|Tiancheng Zhao, Alan W Black and Maxine Eskenazi|
This paper deals with an incremental turn-taking model that provides a novel solution for end-of-turn detection. It includes a flexible framework that enables active system barge-in. In order to accomplish this, a systematic procedure of teaching a dialog system to produce meaningful system barge-in is presented. This procedure improves system robustness and success rate. It includes constructing cost models and learning optimal policy using reinforcement learning. Results show that our model reduces false cut-in rate by 37.1% and response delay by 32.5% compared to the baseline system. Also the learned system barge-in strategy yields a 27.7% increase in average reward from user responses.