Guardado en:
Detalles Bibliográficos
Autores principales: He, Xuzheng, Nan, Nan, Wang, Zhilin, Kang, Ziyue, Mo, Zhuoru, Li, Ao, Pan, Yu, Li, Xiaobing, Yu, Feng, Guan, Xiaohong
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.25498
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914513890050048
author He, Xuzheng
Nan, Nan
Wang, Zhilin
Kang, Ziyue
Mo, Zhuoru
Li, Ao
Pan, Yu
Li, Xiaobing
Yu, Feng
Guan, Xiaohong
author_facet He, Xuzheng
Nan, Nan
Wang, Zhilin
Kang, Ziyue
Mo, Zhuoru
Li, Ao
Pan, Yu
Li, Xiaobing
Yu, Feng
Guan, Xiaohong
contents Generating symphonic music requires simultaneously managing high-level structural form and dense, multi-track orchestration. Existing symbolic models often struggle with a "complexity-control imbalance", in which scaling bottlenecks limit long-term granular steerability. We present SymphonyGen, a 3D hierarchical framework for contemporary cinematic orchestration. SymphonyGen employs a cascading decoder architecture that decomposes the Bar, Track, and Event axes, improving computational efficiency and scalability over conventional 1D or 2D models. We introduce "short-score" conditioning via a beat-quantized multi-voice harmony skeleton, enabling outline control while preserving textural diversity. The model is further refined using Group Relative Policy Optimization (GRPO) with a cross-modal audio-perceptual reward, aligning symbolic output with modern acoustic expectations. Additionally, we implement a dissonance-averse sampling algorithm to suppress unintended tonal clashes during inference. Objective evaluations show that both reinforcement learning and dissonance-averse sampling effectively enhance harmonic cleanliness while maintaining melodic expression. Subjective evaluations demonstrate that SymphonyGen outperforms baselines in musicality and preference for orchestral music generation. Demo page: https://symphonygen.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2604_25498
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SymphonyGen: 3D Hierarchical Orchestral Generation with Controllable Harmony Skeleton
He, Xuzheng
Nan, Nan
Wang, Zhilin
Kang, Ziyue
Mo, Zhuoru
Li, Ao
Pan, Yu
Li, Xiaobing
Yu, Feng
Guan, Xiaohong
Sound
Artificial Intelligence
Generating symphonic music requires simultaneously managing high-level structural form and dense, multi-track orchestration. Existing symbolic models often struggle with a "complexity-control imbalance", in which scaling bottlenecks limit long-term granular steerability. We present SymphonyGen, a 3D hierarchical framework for contemporary cinematic orchestration. SymphonyGen employs a cascading decoder architecture that decomposes the Bar, Track, and Event axes, improving computational efficiency and scalability over conventional 1D or 2D models. We introduce "short-score" conditioning via a beat-quantized multi-voice harmony skeleton, enabling outline control while preserving textural diversity. The model is further refined using Group Relative Policy Optimization (GRPO) with a cross-modal audio-perceptual reward, aligning symbolic output with modern acoustic expectations. Additionally, we implement a dissonance-averse sampling algorithm to suppress unintended tonal clashes during inference. Objective evaluations show that both reinforcement learning and dissonance-averse sampling effectively enhance harmonic cleanliness while maintaining melodic expression. Subjective evaluations demonstrate that SymphonyGen outperforms baselines in musicality and preference for orchestral music generation. Demo page: https://symphonygen.github.io/
title SymphonyGen: 3D Hierarchical Orchestral Generation with Controllable Harmony Skeleton
topic Sound
Artificial Intelligence
url https://arxiv.org/abs/2604.25498