Towards addressee recognition in smart robotic environments

Abstract

This work explores what people do to inform their surroundings about who is the main addressee of their communicative acts in smart environments. A corpus of naive users, solving daily tasks in a smart home, which is additionally inhabited by a robot, is investigated. Evidence drawn from the corpus is used to create a first model for addressee recognition in smart environments. Finally, the performance of the model is evaluated using the corpus, and possible future improvements and challenges are discussed. The main contribution of this work is a detailed analysis of human addressing cues in smart environments, and the resulting, evidence based addressing model.