Discovery of Repeated Patterns in polyphonic music with unsupervised learning

Manca Žerovnik (2017) Discovery of Repeated Patterns in polyphonic music with unsupervised learning. MSc thesis.

Preview

Abstract

In this work we introduce an upgrade of compositional hierarchical model for repated pattern discovery in polyphonic symbolic music. Compositional hierarchical model is a deep architecture with multi layer structure. Pattern discovery is made in an unsupervised manner. We test algorithm on public datasets and compare it with other approaches. We present a visualization of results in form of web application. Finally we make a classification of slovenian folk songs based on discovered repeated patterns.

Item Type:

Thesis (MSc thesis)

Keywords:

music information retrieval, compositional hierarchical model, discovery of repeated patterns

Number of Pages:

Language of Content:

Slovenian

Mentor / Comentors:

Name and Surname	ID	Function
doc. dr. Matija Marolt	271	Mentor

Link to COBISS:

http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1537574595)

Institution:

University of Ljubljana

Department:

Faculty of Computer and Information Science

Item ID:

3946

Date Deposited:

14 Sep 2017 15:05

Last Modified:

06 Oct 2017 13:13

URI:

http://eprints.fri.uni-lj.si/id/eprint/3946

Actions (login required)

View Item