Facilitating use of speech recognition software for people with disabilities: A comparison of three treatments

Abstract

This study examined the relative benefit of three interventions (i.e. physiological, behavioural, and pragmatic) designed to facilitate speech recognition software use. Participants were 15 adults with dysarthria associated with a variety of aetiological conditions, including cerebral palsy, Parkinson's disease, and motor neuron disease. Results suggested no clear dysarthric profile that would preclude at least some degree of speech recognition system use. Participants demonstrated systematic improvement in their dictation rates regardless of treatment order. The physiological treatment produced significantly higher dictation rates overall than the behavioural—but not the pragmatic—treatment. This finding suggests that improvement was not simply a function of software training, at least for the physiological treatment. This conclusion also was supported by changes in the participants' speech production during a post‐treatment assessment.

• Speech recognition software
• dysarthria
• speech therapy
• computer access

Notes

1. The results for order from the analysis of variance are not reported here because they are not relevant to the aims of the research. The cumulative effects across the sequence of treatments for each participant are controlled through counterbalancing treatment order across participants and by comparing treatments as a main effect. The results for order can be obtained directly from the authors for the interested reader.