公开(公告)号：US20120156660A1

公开(公告)日：2012-06-21

申请号：US13327392

申请日：2011-12-15

申请人： Oh Woog KWON ,  Sung Kwon CHOI ,  Ki Young LEE ,  Yoon Hyung ROH ,  Young Kil KIM ,  Eun Jin PARK ,  Yun JIN ,  Chang Hyun KIM ,  Young Ae SEO ,  Seong YANG, II ,  Jin Xia HUANG ,  Jong Hun SHIN ,  Yun Keun LEE ,  Sang Kyu PARK

发明人： Oh Woog KWON ,  Sung Kwon CHOI ,  Ki Young LEE ,  Yoon Hyung ROH ,  Young Kil KIM ,  Eun Jin PARK ,  Yun JIN ,  Chang Hyun KIM ,  Young Ae SEO ,  Seong YANG, II ,  Jin Xia HUANG ,  Jong Hun SHIN ,  Yun Keun LEE ,  Sang Kyu PARK

IPC分类号： G09B19/04

CPC分类号： G09B19/06 ,  G09B5/06

摘要： A dialogue system include learning initiation unit which receives conversation education domain and target completion condition inconversation education domain and receives user's utterance, voice recognition unit which converts user's utterance into utterance text based on utterance information, language understanding unit which determines user's dialogue act based on converted utterance text and generates logical expression using slot expression corresponding to determined dialogue act and slot expression defined in conversation education domain, dialogue/progress management unit which determines utterance vertex with logical expression similar to that of utterance patterns of plurality of utterance vertices connected to system's final utterance vertex in dynamic dialogue graph and determines utterance vertices connected to determined utterance vertex as next utterance, system dialogue generation unit which retrieves utterance patterns connected to utterance vertex corresponding to determined next utterance and generates system's utterance sentence, and voice synthesizer which synthesizes system's utterance sentence into voice and outputs synthesized voice.

摘要翻译： 对话系统包括接收会话教育领域和目标完成条件不合理教育领域并接收用户话语的学习启动单元，基于话语信息将用户话语转换为话语文本的语音识别单元，基于转换的用户决定用户对话行为的语言理解单元 发音文本，并使用与会话教育领域中定义的确定对话行为和时隙表达式相对应的时隙表达式生成逻辑表达式，对话/进度管理单元，其确定具有与系统最终连接的多个话语顶点的话语模式相似的逻辑表达式的话语顶点 在动态对话图中发出话题顶点并确定连接到确定的话语顶点的话语顶点作为下一个发音，系统对话生成单元检索连接到对应于d的话语顶点的话语模式 产生下一个发音并产生系统的话语句子，以及将系统的话语句合成语音并输出合成语音的语音合成器。

公开(公告)号：US20090055177A1

公开(公告)日：2009-02-26

申请号：US12109932

申请日：2008-04-25

申请人： Byung Ok KANG ,  Ho Young JUNG ,  Yun Keun LEE

发明人： Byung Ok KANG ,  Ho Young JUNG ,  Yun Keun LEE

IPC分类号： G10L15/06

CPC分类号： G10L15/20

摘要： Provided are an apparatus and method for generating a noise adaptive acoustic model including a noise adaptive discriminative adaptation method. The method includes: generating a baseline model parameter from large-capacity speech training data including various noise environments; and receiving the generated baseline model parameter and applying a discriminative adaptation method to the generated results to generate an migrated acoustic model parameter suitable for an actually applied environment.

摘要翻译： 提供了一种用于生成包括噪声自适应识别适应方法的噪声自适应声学模型的装置和方法。 该方法包括：从包括各种噪声环境的大容量语音训练数据生成基线模型参数; 以及接收所生成的基线模型参数并将所述鉴别适应方法应用于所生成的结果以产生适用于实际应用环境的迁移的声学模型参数。

公开(公告)号：US20130112375A1

公开(公告)日：2013-05-09

申请号：US13303909

申请日：2011-11-23

申请人： Jee Hoon CHOI ,  Jung Hyun YOO ,  Byung Ho SUNG ,  Yun Keun LEE ,  Min Whan SEO

发明人： Jee Hoon CHOI ,  Jung Hyun YOO ,  Byung Ho SUNG ,  Yun Keun LEE ,  Min Whan SEO

IPC分类号： F28D15/04 ,  B21D53/02

CPC分类号： F28D15/043 ,  F28D15/046

摘要： An evaporator for a looped heat pipe (LHP) system, in which a working fluid circulates to cool heat generating electronic components that generate heat during operation, the evaporator including: a body comprising an inlet through which the working fluid enters and an outlet through which the working fluid is discharged; a sintered wick that is included in the body, wherein the sintered wick is formed by sintering a metal powder, and a plurality of pores are formed in the sintered wick; and an additional layer that is formed on a vaporization surface of the sintered wick where evaporation of the working fluid occurs, wherein a plurality of through holes are formed in the additional layer such that the working fluid changed into a vapor state passes through the additional layer after passing the sintered wick.

摘要翻译： 一种用于循环热管（LHP）系统的蒸发器，其中工作流体循环以冷却在运行期间产生热量的发热电子部件，所述蒸发器包括：主体，其包括工作流体进入的入口和出口， 工作流体排出; 包括在本体中的烧结芯，其中通过烧结金属粉末形成烧结芯，并且在烧结芯中形成多个孔; 以及形成在烧结芯的蒸发表面上的另外的层，其中发生工作流体的蒸发，其中在附加层中形成多个通孔，使得工作流体变为蒸汽状态通过附加层 通过烧结芯后。

公开(公告)号：US20100154015A1

公开(公告)日：2010-06-17

申请号：US12437261

申请日：2009-05-07

申请人： Byung Ok KANG ,  Eui Sok CHUNG ,  Ji Hyun WANG ,  Yun Keun LEE ,  Jeom Ja KANG ,  Jong Jin KIM ,  Ki-young PARK ,  Jeon Gue PARK ,  Sung Joo LEE ,  Hyung-Bae JEON ,  Ho-Young JUNG ,  Hoon CHUNG

发明人： Byung Ok KANG ,  Eui Sok CHUNG ,  Ji Hyun WANG ,  Yun Keun LEE ,  Jeom Ja KANG ,  Jong Jin KIM ,  Ki-young PARK ,  Jeon Gue PARK ,  Sung Joo LEE ,  Hyung-Bae JEON ,  Ho-Young JUNG ,  Hoon CHUNG

IPC分类号： H04N7/173 ,  G10L15/04 ,  G06F17/30

CPC分类号： H04N21/6125 ,  G10L15/07 ,  H04N21/42203 ,  H04N21/42204 ,  H04N21/4334 ,  H04N21/4394 ,  H04N21/472 ,  H04N21/8405

摘要： A metadata search apparatus using speech recognition includes a metadata processor for processing contents metadata to obtain allomorph of target vocabulary required for speech recognition and search; a metadata storage unit for storing the contents metadata; a speech recognizer for performing speech recognition on speech data uttered by a user by searching the allomorph of the target vocabulary; a query language processor for extracting a keyword from the vocabulary speech-recognized by the speech recognizer; and a search processor for searching the metadata storage unit to extract the contents metadata corresponding to the keyword. An IPTV receiving apparatus employs the metadata search apparatus to provide IPTV services through the functions of speech recognition.

摘要翻译： 使用语音识别的元数据搜索装置包括用于处理内容元数据以获得语音识别和搜索所需的目标词汇的变形的元数据处理器; 用于存储内容元数据的元数据存储单元; 用于通过搜索目标词汇的变体来对用户发出的语音数据执行语音识别的语音识别器; 查询语言处理器，用于从由语音识别器识别的词汇中提取关键词; 以及搜索处理器，用于搜索元数据存储单元以提取与该关键字对应的内容元数据。 IPTV接收装置利用元数据搜索装置通过语音识别的功能提供IPTV服务。

公开(公告)号：US20090076817A1

公开(公告)日：2009-03-19

申请号：US12047634

申请日：2008-03-13

申请人： Hyung Bae JEON ,  Kyu Woong HWANG ,  Seung Hi KIM ,  Hoon CHUNG ,  Jun PARK ,  Yun Keun LEE

发明人： Hyung Bae JEON ,  Kyu Woong HWANG ,  Seung Hi KIM ,  Hoon CHUNG ,  Jun PARK ,  Yun Keun LEE

IPC分类号： G10L15/00

CPC分类号： G10L15/187 ,  G10L2015/025

摘要： Provided are an apparatus and method for recognizing speech, in which reliability with respect to phoneme-recognized phoneme sequences is calculated and performance of speech recognition is enhanced using the calculated results. The method of recognizing speech includes the steps of: determining a boundary between phonemes included in character sequences that are phonetically input to detect each phoneme interval; calculating reliability according to a probability that a phoneme indicated by the detected phoneme interval corresponds to a phoneme included in a predefined phoneme model; calculating a phoneme alignment cost with respect to the character sequences based on the calculated reliability and a pre-trained and stored phoneme recognition probability distribution; and performing phoneme alignment based on the calculated phoneme alignment cost to perform speech recognition on the input character sequences. As a result, reliability with respect to the phoneme-recognized phoneme sequences can be calculated, and the performance of speech recognition can be enhanced using the calculated results.

摘要翻译： 提供了一种用于识别语音的装置和方法，其中计算相对于音素识别的音素序列的可靠性，并且使用所计算的结果来增强语音识别的性能。 识别语音的方法包括以下步骤：确定语音输入的字符序列中包含的音素之间的边界，以检测每个音素间隔; 根据由检测到的音素间隔指示的音素对应于包含在预定音素模型中的音素的概率来计算可靠性; 基于计算的可靠性和预先训练和存储的音素识别概率分布来计算相对于字符序列的音素对准成本; 并且基于计算的音素对准成本执行音素对准以对输入的字符序列执行语音识别。 结果，可以计算相对于音素识别的音素序列的可靠性，并且可以使用计算结果来增强语音识别的性能。