Sound Event Localization and Detection Using CRNN on Pairs of Microphones

François Grondin; François Glass; Iwona Sobieraj; Mark D. Plumbley

doi:10.33682/4v2a-7q02

Back

Sound Event Localization and Detection Using CRNN on Pairs of Microphones

Conference presentation

Open access

Peer reviewed

Sound Event Localization and Detection Using CRNN on Pairs of Microphones

François Grondin, François Glass, Iwona Sobieraj and Mark D. Plumbley

Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019), pp.84-88

New York University

The Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019) (New York, USA, 25/10/2019 - 26/10/2019)

10/2019

DOI: https://doi.org/10.33682/4v2a-7q02

Abstract

Sound event detection; Sound source localization; Time difference of arrival; Neural network

This paper proposes sound event localization and detection methods from multichannel recording. The proposed system is based on two Convolutional Recurrent Neural Networks (CRNNs) to perform sound event detection (SED) and time difference of arrival (TDOA) estimation on each pair of microphones in a microphone array. In this paper, the system is evaluated with a four-microphone array, and thus combines the results from six pairs of microphones to provide a final classification and a 3-D direction of arrival (DOA) estimate. Results demonstrate that the proposed approach outperforms the DCASE 2019 baseline system.

Files and links (3)

pdf

GrondinGlassSobierajP19-dcase488.29 kBDownload View

Text Open Access

url

https://doi.org/10.33682/4v2a-7q02View

Published (Version of record)

url

http://dcase.community/workshop2019/View

Organisation

Metrics

100 File views/ downloads

51 Record Views

Details

Title: Sound Event Localization and Detection Using CRNN on Pairs of Microphones
Creators: François Grondin
François Glass
Iwona Sobieraj
Mark D. Plumbley
Contributors: Michael Mandel (Editor)
Justin Salamon (Editor)
Daniel P. W. Ellis (Editor)
Publication Details: Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019), pp.84-88
Conference: The Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019) (New York, USA, 25/10/2019 - 26/10/2019)
Publisher: New York University
Date published: 10/2019
Date submitted: 05/11/2019
Grant note: Funder: Signify | Funder: The European Union’s H2020 Framework Programme (H2020-MSCA-ITN-2014) | Funder: EPSRC - Engineering and Physical Sciences Research Council | Grant ID: H2020-MSCA-ITN-2014 | Grant ID: EP/N014111/1
Identifiers: 99512918002346
Copyright: Copyright 2019 The Authors. This work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit: http://creativecommons.org/licenses/by/4.0/
Academic Unit: School of Computer Science and Electronic Engineering
Resource Type: Conference presentation

Sound Event Localization and Detection Using CRNN on Pairs of Microphones

Abstract

Files and links (3)

Metrics

Details

Usage Policy