Personality prediction based on intonation stylization

Reichel, Uwe D. (2015): Personality prediction based on intonation stylization. ICPhS 2015: 18th International Congress of Phonetic Sciences, Glasgow, Scotland, 10.- 14. August 2015.

Abstract

This study's aim is to predict speaker personality from intonation patterns in spoken dialogs. Intonation patterns were extracted by a parametric superpositional stylization approach that allows for pattern description on a parametric as well as on a categorical level. Based on features derived from these representations we trained support vector machines and fitted generalized linear regression models to predict speaker personality with respect to the four dimensions acting, extroversion, other-directedness, and sensitivity. The personality classification accuracies ranged from 79 to 91%.

• Item Type: Conference or Workshop Item (Paper)
• Keywords: intonation; stylization; personality; machine learning
• Faculties: Languages and Literatures > Department 2 > Speech Science
• Subjects: 400 Language > 410 Linguistics
• Language: English