Please use this identifier to cite or link to this item:
http://dspace.dtu.ac.in:8080/jspui/handle/repository/15818
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | RATHORE, SHASHANK | - |
dc.date.accessioned | 2017-07-21T13:54:17Z | - |
dc.date.available | 2017-07-21T13:54:17Z | - |
dc.date.issued | 2017-07 | - |
dc.identifier.uri | http://dspace.dtu.ac.in:8080/jspui/handle/repository/15818 | - |
dc.description.abstract | Humans have the ability to distinguish between two types of music very easily by listening to the songs for a short duration only. This decision cannot be only made only on the basis of basic music features, BPM and different pitches. This requires deeper understanding of the music. Machine Learning has been able to predict the different genres of music in a large collection of data. We are here trying to use this behavior by using various machine learning approaches and their accuracy in prediction. For feature extraction purpose of music we have taken MFCC (Mel Frequency Coefficients) into consideration which has given us improved performance. By using different machine learning algorithms we are able to understand music digitally on a new level that will help use it in other applications effectively for future purposes. | en_US |
dc.language.iso | en | en_US |
dc.relation.ispartofseries | TD-2791; | - |
dc.subject | MACHINE LEARNING APPROACHES | en_US |
dc.subject | MUSIC GENRE CLASSIFICATION | en_US |
dc.subject | MFCC | en_US |
dc.title | MACHINE LEARNING APPROACHES FOR MUSIC GENRE CLASSIFICATION | en_US |
dc.type | Thesis | en_US |
Appears in Collections: | M.E./M.Tech. Computer Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Shashank Thesis.pdf | 1.04 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.