MusiCLEF: a Benchmark Activity in Multimodal Music Information Retrieval

This work presents the rationale, tasks and procedures of MusiCLEF, a novel benchmarking activity that has been developed along with the Cross-Language Evaluation Forum (CLEF). The main goal of MusiCLEF is to promote the development of new methodologies for music access and retrieval on real public music collections, which can combine content-based information, automatically extracted from music files, with contextual information, provided by users via tags, comments, or reviews. Moreover, MusiCLEF aims at maintaining a tight connection with real application scenarios, focusing on issues on music access and retrieval that are faced by professional users. To this end, this year’s evaluation campaign focused on two main tasks: automatic categorization of music to be used as soundtrack of TV shows and automatic identification of the digitized material of a music digital library.