公开(公告)号：US20120330651A1

公开(公告)日：2012-12-27

申请号：US13530149

申请日：2012-06-22

申请人： Yasunari Obuchi ,  Takeshi Homma

发明人： Yasunari Obuchi ,  Takeshi Homma

IPC分类号： G10L15/20 ,  G10L21/00

CPC分类号： G10L15/30 ,  G10L15/01

摘要： A voice data transferring device intermediates between an in-vehicle terminal and a voice recognition server. In order to check a change in voice recognition performance of the voice recognition server, the voice data transferring device performs a noise suppression processing on a voice data for evaluation in a noise suppression module; transmits the voice data for evaluation to the voice recognition server; and receives a recognition result thereof. The voice data transferring device sets a value of a noise suppression parameter used for a noise suppression processing or a value of a result integration parameter used for a processing of integrating a plurality of recognition results acquired from the voice recognition server, at an optimum value, based on the recognition result of the voice recognition server. This makes it possible to set a suitable parameter even if the voice recognition performance of the voice recognition server changes.

摘要翻译： 语音数据传送装置在车载终端和语音识别服务器之间进行中介。 为了检查语音识别服务器的语音识别性能的变化，语音数据传送装置对噪声抑制模块中的用于评估的语音数据执行噪声抑制处理; 将语音数据发送到语音识别服务器; 并接收其识别结果。 语音数据传送装置将用于噪声抑制处理的噪声抑制参数的值或用于将从语音识别服务器获取的多个识别结果积分的处理的结果积分参数的值设定为最佳值， 基于语音识别服务器的识别结果。 即使语音识别服务器的语音识别性能发生变化，也可以设定合适的参数。

公开(公告)号：US07724910B2

公开(公告)日：2010-05-25

申请号：US11918042

申请日：2005-04-13

申请人： Nobuo Sato ,  Yasunari Obuchi

发明人： Nobuo Sato ,  Yasunari Obuchi

IPC分类号： H03G3/20

CPC分类号： H05B37/0236

摘要： The present invention provides elimination of atmosphere that is not suitable to a space concerned by controlling atmosphere.The present invention is characterized that atmosphere in space is analyzed based on voice, and if atmosphere that is not suitable to the space is detected, the atmosphere in the space is controlled by choosing and irradiating illumination that enables to create atmosphere suitable to the space, atmosphere in the space is controlled for creating atmosphere that is suitable to the space.

摘要翻译： 本发明通过控制气氛来消除不适合于相关空间的气氛。 本发明的特征在于，基于声音分析空间中的气氛，并且如果检测到不适合于空间的气氛，则通过选择和照射能够产生适合于该空间的气氛的照明来控制空间中的气氛， 控制空间中的气氛，以创造适合于空间的气氛。

公开(公告)号：US07467085B2

公开(公告)日：2008-12-16

申请号：US10898935

申请日：2004-07-27

申请人： Yasunari Obuchi ,  Atsuko Koizumi ,  Yoshinori Kitahara ,  Seiki Mizutani

发明人： Yasunari Obuchi ,  Atsuko Koizumi ,  Yoshinori Kitahara ,  Seiki Mizutani

IPC分类号： G10L17/00

CPC分类号： H04M3/42 ,  H04M2201/40 ,  H04M2203/2061 ,  Y10S707/99933 ,  Y10S707/99945 ,  Y10S707/99948

摘要： A method of providing an interpretation service, is disclosed. The method includes the steps of receiving an incoming telephone call from a user, forming a plurality of databases, wherein the plurality of databases includes at least one sentence registered to individual user, receiving at least one user information item via the incoming telephone call, searching at least one of the plurality of databases for at least one sentence correspondent to the at least one information item, outputting, according the step of searching, a translation, from at least one of the plurality of databases, of the at least one sentence correspondent to the at least one information item, and outputting, in audio on the incoming telephone call, the translation of the at least one sentence correspondent to the at least one information item.

摘要翻译： 公开了一种提供口译服务的方法。 该方法包括步骤：从用户接收来话电话，形成多个数据库，其中多个数据库包括至少一个注册到个人用户的句子，经由呼入电话接收至少一个用户信息项，搜索 所述多个数据库中的至少一个数据库用于与所述至少一个信息项相对应的至少一个句子，根据搜索步骤，从所述多个数据库中的至少一个数据库输出所述至少一个句子记者 到所述至少一个信息项，并且在所述传入电话呼叫的音频中输出与所述至少一个信息项相对应的所述至少一个句子的翻译。

公开(公告)号：US20050264425A1

公开(公告)日：2005-12-01

申请号：US11043169

申请日：2005-01-27

申请人： Nobuo Sato ,  Yasunari Obuchi

发明人： Nobuo Sato ,  Yasunari Obuchi

IPC分类号： B66B3/00 ,  B66B5/00 ,  G08B13/16 ,  G08B23/00 ,  G08B25/04 ,  G08B31/00 ,  G10L15/00 ,  G10L15/10 ,  G10L15/28 ,  H04M11/00

CPC分类号： G08B13/1672 ,  G08B31/00

摘要： Provided is a crisis monitoring system that detects a crisis by identifying a person's emotion from his/her utterance includes an input unit to which an audio signal is inputted, a recording unit which records information necessary to judge a crisis situation, and a control unit which controls the input unit and the recording unit. The recording unit records emotion attribute information, which includes a feature of a specific emotion in an audio signal, and the control unit determines a person's emotion by comparing an audio signal inputted to the input unit with the emotion attribute information, and executes a predetermined emergency processing when it is judged that the determined emotion indicates a crisis situation.

摘要翻译： 提供了一种危机监测系统，其通过从他/她的话语中识别人的情绪来检测危机，包括输入音频信号的输入单元，记录判断危机情况所需的信息的记录单元和控制单元， 控制输入​​单元和记录单元。 记录单元记录包括音频信号中的特定情绪的特征的情绪属性信息，并且控制单元通过将输入到输入单元的音频信号与情绪属性信息进行比较来确定人的情绪，并执行预定的紧急情况 当判断出确定的情绪表示危机情况时，处理。

公开(公告)号：US08423369B2

公开(公告)日：2013-04-16

申请号：US13232125

申请日：2011-09-14

申请人： Nobuo Sato ,  Yasunari Obuchi

发明人： Nobuo Sato ,  Yasunari Obuchi

IPC分类号： G10L21/00

CPC分类号： G10L17/26 ,  G10L25/78

摘要： The invention provides a conversational speech analyzer which analyzes whether utterances in a meeting are of interest or concern. Frames are calculated using sound signals obtained from a microphone and a sensor, sensor signals are cut out for each frame, and by calculating the correlation between sensor signals for each frame, an interest level which represents the concern of an audience regarding utterances is calculated, and the meeting is analyzed.

摘要翻译： 本发明提供了一种会话语音分析器，其分析会议中的话语是否感兴趣或关注。 使用从麦克风和传感器获得的声音信号来计算帧，并计算每帧的传感器信号，并且通过计算每帧的传感器信号之间的相关性，计算表示听众关于话语的关注度的兴趣级别， 会议进行了分析。

公开(公告)号：US07950278B2

公开(公告)日：2011-05-31

申请号：US12662304

申请日：2010-04-09

申请人： Nobuo Sato ,  Yasunari Obuchi

发明人： Nobuo Sato ,  Yasunari Obuchi

IPC分类号： G01W1/00

CPC分类号： H05B37/0236

摘要： The present invention provides elimination of atmosphere that is not suitable to a space concerned by controlling atmosphere.The present invention is characterized that atmosphere in space is analyzed based on voice, and if atmosphere that is not suitable to the space is detected, the atmosphere in the space is controlled by choosing and irradiating illumination that enables to create atmosphere suitable to the space, atmosphere in the space is controlled for creating atmosphere that is suitable to the space.

摘要翻译： 本发明通过控制气氛来消除不适合于相关空间的气氛。 本发明的特征在于，基于声音分析空间中的气氛，并且如果检测到不适合于空间的气氛，则通过选择和照射能够产生适合于该空间的气氛的照明来控制空间中的气氛， 控制空间中的气氛，以创造适合于空间的气氛。

公开(公告)号：US20090067646A1

公开(公告)日：2009-03-12

申请号：US11918042

申请日：2005-04-13

申请人： Nobuo Sato ,  Yasunari Obuchi

发明人： Nobuo Sato ,  Yasunari Obuchi

IPC分类号： H03G3/20

CPC分类号： H05B37/0236

摘要： The present invention provides elimination of atmosphere that is not suitable to a space concerned by controlling atmosphere.The present invention is characterized that atmosphere in space is analyzed based on voice, and if atmosphere that is not suitable to the space is detected, the atmosphere in the space is controlled by choosing and irradiating illumination that enables to create atmosphere suitable to the space, atmosphere in the space is controlled for creating atmosphere that is suitable to the space.

摘要翻译： 本发明通过控制气氛来消除不适合于相关空间的气氛。 本发明的特征在于，基于声音分析空间中的气氛，并且如果检测到不适合于空间的气氛，则通过选择和照射能够产生适合于该空间的气氛的照明来控制空间中的气氛， 控制空间中的气氛，以创造适合于空间的气氛。

公开(公告)号：US20070192103A1

公开(公告)日：2007-08-16

申请号：US11705756

申请日：2007-02-14

申请人： Nobuo Sato ,  Yasunari Obuchi

发明人： Nobuo Sato ,  Yasunari Obuchi

IPC分类号： G10L15/04

CPC分类号： G10L17/26 ,  G10L25/78

摘要： The invention provides a conversational speech analyzer which analyzes whether utterances in a meeting are of interest or concern. Frames are calculated using sound signals obtained from a microphone and a sensor, sensor signals are cut out for each frame, and by calculating the correlation between sensor signals for each frame, an interest level which represents the concern of an audience regarding utterances is calculated, and the meeting is analyzed.

摘要翻译： 本发明提供了一种会话语音分析器，其分析会议中的话语是否感兴趣或关注。 使用从麦克风和传感器获得的声音信号来计算帧，并计算每帧的传感器信号，并且通过计算每帧的传感器信号之间的相关性，计算表示听众关于话语的关注度的兴趣级别， 会议进行了分析。

公开(公告)号：US20060224438A1

公开(公告)日：2006-10-05

申请号：US11342556

申请日：2006-01-31

申请人： Yasunari Obuchi ,  Nobuo Sato ,  Akira Date

发明人： Yasunari Obuchi ,  Nobuo Sato ,  Akira Date

IPC分类号： G07G1/00

CPC分类号： G06Q30/02

摘要： The objects of the present invention are, in connection with the provision of information mainly through images to the general public or to individuals, to detect whether the user or users who is or are at a place from where he, she or they can observe the image is or are watching the image or not and to efficiently provide good information by finding out the interest and attributes of the user or users. In order to achieve the above objects, the voice data acquired by the voice inputting unit, the image data currently being provided and information added to the image data are compared, and the degree of attention of the subjects is estimated based on the degree of similitude of these data. And the language used by the user or users is estimated by a language identifying device, and information is provided by using the language.

摘要翻译： 本发明的目的在于，主要通过图像向公众或个人提供信息，以检测是否在或者位于他或她们可以观察到的那个地方的用户 图像是或正在观看图像，并通过查找用户或用户的兴趣和属性来有效地提供良好的信息。 为了实现上述目的，将由语音输入单元获取的语音数据，当前正在提供的图像数据和添加到图像数据的信息进行比较，并且基于相似度来估计被摄体的注意度 的这些数据。 并且用户或用户使用的语言由语言识别装置估计，并且通过使用该语言提供信息。

公开(公告)号：US06789093B2

公开(公告)日：2004-09-07

申请号：US09811560

申请日：2001-03-20

申请人： Yasunari Obuchi ,  Atsuko Koizumi ,  Yoshinori Kitahara ,  Seiki Mizutani

发明人： Yasunari Obuchi ,  Atsuko Koizumi ,  Yoshinori Kitahara ,  Seiki Mizutani

IPC分类号： G06F1700

CPC分类号： H04M3/42 ,  H04M2201/40 ,  H04M2203/2061 ,  Y10S707/99933 ,  Y10S707/99945 ,  Y10S707/99948

摘要： A method and apparatus for providing an interpretation service are disclosed. The method includes the steps of receiving an incoming telephone call from a user, forming a plurality of databases, receiving at least one user information item via the incoming telephone call, searching at least one of the plurality of databases for at least one sentence correspondent to the at least one information item, outputting a translation from at least one of the plurality of databases of the at least one sentence correspondent to the at least one information item, and outputting, in audio on the incoming telephone call, the translation. The apparatus includes an interpreter and a registration service. The registration service includes a private information manager that receives an incoming telephone call from a user, wherein the private information manager manages a plurality of databases, wherein the plurality of databases includes at least one database of sentences registered to the individual user.

摘要翻译： 公开了一种用于提供口译服务的方法和装置。 该方法包括以下步骤：从用户接收进入的电话呼叫，形成多个数据库，经由呼入电话呼叫接收至少一个用户信息项，搜索多个数据库中的至少一个至少一个相应于 所述至少一个信息项从与所述至少一个信息项相对应的所述至少一个句子的所述多个数据库中的至少一个数据库输出翻译，并且在所述传入电话呼叫的音频中输出所述翻译。 该装置包括解释器和注册服务。 注册服务包括从用户接收传入电话呼叫的私人信息管理器，其中私人信息管理器管理多个数据库，其中所述多个数据库包括至少一个注册到该个人用户的句子数据库。