Crafting Creative Melodies: A User-Centric Approach for Symbolic Music Generation

Author:

Dadman Shayan1ORCID,Bremdal Bernt Arild1

Affiliation:

1. Department of Computer Science, UiT, The Arctic University of Tromsø, Lodve Langesgate 2, 8514 Narvik, Norway

Abstract

Composing coherent and structured music is one of the main challenges in symbolic music generation. Our research aims to propose a user-centric framework design that promotes a collaborative environment between users and knowledge agents. The primary objective is to improve the music creation process by actively involving users who provide qualitative feedback and emotional assessments. The proposed framework design constructs an abstract format in which a musical piece is represented as a sequence of musical samples. It consists of multiple agents that embody the dynamics of musical creation, emphasizing user-driven creativity and control. This user-centric approach can benefit individuals with different musical backgrounds, encouraging creative exploration and autonomy in personalized, adaptive environments. To guide the design of this framework, we investigate several key research questions, including the optimal balance between system autonomy and user involvement, the extraction of rhythmic and melodic features through musical sampling, and the effectiveness of topological and hierarchical data representations. Our discussion will highlight the different aspects of the framework in relation to the research questions, expected outcomes, and its potential effectiveness in achieving objectives. Through establishing a theoretical foundation and addressing the research questions, this work has laid the groundwork for future empirical studies to validate the framework and its potential in symbolic music generation.

Funder

Norges Forskningsråd

Publisher

MDPI AG

Reference46 articles.

1. A Survey on Deep Learning for Symbolic Music Generation: Representations, Algorithms, Evaluations, and Challenges;Ji;ACM Comput. Surv.,2023

2. Toward Interactive Music Generation: A Position Paper;Dadman;IEEE Access,2022

3. Jaques, N., Gu, S., Turner, R.E., and Eck, D. (2024, March 12). Tuning Recurrent Neural Networks with Reinforcement Learning. Available online: https://openreview.net/forum?id=Syyv2e-Kx.

4. Roberts, A., Engel, J., Raffel, C., Hawthorne, C., and Eck, D. (2018, January 10–15). A hierarchical latent vector model for learning long-term structure in music. Proceedings of the International Conference on Machine Learning, Stockholm, Sweden.

5. Dadman, S., and Bremdal, B.A. (2023, January 12–14). Multi-agent Reinforcement Learning for Structured Symbolic Music Generation. Proceedings of the International Conference on Practical Applications of Agents and Multi-Agent Systems, Guimaraes, Portugal.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3