Audio classification systems using deep neural networks and an event-driven auditory sensor
METADATA ONLY
Loading...
Author / Producer
Date
2019
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
We describe ongoing research in developing audio classification systems that use a spiking silicon cochlea as the front end. Event-driven features extracted from the spikes are fed to deep networks for the intended task. We describe a classification task on naturalistic audio sounds using a low-power silicon cochlea that outputs asynchronous events through a send-on-delta encoding of its sharply-tuned cochlea channels. Because of the event-driven nature of the processing, silences in these naturalistic sounds lead to corresponding absence of cochlea spikes and savings in computes. Results show 48% savings in computes with a small loss in accuracy using cochlea events. © 2019 IEEE.
Permanent link
Publication status
published
Editor
Book title
Proceedings of the 2019 IEEE Sensors
Journal / series
Volume
Pages / Article No.
8956592
Publisher
IEEE
Event
18th IEEE Sensors Conference (SENSORS 2019)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Event-driven audio; Edge computing; spiking cochlea; Deep learning; Sound classification; Low-power cochlea
Organisational unit
02533 - Institut für Neuroinformatik / Institute of Neuroinformatics