lu.se

Matematikcentrum

Lunds universitet

Denna sida på svenska This page in English

Processing Audio Signals

Advanced speech and audio technology is nowadays ubiquitously available, with most citizens in western societies making daily use of iPods and mobile phones, making free internet phone calls, or watching streaming movies, likely without paying much attention to the technological marvel these applications represent. These applications have been enabled by the vast progress that has been made in speech and audio coding and compression during the recent decades, a progress that is still ongoing.

In our group, we are currently investigating the possibilities to detect and identify various forms of medical conditions from changes in a person’s voice. Many forms of ailments, such as Parkinson’s and Alzheimer’s disease, severe depression, vocal cord cancer, or just a normal cold, will cause one’s voice to change. Together with several medical doctors, surgeons, and speech therapists, we are investigating such voice changes, striving to determine how to separate different ailments as well as how to track how ailments develop over time.

Given the recent outbreak of Corona, we are now also striving to model voice changes that can be suggest early symptoms of Covid-19. For this, as well as for the other studies, we need help from volunteers from all paths of life. We need help both from persons who suffer from illnesses that affect their voice, but also from persons who are well. The latter group is very important for us as a reference group, to allow us to model how the voice varies normally for healthy persons. We have for this reason developed a voice recording app.

To participate in the study, one needs a user login – please just send an email to andreas.jakobsson@matstat.lu.se if you want to participate. A typical voice recording takes about 30-45 seconds and requires almost no effort, so it is not an onerous task. Please help us gather voice data for this!