用神经网络从音频学习发动机声音参数，实现嵌入式实时重合成与调音。
Gradient-Based Learning of Parametric Engine Sound Representations for Real-Time Resynthesis and Tuning on Embedded Systems
- 基于梯度优化的端到端可微框架，从音频数据中学习发动机声学参数。
- 在全转速-扭矩范围内精确建模谐波与宽带音色变化，重建保真度高。
- 参数可直接部署至传统DSP系统，适合汽车音频开发团队使用。
发动机阶次增强在汽车声学设计中至关重要，通过选择性合成谐波来塑造运动感、精致感或力量感等感知品质。本文研究了一种基于神经网络的内燃机声音建模方法，该方法扩展了传统发动机阶次分析与增强技术，通过机器学习从音频数据中推导合成参数，并在合成框架中引入随机成分。该系统将发动机声音参数化为紧凑表示，捕捉全转速-扭矩工作范围内的各阶次及宽带音色变化，同时保持人工可调性，并兼容现有的汽车音频开发框架。方法采用基于梯度的优化与分析-合成一体化的端到端可微实现。最终生成的合成参数集可直接迁移至传统数字信号处理（DSP）实现，用于嵌入式目标部署。频谱指标与听觉测试均证实高重建保真度；集成至成熟的汽车音频开发平台（EVx Suite）进一步验证了其在可部署嵌入式系统上的技术可行性。
原文摘要 · Abstract (English)
Engine order enhancement is central in automotive sound design, where selective harmonics are synthesized to shape perceptual qualities such as sportiness, refinedness, or power. This paper investigates a neural network-based approach to combustion engine sound modeling that extends conventional engine order analysis and enhancement by deriving synthesis parameters from audio data with machine learning and incorporating stochastic components into the synthesis framework. The system parameterizes engine sounds as a compact representation capturing per-order and broadband timbral variation across the full RPM-torque operating range, while remaining manually tunable and compatible with established automotive audio frameworks. The approach leverages gradient-based optimization and analysis-by-synthesis through an end-to-end differentiable implementation. The resulting synthesis parameter set is directly transferable to conventional DSP implementations for deployment on embedded targets. Spectral metrics and listening tests confirm high reconstruction fidelity, and integration into an established automotive audio development platform (EVx Suite) demonstrates technical feasibility on deployment-ready embedded systems.
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。