Paper Info
Title
Investigating the Impact of Language Style and Vocal Expression on Social Roles of Participants in Professional Meetings
Abstract
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.
Year
DOI
Venue
2013
10.1109/ACII.2013.60
ACII
Keywords
Field
DocType
natural language processing,pattern recognition,social sciences computing,speech processing,statistical analysis,language style,professional meeting recordings,recognition system,social roles,speech transcripts,statistical functionals,vocal expression patterns,Language style features,Social Role Labeling,acoustic features
Speech processing,Word usage,Communication,Recognition system,Computer science,Speech recognition,Feature (machine learning),Natural language processing,Artificial intelligence,Statistical analysis
Conference
ISSN
Citations 
PageRank 
2156-8103
2
0.37
References 
Authors
15
2
Name
Order
Citations
PageRank
Ashtosh Sapru1102.55
Herve Bourlard215237.75