公开(公告)号：US20070276672A1

公开(公告)日：2007-11-29

申请号：US10581821

申请日：2004-12-06

申请人： Rika Koyama

发明人： Rika Koyama

IPC分类号： G10L21/00

CPC分类号： B60R16/0373 ,  G10L2015/228

摘要： A language analyzer performs speech recognition on a speech input by a speech input unit, specifies a possible word which is represented by the speech, and the score thereof, and supplies word data representing them to an agent processing unit. The agent processing unit stores process item data which defines a data acquisition process to acquire word data or the like, a discrimination process, and an input/output process, and wires or data defining transition from one process to another and giving a weighting factor to the transition, and executes a flow represented generally by the process item data and the wires to thereby control devices belonging to an input/output target device group. To which process in the flow the transition takes place is determined by the weighting factor of each wire, which is determined by the connection relationship between a point where the process has proceeded and the wire, and the score of word data. The wire and the process item data can be downloaded from an external server.

摘要翻译： 语言分析器对由语音输入单元输入的语音执行语音识别，指定由语音表示的可能单词及其分数，并将代表它们的单词数据提供给代理处理单元。 代理处理单元存储定义用于获取字数据等的数据获取处理的处理项数据，判别处理和输入/输出处理，以及定义从一个进程到另一进程的转换的线或数据，并给出加权因子 并且执行通常由处理项目数据和线路表示的流程，从而控制属于输入/输出目标设备组的设备。 转换过程中的哪个进程由每条线的加权因子决定，该加权因子由进程进行的点与线之间的连接关系和字数据的得分确定。 电线和过程项目数据可以从外部服务器下载。

公开(公告)号：US20070265844A1

公开(公告)日：2007-11-15

申请号：US10581823

申请日：2004-12-06

申请人： Rika Koyama

发明人： Rika Koyama

IPC分类号： G10L15/00

CPC分类号： G10L2015/0631 ,  G10L2015/228

摘要： A language analyzer 2 performs speech recognition on a speech input by a speech input unit 1, specifies a possible word which is represented by the speech, and the score thereof, and supplies word data representing them to an agent processing unit 6. The agent processing unit 6 stores process item data which defines a data acquisition process to acquire word data or the like, a discrimination process, and an input/output process, and wires or data defining transition from one process to another and giving a weighting factor to the transition, and executes a flow represented generally by the process item data and the wires to thereby control devices belonging to an input/output target device group 5. To which process in the flow the transition takes place is determined by the weighting factor of each wire, which is determined by the connection relationship between a point where the process has proceeded and the wire, and the score of word data. The wire and the process item data can be downloaded from an external server.

摘要翻译： 语言分析器2对由语音输入单元1输入的语音执行语音识别，指定由语音表示的可能单词及其分数，并将代表它们的单词数据提供给代理处理单元6.代理处理 单元6存储定义用于获取字数据等的数据获取处理的处理项目数据，鉴别处理和输入/输出处理，以及定义从一个过程到另一过程的转换的线或数据，并给出转移的加权因子 ，并且执行通常由处理项目数据和导线表示的流程，从而控制属于输入/输出目标设备组5的设备。转换发生的流程中的哪个处理由每个线的加权因子确定， 其由进程进行的点与线之间的连接关系和字数据的得分确定。 电线和过程项目数据可以从外部服务器下载。

公开(公告)号：US07529676B2

公开(公告)日：2009-05-05

申请号：US10581823

申请日：2004-12-06

申请人： Rika Koyama

发明人： Rika Koyama

IPC分类号： G10L21/00

CPC分类号： G10L2015/0631 ,  G10L2015/228

摘要： A language analyzer 2 performs speech recognition on a speech input by a speech input unit 1, specifies a possible word which is represented by the speech, and the score thereof, and supplies word data representing them to an agent processing unit 6. The agent processing unit 6 stores process item data which defines a data acquisition process to acquire word data or the like, a discrimination process, and an input/output process, and wires or data defining transition from one process to another and giving a weighting factor to the transition, and executes a flow represented generally by the process item data and the wires to thereby control devices belonging to an input/output target device group 5. To which process in the flow the transition takes place is determined by the weighting factor of each wire, which is determined by the connection relationship between a point where the process has proceeded and the wire, and the score of word data. The wire and the process item data can be downloaded from an external server.

摘要翻译： 语言分析器2对由语音输入单元1输入的语音执行语音识别，指定由语音表示的可能单词及其分数，并将代表它们的单词数据提供给代理处理单元6.代理处理 单元6存储定义用于获取字数据等的数据获取处理的处理项目数据，鉴别处理和输入/输出处理，以及定义从一个过程到另一过程的转换的线或数据，并给出转移的加权因子 ，并且执行通常由处理项目数据和导线表示的流程，从而控制属于输入/输出目标设备组5的设备。转换发生的流程中的哪个处理由每个线的加权因子确定， 其由进程进行的点与线之间的连接关系和字数据的得分确定。 电线和过程项目数据可以从外部服务器下载。

公开(公告)号：US07505909B2

公开(公告)日：2009-03-17

申请号：US10581822

申请日：2004-12-06

申请人： Rika Koyama

发明人： Rika Koyama

IPC分类号： G10L21/00

CPC分类号： G10L15/22 ,  G10L2015/228

摘要： A language analyzer (2) performs speech recognition on a speech input by a speech input unit (1), specifies a possible word which is represented by the speech, and the score thereof, and supplies word data representing them to an agent processing unit (6). The agent processing unit (6) stores process item data which defines a data acquisition process to acquire word data or the like, a discrimination process, and an input/output process, and wires or data defining transition from one process to another and giving a weighting factor to the transition, and executes a flow represented generally by the process item data and the wires to thereby control devices belonging to an input/output target device group (5). To which process in the flow the transition takes place is determined by the weighting factor of each wire, which is determined by the connection relationship between a point where the process has proceeded and the wire, and the score of word data. The wire and the process item data can be downloaded from an external server.

摘要翻译： 语言分析器（2）对由语音输入单元（1）输入的语音执行语音识别，指定由语音表示的可能单词及其分数，并将代表它们的单词数据提供给代理处理单元（ 6）。 代理处理单元（6）存储定义数据获取处理以获取单词数据等的处理项目数据，鉴别处理和输入/输出处理，以及定义从一个进程到另一个进程的转换的线或数据，并给出 加权因子，并且执行通常由处理项目数据和线路表示的流程，从而控制属于输入/输出目标设备组（5）的设备。 转换过程中的哪个进程由每条线的加权因子决定，该加权因子由进程进行的点与线之间的连接关系和字数据的得分确定。 电线和过程项目数据可以从外部服务器下载。

公开(公告)号：US07454347B2

公开(公告)日：2008-11-18

申请号：US10920454

申请日：2004-08-18

申请人： Rika Koyama

发明人： Rika Koyama

IPC分类号： G10L13/00 ,  G10L13/06 ,  G10L13/02

CPC分类号： G10L13/06

摘要： A labeling part 3 analyzes the character string data to produce a phoneme label and a prosody label, partition the voice data stored in a voice database 1 into phonemic data, and label the phonemic data, employing the phoneme label and the like. A phoneme segmenting part 4 connects the voice data labeled with the same kind of phonemic data, and a formant extracting part 5 specifies the frequency of formant of each piece of phonemic data. A processing part 6 decides an evaluation value for each phonemic data based on the frequency of formant, and an error detection part 7 detects the phonemic data of which a deviation of the evaluation value within a set of phonemic data reaches a predetermined amount.

摘要翻译： 标签部分3分析字符串数据以产生音素标签和韵律标签，将存储在语音数据库1中的语音数据分割成音素数据，并使用音素标签等标记音素数据。 音素分割部分4连接用相同类型的音素数据标记的语音数据，共振峰提取部分5指定每个音素数据的共振峰的频率。 处理部分6基于共振峰的频率确定每个音素数据的评估值，并且错误检测部分7检测在一组音素数据内的评估值的偏差达到预定量的音素数据。

公开(公告)号：US20070256435A1

公开(公告)日：2007-11-08

申请号：US10581589

申请日：2004-12-06

申请人： Rika Koyama

发明人： Rika Koyama

IPC分类号： G05D23/19

CPC分类号： B60H1/00757 ,  G10L15/26

摘要： A language analyzer (2) performs speech recognition on a speech input by a speech input unit (1), specifies a possible word which is represented by the speech, and the score thereof, and supplies word data representing them to an agent processing unit (6). The agent processing unit (6) stores process item data which defines a data acquisition process to acquire word data or the like, a discrimination process, and an input/output process, and wires or data defining transition from one process to another and giving a transition constant to the transition, and executes a flow represented generally by the process item data and the wires, thereby controlling devices belonging to an input/output target device group (5). To which process in the flow the transition takes place is determined by the weighting factor of each wire, which is determined by the connection relationship between a point where the process has proceeded and the wire, and the score of word data

摘要翻译： 语言分析器（2）对由语音输入单元（1）输入的语音执行语音识别，指定由语音表示的可能单词及其分数，并将代表它们的单词数据提供给代理处理单元（ 6）。 代理处理单元（6）存储定义数据获取处理以获取单词数据等的处理项目数据，鉴别处理和输入/输出处理，以及定义从一个进程到另一个进程的转换的线或数据，并给出 过渡常数，并且执行通常由过程项目数据和线路表示的流程，从而控制属于输入/输出目标设备组（5）的设备。 转移发生的流程中的哪个过程由每个线的加权因子决定，该加权因子由进程进行的点与线之间的连接关系和字数据的得分确定

公开(公告)号：US07822614B2

公开(公告)日：2010-10-26

申请号：US10581821

申请日：2004-12-06

申请人： Rika Koyama

发明人： Rika Koyama

IPC分类号： G10L21/00

CPC分类号： B60R16/0373 ,  G10L2015/228

摘要： A language analyzer performs speech recognition on a speech input by a speech input unit, specifies a possible word which is represented by the speech, and the score thereof, and supplies word data representing them to an agent processing unit. The agent processing unit stores process item data which defines a data acquisition process to acquire word data or the like, a discrimination process, and an input/output process, and wires or data defining transition from one process to another and giving a weighting factor to the transition, and executes a flow represented generally by the process item data and the wires to thereby control devices belonging to an input/output target device group. To which process in the flow the transition takes place is determined by the weighting factor of each wire, which is determined by the connection relationship between a point where the process has proceeded and the wire, and the score of word data. The wire and the process item data can be downloaded from an external server.

摘要翻译： 语言分析器对由语音输入单元输入的语音执行语音识别，指定由语音表示的可能单词及其分数，并将代表它们的单词数据提供给代理处理单元。 代理处理单元存储定义用于获取字数据等的数据获取处理的处理项数据，判别处理和输入/输出处理，以及定义从一个进程到另一进程的转换的线或数据，并给出加权因子 并且执行通常由处理项目数据和线路表示的流程，从而控制属于输入/输出目标设备组的设备。 转换过程中的哪个进程由每条线的加权因子决定，该加权因子由进程进行的点与线之间的连接关系和字数据的得分确定。 电线和过程项目数据可以从外部服务器下载。

公开(公告)号：US20070239443A1

公开(公告)日：2007-10-11

申请号：US10581822

申请日：2004-12-06

申请人： Rika Koyama

发明人： Rika Koyama

IPC分类号： G10L15/22

CPC分类号： G10L15/22 ,  G10L2015/228

摘要： A language analyzer (2) performs speech recognition on a speech input by a speech input unit (1), specifies a possible word which is represented by the speech, and the score thereof, and supplies word data representing them to an agent processing unit (6). The agent processing unit (6) stores process item data which defines a data acquisition process to acquire word data or the like, a discrimination process, and an input/output process, and wires or data defining transition from one process to another and giving a weighting factor to the transition, and executes a flow represented generally by the process item data and the wires to thereby control devices belonging to an input/output target device group (5). To which process in the flow the transition takes place is determined by the weighting factor of each wire, which is determined by the connection relationship between a point where the process has proceeded and the wire, and the score of word data. The wire and the process item data can be downloaded from an external server.

摘要翻译： 语言分析器（2）对由语音输入单元（1）输入的语音执行语音识别，指定由语音表示的可能单词及其分数，并将代表它们的单词数据提供给代理处理单元（ 6）。 代理处理单元（6）存储定义数据获取处理以获取单词数据等的处理项目数据，鉴别处理和输入/输出处理，以及定义从一个进程到另一个进程的转换的线或数据，并给出 加权因子，并且执行通常由处理项目数据和线路表示的流程，从而控制属于输入/输出目标设备组（5）的设备。 转换过程中的哪个进程由每条线的加权因子决定，该加权因子由进程进行的点与线之间的连接关系和字数据的得分确定。 电线和过程项目数据可以从外部服务器下载。

公开(公告)号：US20050060144A1

公开(公告)日：2005-03-17

申请号：US10920454

申请日：2004-08-18

申请人： Rika Koyama

发明人： Rika Koyama

IPC分类号： G10L13/00 ,  G10L13/06 ,  G10L19/14

CPC分类号： G10L13/06

摘要： A labeling part 3 analyzes the character string data to produce a phoneme label and a prosody label, partition the voice data stored in a voice database 1 into phonemic data, and label the phonemic data, employing the phoneme label and the like. A phoneme segmenting part 4 connects the voice data labeled with the same kind of phonemic data, and a formant extracting part 5 specifies the frequency of formant of each piece of phonemic data. A processing part 6 decides an evaluation value for each phonemic data based on the frequency of formant, and an error detection part 7 detects the phonemic data of which a deviation of the evaluation value within a set of phonemic data reaches a predetermined amount.

摘要翻译： 标签部分3分析字符串数据以产生音素标签和韵律标签，将存储在语音数据库1中的语音数据分割成音素数据，并使用音素标签等标记音素数据。 音素分割部分4连接用相同类型的音素数据标记的语音数据，共振峰提取部分5指定每个音素数据的共振峰的频率。 处理部分6基于共振峰的频率确定每个音素数据的评估值，并且错误检测部分7检测在一组音素数据内的评估值的偏差达到预定量的音素数据。