| 摘要 |
<P>PROBLEM TO BE SOLVED: To provide an eyeglass-type display device that is insusceptible to surrounding noise and can accurately translate and display voice of a specific speaker. <P>SOLUTION: An eyeglass-type display device 1 that receives surrounding sound, converts the sound to a sound signal, and captures a visual field, extracts at least one of face image data and face feature data of a speaker from image data of the captured visual field, and based on at least one of the face image data, the face feature data, and the sound signal of the surrounding sound, specifies and extracts a voice signal of the speaker. Then, the device converts the voice signal of the speaker into text data, and converts the text data into text data in another language different from the language of the text data. The text data translated to the another language is overlapped and displayed in the visual field. <P>COPYRIGHT: (C)2012,JPO&INPIT |
