Composition and production of music using Momentum LSTM

Nikam, Sachin (2021) Composition and production of music using Momentum LSTM. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (2MB) | Preview

Abstract

Music plays important part in the field of media and entertainment.Composing and producing music requires high practical and theoretical knowledge which needs training and high skills. Knowledge of instruments becomes necessary and key factor while composing music. This becomes difficult for non-musicians or amateurs artists. This can be fulfilled by training the machines to do so. Use of Machine learning and neural network models is used to produce music from the training data. Multiple models were used previously. LSTM and GRU recurrent neural networks were implemented. Adding momentum to the LSTM can improve the model and predict better accuracy. The paper shows the Momentum LSTM which selects the important features from the midi dataset, which contains different musical features. Purpose of the research shows the use of Momentum LSTM Recurrent Neural Network to train on the Midi files and produce new composed files.

Item Type:	Thesis (Masters)
Subjects:	M Music and Books on Music > M Music Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Clara Chan
Date Deposited:	11 Dec 2021 11:03
Last Modified:	11 Dec 2021 11:03
URI:	https://norma.ncirl.ie/id/eprint/5203

Actions (login required)

View Item