Identifying versions of the same song by means of automatically extracted audio features is a complex task toachieve using computers, even though it may seem very simple for a human listener. The design of a system toperform this job gives the opportunity to analyze which features are relevant for music similarity. This paper focuseson the analysis of tonal and structural similarity and its application to the identification of different versions of thesame piece. This work describes the situations where a song is versioned and several musical aspects aretransformed with respect to the canonical version. A quantitative evaluation is made using tonal descriptors,including chroma representations and tonality, combined with the automatic extraction of a summary of a piecethrough music structural analysis.
展开▼