Key sound/use of transcript information in order to detect the image segment

摘要

Disclosed is a method and system for detecting a particular content in a stream of video data signals preferred by a user. Accordingly, the present invention obtains a user's profile or monitors a user's viewing history of various programs to determine the type of program content that is not watched or not liked by the user. Thereafter, incoming television programs are compared with the user's profile or the user's past viewing information to determine whether some portion of the incoming television programs are liked by the user. The portion of the program content liked by the user is collectively stored in a storage medium, then the user can subsequently view only the segments of the programs preferred by the user.