Simulation and Analysis of ANFIS (Adaptive Neuro-Fuzzy Inference System) for Music Genre

Music comes in many different genres and styles according to its content, which is easy for a human listener to distinguish but hard for a machine to do. This limitation encourages the creation of a system that can help a computer to classify music genre better. This paper proposed a simple method t...

Full description

Saved in:
Bibliographic Details
Published in:IOP conference series. Materials Science and Engineering 2020-03, Vol.771 (1), p.12016
Main Authors: Pratama, A H, Dwiono, W, Tamam, M T
Format: Article
Language:English
Subjects:
Accuracy
Adaptive systems
Artificial neural networks
Classification
Feature extraction
Frequency analysis
Fuzzy logic
Genre
Music
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Music comes in many different genres and styles according to its content, which is easy for a human listener to distinguish but hard for a machine to do. This limitation encourages the creation of a system that can help a computer to classify music genre better. This paper proposed a simple method that can classify music genre on a classical, jazz, pop, and rock using frequency analysis feature extraction and ANFIS classification method. There are two types of ANFIS model, which is model A and model B. The most accurate model, is model A with an average accuracy of 53,33% across all genre. The best model for single genre classification is Model B with 80% accuracy for Classic type.
ISSN:1757-8981
1757-899X
DOI:10.1088/1757-899X/771/1/012016