In this talk I'll present several computational approaches aimed at supporting knowledge discovery in music. This work combines theories and techniques from machine learning, signal processing and music for the automatic analysis of digital music recordings. It is shown how these techniques can be used to extract musically-meaningful information from audio signals, to identify their repetitive structures and representative patterns, including chords, motifs and sections, and to characterize similarities across collections of sounds. Finally, I will show how these methods can facilitate the development of novel modes of access, analysis and interaction with digital content that can help redefine the retrieval, appreciation and study of music.
Copyright. All Rights Reserved.