High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Music Generation using XLSTM

Author(s):

Vedant Kailas Mahajan , Dr. D. Y. Patil Institute of Engineering, Management and Research, Akurdi, Pune-44; Sanchit Bokade, Dr. D. Y. Patil Institute of Engineering, Management and Research, Akurdi, Pune-44; Avni Kolapkar, Dr. D. Y. Patil Institute of Engineering, Management and Research, Akurdi, Pune-44; Arshin Sayyad, Dr. D. Y. Patil Institute of Engineering, Management and Research, Akurdi, Pune-44; Mrs. Vibhavari Jawale, Dr. D. Y. Patil International University, Akurdi, Pune-44

Keywords:

Artificial Intelligence (AI), Natural Language Processing (NLP), Machine Learning (ML), Large Language Modules (LLM)

Abstract

Music generation has gained significant traction with the advent of deep learning techniques, particularly through the use of recurrent neural networks (RNNs) like Long Short-Term Memory (LSTM) networks. The Extended Long Short-Term Memory (xLSTM) model enhances traditional LSTMs by introducing innovations such as exponential gating and modified memory structures, which are particularly beneficial for capturing the complexities of musical composition. This review paper explores the application of xLSTM in music generation, detailing its architecture, advantages, and performance compared to traditional LSTMs and other state-of-the-art models.

Other Details

Paper ID: IJSRDV13I20107
Published in: Volume : 13, Issue : 2
Publication Date: 01/05/2025
Page(s): 182-183

Article Preview

Download Article