A Discriminative Model to Generate Melodies through Evolving LSTM Recurrent Neural Networks-Reference-Cited by-同舟云学术

A Discriminative Model to Generate Melodies through Evolving LSTM Recurrent Neural Networks

Published:2021-07-01 Issue: Volume: Page:52-59
ISSN:2394-4099
Container-title:International Journal of Scientific Research in Science, Engineering and Technology
language:en
Short-container-title:IJSRSET

Author:

Ashwin Nanda¹,Adusumilli Uday Kumar²,Kurra Lakshmi³,N Kemparaju⁴

Affiliation:

1. Professor, Dept. of Information Science and Engineering, East Point College of Engineering and Technology, Bangalore, India

2. Product Support Analyst, Associate, Infor, Bangalore, India

3. Student, Dept. of Information Science and Engineering, East Point College of Engineering and Technology, Bangalore, India

4. Head, Dept. of Information Science and Engineering, East Point College of Engineering and Technology, Bangalore, India

Abstract

The paper describes a method that uses evolving LSTM recurrent neural networks to generate melodic music through a discriminative model. The approach enclosed has achieved an accuracy level of over 90%, thus enabling our model to understand & generate music as per the input parameters. The input expected from the user is minimal and can be provided by a layman. The experiments presented here demonstrate how LSTM can successfully learn a form of training music data and compose a novel (and pleasing) melody based on that style of training. LSTM can play melodies with good timing and appropriate structure if the parameters have been set appropriately. The RNN Model presented in this paper leverages the benefits of LSTM networks and demonstrates how this feat can be achieved.

Publisher

Technoscience Academy

Subject

General Medicine

Reference31 articles.

1. Breuleux, O., Bengio, Y., and Vincent, P. (2011). Quickly generating representative samples from an RBM-derived process. Neural Computation, 23 (8), 20532073.

2. Karpathy, A., The unreasonable effectiveness of recurrent neural networks, 2015.

3. Eck, D. and Schmidhuber, J. Finding temporal structure in music: Blues improvisation with LSTM recurrent networks. In NNSP, pp. 747–756, 2002.

4. D. A. and M. Clements. Melody spotting using hidden markov models. In J. S. Downie and D. Bainbridge, editors, Proceedings of the 2nd Annual International Symposium on Music Information Retrieval (ISMIR), pages 109–117, Indiana University, Bloomington, Indiana, October 2001.

5. J. P. Bello, L. Daudet, and M. B. Sandler. Time-domain polyphonic transcription using self-generating databases. In Proceedings of the 112th Convention of the Audio Engineering Society, Munich, Germany, May 2002.