University of Twente Student Theses

Login

Classifying Classical Piano Music Into Time Period Using Machine Learning

Spijker, B.C. van 't (2020) Classifying Classical Piano Music Into Time Period Using Machine Learning.

[img] PDF
1MB
Abstract:The combination of Music and Machine Learning is a popular topic. Much research has been done attempting to classify pop music in different genres, but classical music has been looked at less, mainly because of the lack of available datasets. In this paper, classical piano music dating from the 17th to the 20th century is classified into the category period of composition. For this the MAESTRO dataset from Magenta is used, consisting of approximately 200 hours of piano performance recordings. Mel-Frequency Cepstral Coefficients and Chromagrams are evaluated as features, and they are tested with Convolutional Neural Networks, Long Short-Term Memory (a type of Recurrent Neural Networks) and Support Vector Machines as Machine Learning algorithms.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:01 general works, 02 science and culture in general, 24 dramaturgy, musicology, 54 computer science
Programme:Business Information Technology MSc (60025)
Link to this item:http://purl.utwente.nl/essays/80618
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page