What is it about?
This paper attempts to provide a task-oriented survey of symbolic music generation based on deep learning techniques, covering most of the currently popular music generation tasks. The distinct models under the same task are set forth briefly and strung according to their motivations, basically in chronological order. Moreover, we summarize the common datasets suitable for various tasks, discuss the music representations and the evaluation methods, highlight current challenges in symbolic music generation, and finally point out potential future research directions.
Featured Image
Photo by Possessed Photography on Unsplash
Why is it important?
This survey summarizes various methods under the same music generation subtask so that researchers can quickly grasp the current situation and learn from other methods, which brings great convenience for follow-up studies. According to whether the music generation has conditions, controls, performance characteristics, or interaction with people, symbolic music generation is divided into five categories: generation from scratch, conditional generation, controllable generation, performance generation, and interactive generation. Each generation task is further divided into finer-grained subtasks.
Perspectives
Read the Original
This page is a summary of: A Survey on Deep Learning for Symbolic Music Generation: Representations, Algorithms, Evaluations, and Challenges, ACM Computing Surveys, May 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3597493.
You can read the full text:
Resources
Contributors
The following have contributed to this page