cs.RONov 12, 2026

Robots That Talk Too Much and Don't Listen Enough

Authors: Graham Wilcock, Kristiina Jokinen

Organizations: CDM Interact and University of Helsinki, Helsinki, Finland · University of Helsinki and CNRS-AIST Joint Robotics Lab, Tsukuba, Japan · Also Visiting Professor at Institute of Science Tokyo, Tokyo, Japan.

Abstract

Until recently, the biggest obstacles to natural spoken interaction with social robots were speech recognition errors and turn-taking failures. Advances in speech recognition have enabled much better spoken interaction, but turn-taking failures and other misunderstandings continue to be far too prevalent. This short paper looks back at earlier methods for improving speech recognition and turn-taking in interaction with social robots, and then looks at what can be done today, arguing that multimodal bidirectional streaming is needed to reduce the frequency of turn-taking failures.

Figures & tables

Explore similar work

CardsList
  1. Multimodal Socially Aware Framework for Human-Robot Interaction in Virtual Reality

    Oct 25, 2026Richard Xu, Dakarai Crowder, Alexis E. Block +1Human-Robot InteractionSocial Robotics

  2. Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders

    Jul 8, 2026Antonio Cano, Guillermo Pérez, Luis Merino +1Conversational AgentsHuman-Robot Interaction

  3. Towards an Extensible Benchmark for Spoken Dialogue with Social Robots

    Oct 6, 2026Casey Kennington, Ross Mead, Saad Elbeleidy +1Spoken Dialogue SystemsMulti-Turn Dialogue Evaluation