用神经网络模拟非线性弹性板振动，提升音频合成实时性
Evaluation of Neural Surrogates for Physical Modelling Synthesis of Nonlinear Elastic Plates
- 用神经网络替代传统数值方法求解非线性弹性板振动
- 短序列训练模型在长序列预测中出现误差累积与失真
- 强调时域误差不足反映真实听觉质量，适合音频合成研究者
物理建模合成旨在通过振动结构的物理仿真生成音频。薄弹性板常用于模拟鼓面。传统数值方法如有限差分和有限元虽精度高，但计算成本大，难以用于实时音频应用。本文对比分析了基于神经网络的方法对非线性弹性板振动的求解能力。我们评估了多个前沿模型，这些模型在短序列上训练，以自回归方式预测长序列。结果显示部分模型存在局限性，仅关注时域预测误差不足以判断性能优劣。论文讨论了对实时音频合成的影响，并提出改进神经方法模拟非线性振动的未来方向。
原文摘要 · Abstract (English)
Physical modelling synthesis aims to generate audio from physical simulations of vibrating structures. Thin elastic plates are a common model for drum membranes. Traditional numerical methods like finite differences and finite elements offer high accuracy but are computationally demanding, limiting their use in real-time audio applications. This paper presents a comparative analysis of neural network-based approaches for solving the vibration of nonlinear elastic plates. We evaluate several state-of-the-art models, trained on short sequences, for prediction of long sequences in an autoregressive fashion. We show some of the limitations of these models, and why is not enough to look at the prediction error in the time domain. We discuss the implications for real-time audio synthesis and propose future directions for improving neural approaches to model nonlinear vibration.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。