公开(公告)号：US20100198093A1

公开(公告)日：2010-08-05

申请号：US12656541

申请日：2010-02-02

申请人： Yuusuke Katayama ,  Katsushi Asami ,  Manabu Otsuka

发明人： Yuusuke Katayama ,  Katsushi Asami ,  Manabu Otsuka

IPC分类号： A61B5/0402 ,  G10L15/00

CPC分类号： G10L15/22 ,  A61B5/117 ,  G10L2015/221 ,  G10L2015/227

摘要： A voice recognition apparatus includes: a voice input element for inputting voice of an user; a voice pattern memory for storing multiple voice patterns respectively corresponding to multiple phrases; a voice recognition element for calculating a similarity degree between the voice and each voice pattern and determining the highest similarity degree so that one voice pattern corresponding to the highest similarity degree is recognized as the voice; a display for displaying a recognition result corresponding to the one voice pattern; an execution determination element for executing a process according to the one voice pattern when a predetermined operation is input by the user; a load estimation element for estimating a load of the user; and a display controller for controlling the display based on a positive correlation between the load and display repetition of the recognition result on the display.

摘要翻译： 语音识别装置包括：用于输入用户语音的语音输入元件; 用于分别对应于多个短语的多个语音模式的语音图案存储器; 语音识别元件，用于计算语音和每个语音模式之间的相似度并确定最高相似度，使得与最高相似度对应的一个语音模式被识别为语音; 显示器，用于显示与一个声音图形相对应的识别结果; 执行确定元件，用于当用户输入预定操作时，执行根据所述一个语音模式的处理; 用于估计用户的负载的负载估计元件; 以及显示控制器，用于基于显示器上的识别结果的负载和显示重复之间的正相关来控制显示。

公开(公告)号：US08478601B2

公开(公告)日：2013-07-02

申请号：US12656541

申请日：2010-02-02

申请人： Yuusuke Katayama ,  Katsushi Asami ,  Manabu Otsuka

发明人： Yuusuke Katayama ,  Katsushi Asami ,  Manabu Otsuka

IPC分类号： G10L15/00

CPC分类号： G10L15/22 ,  A61B5/117 ,  G10L2015/221 ,  G10L2015/227

摘要： A voice recognition apparatus includes: a voice input element for inputting voice of an user; a voice pattern memory for storing multiple voice patterns respectively corresponding to multiple phrases; a voice recognition element for calculating a similarity degree between the voice and each voice pattern and determining the highest similarity degree so that one voice pattern corresponding to the highest similarity degree is recognized as the voice; a display for displaying a recognition result corresponding to the one voice pattern; an execution determination element for executing a process according to the one voice pattern when a predetermined operation is input by the user; a load estimation element for estimating a load of the user; and a display controller for controlling the display based on a positive correlation between the load and display repetition of the recognition result on the display.

摘要翻译： 语音识别装置包括：用于输入用户语音的语音输入元件; 用于分别对应于多个短语的多个语音模式的语音图案存储器; 语音识别元件，用于计算语音和每个语音模式之间的相似度，并确定最高相似度，使得与最高相似度相对应的一个语音模式被识别为语音; 显示器，用于显示与一个声音图形相对应的识别结果; 执行确定元件，用于当用户输入预定操作时，执行根据所述一个语音模式的处理; 用于估计用户的负载的负载估计元件; 以及显示控制器，用于基于显示器上的识别结果的负载和显示重复之间的正相关来控制显示。