ZemPod: A semantic web approach to podcasting

Oscar Celma, Yves Raimond

Abstract


In this paper we present a semantic web approach to solve some current limitations of podcasting. The main shortcomings of podcasts are two. The first one is that there is no formal description of the contents of a podcast session, apart from a textual description only available in HTML. The second problem is that a podcast session consists of a single audio file. Thus, it is very difficult to seek into one of the music tracks that compose a podcast. Our proposal to cope with these problems uses traditional audio signal processing – such as speech versus music segmentation, and audio identification –, and semantic web techniques to automatically describe and decompose the audio content of a podcast session. Yet, we believe that adding semantics to the podcast to explain its content, and decomposing it into smaller and meaningful chunks (that permits seeking into the inner parts of the file) will ease important music information retrieval tasks, such as recommendation, filtering and discovery. © 2008 Elsevier B.V. All rights reserved.

Full Text: PDF
Type of Paper: System Paper
Keywords: Podcasting; Semantic web; Audio; Music ontology; Music information retrieval
Show BibTex format: BibTeX