An Instrumental Intelligibility Metric Based on Information Theory

Journal article (2018)

Authors

Steven Van Kuyk Victoria University of Wellington
W.B. Kleijn Signal Processing Systems - EEMCS , Victoria University of Wellington
R.C. Hendriks Signal Processing Systems - EEMCS
Research Group
Signal Processing Systems (EEMCS) (TU Delft)
Intelligibility Mutual information
More Info
expand_more

Published Date

2018

Language

English

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.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Microelectronics

Research Group

Signal Processing Systems

Abstract

We propose a monaural intrusive instrumental intelligibility metric called SIIB (speech intelligibility in bits). SIIB is an estimate of the amount of information shared between a talker and a listener in bits per second. Unlike existing information theoretic intelligibility metrics, SIIB accounts for talker variability and statistical dependencies between time-frequency units. Our evaluation shows that relative to state-of-the-art intelligibility metrics, SIIB is highly correlated with the intelligibility of speech that has been degraded by noise and processed by speech enhancement algorithms.

Files

08113594.pdf
(.pdf | 0.378 Mb)