prikaz prve stranice dokumenta Entropijska analiza glazbe u vremensko-freknvecijskoj domeni
Access restricted to students and staff of home institution
master's thesis
Entropijska analiza glazbe u vremensko-freknvecijskoj domeni
Rijeka: University of Rijeka, Faculty of Engineering, 2021. urn:nbn:hr:190:314462
Miletić, Ema
University of Rijeka
Faculty of Engineering
Department of Computer Engineering
Section of Software Engineering

Institutional repository: Repository of the University of Rijeka, Faculty of Engineering

Cite this document

Miletić, E. (2021). Entropijska analiza glazbe u vremensko-freknvecijskoj domeni (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:314462

Miletić, Ema. "Entropijska analiza glazbe u vremensko-freknvecijskoj domeni." Master's thesis, University of Rijeka, Faculty of Engineering, 2021. https://urn.nsk.hr/urn:nbn:hr:190:314462

Miletić, Ema. "Entropijska analiza glazbe u vremensko-freknvecijskoj domeni." Master's thesis, University of Rijeka, Faculty of Engineering, 2021. https://urn.nsk.hr/urn:nbn:hr:190:314462

Miletić, E. (2021). 'Entropijska analiza glazbe u vremensko-freknvecijskoj domeni', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 24 December 2024, https://urn.nsk.hr/urn:nbn:hr:190:314462

Miletić E. Entropijska analiza glazbe u vremensko-freknvecijskoj domeni [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2021 [cited 2024 December 24] Available at: https://urn.nsk.hr/urn:nbn:hr:190:314462

E. Miletić, "Entropijska analiza glazbe u vremensko-freknvecijskoj domeni", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:190:314462

Metadata
TitleEntropijska analiza glazbe u vremensko-freknvecijskoj domeni
Title (english)Entropy-Based Analysis of Music in Time-Frequency Domain
AuthorEma Miletić
MentorJonatan Lerga (mentor)
Committee memberKristijan Lenac (predsjednik povjerenstva)
Committee memberGoran Mauša (član povjerenstva)
Committee memberJonatan Lerga (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Computer Engineering)
(Section of Software Engineering)
Rijeka
Defense date and country2021-09-24, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Vremensko-frekvencijske distribucije spektrogram, Wigner-Ville i Choi-Williams glazbenih signala korištene su kao temelj za računane Renyijeve entropije za dani signal. Glazbena su djela grupirana prema raspoloženju koje predstavljaju te je izračun entropije proveden za računalno generirane uzorke glazbe te stvarna glazbena djela. Entropije računalno generiranih uzoraka ponašaju se drugačije u odnosu na entropije stvarnih djela. Rezultati dobiveni računanjem Renyijeve entropije na segnemtima signala prikazani su grafički. Prikazane su entropije pojedinih glazbenih djela grupiranih prema raspoloženju, kao i prosječne entropije za svaku skupinu. Najveću entropiju imaju audio signali koji predstavljaju emociju ljutnje, slijede sreća, smirenost te tuga. Najistaknutija razlika u prosječnim entropijama raznih skupina signala primijećena je kod Wigner-Villea. Iz prikaza entropije signala u kojemu se naglo izmijenju dva raspoloženja uočeno je da entropije dobivene iz spektrograma i Wigner-Villeove distribucije dobro prikazuju prijelaze između dijelova, dok je Choi-Williams distribucija lošija.
Abstract (english)
Renyi entropies of a music signal have been computed from the signal’s time-frequency distributions, namely spectrogram, Wigner-Ville and Choi-Williams. The music has been divided into groups based on its mood. The entropy has been calculated for both computer-generated music samples and real pieces of music. The entropies of computer-generated music behave differently from the entropies of real music signals. The results obtained by calculating Renyi entropy on signal segments are graphically represented for individual music pieces grouped by mood and their average entropies. Signals representing anger have the largest values of entropy, followed by happiness, calmness and sadness. The most distinct difference in the groups’ average entropies has been noticed in Wigner-Ville. The entropy of a signal comprised of multiple mood changes shows that the entropies calculated from the spectrogram and Wigner-Ville distribution are good at discerning the transitions between moods, while Choi-Williams distribution performs more poorly.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:314462
Study programmeTitle: Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2021-10-18 07:32:34