2016 INTERSPEECH INTERSPEECH 2016

On the Influence of Gender on Interruptions in Multiparty Dialogue

Abstract

During conversations, participants do not always alternate turns smoothly. One cause of disturbance particularly prominent in multiparty dialogue is the presence of interruptions: interventions that prevent current speakers from finishing their turns. Previous work, mostly within the field of sociolinguistics, has suggested that the gender of the dialogue participants plays an important role in their interruptive behaviour. We investigate existing hypotheses in this respect by systematically analysing interruptions in a corpus of spoken multiparty meetings that include a minimum of two male and two female participants. We find a number of significant differences, including the fact that women are more often interrupted overall and that men interrupt more often women than other men, in particular using speech overlap to grab the floor. We do not find evidence for the hypothesis that women interrupt other women more frequently than they interrupt men.

🚀 Conference Pioneer — INTERSPEECH 2016
🌉 Interdisciplinary Bridge — Interdisciplinary and Machine Learning and Mathematics & Optimization and Speech & Audio
🧭 Keyword Pioneer — gender analysis
🐣 Hot Topic Early Bird — conversation analysis
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Speech & Audio