| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Razvrščanje glasbe po žanrih s pomočjo strojnega učenja
Authors:ID Zemljina, Tim (Author)
ID Žlahtič, Bojan (Mentor) More about this mentor... New window
Files:.pdf VS_Zemljina_Tim_2026.pdf (2,30 MB)
MD5: A170BECC96C4C450EC468793A62A1DF4
 
Language:Slovenian
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V diplomskem delu smo se ukvarjali z izgradnjo konvolucijske nevronske mreže, specializirane za zaznavanje zvrsti glasbenega vira, podanega v obliki zvočne datoteke. Takšne mreže se že uporabljajo, večinoma v sklopu platform za pretočno predvajanje glasbe kot pripomoček za algoritme predlaganja vsebin. V sklopu tega dela smo primerjali različne oblike predstav zvočnega signala, kot so valovna oblika zvoka in različni spektrogrami, ter raziskovali, kako značilnice, ki jih je mogoče izvleči iz teh predstavitvenih oblik, vplivajo na učinkovitost delovanja mreže. Prav tako smo osnovno obliko mreže nadgradili z uporabo sodobnih metod strojnega učenja in tako poskušali izboljšati uspešnost njenega zaznavanja.
Keywords:Strojno učenje, glasba, razvrščanje podatkov, nevronske mreže, Python
Place of publishing:Maribor
Year of publishing:2026
PID:20.500.12556/DKUM-99091 New window
Publication date in DKUM:24.09.2026
Views:99
Downloads:1
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:30.07.2026

Secondary language

Language:English
Title:Music classification by genre using machine learning
Abstract:In this thesis work we created a convolutional neural network specialized for recognizing the genres of a musical source given in the form of a sound file. These kinds of networks are already in use, mostly in the context of music streaming platforms as an aid for recommendation algorithms. As part of this work we compared different formats for depicting the sound signal such as a wave form and various spectrograms and how the features, which can be extracted from these formats impact the efficacy of the neural network. We had also upgraded the basic form of the network using modern methods of machine learning in the effort to improve the success rate of it's detection.
Keywords:Machine learning, music, data classification, neural networks, Python


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica