公开(公告)号：US20090150146A1

公开(公告)日：2009-06-11

申请号：US12242819

申请日：2008-09-30

申请人： Hoon Young CHO ,  Yun Keun Lee ,  Jeom Ja Kang ,  Byung Ok Kang ,  Kap Kee Kim ,  Sung Joo Lee ,  Ho Young Jung ,  Hoon Chung ,  Jeon Gue Park ,  Hyung Bae Jeon

发明人： Hoon Young CHO ,  Yun Keun Lee ,  Jeom Ja Kang ,  Byung Ok Kang ,  Kap Kee Kim ,  Sung Joo Lee ,  Ho Young Jung ,  Hoon Chung ,  Jeon Gue Park ,  Hyung Bae Jeon

IPC分类号： G10L15/20

CPC分类号： G10L15/20 ,  G10L21/0272 ,  G10L2021/02166

摘要： A microphone-array-based speech recognition system using a blind source separation (BBS) and a target speech extraction method in the system are provided. The speech recognition system performs an independent component analysis (ICA) to separate mixed signals input through a plurality of microphone into sound-source signals, extracts one target speech spoken for speech recognition from the separated sound-source signals by using a Gaussian mixture model (GMM) or a hidden Markov Model (HMM), and automatically recognizes a desired speech from the extracted target speech. Accordingly, it is possible to obtain a high speech recognition rate even in a noise environment.

摘要翻译： 提供了一种基于麦克风阵列的语音识别系统，该系统使用盲源分离（BBS）和目标语音提取方法。 语音识别系统执行独立分量分析（ICA）以将通过多个麦克风输入的混合信号分离成声源信号，通过使用高斯混合模型从分离的声源信号中提取用于语音识别的一个目标语音（ GMM）或隐马尔可夫模型（HMM），并且从所提取的目标语音中自动识别期望的语音。 因此，即使在噪声环境中也可以获得高的语音识别率。

公开(公告)号：US08249867B2

公开(公告)日：2012-08-21

申请号：US12242819

申请日：2008-09-30

申请人： Hoon Young Cho ,  Yun Keun Lee ,  Jeom Ja Kang ,  Byung Ok Kang ,  Kap Kee Kim ,  Sung Joo Lee ,  Ho Young Jung ,  Hoon Chung ,  Jeon Gue Park ,  Hyung Bae Jeon

发明人： Hoon Young Cho ,  Yun Keun Lee ,  Jeom Ja Kang ,  Byung Ok Kang ,  Kap Kee Kim ,  Sung Joo Lee ,  Ho Young Jung ,  Hoon Chung ,  Jeon Gue Park ,  Hyung Bae Jeon

IPC分类号： G10L15/20

CPC分类号： G10L15/20 ,  G10L21/0272 ,  G10L2021/02166

摘要： A microphone-array-based speech recognition system using a blind source separation (BBS) and a target speech extraction method in the system are provided. The speech recognition system performs an independent component analysis (ICA) to separate mixed signals input through a plurality of microphone into sound-source signals, extracts one target speech spoken for speech recognition from the separated sound-source signals by using a Gaussian mixture model (GMM) or a hidden Markov Model (HMM), and automatically recognizes a desired speech from the extracted target speech. Accordingly, it is possible to obtain a high speech recognition rate even in a noise environment.

摘要翻译： 提供了一种基于麦克风阵列的语音识别系统，该系统使用盲源分离（BBS）和目标语音提取方法。 语音识别系统执行独立分量分析（ICA）以将通过多个麦克风输入的混合信号分离成声源信号，通过使用高斯混合模型从分离的声源信号中提取用于语音识别的一个目标语音（ GMM）或隐马尔可夫模型（HMM），并且从所提取的目标语音中自动识别期望的语音。 因此，即使在噪声环境中也可以获得高的语音识别率。

公开(公告)号：US08666739B2

公开(公告)日：2014-03-04

申请号：US13324414

申请日：2011-12-13

申请人： Hyung Bae Jeon ,  Yun Keun Lee ,  Eui Sok Chung ,  Jong Jin Kim ,  Hoon Chung ,  Jeon Gue Park ,  Ho Young Jung ,  Byung Ok Kang ,  Ki Young Park ,  Sung Joo Lee ,  Jeom Ja Kang ,  Hwa Jeon Song

发明人： Hyung Bae Jeon ,  Yun Keun Lee ,  Eui Sok Chung ,  Jong Jin Kim ,  Hoon Chung ,  Jeon Gue Park ,  Ho Young Jung ,  Byung Ok Kang ,  Ki Young Park ,  Sung Joo Lee ,  Jeom Ja Kang ,  Hwa Jeon Song

IPC分类号： G10L15/00

CPC分类号： G10L15/065 ,  G10L15/187

摘要： Method of the present invention may include receiving speech feature vector converted from speech signal, performing first search by applying first language model to the received speech feature vector, and outputting word lattice and first acoustic score of the word lattice as continuous speech recognition result, outputting second acoustic score as phoneme recognition result by applying an acoustic model to the speech feature vector, comparing the first acoustic score of the continuous speech recognition result with the second acoustic score of the phoneme recognition result, outputting first language model weight when the first coustic score of the continuous speech recognition result is better than the second acoustic score of the phoneme recognition result and performing a second search by applying a second language model weight, which is the same as the output first language model, to the word lattice.

摘要翻译： 本发明的方法可以包括接收从语音信号转换的语音特征向量，通过对接收的语音特征向量应用第一语言模型来执行第一搜索，并且将字格的字格和第一声分数输出为连续语音识别结果，输出 第二声学分数作为音素识别结果，通过对语音特征向量应用声学模型，将连续语音识别结果的第一声学分数与音素识别结果的第二声学分数进行比较，当第一个coustic分数输出第一语言模型权重时， 连续语音识别结果比音素识别结果的第二声分数更好，并且通过将与输出第一语言模型相同的第二语言模型权重应用于单词格来进行第二搜索。

公开(公告)号：US20120150539A1

公开(公告)日：2012-06-14

申请号：US13324414

申请日：2011-12-13

申请人： Hyung Bae Jeon ,  Yun Keun Lee ,  Eui Sok Chung ,  Jong Jin Kim ,  Hoon Chung ,  Jeon Gue Park ,  Ho Young Jung ,  Byung Ok Kang ,  Ki Young Park ,  Sung Joo Lee ,  Jeom Ja Kang ,  Hwa Jeon Song

发明人： Hyung Bae Jeon ,  Yun Keun Lee ,  Eui Sok Chung ,  Jong Jin Kim ,  Hoon Chung ,  Jeon Gue Park ,  Ho Young Jung ,  Byung Ok Kang ,  Ki Young Park ,  Sung Joo Lee ,  Jeom Ja Kang ,  Hwa Jeon Song

IPC分类号： G10L15/00

CPC分类号： G10L15/065 ,  G10L15/187

摘要： Method of the present invention may include receiving speech feature vector converted from speech signal, performing first search by applying first language model to the received speech feature vector, and outputting word lattice and first acoustic score of the word lattice as continuous speech recognition result, outputting second acoustic score as phoneme recognition result by applying an acoustic model to the speech feature vector, comparing the first acoustic score of the continuous speech recognition result with the second acoustic score of the phoneme recognition result, outputting first language model weight when the first coustic score of the continuous speech recognition result is better than the second acoustic score of the phoneme recognition result and performing a second search by applying a second language model weight, which is the same as the output first language model, to the word lattice.

摘要翻译： 本发明的方法可以包括接收从语音信号转换的语音特征向量，通过对接收的语音特征向量应用第一语言模型来执行第一搜索，并且将字格的字格和第一声分数输出为连续语音识别结果，输出 第二声学分数作为音素识别结果，通过对语音特征向量应用声学模型，将连续语音识别结果的第一声学分数与音素识别结果的第二声学分数进行比较，当第一个coustic分数输出第一语言模型权重时， 连续语音识别结果比音素识别结果的第二声分数更好，并且通过将与输出第一语言模型相同的第二语言模型权重应用于单词格来进行第二搜索。

公开(公告)号：US20130013297A1

公开(公告)日：2013-01-10

申请号：US13542118

申请日：2012-07-05

申请人： Hwa Jeon SONG ,  YunKeun Lee ,  Jeon Gue Park ,  Jong Jin Kim ,  Ki-Young Park ,  Hoon Chung ,  Hyung-Bae Jeon ,  Ho Young Jung ,  Euisok Chung ,  Jeom Ja Kang ,  Byung Ok Kang ,  Sang Kyu Park ,  Sung Joo Lee ,  Yoo Rhee Oh

发明人： Hwa Jeon SONG ,  YunKeun Lee ,  Jeon Gue Park ,  Jong Jin Kim ,  Ki-Young Park ,  Hoon Chung ,  Hyung-Bae Jeon ,  Ho Young Jung ,  Euisok Chung ,  Jeom Ja Kang ,  Byung Ok Kang ,  Sang Kyu Park ,  Sung Joo Lee ,  Yoo Rhee Oh

IPC分类号： G10L15/00

CPC分类号： H04M1/72552 ,  G10L15/083 ,  G10L15/30 ,  H04M2250/74 ,  H04W4/12

摘要： A message service method using speech recognition includes a message server recognizing a speech transmitted from a transmission terminal, generating and transmitting a recognition result of the speech and N-best results based on a confusion network to the transmission terminal; if a message is selected through the recognition result and the N-best results and an evaluation result according to accuracy of the message are decided, the transmission terminal transmitting the message and the evaluation result to a reception terminal; and the reception terminal displaying the message and the evaluation result.

摘要翻译： 使用语音识别的消息服务方法包括识别从发送终端发送的语音的消息服务器，基于混淆网络生成并发送语音的识别结果和N个最佳结果到发送终端; 如果通过识别结果选择了消息，并且确定了根据消息精度的N最佳结果和评估结果，则发送终端将消息和评估结果发送到接收终端; 接收终端显示消息和评估结果。

公开(公告)号：US08234112B2

公开(公告)日：2012-07-31

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：US08346545B2

公开(公告)日：2013-01-01

申请号：US12626548

申请日：2009-11-25

申请人： Ho Young Jung ,  Byung Ok Kang

发明人： Ho Young Jung ,  Byung Ok Kang

IPC分类号： G10L15/20

CPC分类号： G10L21/0208 ,  G10L15/20 ,  G10L21/0216 ,  G10L21/0232 ,  G10L25/78

摘要： A model-based distortion compensating noise reduction apparatus for speech recognition, includes: a speech absence probability calculator for calculating the probability distribution for absence and existence of a speech using the sound absence and existence information for the frames; a noise estimation updater for estimating a more accurate noise component by updating the variance of the clean speech and noise for each frame; and a speech absence probability-based noise filter for outputting a first clean speech through the speech absence probability transmitted from the speech absence probability calculator and a first noise filter. Further, the model-based distortion compensating noise reduction apparatus includes a post probability calculator for calculating post probabilities for mixtures using a GMM containing a clean speech in the first clean speech; and a final filter designer for forming a second noise filter and outputting an improved final clean speech signal using the second noise filter.

摘要翻译： 一种用于语音识别的基于模型的失真补偿降噪装置，包括：语音缺失概率计算器，用于使用所述帧的声音缺失和存在信息来计算语音的不存在和存在的概率分布; 噪声估计更新器，用于通过更新每个帧的干净语音和噪声的方差来估计更精确的噪声分量; 以及基于语音缺失概率的噪声滤波器，用于通过从语音不存在概率计算器发送的语音缺失概率和第一噪声滤波器输出第一干净语音。 此外，基于模型的失真补偿降噪装置包括：后概率计算器，用于使用在第一清洁语音中包含干净语音的GMM来计算混合的后概率; 以及最终滤波器设计器，用于形成第二噪声滤波器并使用第二噪声滤波器输出改进的最终清洁语音信号。

公开(公告)号：US08094162B2

公开(公告)日：2012-01-10

申请号：US12183422

申请日：2008-07-31

申请人： Ho Young Jung

发明人： Ho Young Jung

IPC分类号： G09G5/00 ,  G09G5/02 ,  G09G5/10 ,  H04N5/46 ,  G03F3/08 ,  G06K9/00 ,  G06K9/40 ,  H04N5/58 ,  H04N9/64

CPC分类号： G09G3/2003 ,  G09G5/02 ,  G09G2320/0242 ,  G09G2320/066 ,  G09G2320/0666 ,  G09G2320/0673 ,  H04N1/6011 ,  H04N1/628

摘要： Method and device are disclosed for adjusting a preferred color which enables a user to set a preferred color conveniently and a liquid crystal display device with the same. The method and device for adjusting a preferred color includes displaying a menu selection image and setting a variety of optional information, making successive display of at least one selection image which shows a plurality of selection images having information on preferred colors different from one another to set information on the preferred colors in succession, and storing the information on the preferred colors set and generating an image having preferred colors adjusted according to the information on the preferred colors stored.

摘要翻译： 公开了用于调节优选颜色的方法和装置，其使得用户能够方便地设置优选的颜色和具有该颜色的液晶显示装置。 用于调整优选颜色的方法和装置包括显示菜单选择图像和设置各种可选信息，使连续显示至少一个选择图像，其显示具有彼此不同的优选颜色信息的多个选择图像，以设置 关于优选颜色的信息，并且存储关于所设置的优选颜色的信息，并且生成根据关于所存储的优选颜色的信息来调整的具有优选颜色的图像。

公开(公告)号：US20090280379A1

公开(公告)日：2009-11-12

申请号：US12288301

申请日：2008-10-17

申请人： Ki Yun Cho ,  Jung Ki Park ,  Ho Young Jung ,  Kyung A. Sung

发明人： Ki Yun Cho ,  Jung Ki Park ,  Ho Young Jung ,  Kyung A. Sung

IPC分类号： H01M8/00

CPC分类号： H01M4/928 ,  H01M4/8668 ,  H01M4/8828 ,  H01M4/90 ,  H01M4/92 ,  H01M8/1007

摘要： The present invention relates to an electrode binder solution composition for a polymer electrolyte fuel cell comprising a mixture of a solvent and a nonsolvent. The electrode binder solution composition can significantly improve electrode activity by maximizing formation of a three-phase interface of catalyst, binder and fuel at the electrode catalytic layer of the polymer electrolyte fuel cell. The present invention relates to a preparation method of an electrode binder solution for a polymer electrolyte fuel cell, the electrode binder solution for a polymer electrolyte fuel cell comprising a sulfonated proton exchange hydrocarbon-based polymer and a mixture of a solvent and a nonsolvent. The present invention also relates to a preparation method of an electrode catalyst slurry comprising the steps of: mixing an electrode binder solution composition for a polymer electrolyte fuel cell with a platinum catalyst and drying the mixture; and heat-treating the dried mixture to maximize interface between the electrode binder and the catalyst.

摘要翻译： 本发明涉及一种包含溶剂和非溶剂的混合物的固体高分子型燃料电池用电极粘合剂溶液组合物。 电极粘合剂溶液组合物可以通过在聚合物电解质燃料电池的电极催化剂层处最大化催化剂，粘合剂和燃料的三相界面的形成来显着改善电极活性。 本发明涉及一种聚合物电解质燃料电池用电极粘合剂溶液的制备方法，包含磺化质子交换烃类聚合物和溶剂与非溶剂的混合物的固体高分子型燃料电池用电极粘合剂溶液。 本发明还涉及电极催化剂浆料的制备方法，包括以下步骤：将聚合物电解质燃料电池用电极粘合剂溶液组合物与铂催化剂混合并干燥该混合物; 并对干燥的混合物进行热处理以最大化电极粘合剂和催化剂之间的界面。

公开(公告)号：US20130035938A1

公开(公告)日：2013-02-07

申请号：US13540047

申请日：2012-07-02

申请人： Ho Young Jung

发明人： Ho Young Jung

IPC分类号： G10L15/04

CPC分类号： G10L15/08 ,  G10L15/05 ,  G10L2015/088

摘要： The present invention includes a hierarchical search process. The hierarchical search process includes three steps. In a first step, a word boundary is determined using a recognition method of determining a following word dependent on a preceding word, and a word boundary detector. In a second step, word unit based recognition is performed in each area by dividing an input voice into a plurality of areas based on the determined word boundary. Finally, in a third step, a language model is applied to induce an optimal sentence recognition result with respect to a candidate word that is determined for each area. The present invention may improve the voice recognition performance, and particularly, the sentence unit based consecutive voice recognition performance.

摘要翻译： 本发明包括层次搜索过程。 分层搜索过程包括三个步骤。 在第一步骤中，使用确定依赖于前一个字的后续字的识别方法和字边界检测器来确定字边界。 在第二步骤中，通过基于确定的字边界将输入语音划分成多个区域，在每个区域中执行基于单元的识别。 最后，在第三步骤中，应用语言模型以针对为每个区域确定的候选词引发最佳句子识别结果。 本发明可以提高语音识别性能，特别是基于句子单元的连续语音识别性能。