Measuring the intelligibility of dysarthric speech through automatic speech recognition in a pluricentric language

Wei Xue, Catia Cucchiarini, Roeland van Hout, Helmer Strik

Abstract: Highlights•Adding dysarthric speech resources from the dominant variety for training improves automatic recognition of dysarthric speech of the non-dominant variety.•Improvements are achieved for both the automatic transcriptions and objective, automatic global measures of dysarthric speech intelligibility.•Automatic speech recognition models perform differently in two scenarios that are defined depending on whether or not speech resources from the non-dominant variety are available for training.