Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/17931
Title: Automatic music mood classification
Authors: Tan, Kian Tong.
Keywords: DRNTU::Engineering
Issue Date: 2009
Abstract: With high popularity of audio files and increasing size of data storages devices, organizing audio files became a huge problem. In order to provide a better solution of storing and classifying music, this project will create a program that will automatically classify the music according to the mood that is usually perceived by the listeners. Before starting on how to classify music moods, one would need to know what the music moods are and how are they is going to be classified. It is found that Hevner’s classification of music moods is one of the ways that can classify the music moods. According to Hevner’s classification, there are eight major music mood categories. All the music emotions are classified under these eight groups. In this project, statistical approach is being used towards automatic classification of music moods. As a result, data about the song needed to be gathered. This is being done by using MATLAB and MIR toolbox to help in extracting the music features and the data. Data being mainly mean and standard deviation of each music feature. A total 76 different data feature are obtained. The song database is divided in to two, 320 training files and 160 testing files. In the end, only 71.25% of accuracy is obtained in classifying 4 groups.
URI: http://hdl.handle.net/10356/17931
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
E_A3176-081.pdf
  Restricted Access
629.54 kBAdobe PDFView/Open

Page view(s)

257
checked on Sep 28, 2020

Download(s)

10
checked on Sep 28, 2020

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.