Development of music emotion classification system using convolution neural network
- PDF / 1,372,281 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 83 Downloads / 271 Views
Development of music emotion classification system using convolution neural network Deepti Chaudhary1,3 · Niraj Pratap Singh1 · Sachin Singh2 Received: 27 May 2020 / Accepted: 16 November 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Music emotion classification (MEC) is the multidisciplinary research area that is related to perceive the emotions from the songs and label the songs with particular emotion classes. MEC systems (MECS) extract the features from the songs and then the songs are categorized on the basis of emotions by comparing their features. In this paper an MECS has been proposed that makes use of Convolutional Neural Network (CNN) by converting the music to their visual representation known as spectrograms. By using CNN extraction of specific features of music signals is not necessarily required to classify the songs. In this work two MECS are trained and tested by using Hindi database by using CNN and third MECS system is developed by using SVM. In first MECS spectrograms are obtained by using hamming windows of size 2048 and noverlap factor of 1024 and in second MECS spectrograms are obtained by using hamming windows of size 1024 and noverlap factor of 512. The three combinations of CNN layers are used in order to classify the songs in four, eight and sixteen classes on the basis of emotional tags. The performance of MECS design is analyzed on the basis of training accuracy, validation accuracy, training loss and validation loss. Results show that the two MECS systems developed by CNN has better accuracy and less loss than the third MECS system modeled by SVM. Keywords Music emotion classification (MEC) · Convolution neural network (CNN) · Spectrograms · Emotion model
1 Introduction Music is originated from a Greek term “mousike”, which means “art of Muses”. In ancient times, Muses is related with goddesses of music, art, poetry and dance. Music can be produced by arranging various sounds together. These sounds can be vocal or instrumental. Music is a source of entertainment for people. Every work becomes interesting by playing music in background. Not only species other than humans can sing but also react to music in a similar manner * Deepti Chaudhary [email protected] 1
Department of Electronics Engineering, National Institute of Technology Kurukshetra, Kurukshetra, Haryana 136119, India
2
Department of Electrical and Electronics Engineering, National Institute of Technology, New Delhi, Delhi 110040, India
3
Electronics and Communication Department, University Institute of Engineering and Technology, Kurukshetra University, Kurukshetra, Haryana 136119, India
as humans. Birds and animals react emotionally different for distinct variety of songs. The term emotion is originated from a French word emouvoir, which means “to stir up”. Emotion is psychological arousal that can regulate behaviour and thoughts of human beings. Emotion can be described by considering noticeable feelings, expressions and reaction to a particular event for a short
Data Loading...
