ALBERT MEROÑO PEÑUELA
Vrije Universiteit Amsterdam
The Digital Humanities (DH) present a variety of challenges to computer science that rely on semantics. Many humanities scholars have research questions addressing the semantics of concepts in their areas of expertise ('What did this action by this person in the past mean?' 'What does harmony in blues music really mean?' 'What is the meaning of this systematic mistake by this painter?'). Some researchers are looking into formal and explicit ways of representing semantics in DH (with the help of Semantic Web technology) in order to support research addressing these questions.
Music Information Retrieval (MIR) researches methods to analyze and organize music at large scale, primarily by extracting musical features from audio, symbolic notation (scores) and metadata. One of the most important problems in this field is the so-called "music semantic gap": the disconnect between the concepts that can be extracted from music (pitch, intensity, beat, timbre, etc.) and the concepts that users employ for retrieval (danceability, emotions, memories, etc.).
In this talk, Albert Meroño Peñuela will summarize the ongoing efforts to bridge this gap by means of knowledge representations used in the Semantic Web (RDF and ontologies). In particular, he will describe recent research at the Vrije Universiteit Amsterdam on applying semantic models to the popular digital music format MIDI, and its implications for a future Web capable of providing a universal interface to musical knowledge.