Classify Song Genre from Audio Data |
Author(s): |
| Aditya Panchal , A. D. Patel Institute of Technology; Advait Thakkar, A. D. Patel Institute of Technology |
Keywords: |
| Music Genre Classification, Machine Learning, Pattern Classification, Feature Selection, Data Manipulation, Importing and Cleaning Data, NumPy, Pandas, Python3, Audio Signal Processing, Music, Signal Classification, Statistical Analysis, Feature Extraction, Information Retrieval |
Abstract |
|
This system was focused on creating a classifying application based on music genre. The first and basic step to achieve this task is to have a data set with the clear differential genre based on which we will make the decisions, followed by normalization of data, which is performed by use of python libraries like Librosa and PyAudio. There are also built-in modules for some basic audio functionalities in these libraries or by performing component analysis which is a statistical procedure that uses an orthogonal transformation to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables on that data. Finally, compare the trained decision tree to logistic regression for classifying the genre of the given song. |
Other Details |
|
Paper ID: IJSRDV7I60231 Published in: Volume : 7, Issue : 6 Publication Date: 01/09/2019 Page(s): 438-440 |
Article Preview |
|
|
|
|
