专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09009035B2 Method for processing multichannel acoustic signal, system therefor, and program 有权
标题翻译：多通道声信号处理方法，系统及程序
公开(公告)号：US09009035B2
公开(公告)日：2015-04-14
申请号：US13201354
申请日：2010-02-08
申请人： Masanori Tsujikawa , Ryosuke Isotani , Tadashi Emori , Yoshifumi Onishi
发明人： Masanori Tsujikawa , Ryosuke Isotani , Tadashi Emori , Yoshifumi Onishi
IPC分类号： G10L21/02 , H04B15/00 , G10L21/0272
CPC分类号： G10L21/0272
摘要： A method for processing multichannel acoustic signals which processes input signals of a plurality of channels including the voices of a plurality of speaking persons. The method is characterized by detecting the voice section of each speaking person or each channel, detecting overlapped sections wherein the detected voice sections are common between channels, determining a channel to be subjected to crosstalk removal and the section thereof by use of at least voice sections not including the detected overlapped sections, and removing crosstalk in the sections of the channel to be subjected to the crosstalk removal.
摘要翻译：一种用于处理多声道声信号的方法，其处理包括多个说话人的声音的多个声道的输入信号。该方法的特征在于检测每个说话人或每个频道的语音部分，检测重叠部分，其中检测到的语音部分在频道之间是公共的，通过使用至少语音部分确定要进行串扰消除的频道及其部分不包括检测到的重叠部分，并且消除要进行串扰消除的信道的部分中的串扰。

2. 发明授权

US08639507B2 Voice recognition system, voice recognition method, and program for voice recognition 有权
标题翻译：语音识别系统，语音识别方法和语音识别程序
公开(公告)号：US08639507B2
公开(公告)日：2014-01-28
申请号：US12808393
申请日：2008-12-22
申请人： Fumihiro Adachi , Ryosuke Isotani , Ken Hanazawa
发明人： Fumihiro Adachi , Ryosuke Isotani , Ken Hanazawa
IPC分类号： G10L15/00
CPC分类号： G10L15/08
摘要： The present invention enables the recognition process at high speed even when a lot of garbage is included in the grammar. The first voice recognition processing unit generates a recognition hypothesis graph which indicates a structure of hypothesis that is derived according to a first grammar together with a score associated with respective connections of a recognition unit by executing a voice recognition process based on the first grammar to a voice feature amount of input voice, and the second voice recognition processing unit outputs the recognition result from a total score of a hypothesis which is derived according to a second grammar after executing a voice recognition process according to the second grammar that is specified to accept a section other than keywords in input voice as the garbage section to a voice feature amount of input voice, and the second voice recognition processing unit acquires the structure and the score of the garbage section from the recognition hypothesis graph.
摘要翻译：本发明即使在语法中包含大量垃圾的情况下也能够高速识别处理。第一语音识别处理单元生成识别假设图，该识别假设图表示根据第一语法导出的假设的结构以及与基于第一语法的语音识别处理相关联的与识别单元的各个连接相关联的得分声音特征量的输入声音，并且第二语音识别处理单元根据指定为接受一个声音特征量的第二语法执行语音识别处理之后从根据第二语法导出的假设的总分输出识别结果输入语音中的关键字以外的区段作为输入语音的语音特征量的垃圾部分，第二语音识别处理单元从识别假设图获取垃圾部分的结构和得分。

3. 发明申请

US20110191100A1 LANGUAGE MODEL SCORE LOOK-AHEAD VALUE IMPARTING DEVICE, LANGUAGE MODEL SCORE LOOK-AHEAD VALUE IMPARTING METHOD, AND PROGRAM STORAGE MEDIUM 有权
标题翻译：语言型号分数看法 - 前端值转换设备，语言模型等级前景值转换方法和程序存储介质
公开(公告)号：US20110191100A1
公开(公告)日：2011-08-04
申请号：US12992760
申请日：2009-03-27
申请人： Koji Okabe , Ryosuke Isotani , Kiyoshi Yamabana , Ken Hanazawa
发明人： Koji Okabe , Ryosuke Isotani , Kiyoshi Yamabana , Ken Hanazawa
IPC分类号： G06F17/21
CPC分类号： G10L15/187
摘要： A speech recognition apparatus that performs frame synchronous beam search by using a language model score look-ahead value prevents the pruning of a correct answer hypothesis while suppressing an increase in the number of hypotheses. A language model score look-ahead value imparting device 108 is provided with a word dictionary 203 that defines a phoneme string of a word, a language model 202 that imparts a score of appearance easiness of a word, and a smoothing language model score look-ahead value calculation means 201. The smoothing language model score look-ahead value calculation means 201 obtains a language model score look-ahead value at each phoneme in the word from the phoneme string of the word defined by the word dictionary 203 and the language model score defined by the language model 202 so that the language model score look-ahead values are prevented from concentrating on the beginning of the word.
摘要翻译：通过使用语言模型评分预测值执行帧同步波束搜索的语音识别装置防止修正正确的答案假设，同时抑制假设数量的增加。语言模型得分预先值赋予装置108具有定义单词的音素串的单词字典203，赋予单词外观容易度的语言模型202以及平滑语言模型分数查找表，平滑语言模型分数预测值计算装置201从单词字典203定义的单词的音素串和语言模型中获得单词中每个音素处的语言模型分数预先值由语言模型202定义的分数，使得语言模型得分先验值被阻止集中在单词的开头。

4. 发明授权

US08954323B2 Method for processing multichannel acoustic signal, system thereof, and program 有权
标题翻译：多通道声信号处理方法，系统及程序
公开(公告)号：US08954323B2
公开(公告)日：2015-02-10
申请号：US13201389
申请日：2010-02-08
申请人： Masanori Tsujikawa , Tadashi Emori , Yoshifumi Onishi , Ryosuke Isotani
发明人： Masanori Tsujikawa , Tadashi Emori , Yoshifumi Onishi , Ryosuke Isotani
IPC分类号： G10L21/02 , G10L15/20 , G10L21/0272
CPC分类号： G10L21/0272
摘要： A method for processing multichannel acoustic signals, whereby input signals of a plurality of channels including the voices of a plurality of speaking persons are processed. The method is characterized by comprising: calculating the first feature quantity of the input signals of the multichannels for each channel; calculating similarity of the first feature quantity of each channel between the channels; selecting channels having high similarity; separating signals using the input signals of the selected channels; inputting the input signals of the channels having low similarity and the signals after the signal separation; and detecting a voice section of each speaking person or each channel.
摘要翻译：一种用于处理多声道声信号的方法，由此处理包括多个说话人的声音的多个声道的输入信号。该方法的特征在于包括：计算每个信道的多信道的输入信号的第一特征量; 计算通道之间每个通道的第一特征量的相似度; 选择具有高相似性的信道; 使用所选择的信道的输入信号分离信号; 输入具有低相似性的信道的输入信号和信号分离之后的信号; 并且检测每个说话人或每个频道的语音部分。

5. 发明申请

US20120029915A1 METHOD FOR PROCESSING MULTICHANNEL ACOUSTIC SIGNAL, SYSTEM THEREFOR, AND PROGRAM 有权
标题翻译：用于处理多通道声学信号的方法，系统及其程序
公开(公告)号：US20120029915A1
公开(公告)日：2012-02-02
申请号：US13201354
申请日：2010-02-08
申请人： Masanori Tsujikawa , Ryosuke Isotani , Tadashi Emori , Yoshifumi Onishi
发明人： Masanori Tsujikawa , Ryosuke Isotani , Tadashi Emori , Yoshifumi Onishi
IPC分类号： G10L21/02
CPC分类号： G10L21/0272
摘要： A method for processing multichannel acoustic signals which processes input signals of a plurality of channels including the voices of a plurality of speaking persons. The method is characterized by detecting the voice section of each speaking person or each channel, detecting overlapped sections wherein the detected voice sections are common between channels, determining a channel to be subjected to crosstalk removal and the section thereof by use of at least voice sections not including the detected overlapped sections, and removing crosstalk in the sections of the channel to be subjected to the crosstalk removal.
摘要翻译：一种用于处理多声道声信号的方法，其处理包括多个说话人的声音的多个声道的输入信号。该方法的特征在于检测每个说话人或每个频道的语音部分，检测重叠部分，其中检测到的语音部分在频道之间是公共的，通过使用至少语音部分确定要进行串扰消除的频道及其部分不包括检测到的重叠部分，并且消除要进行串扰消除的信道的部分中的串扰。

6. 发明申请

US20110131043A1 VOICE RECOGNITION SYSTEM, VOICE RECOGNITION METHOD, AND PROGRAM FOR VOICE RECOGNITION 有权
标题翻译：语音识别系统，语音识别方法和语音识别程序
公开(公告)号：US20110131043A1
公开(公告)日：2011-06-02
申请号：US12808393
申请日：2008-12-22
申请人： Fumihiro Adachi , Ryosuke Isotani , Ken Hanazawa
发明人： Fumihiro Adachi , Ryosuke Isotani , Ken Hanazawa
IPC分类号： G10L15/00
CPC分类号： G10L15/08
摘要： The present invention enables the recognition process at high speed even when a lot of garbage is included in the grammar. The first voice recognition processing unit generates a recognition hypothesis graph which indicates a structure of hypothesis that is derived according to a first grammar together with a score associated with respective connections of a recognition unit by executing a voice recognition process based on the first grammar to a voice feature amount of input voice, and the second voice recognition processing unit outputs the recognition result from a total score of a hypothesis which is derived according to a second grammar after executing a voice recognition process according to the second grammar that is specified to accept a section other than keywords in input voice as the garbage section to a voice feature amount of input voice, and the second voice recognition processing unit acquires the structure and the score of the garbage section from the recognition hypothesis graph.
摘要翻译：本发明即使在语法中包含大量垃圾的情况下也能够高速识别处理。第一语音识别处理单元生成识别假设图，该识别假设图表示根据第一语法导出的假设的结构以及与基于第一语法的语音识别处理相关联的与识别单元的各个连接相关联的得分声音特征量的输入声音，并且第二语音识别处理单元根据指定为接受一个声音特征量的第二语法执行语音识别处理之后从根据第二语法导出的假设的总分输出识别结果输入语音中的关键字以外的区段作为输入语音的语音特征量的垃圾部分，第二语音识别处理单元从识别假设图获取垃圾部分的结构和得分。

7. 发明授权

US08682668B2 Language model score look-ahead value imparting device, language model score look-ahead value imparting method, and program storage medium 有权
标题翻译：语言模型评分预测值赋予装置，语言模型评分预先值赋予方法和程序存储介质
公开(公告)号：US08682668B2
公开(公告)日：2014-03-25
申请号：US12992760
申请日：2009-03-27
申请人： Koji Okabe , Ryosuke Isotani , Kiyoshi Yamabana , Ken Hanazawa
发明人： Koji Okabe , Ryosuke Isotani , Kiyoshi Yamabana , Ken Hanazawa
IPC分类号： G10L15/02 , G10L15/04 , G10L15/06
CPC分类号： G10L15/187
摘要： A speech recognition apparatus that performs frame synchronous beam search by using a language model score look-ahead value prevents the pruning of a correct answer hypothesis while suppressing an increase in the number of hypotheses. A language model score look-ahead value imparting device 108 is provided with a word dictionary 203 that defines a phoneme string of a word, a language model 202 that imparts a score of appearance easiness of a word, and a smoothing language model score look-ahead value calculation means 201. The smoothing language model score look-ahead value calculation means 201 obtains a language model score look-ahead value at each phoneme in the word from the phoneme string of the word defined by the word dictionary 203 and the language model score defined by the language model 202 so that the language model score look-ahead values are prevented from concentrating on the beginning of the word.
摘要翻译：通过使用语言模型评分预测值执行帧同步波束搜索的语音识别装置防止修正正确的答案假设，同时抑制假设数量的增加。语言模型得分预先值赋予装置108具有定义单词的音素串的单词字典203，赋予单词外观容易度的语言模型202以及平滑语言模型分数查找表，平滑语言模型分数预测值计算装置201从单词字典203定义的单词的音素串和语言模型中获得单词中每个音素处的语言模型分数预先值由语言模型202定义的分数，使得语言模型得分先验值被阻止集中在单词的开头。

8. 发明申请

US20120046940A1 METHOD FOR PROCESSING MULTICHANNEL ACOUSTIC SIGNAL, SYSTEM THEREOF, AND PROGRAM 有权
标题翻译：用于处理多通道声学信号的方法，系统及程序
公开(公告)号：US20120046940A1
公开(公告)日：2012-02-23
申请号：US13201389
申请日：2010-02-08
申请人： Masanori Tsujikawa , Tadashi Emori , Yoshifumi Onishi , Ryosuke Isotani
发明人： Masanori Tsujikawa , Tadashi Emori , Yoshifumi Onishi , Ryosuke Isotani
IPC分类号： G10L11/00
CPC分类号： G10L21/0272
摘要： A method for processing multichannel acoustic signals, whereby input signals of a plurality of channels including the voices of a plurality of speaking persons are processed. The method is characterized by comprising: calculating the first feature quantity of the input signals of the multichannels for each channel; calculating similarity of the first feature quantity of each channel between the channels; selecting channels having high similarity; separating signals using the input signals of the selected channels; inputting the input signals of the channels having low similarity and the signals after the signal separation; and detecting a voice section of each speaking person or each channel.
摘要翻译：一种用于处理多声道声信号的方法，由此处理包括多个说话人的声音的多个声道的输入信号。该方法的特征在于包括：计算每个信道的多信道的输入信号的第一特征量; 计算通道之间每个通道的第一特征量的相似度; 选择具有高相似性的信道; 使用所选择的信道的输入信号分离信号; 输入具有低相似性的信道的输入信号和信号分离之后的信号; 并且检测每个说话人或每个频道的语音部分。

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