ANTS: A Complete System for Automatic News Programme Annotation Based on Multimodal Analysis

Abstract

This paper describes an integrated system for the acquisition, automatic annotation and Web publication of television broadcast news programmes named ANTS (automatic newscast transcription system). The system consists of several analysis components integrated in a unified architecture. Users have the possibility to access a large daily-growing database of news stories from the main national channels, all identified, categorised and published in a fully automatic way. The system identifies story boundaries, extracts texts from spoken content, classifies stories by subject and links external relevant information coming from the Web. Performances of the system have been evaluated in a real-life scenario, by providing an instance of the system to a panel of professional users inside RAI. The strength of the approach behind ANTS consists in the ability to integrate several heterogeneous analysis components in a performant and ready-for-production environment, capable of elaborating many hours of material per day without significant service drops and with sufficiently good accuracy for industrial employment in large broadcasting facilities.