We introduce new techniques for extracting, analyzing, and visualizing textual contents from instructional videos of low production quality. Using Automatic Speech Recognition, ap...
Joke-o-mat HD is a system that allows a user to navigate sitcoms (such as Seinfeld) by "narrative themes", including scenes, punchlines, and dialog segments. The themes ...
The Broadcast News Editor (BNE) and Broadcast News Navigator (BNN) are fully implemented systems that exploit integrated image, speech, and language processing to support intellig...
To realize the long-term goal of ubiquitous computing, technological advances in multi-channel acoustic analysis are needed in order to solve several basic problems, including spe...
Dusan Macho, Jaume Padrell, Alberto Abad, Climent ...
A multimedia presentation refers to the presentation of multimedia data using output devices such as monitors for text and video, and speakers for audio. Each presentation consist...