Publications

BibTex format

@article{Grinstein:2024:10.1109/OJSP.2023.3340057,
author = {Grinstein, E and Hicks, CM and Van, Waterschoot T and Brookes, M and Naylor, PA},
doi = {10.1109/OJSP.2023.3340057},
journal = {IEEE Open Journal of Signal Processing},
pages = {19--28},
title = {The Neural-SRP Method for Universal Robust Multi-Source Tracking},
url = {http://dx.doi.org/10.1109/OJSP.2023.3340057},
volume = {5},
year = {2024}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Neural networks have achieved state-of-the-art performance on the task of acoustic Direction-of-Arrival (DOA) estimation using microphone arrays. Neural models can be classified as end-to-end or hybrid, each class showing advantages and disadvantages. This work introduces Neural-SRP, an end-to-end neural network architecture for DOA estimation inspired by the classical Steered Response Power (SRP) method, which overcomes limitations of current neural models. We evaluate the architecture on multiple scenarios, namely, multi-source DOA tracking and single-source DOA tracking under the presence of directional and diffuse noise. The experiments demonstrate that our proposed method compares favourably in terms of computational and localization performance with established neural methods on various recorded and simulated benchmark datasets.
AU  - Grinstein,E
AU  - Hicks,CM
AU  - Van,Waterschoot T
AU  - Brookes,M
AU  - Naylor,PA
DO  - 10.1109/OJSP.2023.3340057
EP  - 28
PY  - 2024///
SP  - 19
TI  - The Neural-SRP Method for Universal Robust Multi-Source Tracking
T2  - IEEE Open Journal of Signal Processing
UR  - http://dx.doi.org/10.1109/OJSP.2023.3340057
VL  - 5
ER  -

Download

Mr Mike Brookes

Contact

Assistant

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)