Uri Nieto, from the Music and Audio Research Lab of NYU, will give a talk on "Music Structure Analysis using Matrix Factorization" on Thursday, January 10th, at 3:30pm in room 52.321.

Abstract: We propose a novel and fast approach to discover structure in western popular music by using a specific type of matrix factorization that adds a convex constrain to obtain a decomposition that can be interpreted as a set of weighted cluster centroids. We show that these centroids capture the different sections of a musical piece (e.g. verse, chorus) in a more consistent and efficient way than classic non-negative matrix factorization. This technique is capable of identifying the boundaries of the sections and then grouping them into different clusters.

Biography: Oriol Nieto is currently pursuing a Ph.D degree in Music Technology at the New York University, supervised by Morwaread Farbood and Juan Bello. He is a guitarist, violinist, composer, and music technologist. He received a B.S. in computer science from Polytechnic University of Catalonia (UPC), an M.S. in Information Technologies, Communication, and Audiovisual Media from Pompeu Fabra University (UPF), and an M.A. in Music, Science and Technology from Stanford University. His main interests are Music Information Retrieval, Music Cognition, Machine Learning, and Mobile Music.

Uri Nieto's website