Olympus Corporation

Hiroyuki Tokiwa

Osamu Nonaka

Kenta Yumoto

A speech recognition apparatus according to an embodiment includes a microphone that acquires an audio stream in which speech vocalized by a person is recorded, a camera that acquires an image data in which at least a mouth of the person is captured, and an operation element that recognizes speech including a consonant vocalized by the person, based on the audio stream, estimates the consonant vocalized by the person, based on the shape of the mouth of the person in the image data, and specifies the consonant based on the estimated consonant and the speech-recognized consonant.

Speech recognition apparatus and speech recognition method

There is disclosed an image processing program causing a computer to perform the following operations setting image processing executed for a processing target image as application image processing, setting a plurality of predetermined processing parameter values used in the application image processing, executing the application image processing based on the parameter values to generate a plurality of processing result images, generating reduced images of the processing result images, displaying the reduced images, selecting one of reduced images, deciding the processing parameter values of the processing result image corresponding to the selected reduced image as a processing parameter values of the application image processing, setting the processing result image corresponding to the selected reduced image as a new processing target image, setting another kind of image processing as new application image processing, and repeatedly executing the process from the parameter setting processing to the image processing setting processing.

Growing community of inventors

Hachioji, Japan

Hiroyuki Tokiwa