Download
PDF 1.31 MB
undergraduate thesis
8   8
Tempo and beat estimation of musical signals
Irena Mostarac (2017)
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing
Metadata
TitlePrepoznavanje tempa pjesme iz glazbenog signala
AuthorIrena Mostarac
Mentor(s)Irena Galić (thesis advisor)
Abstract
U ovom radu objašnjeno je kako se Fourierovom transformacijom i autokorelacijskom funkcijom mogu obrađivati glazbeni signali. Pritom je cilj odrediti glazbeni tempo iz signala pomoću udaljenosti između dva susjedna vrha u glazbenom signalu. Obrađene metode daju rezultate o tempu preko različitih vrsta i količina filtra. Rezultati su ovisni o metodi i vrsti signala, a u mjerenju se upotrijebilo 16 različitih glazbenih žanrova. Mjerenja se vrše računalnom obradom signala dijelom u online izvedbama, a većim dijelom u programu Matlab. Metode koje su korištene u usporednim mjerenjima su metoda otkucaja i Scheirerova metoda
Keywordstempo bpm musical signal Fourier tap method Tolonen Karjalainen Scheirer
Parallel title (English)Tempo and beat estimation of musical signals
Committee MembersIrena Galić (committee chairperson)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Lower level organizational unitsDepartment of Software Engineering
Chair of Visual Computing
PlaceOsijek
StateCroatia
Scientific field, discipline, subdisciplineTECHNICAL SCIENCES
Computing
Program Engineering
Study programme typeprofessional
Study levelundergraduate
Study programmeProfessional study programme of Electrical Engineering; specializations in: Power Engineering, Automation, Informatics
Study specializationInformatics
Academic title abbreviationbacc.ing.el.
Genreundergraduate thesis
Language Croatian
Defense date2017-09-27
Parallel abstract (English)
This paper explains how Fourier's transformation and autocorrelation function can process musical signals. The purpose is to define the musical pitch of the signal by the distance between the two neighboring peaks in the musical signal. The methods used give tempo results across different types and quantities of filters. Results depend on the method and type of signal and in measurements are used 16 different music genres. Measurements are performed by computer processing of the signal partly in online performances and mostly in Matlab. The methods used in comparative measurements are the tap method and Scheirer's method
Parallel keywords (Croatian)tempo bpm glazbeni signal Fourier metoda otkucaja Tolonen Karjalainen Scheirer
Resource typetext
Access conditionOpen access
Terms of usehttp://rightsstatements.org/vocab/InC/1.0/
URN:NBNhttps://urn.nsk.hr/urn:nbn:hr:200:964565