An Adaptive Neural Mechanism with a Lizard Ear Model for Binaural Acoustic Tracking

Publikation: Bidrag til bog/antologi/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Resumé

Acoustic tracking of a moving sound source is relevant in many domains including robotic phonotaxis and human-robot interaction. Typical approaches rely on processing time-difference-of-arrival cues obtained via multi-microphone arrays with Kalman or particle filters, or other computationally expensive algorithms. We present a novel bioinspired solution to acoustic tracking that uses only two microphones. The system is based on a neural mechanism coupled with a model of the peripheral auditory system of lizards. The peripheral auditory model provides sound direction information which the neural mechanism uses to learn the target’s velocity via fast correlation-based unsupervised learning. Simulation results for tracking a pure tone acoustic target moving along a semi-circular trajectory validate our approach. Three different angular velocities in three separate trials were employed for the validation. A comparison with a Braitenberg vehicle-like steering strategy shows the improved performance of our learning-based approach.
OriginalsprogEngelsk
TitelFrom Animals to Animats 14 : 14th International Conference on Simulation of Adaptive Behavior, SAB 2016, Aberystwyth, UK, August 23-26, 2016, Proceedings
RedaktørerElio Tuci, Alexandros Giagkos, Myra Wilson, John Hallam
ForlagSpringer
Publikationsdatoaug. 2016
Sider79-90
ISBN (Trykt)978-3-319-43487-2
ISBN (Elektronisk)978-3-319-43488-9
DOI
StatusUdgivet - aug. 2016
BegivenhedThe 14th International Conference on the Simulation of Adaptive Behavior - Aberystwyth University, Aberystwyth, Storbritannien
Varighed: 23. aug. 201626. aug. 2016
http://www.sab2016.org

Konference

KonferenceThe 14th International Conference on the Simulation of Adaptive Behavior
LokationAberystwyth University
LandStorbritannien
ByAberystwyth
Periode23/08/201626/08/2016
Internetadresse
NavnLecture Notes in Computer Science
Vol/bind9825
ISSN0302-9743

Fingeraftryk

Acoustics
Microphones
Acoustic waves
Human robot interaction
Unsupervised learning
Angular velocity
Robotics
Trajectories
Processing
Time difference of arrival

Citer dette

Shaikh, D., & Manoonpong, P. (2016). An Adaptive Neural Mechanism with a Lizard Ear Model for Binaural Acoustic Tracking. I E. Tuci, A. Giagkos, M. Wilson, & J. Hallam (red.), From Animals to Animats 14: 14th International Conference on Simulation of Adaptive Behavior, SAB 2016, Aberystwyth, UK, August 23-26, 2016, Proceedings (s. 79-90). Springer. Lecture Notes in Computer Science, Bind. 9825 https://doi.org/10.1007/978-3-319-43488-9_8
Shaikh, Danish ; Manoonpong, Poramate. / An Adaptive Neural Mechanism with a Lizard Ear Model for Binaural Acoustic Tracking. From Animals to Animats 14: 14th International Conference on Simulation of Adaptive Behavior, SAB 2016, Aberystwyth, UK, August 23-26, 2016, Proceedings. red. / Elio Tuci ; Alexandros Giagkos ; Myra Wilson ; John Hallam. Springer, 2016. s. 79-90 (Lecture Notes in Computer Science, Bind 9825).
@inproceedings{897ecfb5b9d045c5a17bc22d23b0c601,
title = "An Adaptive Neural Mechanism with a Lizard Ear Model for Binaural Acoustic Tracking",
abstract = "Acoustic tracking of a moving sound source is relevant in many domains including robotic phonotaxis and human-robot interaction. Typical approaches rely on processing time-difference-of-arrival cues obtained via multi-microphone arrays with Kalman or particle filters, or other computationally expensive algorithms. We present a novel bioinspired solution to acoustic tracking that uses only two microphones. The system is based on a neural mechanism coupled with a model of the peripheral auditory system of lizards. The peripheral auditory model provides sound direction information which the neural mechanism uses to learn the target’s velocity via fast correlation-based unsupervised learning. Simulation results for tracking a pure tone acoustic target moving along a semi-circular trajectory validate our approach. Three different angular velocities in three separate trials were employed for the validation. A comparison with a Braitenberg vehicle-like steering strategy shows the improved performance of our learning-based approach.",
keywords = "Binaural acoustic tracking, correlation learning, lizard peripheral auditory system",
author = "Danish Shaikh and Poramate Manoonpong",
year = "2016",
month = "8",
doi = "10.1007/978-3-319-43488-9_8",
language = "English",
isbn = "978-3-319-43487-2",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "79--90",
editor = "Elio Tuci and Alexandros Giagkos and Myra Wilson and John Hallam",
booktitle = "From Animals to Animats 14",
address = "Germany",

}

Shaikh, D & Manoonpong, P 2016, An Adaptive Neural Mechanism with a Lizard Ear Model for Binaural Acoustic Tracking. i E Tuci, A Giagkos, M Wilson & J Hallam (red), From Animals to Animats 14: 14th International Conference on Simulation of Adaptive Behavior, SAB 2016, Aberystwyth, UK, August 23-26, 2016, Proceedings. Springer, Lecture Notes in Computer Science, bind 9825, s. 79-90, The 14th International Conference on the Simulation of Adaptive Behavior, Aberystwyth, Storbritannien, 23/08/2016. https://doi.org/10.1007/978-3-319-43488-9_8

An Adaptive Neural Mechanism with a Lizard Ear Model for Binaural Acoustic Tracking. / Shaikh, Danish; Manoonpong, Poramate.

From Animals to Animats 14: 14th International Conference on Simulation of Adaptive Behavior, SAB 2016, Aberystwyth, UK, August 23-26, 2016, Proceedings. red. / Elio Tuci; Alexandros Giagkos; Myra Wilson; John Hallam. Springer, 2016. s. 79-90 (Lecture Notes in Computer Science, Bind 9825).

Publikation: Bidrag til bog/antologi/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

TY - GEN

T1 - An Adaptive Neural Mechanism with a Lizard Ear Model for Binaural Acoustic Tracking

AU - Shaikh, Danish

AU - Manoonpong, Poramate

PY - 2016/8

Y1 - 2016/8

N2 - Acoustic tracking of a moving sound source is relevant in many domains including robotic phonotaxis and human-robot interaction. Typical approaches rely on processing time-difference-of-arrival cues obtained via multi-microphone arrays with Kalman or particle filters, or other computationally expensive algorithms. We present a novel bioinspired solution to acoustic tracking that uses only two microphones. The system is based on a neural mechanism coupled with a model of the peripheral auditory system of lizards. The peripheral auditory model provides sound direction information which the neural mechanism uses to learn the target’s velocity via fast correlation-based unsupervised learning. Simulation results for tracking a pure tone acoustic target moving along a semi-circular trajectory validate our approach. Three different angular velocities in three separate trials were employed for the validation. A comparison with a Braitenberg vehicle-like steering strategy shows the improved performance of our learning-based approach.

AB - Acoustic tracking of a moving sound source is relevant in many domains including robotic phonotaxis and human-robot interaction. Typical approaches rely on processing time-difference-of-arrival cues obtained via multi-microphone arrays with Kalman or particle filters, or other computationally expensive algorithms. We present a novel bioinspired solution to acoustic tracking that uses only two microphones. The system is based on a neural mechanism coupled with a model of the peripheral auditory system of lizards. The peripheral auditory model provides sound direction information which the neural mechanism uses to learn the target’s velocity via fast correlation-based unsupervised learning. Simulation results for tracking a pure tone acoustic target moving along a semi-circular trajectory validate our approach. Three different angular velocities in three separate trials were employed for the validation. A comparison with a Braitenberg vehicle-like steering strategy shows the improved performance of our learning-based approach.

KW - Binaural acoustic tracking

KW - correlation learning

KW - lizard peripheral auditory system

U2 - 10.1007/978-3-319-43488-9_8

DO - 10.1007/978-3-319-43488-9_8

M3 - Article in proceedings

SN - 978-3-319-43487-2

T3 - Lecture Notes in Computer Science

SP - 79

EP - 90

BT - From Animals to Animats 14

A2 - Tuci, Elio

A2 - Giagkos, Alexandros

A2 - Wilson, Myra

A2 - Hallam, John

PB - Springer

ER -

Shaikh D, Manoonpong P. An Adaptive Neural Mechanism with a Lizard Ear Model for Binaural Acoustic Tracking. I Tuci E, Giagkos A, Wilson M, Hallam J, red., From Animals to Animats 14: 14th International Conference on Simulation of Adaptive Behavior, SAB 2016, Aberystwyth, UK, August 23-26, 2016, Proceedings. Springer. 2016. s. 79-90. (Lecture Notes in Computer Science, Bind 9825). https://doi.org/10.1007/978-3-319-43488-9_8