Compositional hierarchical model for multi-f0 estimation

Manca Žerovnik (2014) Compositional hierarchical model for multi-f0 estimation. EngD thesis.

Preview

Abstract

This thesis focuses on the field of music information retrieval. We present the compositional hierarchical model for music information retrieval and evaluate it on the task of multiple fundamental frequency estimation on publicly available MAPS dataset. We evaluate the robustness of the model by varying the parameters of the model and analyse the results through graphical visualizations of model's provided hypotheses. Additionally, we provide improvements to the results through the analysis of the model's output.

Item Type:

Thesis (EngD thesis)

Keywords:

music information retrieval, multiple fundamental frequency estimation, compositional hierarchical model, evaluation

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=50070&select=(ID=00010777428)

Institution:

University of Ljubljana

Department:

Faculty of Computer and Information Science

Item ID:

2657

Date Deposited:

09 Sep 2014 16:23

Last Modified:

29 Sep 2014 12:14

URI:

http://eprints.fri.uni-lj.si/id/eprint/2657

Actions (login required)

View Item