Computational engine sound modeling is central to the automotive audio industry, particularly for active sound design applications and virtual prototyping. Emerging data-driven engine sound synthesis methods require large volumes of standardized, clean audio recordings with precisely time-aligned operating-state annotations: data that is difficult to obtain due to high costs, specialized measurement equipment requirements, and inevitable noise contamination. We present an analysis-driven framework for generating engine audio with sample-accurate control annotations. The method extracts harmonic structures from real recordings through pitch-adaptive spectral analysis, which then drive an extended parametric harmonic-plus-noise synthesizer. With this framework, we augment 5-10 min of source audio per engine 15-30x via diverse control trajectories and parametric variation, producing the Procedural Engine Sounds Dataset (19.0 h, 5,935 files): a set of engine audio signals with sample-accurate RPM and torque annotations spanning a wide range of operating conditions, signal complexities, and harmonic profiles. Comparison against real recordings validates that the synthesized data preserves characteristic harmonic structures, and a baseline differentiable synthesis network trained on the dataset confirms its suitability for data-driven engine sound modeling. The dataset is released publicly to support research on engine timbre analysis, control parameter estimation, and neural generative synthesis.
Figures & tables
Fig. 1: Engine order magnitudes across RPM and torque range for one representative configuration, comparing source recordings (left, 90 min) to framework-generated synthetic signals (right, 150 min from 5 min extraction material). Upper panels plot per-order magnitude Ah as a function of RPM; lower panels plot the same against torque. Preserved structural features demonstrate acoustic authenticity under 30 × augmentation.
Fig. 2: Training and validation loss for the neural synthesis model on datasets A, B, and C. Stable convergence at early stopping demonstrates suitability for data-driven methods; Esc points (defined as positions with 8 following epochs of no significant improvement) shift earlier from A to C with increasing non-deterministic content.