An Instrumental Intelligibility Metric Based on Information Theory
Steven Van Kuyk (Victoria University of Wellington)
W. Bastiaan Kleijn (Victoria University of Wellington, TU Delft - Signal Processing Systems)
Richard C. Hendriks (TU Delft - Signal Processing Systems)
More Info
expand_more
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.