In this paper, we present Duplex Conversation, a multi-turn, multimodal spoken dialogue system that enables telephone-based agents to interact with customers like a human. We use the concept of full-duplex in telecommunication to demonstrate what a human-like interactive experience should be and how to achieve smooth turn-taking through three subtasks: user state detection, backchannel selection, and barge-in detection. Besides, we propose semi-supervised learning with multimodal data augmentation to leverage unlabeled data to increase model generalization. Experimental results on three sub-tasks show that the proposed method achieves consistent improvements compared with baselines. We deploy the Duplex Conversation to Alibaba intelligent customer service and share lessons learned in production. Online A/B experiments show that the proposed system can significantly reduce response latency by 50%.
@article{arxiv.2205.15060,
title = {Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems},
author = {Ting-En Lin and Yuchuan Wu and Fei Huang and Luo Si and Jian Sun and Yongbin Li},
journal= {arXiv preprint arXiv:2205.15060},
year = {2022}
}