Real-time captioning system with pronunciation alongside Chinese characters using voice recognition for hearing impaired persons

摘要

The input operator speaks to input personal computer listening to speaker's speeches. The input personal computer recognizes speaker's speeches by voice recognition software, projects letters, and sends recognized speaker's speeches to the correct personal computer. The correct operator corrects words with wrong letters and omitted letters. The corrected letters send to the display computer. The display computer projects captions with pronunciation alongside Chinese characters. We report on the system configurations, functions and the results of testing (validity of pronunciation alongside Chinese characters, example of caption form).