A Creating Musical Compositions Through Recurrent Neural Networks: An Approach for Generating Melodic Creations
Authors:
P. Prasanth Anand, Najib Sulthan, G Jayanth, P. Deepika, Azlin Abd Jamil
Addresses:
1,2,3,4Department of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, India, India. 5Department of Research and Innovation, Universiti Teknologi Malaysia, Johor Bahru, Malaysia. pp2259@srmist.edu.in1, na2772@srmist.edu.in2, gg4307@srmist.edu.in3, deepikap2@srmist.edu.in4, azlinjamil@utm.my5
The task of music generation is complex and demanding, necessitating the understanding and modeling intricate musical patterns and structures. RNNs have been demonstrated to be effective in generating music, as they can learn to generate sequence data, including musical notes. This project proposes a novel approach for generating melodic creations using Long Short-Term Memory (LSTM) networks. As an RNN, LSTMs are well-equipped to learn long-lasting dependencies in sequence data, making them an ideal choice for music generation, where the model must learn patterns and relationships among musical notes over a long period. The proposed methodology is derived from a Hierarchical LSTM structure. This structure enables the model to comprehend the various levels of musical structure, including the melody’s note order, rhythm, and contour. The model is initially trained on a set of MIDI files, enabling it to comprehend musical patterns and structures across various genres and styles. Once the model has been trained, it can create new melodies. To begin with, the model is provided with a seed melody. The model then utilizes its musical knowledge to extend the seed melody. The model is also capable of generating melodies in a particular style. This is achieved by training the model on a set of melodies in that particular style. Subsequently, the model can create new melodies in the same style as those in the training set. This approach can be applied to various applications, including creating new and original music for games, films, and other uses, and educational resources for musicians and songwriters.
Keywords: Music Generation; Machine Learning; Deep Learning; Artificial Intelligence; Music and Technology; Long Short-Term Memory; Melody Creation; Art and Technology; Recurrent Neural Networks.
Received on: 29/11/2022, Revised on: 27/01/2023, Accepted on: 02/03/2023, Published on: 07/04/2023
FMDB Transactions on Sustainable Computing Systems, 2023 Vol. 1 No. 2, Pages: 54-64
- Views : 214
- Downloads : 17