On speaker-independent personality perception and prediction from speech

In this paper, we present ongoing experiments and insights re-garding automatic and human assessment of perceived person-ality. While within the INTERSPEECH Speaker Trait Chal-lenge participants will train systems in order to recognize bi-nary targets along the Big 5 personality trait, we will analyze and discuss properties of the data, the labeling scheme and the predictive quality. Conducting factor analyses, estimating re-liability, and building regression models capturing dimensions of personality we compare all results to our own work and in-troduce a new extension of our personality database. In con-clusion, this paper contributes in methodology and understand-ing on how to asses the perceived personality from an unknown speaker by humans and machines. Index Terms: extra-linguistic speech properties, personality modeling from speech, speaker characteristic