Abstract

Voice controlled environmental control interfaces can be a life changing technology for users with disabilities. However, often these users suffer from speech disorders (e.g. dysarthria), making ASR very challenging. Acoustic model adaptation can improve the performance of the ASR , but the error rate will still be high for severe dysarthric speakers. POMDP -based dialogue management can improve the performance of these interfaces due to its robustness against high ASR error rates and its ability to find the optimal dialogue policy in each environment (e.g. the optimal policy depending on the dysarthria severity of the speaker or on the amount of acoustic data used to adapt the ASR ). However, very little research has been done so far in dialogue model adaptation to unique users interacting with a system over a long period of time. This talk explains how statistical dialogue management can be applied to an environmental control interface such as homeService. It also explores different methods to adapt Gaussian process-based dialogue policies and RNN -based dialogue state trackers to unique users, and methods to adapt these models online as more data from the user becomes available.