Say no more! Natural Language Processing for diagnosis and screening in psychiatry

Duration November 2020 - November 2021  
PI drs. Janna de Boer, MD, UMC Utrecht
Funders Sunovion, CLARIAH 

The efficacy of speech language analysis in psychiatry is widely studied, as speech is an important source of information on a person's state of health. In addition, many psychiatric disorders are characterised by (mild) language and/or speech disorders. To date, such analyses have been very labour-intensive, as all conversations are transcribed manually.

This project aims to use CLARIAH's automatic speech recognition (ASR) to analyse whether speech from patients with a psychiatric disorder can also be accurately and automatically recognised. At present, it is not yet clear whether the speech of people with a language and/or speech disorder can be recognised accurately enough to be used for clinical purposes such as diagnostics or prognosis.