A framework for improving error detection and correction in spoken dialog systems

David Griol, José Manuel Molina
2016 Soft Computing - A Fusion of Foundations, Methodologies and Applications  
One of the main problems which must be considered during the interaction with a spoken conversational interface is the propagation of errors through the different modules in the system. In this paper, we propose a novel framework to improve the error detection and correction processes in spoken conversational interfaces. The framework combines user behavior and error modeling to estimate the probability of the presence of errors in the user utterance. This estimation is considered as an
more » ... al input of the dialog manager and used to compute whether it is necessary to correct possible errors. We have designed an strategy differentiating between the main misunderstanding and non-understanding scenarios, so that the dialog manager can provide an acceptable tailored response when entering the error correction state. We also contribute the practical application of the proposed technique for a dialog system acting as a customer support service.Our results show the appropriateness of our technique to correctly detect and react to errors, enhancing the system performance and user satisfaction.
doi:10.1007/s00500-016-2290-z fatcat:icfwutyuafeplalq2l3w4sv33u