Physics-Informed Neural Engine Sound Modeling with Differentiable Pulse-Train Synthesis

2026-03-10

AI Summary

This work addresses the challenge of accurately capturing the impulsive characteristics and underlying physical mechanisms of engine sounds using conventional neural audio synthesis methods. To this end, the authors propose the Pulse-Train-Resonator (PTR) model, a differentiable synthesis architecture that explicitly models the temporal structure and waveform of exhaust pressure pulses by feeding a parameterized, ignition-aligned pulse train into a recursive Karplus-Strong resonator. The model incorporates key physical priors—including harmonic decay, thermodynamic pitch modulation, valve dynamics, exhaust resonance, and throttle operation—to achieve high-fidelity and interpretable synthesis. Evaluated on 7.5 hours of audio from three engine types, PTR demonstrates a 21% improvement in harmonic reconstruction and a 5.7% reduction in total loss compared to a harmonic-plus-noise baseline.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Engine sounds originate from sequential exhaust pressure pulses rather than sustained harmonic oscillations. While neural synthesis methods typically aim to approximate the resulting spectral characteristics, we propose directly modeling the underlying pulse shapes and temporal structure. We present the Pulse-Train-Resonator (PTR) model, a differentiable synthesis architecture that generates engine audio as parameterized pulse trains aligned to engine firing patterns and propagates them through recursive Karplus-Strong resonators simulating exhaust acoustics. The architecture integrates physics-informed inductive biases including harmonic decay, thermodynamic pitch modulation, valve-dynamics envelopes, exhaust system resonances and derived engine operating modes such as throttle operation and deceleration fuel cutoff (DCFO). Validated on three diverse engine types totaling 7.5 hours of audio, PTR achieves a 21% improvement in harmonic reconstruction and a 5.7% reduction in total loss over a harmonic-plus-noise baseline model, while providing interpretable parameters corresponding to physical phenomena. Complete code, model weights, and audio examples are openly available.

Problem

• engine sound modeling
• pulse-train synthesis
• physics-informed neural networks
• differentiable audio synthesis
• exhaust acoustics

Innovation

• Physics-Informed Neural Modeling
• Differentiable Synthesis
• Pulse-Train Resonator
• Engine Sound Synthesis
• Exhaust Acoustics