prikaz prve stranice dokumenta Pretraživanje glazbenih informacija
Access restricted to students and staff of home institution
master's thesis
Pretraživanje glazbenih informacija
Zagreb: University of Zagreb, University of Zagreb, Faculty of Humanities and Social Sciences, 2020. urn:nbn:hr:131:354833
Majić, Silvio
University of Zagreb
Faculty of Humanities and Social Sciences
Department of information and Communication sciences

Institutional repository: ODRAZ

Cite this document

Majić, S. (2020). Pretraživanje glazbenih informacija (Master's thesis). Zagreb: University of Zagreb, Faculty of Humanities and Social Sciences. Retrieved from https://urn.nsk.hr/urn:nbn:hr:131:354833

Majić, Silvio. "Pretraživanje glazbenih informacija." Master's thesis, University of Zagreb, Faculty of Humanities and Social Sciences, 2020. https://urn.nsk.hr/urn:nbn:hr:131:354833

Majić, Silvio. "Pretraživanje glazbenih informacija." Master's thesis, University of Zagreb, Faculty of Humanities and Social Sciences, 2020. https://urn.nsk.hr/urn:nbn:hr:131:354833

Majić, S. (2020). 'Pretraživanje glazbenih informacija', Master's thesis, University of Zagreb, Faculty of Humanities and Social Sciences, accessed 28 April 2024, https://urn.nsk.hr/urn:nbn:hr:131:354833

Majić S. Pretraživanje glazbenih informacija [Master's thesis]. Zagreb: University of Zagreb, Faculty of Humanities and Social Sciences; 2020 [cited 2024 April 28] Available at: https://urn.nsk.hr/urn:nbn:hr:131:354833

S. Majić, "Pretraživanje glazbenih informacija", Master's thesis, University of Zagreb, Faculty of Humanities and Social Sciences, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:131:354833

Metadata
TitlePretraživanje glazbenih informacija
Title (english)Music information retrieval
AuthorSilvio Majić
MentorKristina Kocijan (mentor)
Committee memberNikolaj Lazić (predsjednik povjerenstva)
Committee memberIvan Dunđer (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Humanities and Social Sciences
(Department of information and Communication sciences)
Zagreb
Defense date and country2020-07-06, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Information and Communication Sciences
Information and Software Engineering
Abstract
Cilj ovoga diplomskog rada bio je istražiti područje pretraživanja glazbenih informacija (engl. music information retrieval). Pretraživanje glazbenih informacija bavi se vađenjem informacijama i zaključaka iz glazbe, indeksiranjem glazbe koristeći njena svojstva i razvojem različitih shema za pretraživanje i povrat glazbenih informacija. Kako bi se svi ti ciljevi postigli analiziraju se neka od glazbenih svojstva kao što su: ton, boja tona, harmonija itd. Nakon toga se pregledavaju neka područja unutar domene pretraživanja glazbenih informacija: audioidentifikacija, glazbene preporuke i jezici za opisivanje glazbe. Svako to područje se pojašnjava i navodi kako funkcionira te se navedi i nekoliko primjera. U praktičnom dijelu rada se radi klasifikacija žanrova uz pomoć programskog jezika Python i raznih knjižnica. Pojašnjava se ukratko samo područje klasifikacija žanrova i njene probleme. Za analizu svojstva pjesama se koristi Python knjižnica pod nazivom Librosa, a za klasifikaciju se koristi knjižnica Scikit-learn. Na kraju rada se pregledavaju rezultati klasifikacije i uspoređuju s rezultatima drugih radova koji su isto vršili klasifikaciju nad istim skupom podataka.
Abstract (english)
The aim of this graduate thesis was to explore the domain of music information retreival. Music information retrieval deals with extracting information and conclusions from music, indexing music using its properties, and developing various schemes for searching and retrieving music information. In order to achieve all these goals, some of the musical properties are analyzed, such as: tone, timbre, harmony, etc. After that, a couple of areas within the domain of music information retrieval are examined: audio identification, music recommendations and languages for describing music. Each of these areas is explained how it works, and a few examples are given. In the practical part, the classification of genres is done with the help of the Python programming language and various libraries. Genre classification task and its problems are explained briefly. A Python library called Librosa is used to analyze song properties, and Scikit-learn library is used for classification. At the end of the paper, the results of the classification are reviewed and compared with the results of other papers that also performed the classification on the same data set.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:131:354833
Study programmeTitle: Information Sciences; specializations in: Computer Science (Teaching, Research), Informatology, Information Sciences (teaching), Information Sciences (research)
Course: Information Sciences (research)
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra informacijskih znanosti (magistar/magistra informacijskih znanosti)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2020-07-07 11:50:26