@inproceedings{A. 2022,
Author = {A. F. McKinney and B. Cauchi},
Title = {Non-intrusive prediction of speech intelligibility for the first Clarity Prediction Challenge (CPC1)},

Year = {2022},
Booktitle = {Clarity Challenge},
Url = { https://claritychallenge.org/clarity2022-workshop/papers/Clarity_2022_CPC1_paper_mckinney.pdf},
type = {inproceedings},
Abstract = {Most existing speech intelligibility measures are either designed
for single-channel applications – hence unsuited to evaluate
hearing aid algorithms –or intrusive, applicable only in simulated scenarios in which the clean signal is available. Non-
intrusive speech intelligibility measures able to reliably predict
speech intelligibility without knowledge of the clean signal are
urgently needed. This paper proposes a non-intrusive measure
that predicts speech intelligibility using only the processed signals and audiogram of the listener as input. The proposed measure relies on three steps, namely a hearing-loss model, a feature extractor and a predicting function. The hearing loss model
uses the target signal and the listener’s audiogram as input while
the feature extractor and the predicting function are trained on
processed signals labeled in terms of speech intelligibility during a listening test. The evaluation is conducted using cross-
validation on both tracks of the first Clarity Prediction Challenge (CPC1).}
}
@COMMENT{Bibtex file generated on }