Music Classification in MIDI Format based on LSTM Mdel

2020/10/15 by Yiting Xia, Xia, Yiting, Yiwei Jiang +3
Computer Science · Arts and Humanities · #Music and Audio Processing #Music Technology and Sound Studies #Diverse Musicological Studies

paper · pdf · doi:10.48550/arxiv.2010.07739

Abstract

Music classification between music made by AI or human composers can be done by deep learning networks. We first transformed music samples in midi format to natural language sequences, then classified these samples by mLSTM (multiplicative Long Short Term Memory) + logistic regression. The accuracy of the result evaluated by 10-fold cross validation can reach 90%. Our work indicates that music generated by AI and human composers do have different characteristics, which can be learned by deep learning networks.

Related

• Melody Classifier with Stacked-LSTM
• Music Generation with Deep Learning
• Comparision Of Adversarial And Non-Adversarial LSTM Music Generative Models
• Bach Style Music Authoring System based on Deep Learning
• From Artificial Neural Networks to Deep Learning for Music Generation -- History, Concepts and Trends