Genre classification of songs using neural network

Author

Goel, Ankush ; Sheezan, Mohd ; Masood, Sarfaraz ; Saleem, Asma

Author_Institution

Dept. of Comput. Eng., Jamia Millia Islamia, New Delhi, India

fYear

2014

fDate

26-28 Sept. 2014

Firstpage

285

Lastpage

289

Abstract

The objective here is to eliminate the manual work of classifying genres of song in each song. With this startup work songs can be classified in real-time and proposed parallel architecture can be implemented on the multi-processing system as well. In this paper a set of features are obtained like beats/tempo, energy, loudness, speechiness, valence, danceability, acousticness, discrete wavelet transform etc., using Echonest libraries and are fed into the Parallel Multi-Layer Perceptron Network to obtain the genres of the song. The proposed scheme has an accuracy of 85% when used to classify two genres of songs that are Sufi and Classical.

Keywords

discrete wavelet transforms; multilayer perceptrons; multiprocessing systems; music; parallel processing; pattern classification; discrete wavelet transform; multilayer perceptron network; multiprocessing system; neural network; parallel architecture; song genre classification; Accuracy; Discrete wavelet transforms; Feature extraction; Mel frequency cepstral coefficient; Mood; Neural networks; Rocks; classification; echonest; genre; multilayered perceptron; songs;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Communication Technology (ICCCT), 2014 International Conference on

Conference_Location

Allahabad

Print_ISBN

978-1-4799-6757-5

Type

conf

DOI

10.1109/ICCCT.2014.7001506

Filename

7001506