for healthcare and research
The Language Explorer project is funded by the National Institute for Health Research (NIHR) [NIHR200889 i4i]. It is a collaborative product development project which started in November 2019 with the aim of designing, developing and evaluating a language sampling tool that can save time for speech and language therapists.
A two-year study
In 2020 we embarked on a challenge to gather samples of children across the UK retelling the treasure themed story within the Language Explorer app. We needed 600 children aged from four to eight, covering a range of socio-economic groups and from around the country. We were so pleased to reach this target. Following that the Research Associates at Newcastle University have transcribed and analysed the samples by hand, which has been compared with features in the tool as well as being used to train machine learning models. At the end of the year we are ready to start evaluating the app in clinics across the NHS.
Speech recognition technology is one of the core technologies in use in this project as the child records their story retell into the app and it needs to be transcribed so that the analysis of language can take place
The tool analyses linguistic features in the sample. It looks at the language features that are expected to have been acquired at different ages. It also looks at the macrostructure elements of the story.
The accuracy of the calculation of the features by the software has been compared to that of the Newcastle University researchers and features needed to meet an acceptable agreement score to move forward to the clinical version of the tool.