Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 21, 2025Computer Music Journal

Toward Guided Musical Form: Structuring Generative Music with LLMs

View Full Paper
Ask AI
Bookmark
Share

Authors

LALilac Atassi

Discussion

Loading...

Member takes

Overview

This article demonstrates how generative models improve musical form in long compositions, indicating more coherent structure across temporal scales.

Key Points

  • Coherent structure is produced in long-form music using generative models and hierarchical design, enhancing listening experience.
  • Music generated shows greater variation and coherence, supported by quantitative metrics and listening tests.
  • Hierarchical approach combines large language models with audio generation for optimized musical structure.
  • Iterative refinement highlights the significance of prompt design in improving music generation quality.

Cite This Study

Lilac Atassi (2025) studied this question.

synapsesocial.com/papers/6924e3ecc0ce034ddc34ed5ahttps://doi.org/10.1162/comj.a.682
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Large Language Models: From Notes to Musical Form2024
  2. 2Large Language Models' Internal Perception of Symbolic Music2025
  3. 3Probing Audio-Generation Capabilities of Text-Based Language Models2025
  4. 4MuPT: A Generative Symbolic Music Pretrained Transformer2024 · 3 citations
  5. 5SongComposer: A Large Language Model for Lyric and Melody Composition in Song Generation2024 · 4 citations