Memory-based Robust Interpretation of Recognised Speech

We describe a series of experiments in which memory-based machine learning techniques are used for the interpretation of spoken user input in human-machine interactions. In these experiments, the task is to determine the dialogue act of the user input and the type of information slots the user fills, on the basis of a variety of features representing the spoken input (speech measurements and word recognition information) as well as its context (the interaction history). In the first experiment, we perform this task using the complete word graph output of the automatic speech recogniser. This yields an overall accuracy of 76.2%, with an F-score of 91.3 on dialogue act classification and an F-score of 87.7 on filled slot types. In the second experiment, we investigate the usefulness of two approaches to filtering out possibly non-contributing word recognition information from the speech recogniser output: (i) filtering out disfluencies, and (ii) keeping only syntactic chunk heads