A novel LSTM music generator based on the fractional time-frequency feature extraction

TL;DR

This paper introduces a new AI-based music generation system utilizing fractional Fourier transform for feature extraction and LSTM networks for prediction, producing music comparable to human compositions.

Contribution

The paper presents a novel combination of fractional Fourier transform and LSTM for music generation, enhancing feature extraction and prediction accuracy.

Findings

Generated music is of high quality and comparable to human compositions.

The system effectively extracts spectral features using FrFT.

LSTM network successfully predicts music sequences based on extracted features.

Abstract

In this paper, we propose a novel approach for generating music based on an artificial intelligence (AI) system. We analyze the features of music and use them to fit and predict the music. The fractional Fourier transform (FrFT) and the long short-term memory (LSTM) network are the foundations of our method. The FrFT method is used to extract the spectral features of a music piece, where the music signal is expressed on the time and frequency domains. The LSTM network is used to generate new music based on the extracted features, where we predict the music according to the hidden layer features and real-time inputs using GiantMIDI-Piano dataset. The results of our experiments show that our proposed system is capable of generating high-quality music that is comparable to human-generated music.