Wikipedia based semantic metadata annotation of audio transcripts

A method to automatically annotate video items with semantic metadata is presented. The method has been developed in the context of the Papyrus project to annotate documentary- like broadcast videos with a set of relevant keywords using automatic speech recognition (ASR) transcripts as a primary complementary resource. The task is complicated by the high word error rate (WER) of the ASR for this kind of videos. For this reason a novel relevance criterion based on domain information is proposed. Wikipedia is used both as a source of metadata and as a linguistic resource for disambiguating keywords and for eliminating the out of topic/out of domain keywords. Documents are annotated with relevant links to Wikipedia pages, concepts definitions, synonyms, translations and concepts categories.