Abstract :
TV movies that respond to words spoken by viewers can simulate entertaining face-to-face conversations between each viewer and screen actors or cartoon characters in the movie. The actors and cartoons will reply responsively with lip-sync sound to words spoken by viewers. Different audio and video frames can be addressed on a videodisc to provide one of several alternative replies or alternative actions at each branch point in the movie, depending on what the viewer says to a speech-recognition unit. A simple speech-recognition unit can be used because the number of words to be recognized at each branch point is restricted to just a few words. Different words are used at different branch points to make the dialog realistic. To inform viewers of what words they can use at each branch point, a menu of prompting words is displayed on a hand-held unit. These prompting words are programmed to be phonetically distinct to be easily distinguishable from each other. A viewer speaks one of the displayed words and the speech-recognition unit decides which of the expected words was spoken. Viewers can input questions or make other remarks by speaking a displayed code word which stands for a whole sentence, or by pressing a button next to a sentence displayed on the hand-held unit.