ORIGINAL RESEARCH article
Front. Comput. Sci.
Sec. Human-Media Interaction
Volume 7 - 2025 | doi: 10.3389/fcomp.2025.1543074
This article is part of the Research TopicEmbodied Perspectives on Sound and Music AIView all articles
NeuralConstraints: Integrating a Neural Generative Model with Constraint-Based Composition
Provisionally accepted
- 1University of Bergen, Bergen, Norway
- 2University of Manitoba, Winnipeg, Manitoba, Canada
- 3Harvard University, Cambridge, Massachusetts, United States
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
We present 'NeuralConstraints,' a suite of computer-assisted composition tools that integrates a feedforward neural network as a rule within a constraint-based composition framework. 'NeuralConstraints' combines the predictive generative abilities of neural networks trained on symbolic musical data with an advanced backtracking constraint algorithm. It provides a userfriendly interface for exploring symbolic neural generation, while offering a higher level of creative control compared to conventional neural generative processes, leveraged by the constraint solver. This article outlines the technical implementation of the core functionalities of 'NeuralConstraints' and illustrates their application through specific tests and examples of use.
Keywords: artificial intelligence, machine learning, human-computer interaction, Computer-Assisted Composition, neural networks, deep learning, Constraints Solver Algorithms
Received: 10 Dec 2024; Accepted: 09 Apr 2025.
Copyright: © 2025 Vassallo, Sandred and Vincenot. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Juan Sebastian Vassallo, University of Bergen, Bergen, Norway
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.