GANs-based Music Generation: Unlocking the Power of Music

Emotion-Based Music Generation using Generative Adversarial Networks (GANs) refers to a brand-new approach that involves both the recognition of human emotions and generative adversarial networks to produce melodies specific to the user’s emotions. Emotions can be detected from various input sources including textual inputs, facial images or images of physiological signs. These emotions are processed and labelled according to the genre before feeding into a GAN; the generator synthesizes new music given certain detected emotion; the discriminator then further Refines the generated music output by comparing its quality to real music. A post-processing takes place in order to make the generated music conform to style and structure expectations. This approach yields possible uses in education or learning, adoption of music during treatment, entertainment as well as emotions.

Authors

Institutions

Publication Details

Published
2025-05-21
DOI
https://doi.org/10.1109/icaiss61471.2025.11042077
Primary Topic
Music Technology and Sound Studies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

GANs-based Music Generation: Unlocking the Power of Music

H. Anandakumar, S. Ananthi, S Rithika, S Oviya
Music Technology and Sound Studies
article

GANs-based Music Generation: Unlocking the Power of Music

H. Anandakumar, S. Ananthi, S Rithika, S Oviya
article en

Abstract

Emotion-Based Music Generation using Generative Adversarial Networks (GANs) refers to a brand-new approach that involves both the recognition of human emotions and generative adversarial networks to produce melodies specific to the user’s emotions. Emotions can be detected from various input sources including textual inputs, facial images or images of physiological signs. These emotions are processed and labelled according to the genre before feeding into a GAN; the generator synthesizes new music given certain detected emotion; the discriminator then further Refines the generated music output by comparing its quality to real music. A post-processing takes place in order to make the generated music conform to style and structure expectations. This approach yields possible uses in education or learning, adoption of music during treatment, entertainment as well as emotions.

Sri Eshwar College of Engineering
Openalex Percentile: Top 87%
Music Technology and Sound Studies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.