Jul 2026· Journal of Internet Technology· Vol 27, pp. 603-613· 0 citations
TL;DR
This study proposes a symbolic music generation system that integrates supervised learning and reinforcement learning and employs recurrent neural networks for sequence modeling, while a reinforcement learning module formulates music rules as reward functions to guide pitch, duration, and rhythm.
Abstract
Deep learning has been widely applied to digital art and music creation. However, producing melodies that follow music theory and match human compositional patterns remains challenging. This study proposes a symbolic music generation system that integrates supervised learning and reinforcement learning. The core framework employs recurrent neural networks for sequence modeling, while a reinforcement learning module formulates music rules as reward functions to guide pitch, duration, and rhythm. This hybrid approach helps produce outputs that better match human compositional patterns. We deploy the proposed framework as an Internet-based system that supports five distinct music styles and is publicly accessible online.
The proposed RL-based dynamic control system successfully transforms score elements into performance actions which enable robots to deliver expressive music performances.
A cross-modal framework that learns implicit music styles from raw audio and applies them to symbolic music generation and generates piano performances jointly conditioned on a lead sheet and a reference audio example, enabling controllable and stylistically faithful arrangement.
Jing-Wei Zhao, Gus G. Xia, Ziyu Wang et al.· 0 citations
This work proposes to learn a world model of piano sound using JEPA by framing music as an action-conditioned system, and shows that the learned model captures the relationships between musical actions and their resulting sound.
Ziyu Wang, Kun Fang, Yann LeCun· arXiv.org· 0 citations
Music is an expression of emotion and a universal language that connects people across various cultures. From timeless classical pieces to modern electronic beats, artificial intelligence is capable of composing, arranging, and even crafting refined musical arrangements in a wide variety of styles. This study, trains...
Duddela Sai Prashanth, Rakshith Bhandary, Bharath Rai et al.· Scientific Reports· 0 citations
In this paper, we study the task of automatic music upmixing, wherein a system predicts spatial mixing parameters from a multi-stem recording. Different from existing methods that rely on task-specific music encoders, we approach this task via audio language model (ALM) post-training, leveraging rich representations fr...
Zi-Xun Guo, Calvin Murdock, Sanjeel Parekh et al.· 0 citations
A reinforcement-learning model with a continuous action space that integrates sound synthesis during training and live performance is introduced and five complementary reward functions for matching target sounds are proposed.
Vincenzo Madaghiele, S. Fasciani, T. Kelkar et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
