Abstract: A technique for automated analysis of multimedia, such as, for example, a news broadcast. A Broadcast News Editor and Broadcast News Navigator system analyze, select, condense, and then present news summaries. The system enables not only viewing a hierarchical table of contents of the news, but also summaries tailored to individual needs. This is accomplished through story segmentation and proper name extraction which enables the use of common information retrieval methodologies, such as Web browsers. Robust segmentation processing is provided using multistream analysis on imagery, audio, and closed captioned stream cue events according to a finite state model indicative of the presentation class.

Abstract: A system and method are provided that use explicitly and implicitly derived models of user information needs and content and presentation preferences together with relevancy feedback to expand a user's original query to the most related terms in a corpus and/or to allow the user to provide interactive feedback to enhance the relevance of selected news stories and display profile of the selected news stories. By personalizing both the selection of stories and the form in which they are delivered, users are provided with tailored broadcast news.

Abstract: A technique for automated analysis of multimedia, such as, for example, a news broadcast. A Broadcast News Editor and Broadcast News Navigator system analyze, select, condense, and then present news summaries. The system enables not only viewing a hierarchical table of contents of the news, but also summaries tailored to individual needs. This is accomplished through story segmentation and proper name extraction which enables the use of common information retrieval methodologies, such as Web browsers. Robust segmentation processing is provided using multistream analysis on imagery, audio, and closed captioned stream cue events.