Accessible Neuroimaging Research and Dissemination via Speech to Text Apps

Accessibility is a critical dimension of diversity and inclusivity. In this roundtable, we will focus on current best practices and the latest technology to improve hearing accessibility in 2 scenarios: firstly, at the OHBM Annual Meeting, and secondly, in the MRI environment. While hearing accessibility procedures are often developed to enable people with sensory impairments (e.g., people who are D/deaf, or those with hearing loss) to receive information, hearing accessibility principles actually improve comprehension of spoken language for the vast majority of people. For example, people for whom English is an additional language, and people with auditory processing difficulties (common in older age, neurodegenerative illness, and in conditions like ADHD, autism, and learning disorder), benefit from these principles. Further, it is known from bilingual and educational psychology that comprehension and retention is improved when content is delivered both orally and with captions (e.g., Zheng et al., 2022; Adesope & Nesbit, 2012).

In this roundtable, we will demonstrate that

1) Multilingual transcription is possible at international conferences
2) Supplementing auditory instructions in the MRI environment with captions improves the experience for all participants/patients, and expands diversity of participant pools by enabling individuals with mild hearing loss to participate in MRI studies
3) Providing captioned instructions in the MRI environment opens novel opportunities for functional neuroimaging in understudied populations, including people who are D/deaf or with hearing loss, cerebral palsy, Parkinson’s or Amyotrophic Lateral Sclerosis (ALS), among others 

Communication during MRI procedures is often hindered by the scanner’s loud noise. To address this, NALscribe, a speech-to-text app developed by the National Acoustic Laboratories (NAL) in Australia, provides real-time captions and supports transcription in over 15 languages. Originally designed for audiology clinics, it has been widely adopted in settings such as healthcare appointments, classrooms, and family gatherings.

Clear communication between the radiographer and the patient or research participant inside the MRI scanner is crucial for ensuring compliance with scan requirements (e.g., task instructions), minimizing motion artifacts, and providing reassurance. However, the low audio quality of most MRI intercom systems, combined with earplugs, positioning foam, and the scanner’s inherent noise, makes it difficult for even those with normal hearing to understand speech. For individuals with hearing loss (including D/deaf people, older adults, and those with sensory processing disorders), the intelligibility of auditory communication in the scanner is significantly reduced.

We demonstrate how NALscribe can overcome these barriers by displaying real-time captions on a screen inside the MRI room, viewable by patients through a mirror. This approach enhances procedural efficiency, patient understanding, and the overall MRI experience.

Additionally, NALscribe AR, an augmented reality live captioning app for AR headsets, like the Apple Vision Pro, offers spatially-positioned captions. This technology could allow patients to simultaneously view captions alongside medical documents or scans displayed on the headset, creating a more immersive and informed experience. This has potential in preparatory phases, post-imaging debriefings, and neuroscience research, enhancing communication accessibility across healthcare and clinical practice.
 

High-definition transcranial current stimulation (HD-tDCS) shows promise for improving ageing working memory performance. In this pitch, the preliminary findings of an ERP study investigating the efficacy of HD-tDCS on working memory in healthy older adults will be described, highlighting how prior task practice may affect the HD-tDCS after-effect in light of the activity-dependent model. This summary will be presented in Chinese with speech-to-text transcription in English (zoom or PPT 365).
 

High-definition transcranial current stimulation (HD-tDCS) shows promise for improving ageing working memory performance. In this pitch, the preliminary findings of an ERP study investigating the efficacy of HD-tDCS on working memory in healthy older adults will be described, highlighting how prior task practice may affect the HD-tDCS after-effect in light of the activity-dependent model. This summary will be presented in Chinese with speech-to-text transcription in English (zoom or PPT 365). 

Speech to text apps work very well in most situations. For this to work, three key ingredients are a) clear speech, b) audibility and c) connectivity. However, accuracy can decrease with accented speech stemming from hearing loss or with English as a second language. To demonstrate these factors in the context of speech-to-text apps, we present results that compare human and automated transcription of 60+ talks over 5 days at a recent scientific conference. At the same time, the presentation will make use of Google’s Project Relate, which is a speech to text app customized for accented speech. On a related note, Google’s Project Euphonia is targeted at patients with cerebral palsy, Parkinson’s or Amyotrophic Lateral Sclerosis (ALS) which could open up new opportunities for functional neuroimaging.