate group.

公开(公告)号：US07584102B2

公开(公告)日：2009-09-01

申请号：US10294901

申请日：2002-11-15

申请人： Kwangil Hwang ,  Eric Fieleke

发明人： Kwangil Hwang ,  Eric Fieleke

IPC分类号： G10L15/00

CPC分类号： G10L15/18 ,  G10L15/183

摘要： Building a language model for use in speech recognition includes identifying without user interaction a source of text related to a user. Text is retrieved from the identified source of text and a language model related to the user is built from the retrieved text.

摘要翻译： 构建用于语音识别的语言模型包括在没有用户交互的情况下识别与用户相关的文本源。 从识别的文本源检索文本，并从检索到的文本构建与用户相关的语言模型。

公开(公告)号：US07606708B2

公开(公告)日：2009-10-20

申请号：US11344163

申请日：2006-02-01

申请人： Kwangil Hwang

发明人： Kwangil Hwang

IPC分类号： G10L15/00 ,  G10L21/00

CPC分类号： G10L15/19 ,  G10L15/06 ,  G10L15/183

摘要： A method, apparatus, and medium for generating a grammar network for speech recognition and a dialogue speech recognition are provided. A method, apparatus, and medium for employing the same are provided. The apparatus for generating a grammar network for speech recognition includes: a dialogue history storage unit storing a dialogue history between a system and a user; a semantic map formed by clustering words forming each dialogue sentence included in a dialogue sentence corpus depending on semantic correlation, and generating a first candidate group formed of a plurality of words having the semantic correlation extracted for each word forming a dialogue sentence provided from the dialogue history storage unit; a sound map formed by clustering words forming each dialogue sentence included in the dialogue sentence corpus depending on acoustic similarity, and generating a second candidate group formed of a plurality of words having an acoustic similarity extracted for each word forming the dialogue sentence provided from the dialogue history storage unit and each word of the first candidate group; and a grammar network construction unit constructing a grammar network by combining the first candidate group and the second candidate group.

摘要翻译： 提供了一种用于生成用于语音识别的语法网络和对话语音识别的方法，装置和介质。 提供了一种用于使用它们的方法，装置和介质。 用于生成用于语音识别的语法网络的装置包括：存储系统和用户之间的对话历史的对话历史存储单元; 根据语义相关性，将形成包括在对话句子语料库中的每个对话句子的​​单词聚类形成的语义地图，以及生成由多个单词组成的第一候选组，所述单词具有从形成由对话提供的对话语句的每个单词提取的语义关联 历史存储单元; 通过将形成包括在对话句子语句中的每个对话句的单词聚类成取决于声学相似性而形成的声音映射，并且生成由对应于从形成由对话提供的对话句的每个单词提取的具有声学相似度的多个单词形成的第二候选组 历史存储单元和第一候选组的每个单词; 以及通过组合第一候选组和第二候选组来构建语法网络的语法网络构造单元。

公开(公告)号：US07294794B2

公开(公告)日：2007-11-13

申请号：US11497292

申请日：2006-08-02

申请人： Chang-kyu Choi ,  Seong-woon Kim ,  Sungi Hong ,  Jun-ho Park ,  Kwangil Hwang ,  Hongseok Yang ,  Yillmyung Yim ,  Yeun-bae Kim ,  Namwoo Kim ,  Byungin Yoo

发明人： Chang-kyu Choi ,  Seong-woon Kim ,  Sungi Hong ,  Jun-ho Park ,  Kwangil Hwang ,  Hongseok Yang ,  Yillmyung Yim ,  Yeun-bae Kim ,  Namwoo Kim ,  Byungin Yoo

IPC分类号： H01H13/02

CPC分类号： H01H13/83 ,  G06F1/1626 ,  G06F1/1662 ,  G06F3/0238 ,  H01H2219/012 ,  H01H2221/004 ,  H01H2221/016 ,  H01H2221/07 ,  H01H2223/014 ,  H04M1/23

摘要： A button input apparatus with a display function, which generates a switch signal in response to a user's press, and a portable electronic device having the same. The button input apparatus includes: a plurality of lever buttons each having a transparent window in at least a portion thereof, and one fixed edge on one side of the transparent window, so that the buttons are elastically vertically flexible; a switch substrate, which is disposed below the plurality of lever buttons, including openings respectively corresponding to the transparent windows, and generating a switch signal according to a motion of any of the plurality of lever buttons via a plurality of switches disposed to respectively correspond to elastic parts of the lever buttons; and a display panel, which provides an image in an area corresponding to each of the transparent windows, at least a portion of the display panel being disposed below the plurality of lever buttons.

摘要翻译： 具有显示功能的按钮输入装置，其响应于用户的按压产生开关信号，以及具有该按钮的便携式电子设备。 按钮输入装置包括：至少一部分具有透明窗口的多个杠杆按钮和透明窗口一侧的一个固定边缘，使得按钮弹性地垂直地柔性; 开关基板，其设置在所述多个杠杆按钮下方，包括分别对应于所述透明窗口的开口，并且经由多个开关分别对应于多个开关的多个开关，根据所述多个杠杆按钮中的任何一个的运动产生开关信号 杠杆按钮的弹性部分; 以及显示面板，其在与每个透明窗口相对应的区域中提供图像，所述显示面板的至少一部分设置在所述多个杠杆按钮的下方。

公开(公告)号：US20060143005A1

公开(公告)日：2006-06-29

申请号：US11263826

申请日：2005-11-02

申请人： Kwangil Hwang

发明人： Kwangil Hwang

IPC分类号： G10L15/16

CPC分类号： G10L15/02 ,  G06K9/00496 ,  G10L15/142

摘要： A method and apparatus for determining the possibility of pattern recognition of time series signal independent of a pattern recognition ratio is provided. The method for determining the possibility of pattern recognition of time series signal includes extracting a time forward feature and a time reversed feature from an input signal having a time series pattern, generating time forward alignment and time reversed alignment by using the time forward feature and the time reversed feature, comparing the time forward alignment with the time reversed alignment to compute a likelihood of pattern recognition, and determining that the input signal can be recognized if the likelihood is larger than a predetermined threshold value. The possibility of the pattern recognition of the whole system can be determined, independent of the pattern recognition capability of each of the pattern recognition models, by extracting the patterns from the time series signal by using the plurality of the pattern recognition models and then obtaining the likelihood between the patterns to compare the likelihood with the threshold value. In addition, the pattern recognition can be performed in the non-limited environment.