Generating artificial noise for testing speech recognition systems

Allwright, D.J. and Brown, M. (2002) Generating artificial noise for testing speech recognition systems. European Study Group with Industry > 43rd ESGI [Lancaster 2/4/2002 - 5/4/2002].

Full text available as:

PDF - Requires Adobe Acrobat Reader or other PDF viewer.

EPrint Type:	Study Group Report
Study Group:	European Study Group with Industry > 43rd ESGI [Lancaster 2/4/2002 - 5/4/2002]
Company Name:	Jomega Ltd
Industrial Sector:	Transport and Automotive
Additional Contributors:	Eyres, R. and Griffin, T. and Howison, S.D. and Jacobs, R. and Please, C.P. and Rosing, R. and Wilson, E.
ID Code:	20
Deposited By:	Gordon White
Deposited On:	10 June 2004

Problem Statement

The Study Group was presented with the problem of determining how to generate noise samples appropriate for reliably testing the quality of in-car speech recognition systems. Speech-driven applications are becoming more common in cars and it is important to be able to test how well such systems perform and to identify those aspects of the noise which may cause diffculties for the systems. This requires the characterisation of the noise environment within a car. These characterisations must then be used to efficiently compress the information so that testing can be performed economically.

Archive Staff Only: edit this record