Voice-Assisted Technology as a Potential Tool for Addressing Speech and Voice Concerns Experienced by People With Parkinson's Disease and Other Conditions Presenting With Dysarthria: A Scoping Review.
Jodie Mills, Orla Duffy, Katy Pedlow and 1 others
PMID 41116223WHAT IT FOUND
Off-the-shelf smart speakers may encourage clearer, louder speech in people with dysarthria, but recognition is unreliable and varies by severity.
Therapists should use them cautiously for home practice, not as assessment tools, watching for frustration and bias.
Key findings
01One semi-randomized trial found statistically significant improvements in intelligibility ratings for adults with intellectual disability using smart speakers, while other included studies relied on self-reported changes.
02Automatic speech recognition accuracy drops significantly with severe dysarthria and fails to distinguish mild from moderate cases, making it unsuitable for monitoring progression or assessing speech severity.
03Users often adapt their speech (increasing volume, slowing rate) to be understood by the device, but this can cause frustration and does not necessarily translate to better recognition in everyday human conversation.
STILL TO COME
How it was doneWhat they foundWhat it means for SLPs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
Only five studies met inclusion criteria, and most were low quality (cross-sectional surveys, qualitative, or small experimental designs). Two review authors were involved in two of the included studies, creating potential selection bias. Most evidence on speech change is self-reported rather than objectively measured. The review only included English-language papers, limiting generalizability to non-English speakers. VAT technology and algorithms change rapidly, so findings may become outdated quickly. No studies directly measured the impact of VAT on participation or well-being in a controlled way.
Declared interests
The authors declare no conflicts of interest. The review was part of a PhD project at Ulster University.
The easy way to misread this
Do not assume that because a smart speaker understands a client's speech, their intelligibility has improved for human listeners. Recognition errors are high in conversational settings, and devices may accept overly simplified or unnatural speech adaptations that do not transfer to daily life.
Summarised by AI from the full paper, without a clinician reviewing it. Check it against the source before it changes what you do. Read it on PubMed →