METEOR: Melody-aware Texture-controllable Symbolic Orchestral Music Generation via Transformer VAE

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Le, Dinh-Viet-Toan, Yang, Yi-Hsuan
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909666055815168
author Le, Dinh-Viet-Toan
Yang, Yi-Hsuan
author_facet Le, Dinh-Viet-Toan
Yang, Yi-Hsuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_11753
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle METEOR: Melody-aware Texture-controllable Symbolic Orchestral Music Generation via Transformer VAE
Le, Dinh-Viet-Toan
Yang, Yi-Hsuan
Sound
Audio and Speech Processing
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.
title METEOR: Melody-aware Texture-controllable Symbolic Orchestral Music Generation via Transformer VAE
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2409.11753