prikaz prve stranice dokumenta Akustički otisci
No public access
master's thesis
Akustički otisci
2015. urn:nbn:hr:168:285608
Tumbri, Jurica
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Tumbri, J. (2015). Akustički otisci (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:285608

Tumbri, Jurica. "Akustički otisci." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2015. https://urn.nsk.hr/urn:nbn:hr:168:285608

Tumbri, Jurica. "Akustički otisci." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2015. https://urn.nsk.hr/urn:nbn:hr:168:285608

Tumbri, J. (2015). 'Akustički otisci', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 16 April 2024, https://urn.nsk.hr/urn:nbn:hr:168:285608

Tumbri J. Akustički otisci [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2015 [cited 2024 April 16] Available at: https://urn.nsk.hr/urn:nbn:hr:168:285608

J. Tumbri, "Akustički otisci", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2015. Available at: https://urn.nsk.hr/urn:nbn:hr:168:285608

Please login to the repository to save this object to your list.
Metadata
TitleAkustički otisci
Title (english)Acoustic fingerprints
AuthorJurica Tumbri
MentorKristian Jambrošić (mentor)
Committee memberKristian Jambrošić (predsjednik povjerenstva)
Committee memberBojan Ivančević (član povjerenstva)
Committee memberIvan Đurek (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2015-07-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U radu je opisan primarni način rada i primjene sustava identifikacija glazbenih zapisa s akustičnim otiscima. Navedeni su opći dijelovi sustava te mogući procesi od pripremne obrade zapisa, izgleda otiska i pretraživanja baze s najvećim fokusom na ekstrakciju značajki. Nabrojane su najviše korištene značajke u amplitudnoj i spektralnoj domeni, te obrađena su dva najzastupljenija algoritma detekcije tempa u glazbi. U sklopu rada su izvedeni algoritmi ekstrakcija značajki u programskom sučelju Matlab čiji se izvorni kodovi nalaze u dodatku. Isti algoritmi su testirani na proizvoljnoj bazi glazbenih zapisa s obzirom na osjetljivost na dužinu analiziranog uzorka, dodani šum, te pomak tona.
Abstract (english)
The paper contains descriptions of the basic workflow and applications of audio identification systems based on acoustic fingerprints. Descriptions contain basic parts of the system and possible processes in it from sample analysis, fingerprint structure and database search and matching with a special emphasis on feature extraction. Listed are the most used features in amplitude and spectral domain, along with the basic tempo detection algorithms. As a part of the thesis, several feature algorithms were implemented in Matlab with their codes added in the supplement. The same algorithms were tested on a database of songs along with testing their sensitivity to length of input sample, added noise and pitch shift.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:285608
Study programmeTitle: Information and Communication Technology
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2018-02-06 14:11:23