Social recommendation using speech recognition: Sharing TV scenes in social networks

Abstract

We describe a novel system which simplifies recommendation of video scenes in social networks, thereby attracting a new audience for existing video portals. Users can select interesting quotes from a speech recognition transcript, and share the corresponding video scene with their social circle with minimal effort. The system has been designed in close cooperation with the largest German public broadcaster (ARD), and was deployed at the broadcasters public video portal. A twofold adaptation strategy adapts our speech recognition system to the given use case. First, a database of speakeradapted acoustic models for the most important speakers in the corpus is created. We use spectral speaker identification for detecting whether one of these speakers is speaking, and select the correspondin g model accordingly. Second, we apply language model adaptation by exploiting prior knowledge about the video category

Sharing Video Emotional Information in the Web

“…In particular, Web video portals offer huge and diverse collections of audiovisual data to the public, including public media archives of large national broadcasters (Schneider et al, 2012). Indeed, in recent years, the growth in multimedia storage and the declining costs for storing multimedia data gave rise to increasingly larger numbers of digital videos available online in video repositories, making it increasingly difficult to retrieve the relevant videos from such large video repositories according to users' interests (Calic et al, 2005).…”