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.
Original language | English |
---|---|
Pages (from-to) | 115-119 |
Number of pages | 5 |
Journal | IEEE Signal Processing Letters |
Volume | 25 |
Issue number | 1 |
DOIs | |
Publication status | Published - 2018 |
Keywords
- Intelligibility
- mutual information