Event-driven Spectrotemporal Feature Extraction and Classification using a Silicon Cochlea Model

TL;DR

This paper introduces a reconfigurable FPGA-based event-driven binaural cochlear system with novel spectrotemporal feature extraction, demonstrating competitive performance on auditory benchmarks and advancing neuromorphic auditory processing.

Contribution

It presents a new FPGA implementation of an event-driven cochlear model with a novel STRF feature extraction method, enhancing real-time auditory signal processing.

Findings

Effective on TIDIGITS benchmark

Comparable or improved accuracy over existing methods

Demonstrates real-time processing capabilities

Abstract

This paper presents a reconfigurable digital implementation of an event-based binaural cochlear system on a Field Programmable Gate Array (FPGA). It consists of a pair of the Cascade of Asymmetric Resonators with Fast Acting Compression (CAR FAC) cochlea models and leaky integrate and fire (LIF) neurons. Additionally, we propose an event-driven SpectroTemporal Receptive Field (STRF) Feature Extraction using Adaptive Selection Thresholds (FEAST). It is tested on the TIDIGTIS benchmark and compared with current event-based auditory signal processing approaches and neural networks.