Analysis of speech data in the clinical management of Parkinsonian symptoms

Parkinson's disease (PD) is the second most common neurodegenerative disorder after Alzheimer's, afflicting 1% of the population above the age of 65. The number of people with PD has icreased in the last 30 years, and it is expected to grow in the next years, due to the ageing of population and possible environmental factors. PD symptoms are both motor and non-motor: to tremor, rigidity and bradykinesia, the most representative symptoms of the disease, a variety of automatic nervous system dysfunction, sleep disorders, depression and anxiety should be added. The symptoms are caused by a lack of dopamine, a neurotransmitter produced by the brain cells that are attacked and depleted by PD. Today there's no cure for PD, the treatments available aim to reduce and control the motor symptoms. Monitoring symptoms progression could be helpful for clinicians and patients, as well as researchers, since it could provide insights on the disease and allow a better personalization of therapies. This work will focus on rigidity and its implications on the speech production process, and it investigates on the possibility to use voice analysis as a proxy for motor symptoms (especially rigidity).