Klasifikasi Alat Musik Tradisional dengan Metode Machine Learning dengan Librosa dan Tensorflow pada Python

Puja Anggeli, S Suroso, M. Zakuan Agung

Abstract


The development of artificial intelligence technology AI (Artificial Intelligence) has been widely applied in various fields of daily life. AI (Artificial Intelligence) is divided into several branches, one of which is Machine Learning. Machine Learning is developed based on statistics, mathematics and data mining so that machines can learn by analyzing data without needing to be reprogrammed. With the development of the music world, not many people and the current generation know about traditional music from their respective regions. Traditional musical instruments produce sound art that has its own characteristics and uniqueness which is passed down from generation to generation. Therefore, to simplify the process of recognizing each musical instrument, a system was created that can classify traditional musical instruments using machine learning. The methods used in this research are librosa and tensorflow, where tensorflow is used for numerical computing and large-scale machine learning projects that have the best performance in classifying. In this study using Python 3.6 as a programming language and using PyCharm as a Integrated Development Environment (IDE). From the results, the system accuracy as expected after being tested several times, namely 91%.

Full Text:

PDF

References


IBM Cloud Education. 2020. Machine Learning, https://www.ibm.com/cloud/learn/machine-learning.

Tensorflow, https://www.tensorflow.org/.

GitHub, Inc. 2021. Tensorflow, https://github.com/tensorflow/tensorflow.

Mel Frequency Cepstral Coefficient (MFCC) tutorial, http://practicalcryptography.com/miscellaneous/machine-learning/guide-mel-frequency-cepstral-coefficients-mfccs/.

Librosa Development Team. Librosa. 2013-2021, https://librosa.org/doc/main/index.html.

Hidden Layer Perceptron In Tensorflow, https://www.javapoint.com/hidden-layer-perceptron-in-tensorflow.

Arik Dian Pratama, Hozairi, & Tony Yulianto. Klasifikasi Musik Berdasarkan Genre Menggunakan Jaringan Syaraf Tiruan. Vol 2, No 1. Oktober 2016.

Danny Lionel, Rudy Adipranata, & Endang Setyati. Klasifikasi Genre Musik Menggunakan Metode Deep Learning Convolutional Neural Network dan Mel-Spektrogram. Vol 7, No 1. 2019.

Huzaifah, M. 2017. Comparison of Time-Frequency Resperesentations for Environmental Sound Classification using Convolutional Neural Network. arXiv: 1706.07156.

Endang Retnoningsih, Rully Pramudita. Mengenal Machine Learning Dengan Teknik Supervised dan Unsupervised Learning Menggunakan Python. Vol 7, No.2, Desember 2020. 156-165




DOI: http://dx.doi.org/10.30645/j-sakti.v5i2.390

Refbacks

  • There are currently no refbacks.


J-SAKTI (Jurnal Sains Komputer & Informatika)
Published Papers Indexed/Abstracted By:

Jumlah Kunjungan :

View My Stats