IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

AI-Driven Music Composition by Integrating RNNs and GAs for Personalized Pop Songs

AI-Driven Music Composition by Integrating RNNs and GAs for Personalized Pop Songs
View Sample PDF
Author(s): K. S. Jishnu (SRM Institute of Science and Technology, Kattankulathur, India), P. S. Shijukumar (SRM Institute of Science and Technology, India), G. Bhargavi (SRM Institute of Science and Technology, India), Vimal Sankar (TKM Institute of Technology, India), P. S. Sujith Kumar (Sree Buddha College of Engineering, Pattoor, India)and Nisha Thorakattu Madathil (United Arab Emirates University, UAE)
Copyright: 2026
Pages: 30
Source title: Artificial Intelligence in Music Production: Innovations, Practices, and Industry Implications
Source Author(s)/Editor(s): Randy Joy Magno Ventayen (Pangasinan State University, Phillippines)
DOI: 10.4018/979-8-3373-6279-3.ch006

Purchase

View AI-Driven Music Composition by Integrating RNNs and GAs for Personalized Pop Songs on the publisher's website for pricing and purchasing information.

Abstract

An AI-powered music composition framework is introduced, capable of generating complete pop songs by integrating Recurrent Neural Networks (RNNs) with Genetic Algorithms (GAs). RNNs produce melodically coherent MIDI sequences that reflect long-term musical dependencies, while GAs refine song structure based on user preferences such as variation, transition smoothness, and catchiness. Unlike the MAGMA framework, which is limited to instrumental MIDI creation, the proposed system incorporates vocals using a realistic Text-to-Speech (TTS) engine. Lyrics can be user provided or generated through NLP and are precisely synchronized with the MIDI output using tools such as librosa, pydub, and fluidsynth. The implementation uses Python libraries including tensorflow, torch, pretty-midi, music21, pandas, and matplotlib, and a feedback loop allows users to iteratively improve song quality. The framework aims to make high-quality, personalized music production accessible to musicians, content creators, and professionals.

Related Content

Randy Joy Magno Ventayen, Elmar B. Noche, Maricel Aqui. © 2026. 34 pages.
Evren Idil Yazan. © 2026. 30 pages.
Sonia Ahuja. © 2026. 24 pages.
Saroj Sandeep Phalke, Gitanjali Shinde, Grishma Bobhate, Poonam Railkar, Haribhau R. Bhapkar, Sonal Fatangare. © 2026. 28 pages.
Syrenzo Ramos Sicuan. © 2026. 26 pages.
K. S. Jishnu, P. S. Shijukumar, G. Bhargavi, Vimal Sankar, P. S. Sujith Kumar, Nisha Thorakattu Madathil. © 2026. 30 pages.
Vibha Tiwari, Rahul Lalwani, Akshada Telang. © 2026. 36 pages.
Body Bottom