Intelligent Acoustic Module for Autonomous Vehicles using Fast Gated Recurrent approach

TL;DR

This paper presents a resource-efficient, fast gated recurrent neural network model for acoustic classification in autonomous vehicles, enhancing sound identification and localization capabilities in constrained edge devices.

Contribution

The paper introduces a novel Tiny Gated Recurrent Neural Network model optimized for acoustic classification in autonomous vehicles, with improved performance and reduced size.

Findings

Enhanced accuracy in acoustic classification

Reduced model size and computational requirements

Potential for improved sound localization in urban environments

Abstract

This paper elucidates a model for acoustic single and multi-tone classification in resource constrained edge devices. The proposed model is of State-of-the-art Fast Accurate Stable Tiny Gated Recurrent Neural Network. This model has resulted in improved performance metrics and lower size compared to previous hypothesized methods by using lesser parameters with higher efficiency and employment of a noise reduction algorithm. The model is implemented as an acoustic AI module, focused for the application of sound identification, localization, and deployment on AI systems like that of an autonomous car. Further, the inclusion of localization techniques carries the potential of adding a new dimension to the multi-tone classifiers present in autonomous vehicles, as its demand increases in urban cities and developing countries in the future.