公开(公告)号：US20080243511A1

公开(公告)日：2008-10-02

申请号：US11976179

申请日：2007-10-22

申请人： Yusuke Fujita ,  Ryota Kamoshida ,  Kenji Nagamatsu

发明人： Yusuke Fujita ,  Ryota Kamoshida ,  Kenji Nagamatsu

IPC分类号： G10L13/08 ,  G10L13/06 ,  G10L13/00 ,  G10L21/00

CPC分类号： G10L13/047

摘要： The present invention is a speech synthesizer that generates speech data of text including a fixed part and a variable part, in combination with recorded speech and rule-based synthetic speech. The speech synthesizer is a high-quality one in which recorded speech and synthetic speech are concatenated with the discontinuity of timbres and prosodies not perceived. The speech synthesizer includes: a recorded speech database that previously stores recorded speech data including a recorded fixed part; a rule-based synthesizer that generates rule-based synthetic speech data including a variable part and at least part of the fixed part, from received text; a concatenation boundary calculator that a concatenation boundary position in a region in which the recorded speech data and the rule-based synthetic speech data overlap, based on acoustic characteristics of the recorded speech data and the rule-based synthetic speech data that correspond to the text; a concatenative synthesizer that generates synthetic speech data corresponding to the text by concatenating the recorded speech data and the rule-based synthetic speech data that are segmented in the concatenation boundary position.

摘要翻译： 本发明是一种语音合成器，其与记录的语音和基于规则的合成语音相组合，生成包括固定部分和可变部分的文本的语音数据。 语音合成器是一种高质量的语音合成器，其中录制的语音和合成语音与不被感知的音色和前缀的不连续性相连接。 语音合成器包括：记录语音数据库，其预先存储包括记录的固定部分的记录语音数据; 基于规则的合成器，从接收到的文本生成包括可变部分和至少部分固定部分的基于规则的合成语音数据; 基于记录的语音数据的声学特性和与文本对应的基于规则的合成语音数据，记录语音数据和基于规则的合成语音数据重叠的区域中的级联边界位置的级联边界计算器 ; 一个级联合成器，其通过连接所记录的语音数据和在级联边界位置中分段的基于规则的合成语音数据来产生与文本相对应的合成语音数据。

公开(公告)号：US07991616B2

公开(公告)日：2011-08-02

申请号：US11976179

申请日：2007-10-22

申请人： Yusuke Fujita ,  Ryota Kamoshida ,  Kenji Nagamatsu

发明人： Yusuke Fujita ,  Ryota Kamoshida ,  Kenji Nagamatsu

IPC分类号： G10L13/08

CPC分类号： G10L13/047

摘要： The present invention is a speech synthesizer that generates speech data of text including a fixed part and a variable part, in combination with recorded speech and rule-based synthetic speech. The speech synthesizer is a high-quality one in which recorded speech and synthetic speech are concatenated with the discontinuity of timbres and prosodies not perceived. The speech synthesizer includes: a recorded speech database that previously stores recorded speech data including a recorded fixed part; a rule-based synthesizer that generates rule-based synthetic speech data including a variable part and at least part of the fixed part, from received text; a concatenation boundary calculator that a concatenation boundary position in a region in which the recorded speech data and the rule-based synthetic speech data overlap, based on acoustic characteristics of the recorded speech data and the rule-based synthetic speech data that correspond to the text; a concatenative synthesizer that generates synthetic speech data corresponding to the text by concatenating the recorded speech data and the rule-based synthetic speech data that are segmented in the concatenation boundary position.

摘要翻译： 本发明是一种语音合成器，其与记录的语音和基于规则的合成语音相组合，生成包括固定部分和可变部分的文本的语音数据。 语音合成器是一种高质量的语音合成器，其中录制的语音和合成语音与不被感知的音色和前缀的不连续性相连接。 语音合成器包括：记录语音数据库，其预先存储包括记录的固定部分的记录语音数据; 基于规则的合成器，从接收到的文本生成包括可变部分和至少部分固定部分的基于规则的合成语音数据; 基于记录的语音数据的声学特性和与文本对应的基于规则的合成语音数据，记录语音数据和基于规则的合成语音数据重叠的区域中的级联边界位置的级联边界计算器 ; 一个级联合成器，其通过连接所记录的语音数据和在级联边界位置中分段的基于规则的合成语音数据来产生与文本相对应的合成语音数据。

公开(公告)号：US20120330667A1

公开(公告)日：2012-12-27

申请号：US13527614

申请日：2012-06-20

申请人： Qinghua Sun ,  Kenji Nagamatsu ,  Yusuke Fujita

发明人： Qinghua Sun ,  Kenji Nagamatsu ,  Yusuke Fujita

IPC分类号： G10L13/08

CPC分类号： G10L13/08 ,  G10L13/10

摘要： Included in a speech synthesizer, a natural language processing unit divides text data, input from a text input unit, into a plurality of components (particularly, words). An importance prediction unit estimates an importance level of each component according to the degree of how much each component contributes to understanding when a listener hears synthesized speech. Then, the speech synthesizer determines a processing load based on the device state when executing synthesis processing and the importance level. Included in the speech synthesizer, a synthesizing control unit and a wave generation unit reduce the processing time for a phoneme with a low importance level by curtailing its processing load (relatively degrading its sound quality), allocate a part of the processing time, made available by this reduction, to the processing time of a phoneme with a high importance level, and generates synthesized speech in which important words are easily audible.

摘要翻译： 自然语言处理单元包括在语音合成器中，将从文本输入单元输入的文本数据分成多个分量（特别是单词）。 重要性预测单元根据听众听到合成语音时每个组件有助于理解的程度来估计每个组件的重要程度。 然后，当执行合成处理和重要性级别时，语音合成器基于设备状态来确定处理负载。 合成控制单元和波形发生单元包括在语音合成器中，通过减少其处理负荷（相对劣化其音质）来减少重要性低的音素的处理时间，分配一部分处理时间 通过这种减少，具有高重要度的音素的处理时间，并且生成其中容易听到重要单词的合成语音。

公开(公告)号：US07321808B2

公开(公告)日：2008-01-22

申请号：US11602979

申请日：2006-11-22

申请人： Kenji Nagamatsu

发明人： Kenji Nagamatsu

IPC分类号： G05B19/418

CPC分类号： B25J9/1666 ,  G05B2219/39083 ,  G05B2219/39135 ,  G05B2219/40387

摘要： When braking of a motion of a part of a first robot is assumed to be started at points in time, a first stop position of the first robot part is estimated at each point in time. When braking of a motion of a part of a second robot is assumed to be started at the points in time, an estimated second stop position of the second robot part is obtained at each point in time. When it is determined that the first stop position of the first robot part at one of the points in time and either the actual position or the second stop position of the second robot part for each interval at the one of the points in time are contained in the shared workspace, the first robot part is braked.

摘要翻译： 假设第一机器人的一部分的运动的制动在时间点开始，则在每个时间点估计第一机器人部件的第一停止位置。 假设第二机器人的一部分的运动的制动在时间点开始，则在每个时间点获得第二机器人部件的估计的第二停止位置。 当确定在一个时间点上的每个时间间隔的一个时间点上的第一机器人部件的第一停止位置和第二机器人部件的实际位置或第二停止位置被包含在 共享工作区，第一个机器人部分被制动。

公开(公告)号：US20070118250A1

公开(公告)日：2007-05-24

申请号：US11603103

申请日：2006-11-22

申请人： Kenji Nagamatsu

发明人： Kenji Nagamatsu

IPC分类号： G05B19/04

CPC分类号： B25J9/1666 ,  G05B2219/39083 ,  G05B2219/39088 ,  G05B2219/39136

摘要： In a robot, a first determining unit determines whether there is an interference region in which a first occupation region and a second occupation region are at least partially overlapped with each other. A second determining determines whether a second movable part of another robot is at least partially located in the interference region based on an actual position of the second movable part. A stopping unit begins stopping, at a predetermined timing, movement of the first movable part if it is determined that there is the interference region, and that the second inovable part is at least partially located in the interference region. The predetermined timing is determined based on a positional relationship between an actual position of the first movable part and the interference region.

摘要翻译： 在机器人中，第一确定单元确定是否存在第一占用区域和第二占用区域彼此至少部分重叠的干扰区域。 第二确定基于第二可移动部件的实际位置确定另一个机器人的第二可动部分是否至少部分地位于干涉区域中。 如果确定存在干扰区域，并且第二不可移动部分至少部分地位于干涉区域中，则停止单元在预定定时开始停止第一可移动部分的移动。 基于第一可动部的实际位置与干涉区域之间的位置关系来确定预定定时。

公开(公告)号：US07113909B2

公开(公告)日：2006-09-26

申请号：US09917829

申请日：2001-07-31

申请人： Nobuo Nukaga ,  Kenji Nagamatsu ,  Yoshinori Kitahara

发明人： Nobuo Nukaga ,  Kenji Nagamatsu ,  Yoshinori Kitahara

IPC分类号： G10L13/00

CPC分类号： G10L13/10

摘要： A stereotypical sentence is synthesized into a voice of an arbitrary speech style. A third party is able to prepare prosody data and a user of a terminal device having a voice synthesizing part can acquire the prosody data. The voice synthesizing method determines a voice-contents identifier to point to a type of voice contents of a stereotypical sentence, prepares a speech style dictionary including speech style and prosody data which correspond to the voice-contents identifier, selects prosody data of the synthesized voice to be generated from the speech style dictionary, and adds the selected prosody data to a voice synthesizer 13 as voice-synthesizer driving data to thereby perform voice synthesis with a specific speech style. Thus, a voice of a stereotypical sentence can be synthesized with an arbitrary speech style.

摘要翻译： 一种刻板句被合成为一种任意言语风格的声音。 第三方能够准备韵律数据，并且具有语音合成部分的终端设备的用户可以获取韵律数据。 语音合成方法确定语音内容标识符以指示定型句子的语音内容的类型，准备包括对应于语音内容标识符的语音样式和韵律数据的语音样式字典，选择合成语音的韵律数据 并且将所选择的韵律数据作为语音合成器驱动数据，并将该韵律数据添加到语音合成器13，从而以特定语音风格进行语音合成。 因此，可以以任意的言语风格合成刻板句子的声音。

公开(公告)号：US08706171B2

公开(公告)日：2014-04-22

申请号：US13371878

申请日：2012-02-13

申请人： Kenji Nagamatsu ,  Naoki Watanabe

发明人： Kenji Nagamatsu ,  Naoki Watanabe

IPC分类号： H04M1/00 ,  H04M1/60

CPC分类号： H04M1/6075 ,  G10L25/69 ,  G10L25/72 ,  H04M1/6033 ,  H04M1/6041 ,  H04M1/605 ,  H04M1/6083 ,  H04M1/6091

摘要： A user of a hands-free phone cannot determine with which speech quality the distant side of communication is listened to, and does not know which action to be required to improve the speech quality. In the case of the present invention, a function of presenting an action to be implemented by the user to improve the speech quality at the opposite party is mounted on the hands-free terminal. For the presentation here, it is assumed that the hands-free terminal according to the present invention has a function of estimating the speech quality at the distant side, a function of estimating an action to be implemented by the user to improve the estimated speech quality, and a function of presenting the estimated action to the user.

摘要翻译： 免提电话的用户不能确定通信的远端哪个语音质量被听到，并且不知道为提高语音质量而需要哪个动作。 在本发明的情况下，在免提终端上安装了呈现由用户实现的用于提高对方的语音质量的动作的功能。 为了这里的介绍，假设根据本发明的免提终端具有估计远端的语音质量的功能，估计用户要实现的动作以提高估计语音质量的功能 ，以及向用户呈现估计动作的功能。

公开(公告)号：US07765031B2

公开(公告)日：2010-07-27

申请号：US11603103

申请日：2006-11-22

申请人： Kenji Nagamatsu

发明人： Kenji Nagamatsu

IPC分类号： G05B19/04 ,  G05B4/4061

CPC分类号： B25J9/1666 ,  G05B2219/39083 ,  G05B2219/39088 ,  G05B2219/39136

摘要： In a robot, a first determining unit determines whether there is an interference region in which a first occupation region and a second occupation region are at least partially overlapped with each other. A second determining determines whether a second movable part of another robot is at least partially located in the interference region based on an actual position of the second movable part. A stopping unit begins stopping, at a predetermined timing, movement of the first movable part if it is determined that there is the interference region, and that the second movable part is at least partially located in the interference region. The predetermined timing is determined based on a positional relationship between an actual position of the first movable part and the interference region.

摘要翻译： 在机器人中，第一确定单元确定是否存在第一占用区域和第二占用区域彼此至少部分重叠的干扰区域。 第二确定基于第二可移动部件的实际位置确定另一个机器人的第二可动部分是否至少部分地位于干涉区域中。 如果确定存在干扰区域，并且第二可移动部件至少部分地位于干涉区域中，则停止单元在预定的定时开始停止第一可移动部件的移动。 基于第一可动部的实际位置与干涉区域之间的位置关系来确定预定定时。

公开(公告)号：US20070118249A1

公开(公告)日：2007-05-24

申请号：US11602979

申请日：2006-11-22

申请人： Kenji Nagamatsu

发明人： Kenji Nagamatsu

IPC分类号： G06F19/00

CPC分类号： B25J9/1666 ,  G05B2219/39083 ,  G05B2219/39135 ,  G05B2219/40387

摘要： When braking of a motion of a part of a first robot is assumed to be started at points in time, a first stop position of the first robot part is estimated at each point in time. When braking of a motion of a part of a second robot is assumed to be started at the points in time, an estimated second stop position of the second robot part is obtained at each point in time. When it is determined that the first stop position of the first robot part at one of the points in time and either the actual position or the second stop position of the second robot part for each interval at the one of the points in time are contained in the shared workspace, the first robot part is braked.

摘要翻译： 假设第一机器人的一部分的运动的制动在时间点开始，则在每个时间点估计第一机器人部件的第一停止位置。 假设第二机器人的一部分的运动的制动在时间点开始，则在每个时间点获得第二机器人部件的估计的第二停止位置。 当确定在一个时间点上的每个时间间隔的一个时间点上的第一机器人部件的第一停止位置和第二机器人部件的实际位置或第二停止位置被包含在 共享工作区，第一个机器人部分被制动。

公开(公告)号：US06819301B2

公开(公告)日：2004-11-16

申请号：US10440082

申请日：2003-05-19

申请人： Kenji Nagamatsu ,  Kenichi Mizuishi

发明人： Kenji Nagamatsu ,  Kenichi Mizuishi

IPC分类号： G01C2130

CPC分类号： H04L67/18 ,  G01C21/3617 ,  H04L69/329

摘要： Disclosed here is an information providing system for mobile objects. The system obtains information of a moving purpose of the user of each mobile object to provide the user with information matching with the moving purpose. The information providing system comprises route type determining apparatus for determining the type of the current route on which the user is moving, provided information selecting unit for selecting information to be provided to the user according to the route type determined by the route type determining apparatus, and provided information presenting means for presenting the information selected by the provided information selecting unit to the user. Therefore, the user can receive more proper information according to the user's moving purpose at that time, thereby the convenience of the user is improved while the information provider can improve the advertisement effect by transmitting information to more proper users.

摘要翻译： 这里公开了一种用于移动对象的信息提供系统。 系统获得每个移动对象的用户的移动目的的信息，以向用户提供与移动目的匹配的信息。 信息提供系统包括用于确定用户正在移动的当前路由的类型的路由类型确定装置，用于根据由路由类型确定装置确定的路由类型选择要提供给用户的信息的提供信息选择单元， 并且提供信息呈现装置，用于将由所提供的信息选择单元选择的信息呈现给用户。 因此，用户可以根据用户当时的移动目的接收到更多的适当信息，从而提高用户的便利性，同时信息提供者可以通过向更合适的用户发送信息来改善广告效果。