Comparison between covert sound-production task (sound-imagery) vs. motor-imagery for onset detection in real-life online self-paced BCIs.
Youngjae Song, Francisco Sepulveda
PMID 32028964WHAT IT FOUND
Covertly imagining a high-pitched 'um' sound detected user intent more accurately and faster than imagining hand movements.
The sound task was rated easier by 75% of participants, though it performed no better than motor imagery during text reading.
Key findings
01The sound imagery task achieved a significantly higher True-Positive rate for onset detection compared to motor imagery in both the sliding image and video-watching scenarios.
02System response time was significantly faster for the sound imagery task than for motor imagery across all three daily-life scenarios.
03Sound imagery showed no statistically significant advantage over motor imagery in True-Positive rate or usability scores during the text-reading scenario.
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
The study involved only twelve healthy young adults (aged 19–27), so results may not generalize to patients with motor or speech impairments. The sound imagery task performed no better than motor imagery during text reading, limiting its utility in contexts involving silent reading. There is no direct non-invasive way to validate the exact timing of the user's mental onset, so the system relies on user feedback for accuracy assessment, which introduces potential subjectivity. The study compared two specific mental tasks; it did not test clinical populations or long-term usability.
Declared interests
Funded by the Engineering and Physical Sciences Research Council. No other conflicts of interest were reported.
The easy way to misread this
Do not assume this sound-based BCI will work for patients with severe speech or language impairments. The study was conducted on healthy young adults, and the task requires the ability to mentally produce a specific tone, which may not be accessible to those with aphasia or apraxia.