Acoustic transformations to improve the intelligibility of dysarthric speech
Frank Rudzicz · 2011
This paper describes modifications to acoustic speech signals produced by speakers with dysarthria in order to make those utterances more intelligible to typical listeners. These modifications include the correction of tempo, the adjustment of formant frequencies in sonorants, the removal of aberrant voicing, the deletion of phoneme insertion errors, and the replacement of erroneously dropped phonemes. Through simple evaluations of intelligibility with naïve listeners, we show that the correction of phoneme errors results in the greatest increase in intelligibility and is therefore a desirable mechanism for the eventual creation of augmentative application software for individuals with dysarthria. 1