Syntactic and pragmatic completeness is known to be important for turn-taking
prediction, but so far machine learning models of turn-taking have used such
linguistic information in a limited way. In this paper, we introduce TurnGPT, a
transformer-based language model for predicting turn-shifts in spoken dialog.
The model has been trained and evaluated on a variety of written and spoken
dialog datasets. We show that the model outperforms two baselines used in prior
work. We also report on an ablation study, as well as attention and gradient
analyses, which show that the model is able to utilize the dialog context and
pragmatic completeness for turn-taking prediction. Finally, we explore the
model's potential in not only detecting, but also projecting, turn-completions.

本文介绍了 TurnGPT 语言模型，其通过使用对话的语境和完整性，能够更好地预测口语对话中的转向。我们展示了该模型在多种书面和口头对话数据集上的表现，并证明其胜过之前工作中使用的两个基线模型。此外，我们还研究了模型的各种特性，如注意力和梯度分析，最终认为该模型不仅能够检测转向，而且能够预测完结。

TurnGPT：基于 Transformer 的口语对话转换预测语言模型

TurnGPT: a Transformer-based Language Model for Predicting Turn-taking  in Spoken Dialog

Conversations abound with uncetainties of various kinds. Treating
conversation as inference and decision making under uncertainty, we propose a
task independent, multimodal architecture for supporting robust continuous
spoken dialog called Quartet. We introduce four interdependent levels of
analysis, and describe representations, inference procedures, and decision
strategies for managing uncertainties within and between the levels. We
highlight the approach by reviewing interactions between a user and two spoken
dialog systems developed using the Quartet architecture: Prsenter, a prototype
system for navigating Microsoft PowerPoint presentations, and the Bayesian
Receptionist, a prototype system for dealing with tasks typically handled by
front desk receptionists at the Microsoft corporate campus.

提出了一种基于四个相互依存的分析水平，在口语交互中支持鲁棒性连续对话的任务独立、多模态体系结构 Quartet。通过开发使用 Quartet 的两个口语对话系统 Prsenter 和 Bayesian Receptionist，介绍了处理控制级别内和之间的不确定性的表示、推理程序和决策策略。