prikaz prve stranice dokumenta Automatska transkripcija glazbe
  Download
PDF 2.13 MB
undergraduate thesis
Automatska transkripcija glazbe
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. urn:nbn:hr:200:660540
Sekereš, Ivan
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing

Institutional repository: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek

Cite this document

Sekereš, I. (2023). Automatska transkripcija glazbe (Undergraduate thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:660540

Sekereš, Ivan. "Automatska transkripcija glazbe." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:660540

Sekereš, Ivan. "Automatska transkripcija glazbe." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:660540

Sekereš, I. (2023). 'Automatska transkripcija glazbe', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 12 May 2024, https://urn.nsk.hr/urn:nbn:hr:200:660540

Sekereš I. Automatska transkripcija glazbe [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2023 [cited 2024 May 12] Available at: https://urn.nsk.hr/urn:nbn:hr:200:660540

I. Sekereš, "Automatska transkripcija glazbe", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:200:660540

Metadata
TitleAutomatska transkripcija glazbe
Title (english)Automatic music transcription
AuthorIvan Sekereš
MentorHrvoje Leventić (mentor)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Visual Computing)
Osijek
Defense date and country2023, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Data Processing
Abstract
Problem automatske transkripcije glazbe poznat je znanstvenicima i istraživačima još od 70-ih godina prošlog stoljeća. Iako se čini kao trivijalan zadatak kojemu je cilj pretvorba zvučnog zapisa u notni zapis, zapravo predstavlja široko područje primjene. Područje problema automatske transkripcije podosta je zanimljivo jer objedinjuje glazbene i računalne znanosti te otvara nove mogućnosti proširivanja područja istraživanja obrade zvučnih signala. U ovom radu opisane su glavne značajke glazbe potrebne za proces automatske transkripcije. Opisane su razine automatske transkripcije kao i više glazbene strukture poput harmonije i polifonije. Dani su programski primjeri određivanja visina tonova, ritma, tempa i početaka nota zajedno s vizualnim prikazima izlaza takvih primjera. U svrhu praktičnog dijela stvoren je algoritam za detekciju akorda unutar skladbe. Na primjeru algoritma se jasno primjećuje kako je za usavršavanje detektiranja glazbenih struktura potrebno imati robustan algoritam iz kojeg stoji puno istraživanja. Također su prikazane i uspoređene napredne metode automatske transkripcije koje se koriste postupcima kao što su to množenje nenegativnih matrica i uporabom neuronskih mreža.
Abstract (english)
Automatic transcription problem is knows to scientists and researchers since the 70s of the last century. Although it seems like a trivial task which goal is to convert audio record into a music notation it actually represents wide area of use. The scope of automatic music transcription problem is quite interesting because it unites musical and computer branches of science while opening new possibilities of expanding research area in terms of processing audio signals. This paper describes main features of music needed for the process of automatic transcription. Levels of automatic transcription are described as well as higher musical structures such as harmony and polyphony. Programming examples of determining pitches, rhythm, tempo, and note onsets are provided along with visual representations of the outputs of such examples. For practical purposes of this paper, an algorithm was created for the detection of chords within a composition. The example of the algorithm clearly shows that in order to perfect the detection of musical structures, it is necessary to have a robust algorithm, which is based on a lot of research. Also presented and compared are advanced methods of automatic transcription that use procedures such as nonnegative matrix multiplication and the use of neural networks.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:660540
Study programmeTitle: Undergraduate University Study Programme in Computer Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-10-20 09:07:05