Predicting collaborative task performance using graph interlocutor acoustic network in small group interaction
Journal
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Journal Volume
2020-October
Pages
3122-3126
Date Issued
2020-01-01
Author(s)
Abstract
Recent works have demonstrated that the integration of group-level personality and vocal behaviors can provide enhanced prediction power on task performance for small group interactions. In this work, we propose that the impact of member personality for task performance prediction in groups should be explicitly modeled from both intra and inter-group perspectives. Specifically, we propose a Graph Interlocutor Acoustic Network (G-IAN) architecture that jointly learns the relationship between vocal behaviors and personality attributes with intra-group attention and inter-group graph convolutional layer. We evaluate our proposed G-IAN on two group interaction databases and achieve 78.4% and 72.2% group performance classification accuracy, which outperforms the baseline model that models vocal behavior only by 14% absolute. Further, our analysis shows that Agreeableness and Conscientiousness demonstrate a clear positive impact in our model that leverages the inter-group personality structure for enhanced task performance prediction.
Subjects
Attention mechanism | Graph convolutional network | Group interaction | Personality
Description
21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020, Shanghai, 25 October 2020 -29 October 2020
Type
conference paper