Imperial College London

Dr Patrick A. Naylor

Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Professor of Speech & Acoustic Signal Processing
 
 
 
//

Contact

 

+44 (0)20 7594 6235p.naylor Website

 
 
//

Location

 

803Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Löllmann,
author = {Löllmann, HW and Evers, C and Schmidt, A and Mellmann, H and Barfuss, H and Naylor, PA and Kellermann, W},
publisher = {IEEE},
title = {The LOCATA challenge data corpus for acoustic source localization and tracking},
url = {http://hdl.handle.net/10044/1/59752},
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - Algorithms for acoustic source localization andtracking are essential for a wide range of applications suchas personal assistants, smart homes, tele-conferencing systems,hearing aids, or autonomous systems. Numerous algorithms havebeen proposed for this purpose which, however, are not evaluatedand compared against each other by using a common database sofar. The IEEE-AASP Challenge on sound source localization andtracking (LOCATA) provides a novel, comprehensive data corpusfor the objective benchmarking of state-of-the-art algorithmson sound source localization and tracking. The data corpuscomprises six tasks ranging from the localization of a singlestatic sound source with a static microphone array to the trackingof multiple moving speakers with a moving microphone array.It contains real-world multichannel audio recordings, obtainedby hearing aids, microphones integrated in a robot head, aplanar and a spherical microphone array in an enclosed acousticenvironment as well as positional information about the involvedarrays and sound sources represented by moving human talkersor static loudspeakers.
AU - Löllmann,HW
AU - Evers,C
AU - Schmidt,A
AU - Mellmann,H
AU - Barfuss,H
AU - Naylor,PA
AU - Kellermann,W
PB - IEEE
SN - 2151-870X
TI - The LOCATA challenge data corpus for acoustic source localization and tracking
UR - http://hdl.handle.net/10044/1/59752
ER -