arXiv subjects

Claudio Colangeli

Publications and source records attributed to Claudio Colangeli.

2 recordsLinked to original sources

arXiv2026

The Influence of Interior Noise on Just-Noticeable Speed Differences in Conventional and Electric Vehicles

Electric vehicles (EVs) and internal-combustion-engine vehicles (ICEVs) differ fundamentally in their in-cabin acoustics, notably the attenuation or absence of engine-order content. Prior work reports associations between reduced engine sound, speed underestimation, and poorer speed maintenance; however, research on how EVs' new sound affects speed perception and control is scarce, and most newer studies focus on comfort and subjective pleasantness rather than speed perception. Addressing this gap, the present study uses a two-interval, two-alternative forced-choice (2AFC) paradigm to directly measure just-noticeable differences (JNDs) in speed under ICEV, EV, and silent conditions. Thirty participants performed a 2AFC task in which, on each trial, they viewed two first-person highway clips (reference vs. comparison) and indicated which appeared faster. Results from ANOVA and post-hoc tests indicate that at the 40 km/h reference speed participants showed no clear differences across sound conditions, whereas at 100 km/h there were marked differences in JND: mean values were 1.93 km/h (ICEV), 3.48 km/h (EV), and 5.15 km/h (silence). A psychoacoustic parameter analysis suggests that this effect is not explained by speed-dependent changes in loudness or sharpness; we interpret that RPM-related, clearly audible frequency shifts in ICEV provide the primary contributory cue. For EV NVH or artificial sound design, enhancing speed-contingent, trackable spectral cues while respecting comfort may help maintain drivers' ability to discriminate speed differences.

physics.class-ph↗

arXiv2025

A Domain Knowledge Informed Approach for Anomaly Detection of Electric Vehicle Interior Sounds

The detection of anomalies in automotive cabin sounds is critical for ensuring vehicle quality and maintaining passenger comfort. In many real-world settings, this task is more appropriately framed as an unsupervised learning problem rather than the supervised case due to the scarcity or complete absence of labeled faulty data. In such an unsupervised setting, the model is trained exclusively on healthy samples and detects anomalies as deviations from normal behavior. However, in the absence of labeled faulty samples for validation and the limited reliability of commonly used metrics, such as validation reconstruction error, effective model selection remains a significant challenge. To overcome these limitations, a domain-knowledge-informed approach for model selection is proposed, in which proxy-anomalies engineered through structured perturbations of healthy spectrograms are used in the validation set to support model selection. The proposed methodology is evaluated on a high-fidelity electric vehicle dataset comprising healthy and faulty cabin sounds across five representative fault types viz., Imbalance, Modulation, Whine, Wind, and Pulse Width Modulation. This dataset, generated using advanced sound synthesis techniques, and validated via expert jury assessments, has been made publicly available to facilitate further research. Experimental evaluations on the five fault cases demonstrate the selection of optimal models using proxy-anomalies, significantly outperform conventional model selection strategies.

cs.SD↗