Imagine if you or a loved one could self-check brain function at any time using an app on your phone. This is becoming reality with the development of LOGOS, an automated telephone procedure designed to assess verbal memory.
However, for LOGOS to reach its potential, single spoken word-to-text technology needs to improve to greater than 95% accuracy.
Natural language speech-to-text technologies (such as Siri and Google API) are excellent because they can mine context and usage, but their performance on single isolated words is dismal.
This competition therefore looked for innovative solutions to a discrete problem: detection of a simple set of 15 random words from within an MP3 audio stream. This was a chance to revolutionise the way cognitive disorders such as dementia are managed in future, given early detection and intervention is key.
The winners of the 2018 Innovation Week Coding Challenge were announced at the Innovation Week Student Innovation Challenge and Showcase, held on Tuesday 31 July 2018. Winners Mike Li, Jacqueline Huvanandana, Wilmer Yan shared in $10,000. It is hoped their work will make an important contribution to dementia research.