An intelligibility metric based on a simple model of speech communication

Conference Paper (2016)
Author(s)

Steven Van Kuyk (Victoria University of Wellington)

Bastiaan Kleijn (Victoria University of Wellington)

R. C. Hendriks (TU Delft - Signal Processing Systems)

Research Group
Signal Processing Systems
Copyright
© 2016 Steven van Kuyk, W.B. Kleijn, R.C. Hendriks
DOI related publication
https://doi.org/10.1109/iwaenc.2016.7602933
More Info
expand_more
Publication Year
2016
Language
English
Copyright
© 2016 Steven van Kuyk, W.B. Kleijn, R.C. Hendriks
Research Group
Signal Processing Systems
Bibliographical Note
(Best student paper award)@en
Pages (from-to)
1-5
ISBN (electronic)
978-1-5090-2007-2
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Instrumental measures of speech intelligibility typically produce an index between 0 and 1 that is monotonically related to listening test scores. As such, these measures are dimensionless and do not represent physical quantities. In this paper, we propose a new instrumental intelligibility metric that describes speech intelligibility using bits per second. The proposed metric builds upon an existing intelligibility metric that was motivated by information theory. Our main contribution is that we use a statistical model of speech communication that accounts for noise inherent in the speech production process. Experiments show that the proposed metric performs at least as well as existing state-of-the-art intelligibility metrics.

Files

Kuyk_iwaenc16.pdf
(pdf | 0.321 Mb)
License info not available