Neural Generation of Dialogue Response Timings

2020/05/18 by Matthew Roddy, Roddy, Matthew, Naomi Harte +1 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.CL

paper · pdf · doi:10.48550/arxiv.2005.09128

Accepted to ACL 2020

arxiv created 2020/05/18 · arxiv updated 2020/05/20

Abstract

The timings of spoken response offsets in human dialogue have been shown to vary based on contextual elements of the dialogue. We propose neural models that simulate the distributions of these response offsets, taking into account the response turn as well as the preceding turn. The models are designed to be integrated into the pipeline of an incremental spoken dialogue system (SDS). We evaluate our models using offline experiments as well as human listening tests. We show that human listeners consider certain response timings to be more natural based on the dialogue context. The introduction of these models into SDS pipelines could increase the perceived naturalness of interactions.

Cited by

• Visual Cues Support Robust Turn-taking Prediction in Noise

Related

• Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
• Weakly-Supervised Neural Response Selection from an Ensemble of Task-Specialised Dialogue Agents
• Beyond Words: Multimodal LLM Knows When to Speak
• A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
• When to Talk: Chatbot Controls the Timing of Talking during Multi-turn Open-domain Dialogue Generation