公开(公告)号：US5579468A

公开(公告)日：1996-11-26

申请号：US397727

申请日：1995-03-02

申请人： Hisao Miyauchi ,  Hirosi Iizuka ,  Takashi Kayamori ,  Toshiro Watanabe ,  Norikazu Saito ,  Yutaka Hidai ,  Katsumi Kunihara ,  Masajiro Fukunaga ,  Satoshi Yoshizawa ,  Makoto Hirose ,  Tadashi Hoshiai ,  Tetsuya Yoshimura ,  Nobuo Asahi

发明人： Hisao Miyauchi ,  Hirosi Iizuka ,  Takashi Kayamori ,  Toshiro Watanabe ,  Norikazu Saito ,  Yutaka Hidai ,  Katsumi Kunihara ,  Masajiro Fukunaga ,  Satoshi Yoshizawa ,  Makoto Hirose ,  Tadashi Hoshiai ,  Tetsuya Yoshimura ,  Nobuo Asahi

IPC分类号： G06F15/00 ,  G06F9/44 ,  G06N5/04 ,  G09B19/00

CPC分类号： G09B19/0053

摘要： An architecture providing a human interface includes a user input device, a studio or workplace receiving an output of the user input device, the studio being capable of storing and sharing information, and a plurality of agents or functional modules connected to supply/receive data from the studio. The agents are connected in parallel and perform processing as distributed and cooperative processing of functions by the user. The agents are independent components having independent functions performing processing on data in the studio to receive and store items of information, respectively, from and to the studio as a shared information medium, the studio being accessible to the user and to the plurality of agents. Each of the plurality of agents can be independently started depending upon a status of the studio.

摘要翻译： 提供人机界面的架构包括用户输入设备，接收用户输入设备的输出的工作室或工作场所，能够存储和共享信息的演播室，以及连接到从/ 工作室。 代理并行连接，并由用户执行功能的分布式协同处理。 这些代理是具有独立功能的独立部件，它们对演播室中的数据执行处理，分别从作为共享信息介质的演播室接收和存储信息项目，该工作室可由用户和多个代理访问。 可以根据工作室的状态独立地启动多个代理中的每一个。

公开(公告)号：US4520500A

公开(公告)日：1985-05-28

申请号：US373147

申请日：1982-04-29

申请人： Kaneyoshi Mizuno ,  Isamu Nose ,  Hirosi Iizuka

发明人： Kaneyoshi Mizuno ,  Isamu Nose ,  Hirosi Iizuka

IPC分类号： G10L11/02 ,  G10L15/00 ,  G10L1/00

CPC分类号： G10L15/00 ,  G10L25/87

摘要： This speech recognition system uses a converted-spectrum for comparison of unknown and prestored reference signals. The comparison distance is modified by a weighting factor W to emphasize differences. A straight line approximation of the short term spectrum provides a datum against which the original spectrum is differenced to provide the converted spectrum, and provide deviation signs which are used to modify an initial prestored weighting factor P to form W.

摘要翻译： 该语音识别系统使用转换频谱来比较未知和预存参考信号。 比较距离由权重因子W修改以强调差异。 短期光谱的直线近似提供了原始光谱差分的数据，以提供转换的光谱，并提供用于修改初始预先存储的加权因子P以形成W的偏差符号。