Robust spoken language understanding in a computer game

• Published in: Speech communication Vol. 48; no. 3; pp. 335 - 353
• Main Authors: Boye, Johan, Gustafson, Joakim, Wirén, Mats
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.03.2006
• Subjects: Animated characters; Computational linguistics; Computer games; Computer Generated Language Analysis; Computer Modeling and Simulation; Conversational systems; Datorlingvistik; Dialogue systems; Human Computer Communication; HUMANIORA och RELIGIONSVETENSKAP; HUMANITIES and RELIGION; Languages and linguistics; Linguistic subjects; Lingvistikämnen; Noise; Parsing; Playing; Problem Solving; Robust parsing; Robustness; Spoken language understanding; Språkvetenskap; Voice Recognition; Spoken language understanding; Robust parsing; Animated characters; Conversational systems; Robustness; Dialogue systems; Computer games
• ISSN: 0167-6393; 1872-7182; 1872-7182
• DOI: 10.1016/j.specom.2005.06.015

We present and evaluate a robust method for the interpretation of spoken input to a conversational computer game. The scenario of the game is that of a player interacting with embodied fairy-tale characters in a 3D world via spoken dialogue (supplemented by graphical pointing actions) to solve various problems. The player himself cannot directly perform actions in the world, but interacts with the fairy-tale characters to have them perform various tasks, and to get information about the world and the problems to solve. Hence the role of spoken dialogue as the primary means of control is obvious and natural to the player. Naturally, this means that robust spoken language understanding becomes a critical component. To this end, the paper describes a semantic representation formalism and an accompanying parsing algorithm which works off the output of the speech recogniser’s statistical language model. The evaluation shows that the parser is robust in the sense of considerably improving on the noisy output of the speech recogniser.