THE ROLE OF AUTOMATED SPEECH AND AUDIO ANALYSIS IN SEMANTIC MULTIMEDIA ANNOTATION

This paper overviews the various ways in which automatic speech and audio analysis can be deployed to enhance the semantic annotation of multimedia content, and as a consequence to improve the effectiveness of conceptual access tools. A number of techniques will be presented, including the alignment of text resources, large vocabulary speech recognition, key word spotting and speaker classification. The applicability of techniques will be discussed from a media crossing perspective. The added value will be illustrated by the description of two complementary demonstrators for browsing broadcast news archieves.