What question did this study set out to answer?

The aim is to assess if a personalized speech recognition system can decode severely disordered speech better than human listeners.

June 6, 2026Open Access

Case Report: Tailored automatic speech recognition in global aphasia with dysarthria - a single case proof of concept

Key Points

The aim is to assess if a personalized speech recognition system can decode severely disordered speech better than human listeners.
Single-case proof-of-concept study conducted with a 34-year-old woman post-stroke.
1,120 utterances of target-words were recorded and processed using a compact convolutional neural network (cnn-trad-fpool3).
Word-level accuracy was evaluated against 12 rehabilitation professionals familiar with the patient.
The tailored ASR achieved 72.65% accuracy in speech recognition.
Familiar rehabilitation professionals had an average accuracy of 56.75% (SD = 12.91).
The ASR system significantly outperformed human listeners in intelligibility.

Abstract

Background Severe dysarthria and global aphasia drastically reduce speech intelligibility, confining communication to familiar partners. Automatic speech recognition (ASR) systems may show limited performance when processing such atypical speech. Objective To determine whether a speaker-dependent Voice-Input Voice-Output Communication Aid (VIVOCA) embedded in the CapisciAMe app can decode the speech of a person with severe dysarthria and aphasia more accurately than rehabilitation professionals human listeners (RPHL). Methods We conducted a single-case proof-of-concept study. A 34-year-old woman, 15 years post-stroke, recorded 1,120 utterances of 13 target-words across five prompting modalities. A compact convolutional neural network (cnn-trad-fpool3) was trained on these samples and evaluated on an independent set of 936 utterances. Intelligibility was benchmarked against 12 RPHL familiar with the patient. The primary outcome was word-level accuracy. Results The tailored ASR achieved 72.65 % accuracy, outperforming familiar RPHL (mean = 56.75 %, SD = 12.91). Conclusions A personalized ASR system can exceed the intelligibility of human listeners for profoundly disordered speech, supporting its use as an assistive communication technology.

AI से पूछें

Bookmark

View Full Paper