The AI Mechanic: Acoustic Vehicle Characterization Neural Networks

by   Adam M. Terwilliger, et al.

In a world increasingly dependent on road-based transportation, it is essential to understand vehicles. We introduce the AI mechanic, an acoustic vehicle characterization deep learning system, as an integrated approach using sound captured from mobile devices to enhance transparency and understanding of vehicles and their condition for non-expert users. We develop and implement novel cascading architectures for vehicle understanding, which we define as sequential, conditional, multi-level networks that process raw audio to extract highly-granular insights. To showcase the viability of cascading architectures, we build a multi-task convolutional neural network that predicts and cascades vehicle attributes to enhance fault detection. We train and test these models on a synthesized dataset reflecting more than 40 hours of augmented audio and achieve >92 configuration, cylinder count and aspiration type). Our cascading architecture additionally achieved 93.6 fault prediction, demonstrating margins of 16.4 improvement over naïve and parallel baselines. We explore experimental studies focused on acoustic features, data augmentation, feature fusion, and data reliability. Finally, we conclude with a discussion of broader implications, future directions, and application areas for this work.


page 3

page 9

page 11

page 27


MVD:A Novel Methodology and Dataset for Acoustic Vehicle Type Classification

Rising urban populations have led to a surge in vehicle use and made tra...

A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection

In this paper, we propose a novel four-stage data augmentation approach ...

Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling

This technical report describes the IOA team's submission for TASK1A of ...

Hearing What You Cannot See: Acoustic Detection Around Corners

This work proposes to use passive acoustic perception as an additional s...

GPLA-12: An Acoustic Signal Dataset of Gas Pipeline Leakage

In this paper, we introduce a new acoustic leakage dataset of gas pipeli...

IDMT-Traffic: An Open Benchmark Dataset for Acoustic Traffic Monitoring Research

In many urban areas, traffic load and noise pollution are constantly inc...

Please sign up or login with your details

Forgot password? Click here to reset