Event-driven spectrotemporal feature extraction and classification using a silicon cochlea model

Ying Xu; Samalika Perera; Yeshwanth Bethi; Saeed Afshar; Andre van Schaik

doi:10.3389/fnins.2023.1125210

Event-driven spectrotemporal feature extraction and classification using a silicon cochlea model

Ying Xu, Samalika Perera, Yeshwanth Bethi, Saeed Afshar, Andre van Schaik

Western Sydney University

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

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.

Original language	English
Article number	1125210
Number of pages	12
Journal	Frontiers in Neuroscience
Volume	17
DOIs	https://doi.org/10.3389/fnins.2023.1125210
Publication status	Published - 2023

Bibliographical note

Publisher Copyright:
Copyright © 2023 Xu, Perera, Bethi, Afshar and van Schaik.

Open Access - Access Right Statement

© 2023 Xu, Perera, Bethi, Afshar and van Schaik. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (https://creativecommons.org/licenses/by/4.0/). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

Keywords

neuromorphic engineering
STRF
electronic cochlea
LIF
FEAST
CAR-FAC
event-based feature extraction

Access to Document

10.3389/fnins.2023.1125210

Cite this

@article{f1655a985ebd4c06b1de2f0ed4a93219,

title = "Event-driven spectrotemporal feature extraction and classification using a silicon cochlea model",

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.",

keywords = "neuromorphic engineering, STRF, electronic cochlea, LIF, FEAST, CAR-FAC, event-based feature extraction",

author = "Ying Xu and Samalika Perera and Yeshwanth Bethi and Saeed Afshar and Schaik, {Andre van}",

note = "Publisher Copyright: Copyright {\textcopyright} 2023 Xu, Perera, Bethi, Afshar and van Schaik.",

year = "2023",

doi = "10.3389/fnins.2023.1125210",

language = "English",

volume = "17",

journal = "Frontiers in Neuroscience",

issn = "1662-4548",

publisher = "Frontiers Research Foundation",

}

TY - JOUR

T1 - Event-driven spectrotemporal feature extraction and classification using a silicon cochlea model

AU - Xu, Ying

AU - Perera, Samalika

AU - Bethi, Yeshwanth

AU - Afshar, Saeed

AU - Schaik, Andre van

PY - 2023

Y1 - 2023

N2 - 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.

AB - 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.

KW - neuromorphic engineering

KW - STRF

KW - electronic cochlea

KW - LIF

KW - FEAST

KW - CAR-FAC

KW - event-based feature extraction

UR - https://hdl.handle.net/1959.7/uws:73613

UR - http://www.scopus.com/inward/record.url?scp=85159781047&partnerID=8YFLogxK

U2 - 10.3389/fnins.2023.1125210

DO - 10.3389/fnins.2023.1125210

M3 - Article

SN - 1662-4548

VL - 17

JO - Frontiers in Neuroscience

JF - Frontiers in Neuroscience

M1 - 1125210

ER -

Event-driven spectrotemporal feature extraction and classification using a silicon cochlea model

Abstract

Bibliographical note

Open Access - Access Right Statement

Keywords

Access to Document

Other files and links

Fingerprint

Cite this