DEVELOPMENT OF A SPEECH ENHANCEMENT ALGORITHM FOR THE INTERVENTION OF PARKINSON'S DISEASE WITHIN THE I-PROGNOSIS FRAMEWORK

Parkinson's disease (PD) is a hereditary disease of the neurological system that manifests itself in motor dysfunctions through neurodegeneration. Diagnoses are often made only in advanced stages of the disease, because the accompanying symptoms are usually masked in early stages. Since PD cannot be cured, an early diagnosis is important to alleviate the course of the disease and improve the patients' quality of life. i-PROGNOSIS is a project funded by the EU "Horizon 2020" programme, which investigates the early detection of PD through the use of intelligent technologies in everyday life in order to mitigate the symptoms through appropriate intervention activities [1]. This poster presents one of the intervention strategies called "Voice Enhancement Intervention" (VEI). It addresses the enhancement of PD patients speech intelligibility by applying signal processing strategies to enhance speech signal clarity and level, as well as reducing the noisiness of the recording. The algorithm is selfregulative and uses an objective measurement of signal modulation depth to estimate speech intelligibility [2] for selfadaption.