S3A speaker tracking with Kinect2

Dataset

TE de Campos, Q Liu and M Barnard

University of Surrey

17/11/2020

DOI:

https://doi.org/10.15126/surreydata.00807708

Abstract

Machine Audition

Person detection and tracking

RGB-D

Blind Source Separation

Computer Vision

url

http://www.s3a-spatialaudio.org/datasetsView

External Data Location

url

http://www.s3a-spatialaudio.org/datasetsView

Dataset

1 File views/ downloads

80 Record Views

Title: S3A speaker tracking with Kinect2
Creators: TE de Campos
Q Liu
M Barnard
Contributors: Adrian Hilton (Principal Investigator) - University of Surrey, Centre for Vision, Speech & Signal Processing (CVSSP)
Publisher: University of Surrey
Format: XEF Kinect2 data, JSON, MatLab, Images, Sound
Date published: 17/11/2020
Grant note: Funder: EPSRC | Grant Title: S3A - Future Spatial Audio for Immersive Listener Experience at Home | Grant ID: EP/L000539/1
Identifiers: 99514035802346
Copyright: No restrictions
Academic Unit: FEPS Central Faculty Admin; School of Computer Science and Electronic Engineering; Centre for Vision, Speech & Signal Processing (CVSSP)
Language: English
Resource Type: Dataset