专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明申请

US20100158271A1 METHOD FOR SEPARATING SOURCE SIGNALS AND APPARATUS THEREOF 有权
标题翻译：分离信号信号的方法及其设备
公开(公告)号：US20100158271A1
公开(公告)日：2010-06-24
申请号：US12488215
申请日：2009-06-19
申请人： Ki-young Park , Ho-Young Jung , Yun Keun Lee , Jeon Gue Park , Jeom Ja Kang , Hoon Chung , Sung Joo Lee , Byung Ok Kang , Ji Hyun Wang , Eui Sok Chung , Hyung-Bae Jeon , Jong Jin Kim
发明人： Ki-young Park , Ho-Young Jung , Yun Keun Lee , Jeon Gue Park , Jeom Ja Kang , Hoon Chung , Sung Joo Lee , Byung Ok Kang , Ji Hyun Wang , Eui Sok Chung , Hyung-Bae Jeon , Jong Jin Kim
IPC分类号： H04B15/00
CPC分类号： H04R3/005 , H04R27/00 , H04R2430/03
摘要： A method for separating a sound source from a mixed signal, includes Transforming a mixed signal to channel signals in frequency domain; and grouping several frequency bands for each channel signal to form frequency clusters. Further, the method for separating the sound source from the mixed signal includes separating the frequency clusters by applying a blind source separation to signals in frequency domain for each frequency cluster; and integrating the spectrums of the separated signal to restore the sound source in a time domain wherein each of the separated signals expresses one sound source.
摘要翻译：一种用于从混合信号中分离声源的方法，包括：将混合信号转换成频域中的信道信号; 并且为每个信道信号分组几个频带以形成频率簇。此外，用于从混合信号中分离声源的方法包括通过对每个频率簇的频域中的信号应用盲源分离来分离频率簇; 并且对分离信号的频谱进行积分，以在时域中恢复声源，其中每个分离的信号表示一个声源。

12. 发明申请

US20090157399A1 APPARATUS AND METHOD FOR EVALUATING PERFORMANCE OF SPEECH RECOGNITION 有权
标题翻译：评估语音识别性能的装置和方法
公开(公告)号：US20090157399A1
公开(公告)日：2009-06-18
申请号：US12336208
申请日：2008-12-16
申请人： Hoon-Young CHO , Yunkeun Lee , Ho-Young Jung , Byung Ok Kang , Jeom Ja Kang , Kap Kee Kim , Sung Joo Lee , Hoon Chung , Jeon Gue Park , Hyung-Bae Jeon
发明人： Hoon-Young CHO , Yunkeun Lee , Ho-Young Jung , Byung Ok Kang , Jeom Ja Kang , Kap Kee Kim , Sung Joo Lee , Hoon Chung , Jeon Gue Park , Hyung-Bae Jeon
IPC分类号： G10L15/00
CPC分类号： G10L15/01
摘要： An apparatus for evaluating the performance of speech recognition includes a speech database for storing N-number of test speech signals for evaluation. A speech recognizer is located in an actual environment and executes the speech recognition of the test speech signals reproduced using a loud speaker from the speech database in the actual environment to produce speech recognition results. A performance evaluation module evaluates the performance of the speech recognition by comparing correct recognition results answers with the speech recognition results.
摘要翻译：用于评估语音识别性能的装置包括用于存储用于评估的N个测试语音信号的语音数据库。语音识别器位于实际环境中，并且在实际环境中执行使用来自语音数据库的扬声器再现的测试语音信号的语音识别，以产生语音识别结果。性能评估模块通过将正确的识别结果答案与语音识别结果进行比较来评估语音识别的性能。

13. 发明授权

US08249867B2 Microphone array based speech recognition system and target speech extracting method of the system 失效
标题翻译：基于麦克风阵列的语音识别系统和系统的目标语音提取方法
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。

14. 发明申请

US20090150146A1 MICROPHONE ARRAY BASED SPEECH RECOGNITION SYSTEM AND TARGET SPEECH EXTRACTING METHOD OF THE SYSTEM 失效
标题翻译：基于麦克风阵列的语音识别系统和目标语音提取方法
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。

15. 发明授权

US08666739B2 Method for estimating language model weight and system for the same 失效
标题翻译：用于估计语言模型权重和系统的方法
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。

16. 发明申请

US20120150539A1 METHOD FOR ESTIMATING LANGUAGE MODEL WEIGHT AND SYSTEM FOR THE SAME 失效
标题翻译：用于估算语言模型重量和系统的方法
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。

17. 发明申请

US20100161416A1 METHOD OF PROVIDING TARGETED ADVERTISEMENTS 审中-公开
标题翻译：提供目标广告的方法
公开(公告)号：US20100161416A1
公开(公告)日：2010-06-24
申请号：US12491788
申请日：2009-06-25
申请人： Euisok Chung , Ji Hyun Wang , Byung Ok Kang , Jeon Gue Park , Yunkeun Lee , Hyo-Jung Oh , Chang Ki Lee , Chung Hee Lee , Myung Gil Jang
发明人： Euisok Chung , Ji Hyun Wang , Byung Ok Kang , Jeon Gue Park , Yunkeun Lee , Hyo-Jung Oh , Chang Ki Lee , Chung Hee Lee , Myung Gil Jang
IPC分类号： G06Q30/00 , G06F17/30
CPC分类号： G06Q30/02 , G06Q30/0255
摘要： A method of providing targeted advertisements, includes: generating an advertisement search result using a search query based on a user query or a recommended query; generating an advertisement search result on the basis of a user profile; integrating the advertisement search result generated on the basis of the user profile with the advertisement search result generated by using the search query; and presenting a recommended advertisement list on the basis of the integrated advertisement search result and advertisement information exposed to a user.
摘要翻译：提供目标广告的方法包括：使用基于用户查询或推荐查询的搜索查询生成广告搜索结果; 基于用户简档生成广告搜索结果; 将基于用户简档生成的广告搜索结果与通过使用搜索查询生成的广告搜索结果进行整合; 并根据暴露给用户的综合广告搜索结果和广告信息呈现推荐广告列表。

18. 发明申请

US20110060592A1 IPTV SYSTEM AND SERVICE METHOD USING VOICE INTERFACE 审中-公开
标题翻译：使用语音接口的IPTV系统和服务方法
公开(公告)号：US20110060592A1
公开(公告)日：2011-03-10
申请号：US12784439
申请日：2010-05-20
申请人： Byung Ok Kang , Eui Sok Chung , Ji Hyun Wang , Mi Ran Choi
发明人： Byung Ok Kang , Eui Sok Chung , Ji Hyun Wang , Mi Ran Choi
IPC分类号： G10L21/00 , H04N7/173
CPC分类号： H04N21/440236 , G10L21/0216 , H04N21/42684 , H04N21/4621
摘要： Provided is an IPTV system using voice interface which includes a voice input device, a voice processing device, a query processing and content search device, and a content providing device. The voice processing device performs voice recognition to convert voice into a text. The voice processing device includes a voice preprocessing unit, a sound model database, a language model database, and a decoder. The voice preprocessing unit performs preprocessing which includes improving the quality of sound or removing noise for the received voice, and extracts a feature vector. The decoder converts the feature vector into a text by using a sound model and a language model. Moreover, the voice processing device stores the profile and preference of a user to provide personalized service. The result of voice recognition is updated in a sound model database and a user profile database each time service for a user is provided, the performance of voice recognition and the performance of personalized service can continuously be improved.
摘要翻译：提供了一种使用语音接口的IPTV系统，其包括语音输入设备，语音处理设备，查询处理和内容搜索设备以及内容提供设备。语音处理装置执行语音识别以将语音转换为文本。语音处理装置包括语音预处理单元，声音模型数据库，语言模型数据库和解码器。语音预处理单元执行预处理，其包括提高声音的质量或去除接收到的语音的噪声，并提取特征向量。解码器通过使用声音模型和语言模型将特征向量转换为文本。此外，语音处理装置存储用户的简档和偏好以提供个性化服务。语音识别的结果在声音模型数据库和用户简档数据库中被更新，每次为用户提供服务时，可以不断提高语音识别的性能和个性化服务的性能。

19. 发明授权

US08346545B2 Model-based distortion compensating noise reduction apparatus and method for speech recognition 有权
标题翻译：基于模型的失真补偿降噪装置和语音识别方法
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。

20. 发明申请

US20110077939A1 MODEL-BASED DISTORTION COMPENSATING NOISE REDUCTION APPARATUS AND METHOD FOR SPEECH RECOGNITION 有权
标题翻译：基于模型的失真补偿噪声减少装置和语音识别方法
公开(公告)号：US20110077939A1
公开(公告)日：2011-03-31
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： G10L21/02
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。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式