A spiking neural network approach to auditory source lateralisation

Robert Luke; David McAlpine

doi:10.1109/ICASSP.2019.8683767

A spiking neural network approach to auditory source lateralisation

Robert Luke, David McAlpine

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

5 Citations (Scopus)

Abstract

A novel approach to multi-microphone acoustic source localisation based on spiking neural networks is presented. We demonstrate that a two microphone system connected to a spiking neural network can be used to localise acoustic sources based purely on inter microphone timing differences, with no need for manually configured delay lines. A two sensor example is provided which includes 1) a front end which converts the acoustic signal to a series of spikes, 2) a hidden layer of spiking neurons, 3) an output layer of spiking neurons which represents the location of the acoustic source. We present details on training the network, and evaluation of its performance in quiet and noisy conditions. The system is trained on two locations, and we show that the lateralisation accuracy is 100% when presented with previously unseen data in quiet conditions. We also demonstrate the network generalises to modulation rates and background noise on which it was not trained.

Original language	English
Title of host publication	ICASSP 2019: 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing
Subtitle of host publication	proceedings
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1488-1492
Number of pages	5
ISBN (Electronic)	9781479981311
DOIs	https://doi.org/10.1109/ICASSP.2019.8683767
Publication status	Published - 2019
Event	44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom Duration: 12 May 2019 → 17 May 2019

Conference

Conference	44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
Country/Territory	United Kingdom
City	Brighton
Period	12/05/19 → 17/05/19

Keywords

spiking neural networks
binaural localisation algorithms
acoustic source localisation
machine learning

Access to Document

10.1109/ICASSP.2019.8683767

Cite this

@inproceedings{0bc48a27ba44477db84bebefd3a19a7d,

title = "A spiking neural network approach to auditory source lateralisation",

abstract = "A novel approach to multi-microphone acoustic source localisation based on spiking neural networks is presented. We demonstrate that a two microphone system connected to a spiking neural network can be used to localise acoustic sources based purely on inter microphone timing differences, with no need for manually configured delay lines. A two sensor example is provided which includes 1) a front end which converts the acoustic signal to a series of spikes, 2) a hidden layer of spiking neurons, 3) an output layer of spiking neurons which represents the location of the acoustic source. We present details on training the network, and evaluation of its performance in quiet and noisy conditions. The system is trained on two locations, and we show that the lateralisation accuracy is 100\% when presented with previously unseen data in quiet conditions. We also demonstrate the network generalises to modulation rates and background noise on which it was not trained.",

keywords = "spiking neural networks, binaural localisation algorithms, acoustic source localisation, machine learning",

author = "Robert Luke and David McAlpine",

year = "2019",

doi = "10.1109/ICASSP.2019.8683767",

language = "English",

pages = "1488--1492",

booktitle = "ICASSP 2019: 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 ; Conference date: 12-05-2019 Through 17-05-2019",

}

Luke, R & McAlpine, D 2019, A spiking neural network approach to auditory source lateralisation. in ICASSP 2019: 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing: proceedings., 8683767, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, pp. 1488-1492, 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019, Brighton, United Kingdom, 12/05/19. https://doi.org/10.1109/ICASSP.2019.8683767

A spiking neural network approach to auditory source lateralisation. / Luke, Robert; McAlpine, David.
ICASSP 2019: 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing: proceedings. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2019. p. 1488-1492 8683767.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - A spiking neural network approach to auditory source lateralisation

AU - Luke, Robert

AU - McAlpine, David

PY - 2019

Y1 - 2019

N2 - A novel approach to multi-microphone acoustic source localisation based on spiking neural networks is presented. We demonstrate that a two microphone system connected to a spiking neural network can be used to localise acoustic sources based purely on inter microphone timing differences, with no need for manually configured delay lines. A two sensor example is provided which includes 1) a front end which converts the acoustic signal to a series of spikes, 2) a hidden layer of spiking neurons, 3) an output layer of spiking neurons which represents the location of the acoustic source. We present details on training the network, and evaluation of its performance in quiet and noisy conditions. The system is trained on two locations, and we show that the lateralisation accuracy is 100% when presented with previously unseen data in quiet conditions. We also demonstrate the network generalises to modulation rates and background noise on which it was not trained.

AB - A novel approach to multi-microphone acoustic source localisation based on spiking neural networks is presented. We demonstrate that a two microphone system connected to a spiking neural network can be used to localise acoustic sources based purely on inter microphone timing differences, with no need for manually configured delay lines. A two sensor example is provided which includes 1) a front end which converts the acoustic signal to a series of spikes, 2) a hidden layer of spiking neurons, 3) an output layer of spiking neurons which represents the location of the acoustic source. We present details on training the network, and evaluation of its performance in quiet and noisy conditions. The system is trained on two locations, and we show that the lateralisation accuracy is 100% when presented with previously unseen data in quiet conditions. We also demonstrate the network generalises to modulation rates and background noise on which it was not trained.

KW - spiking neural networks

KW - binaural localisation algorithms

KW - acoustic source localisation

KW - machine learning

UR - https://www.scopus.com/pages/publications/85069474639

U2 - 10.1109/ICASSP.2019.8683767

DO - 10.1109/ICASSP.2019.8683767

M3 - Conference proceeding contribution

AN - SCOPUS:85069474639

SP - 1488

EP - 1492

BT - ICASSP 2019: 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

T2 - 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019

Y2 - 12 May 2019 through 17 May 2019

ER -

A spiking neural network approach to auditory source lateralisation

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this