Error simulation for training statistical dialogue systems

Abstract

Human-machine dialogue is heavily influenced by speech recognition and understanding errors and it is hence desirable to train and test statistical dialogue system policies under realistic noise conditions. This paper presents a novel approach to error simulation based on statistical models for word-level utterance generation, ASR confusions, and confidence score generation. While the method explicitly models the context-dependent acoustic confusability of words and allows the system specific language model and semantic decoder to be incorporated, it is computationally inexpensive and thus potentially suitable for running thousands of training simulations. Experimental evaluation results with a POMDP-based dialogue system and the Hidden Agenda User Simulator indicate a close match between the statistical properties of real and synthetic errors.