Details

Odkrivanje vzorcev v večglasni glasbi z nenadzorovanim učenjem
ID Žerovnik, Manca (Author), ID Marolt, Matija (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (1,25 MB)
MD5: 310FDFE79FEB93B5BFAC93A9B088CFE8
PID: 20.500.12556/rul/8abc653e-cb2d-417b-94f1-c6c9687ecfa3

Abstract
V delu predstavimo nadgradnjo kompozicionalnega hierarhičnega modela za odkrivanje ponavljajočih vzorcev v večglasni glasbi v simbolični obliki. Kompozicionalni hierarhični model je globoka arhitektura zgrajena iz več nivojev, ki vzorce išče na podlagi nenadzorovanega učenja. Algoritem preizkusimo na javno dostopnih zbirkah in ga primerjamo z ostalimi algoritmi na tem področju. Predstavimo upodobitev rezultatov modela v obliki spletne aplikacije. Na podlagi najdenih ponavljajočih vzorcev naredimo klasifikacijo slovenskih ljudskih pesmi glede na variantni tip.

Language:Slovenian
Keywords:pridobivanje informacij iz glasbe, kompozicionalni hierarhični model, odkrivanje ponavljajočih vzorcev
Work type:Master's thesis/paper
Organization:FRI - Faculty of Computer and Information Science
Year:2017
PID:20.500.12556/RUL-95568 This link opens in a new window
Publication date in RUL:20.09.2017
Views:1636
Downloads:391
Metadata:XML DC-XML DC-RDF
:
ŽEROVNIK, Manca, 2017, Odkrivanje vzorcev v večglasni glasbi z nenadzorovanim učenjem [online]. Master’s thesis. [Accessed 25 July 2025]. Retrieved from: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=eng&id=95568
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Discovery of Repeated Patterns in polyphonic music with unsupervised learning
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.

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

Similar documents

Similar works from RUL:
  1. The Development of the Upright for Formula Student Race Car
  2. Construction of a planetary gearbox for a Formula student race car
  3. User interface of a Formula Student race car
  4. Laptime simulation of Formula Student
  5. Development of a steering mechanism for a racing car Formula Student
Similar works from other Slovenian collections:
  1. Suspension design of a Formula Student race car
  2. Strength analysis of formula student race car aerodynamic carriers
  3. Double wishbone suspension design of the formula student race car
  4. Design and production of a variable- length intake manifold for Formula Student racecar
  5. Design of a composite material mould for the chassis of a formula student racecar

Back