Open AccessClassification of Musical Instruments Sound Using Pre-Trained Model with Machine Learning Techniques
Author(s) -
S. Prabavathy
Publication year - 2020
Publication title -
asian journal of managerial science/asian journal of managerial science
Language(s) - English
Resource type - Journals
eISSN - 2583-9810
pISSN - 2249-6300
DOI - 10.51983/ajes-2020.9.1.2369
Subject(s) - support vector machine , computer science , musical , musical instrument , artificial intelligence , process (computing) , machine learning , pattern recognition (psychology) , task (project management) , speech recognition , engineering , art , physics , systems engineering , acoustics , visual arts , operating system
Classify the musical instruments by machine is a challenging task. Musical data classification becomes very popular in research field. A huge manual process required to classify the musical instrument. This proposed system classifies the musical instruments using GoogleNet which is a pretrained network model; SVM and kNN are the two techniques which is used to classify the features. In this paper, to simply musical instruments classifications based on its features which are extracted from various instruments using recent algorithms. The performance of kNN with SVM compares in this proposed work. The musical instruments are identified and its accuracy is computed with the classifiers SVM and kNN, using the SVM with GoogleNet 99% achieve as a high accuracy rate in classifying the musical instruments. In this system sixteen musical instruments used to find the accuracy using SVM and kNN.