The Impact of Background Speech on Interruption Detection in Collaborative Groups

TL;DR

This paper investigates how background speech affects interruption detection in collaborative groups, developing a robust method for classrooms with overlapping conversations and analyzing linguistic cues of interruptions.

Contribution

It introduces a state-of-the-art interruption detection method resilient to overlapping speech and explores linguistic and prosodic features in group interactions.

Findings

Robust interruption detection in multi-group settings

Identification of linguistic cues for interruptions

Analysis of prosodic features in group dialogues

Abstract

Interruption plays a crucial role in collaborative learning, shaping group interactions and influencing knowledge construction. AI-driven support can assist teachers in monitoring these interactions. However, most previous work on interruption detection and interpretation has been conducted in single-conversation environments with relatively clean audio. AI agents deployed in classrooms for collaborative learning within small groups will need to contend with multiple concurrent conversations -- in this context, overlapping speech will be ubiquitous, and interruptions will need to be identified in other ways. In this work, we analyze interruption detection in single-conversation and multi-group dialogue settings. We then create a state-of-the-art method for interruption identification that is robust to overlapping speech, and thus could be deployed in classrooms. Further, our work highlights meaningful linguistic and prosodic information about how interruptions manifest in collaborative group interactions. Our investigation also paves the way for future works to account for the influence of overlapping speech from multiple groups when tracking group dialog.