Section: Software

Demonstrations

Participants : Morgan Bréhinier, Sébastien Campion [correspondent] , Guillaume Gravier.

The gradual migration of television from broadcast diffusion to Internet diffusion offers tremendous possibilities for the generation of rich navigable contents. However, it also raises numerous scientific issues regarding de-linearization of TV streams and content enrichment. In this demonstration, we illustrate how speech in TV news shows can be exploited for de-linearization of the TV stream. In this context, de-linearization consists in automatically converting a collection of video files extracted from the TV stream into a navigable portal on the Internet where users can directly access specific stories or follow their evolution in an intuitive manner.

Structuring a collection of news shows requires some level of semantic understanding of the content in order to segment shows into their successive stories and to create links between stories in the collection, or between stories and related resources on the Web. Spoken material embedded in videos, accessible by means of automatic speech recognition, is a key feature to semantic description of video contents. At IRISA/INRIA Rennes, we have developed multimedia content analysis technology combining automatic speech recognition, natural language processing and information retrieval to automatically create a fully navigable news portal from a collection of video files.

The demonstration was presented in several workshops (Quaero CTC workshop, Journée INRIA Industrie La Télévision du Futur) and a video has been made available online on the portal of the EIT ICT Labs OpenSEM project.

See the demo at http://texmix.irisa.fr .