A Spectro-Temporal Glimpsing Index (STGI) for Speech Intelligibility Prediction
(longer introduction)
| Amin Edraki (Queen’s University, Canada), Wai-Yip Chan (Queen’s University, Canada), Jesper Jensen (Aalborg University, Denmark), Daniel Fogerty (University of Illinois at Urbana-Champaign, USA) |
|---|
We propose a monaural intrusive speech intelligibility prediction (SIP) algorithm called STGI based on detecting glimpses in short-time segments in a spectro-temporal modulation decomposition of the input speech signals. Unlike existing glimpse-based SIP methods, the application of STGI is not limited to additive uncorrelated noise; STGI can be employed in a broad range of degradation conditions. Our results show that STGI performs consistently well across 15 datasets covering degradation conditions including modulated noise, noise reduction processing, reverberation, near-end listening enhancement, checkerboard noise, and gated noise.
