A Testbed for Examining the Timing of Feedback using a Map Task
Gabriel Skantze · 2012
In this paper, we present a fully automated spoken dialogue system that can perform the Map Task with a user. By implementing a trick, the system can convincingly act as an attentive listener, without any speech recognition. An initial study is presented where we let users interact with the system and recorded the interactions. Using this data, we have then trained a Support Vector Machine on the task of identifying appropriate locations to give feedback, based on automatically extractable prosodic and contextual features. 200 ms after the end of the user’s speech, the model may identify response locations with an accuracy of 75%, as compared to a baseline of 56.3%. 1.