BACKGROUND Severe dysarthria and global aphasia drastically reduce speech intelligibility, confining communication to familiar partners. Commercial automatic speech recognition (ASR) engines typically fail with 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 human listeners. 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 command 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 rehabilitation professionals familiar with the patient. The primary outcome was word‑level accuracy. RESULTS The tailored ASR achieved 72.7 % accuracy, outperforming human listeners (mean = 56.2 %, SD = 13.0). Conclusions: A personalized ASR system can exceed the intelligibility of human listeners for profoundly disordered speech, supporting its use as an assistive communication technology. CONCLUSIONS Customized ASR systems represent a transformative assistive technology for individuals with severe dysarthria and aphasia, restoring aspects of communicative independence that may be unattainable through unaided human interaction. The CapisciAMe VIVOCA exemplifies how user-tailored technology can enhance autonomy, social participation, and overall quality of life, and the trajectory from early voice-input/voice-output systems to large-scale personalization efforts supports continued development in this direction.
Mulfari et al. (Thu,) studied this question.