Investigating the Impact of Language Style and Vocal Expression on Social Roles of Participants in Professional Meetings

This paper investigates the influence of social roles on the language style and vocal expression patterns of participants in professional meeting recordings. Language style features are extracted from automatically generated speech transcripts and characterize word usage in terms of psychologically meaningful categories. Vocal expression patterns are generated by applying statistical functionals to low level prosodic and spectral features. The proposed recognition system combines information from both these feature streams to predict participant´s social role. Experiments conducted on almost 12.5 hours of meeting data reveal that recognition system trained using language style features and acoustic features can reach a recognition accuracy of 64% and 68% respectively, in classifying four social roles. Moreover, recognition accuracy increases to 69% when information from both feature streams is taken into consideration.