The project aims at exploring the potentials of everyday life audio signals to estimate affective states passively and in real-time. Technical development of an assessment device, privacy aspects and validation in the field are covered in the project.

Duration

• 3 years

Participating institutions

• KIT KD2School (http://kd2school.info/)
• University Bremen (https://www.uni-bremen.de/csl)

Progress in mobile technology in recent years enables studying processes in daily life, using digital phenotyping, smartphone technology and wearables. The focus of this project is affect, one of the most central determinants of adaptive systems. Leveraging recent developments from affective computing, we will extract sentiment and voice features of spoken language from daily life assessments as input for adaptive systems. We will partly focus on mental health populations to achieve maximum differences in experienced affect in everyday life.