Real-Time Closed-Captioning Using Speech Recognition

There is a great need for more TV programs to be closed-captioned to help hearing impaired and elderly people watch TV. For that purpose, automatic speech recognition is expected to contribute to providing text from speech in real-time. NHK has been using speech recognition for closed-captioning of some of its news, sports and other live TV programs. In news programs, automatic speech recognition applied to anchorpersons’ speech in a studio has been used with a manual error correction system from 2000 to 2006. Live TV programs, such as music shows, baseball games, and the Olympic Games, have been closed-captioned since 2001 by using a re-speak method in which another speaker listens to the program contents and rephrases them for speech recognition. To efficiently expand closedcaptioning, a new hybrid speech recognition system that switches input speech between the original program sound and the rephrased speech with fewer correction operators is under study.