---
title: "METEOR: Melody-aware Texture-controllable Symbolic Music Re-Orchestration via Transformer VAE"
authors:
  - "Dinh-Viet-Toan Le"
  - "Yi-Hsuan Yang"
doi: "10.24963/ijcai.2025/1125"
url: "https://ijcai.org/proceedings/2025/1125"
pdf: "https://ijcai.org/proceedings/2025/1125.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "10126-10134"
track: "AI, Arts & Creativity"
keywords:
  - "Methods and resources: AI systems for collaboration and co-creation"
  - "Methods and resources: Machine learning, deep learning, neural models, reinforcement learning"
  - "Application domains: Music and sound"
---

# METEOR: Melody-aware Texture-controllable Symbolic Music Re-Orchestration via Transformer VAE

Dinh-Viet-Toan Le, Yi-Hsuan Yang

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 10126-10134. DOI: [10.24963/ijcai.2025/1125](https://doi.org/10.24963/ijcai.2025/1125)

## Abstract

Re-orchestration is the process of adapting a music piece for a different set of instruments. By altering the original instrumentation, the orchestrator often modifies the musical texture while preserving a recognizable melodic line and ensures that each part is playable within the technical and expressive capabilities of the chosen instruments.
    
In this work, we propose METEOR, a model for generating Melody-aware Texture-controllable re-Orchestration with a Transformer-based variational auto-encoder (VAE). This model performs symbolic instrumental and textural music style transfers with a focus on melodic fidelity and controllability. We allow bar- and track-level controllability of the accompaniment with various textural attributes while keeping a homophonic texture. With both subjective and objective evaluations, we show that our model outperforms style transfer models on a re-orchestration task in terms of generation quality and controllability. Moreover, it can be adapted for a lead sheet orchestration task as a zero-shot learning model, achieving performance comparable to a model specifically trained for this task.