Automated speech enabled human-computer interfaces have become essential for the competiveness of many Canadian industries. The demand for more natural, simplified, and low cost user interfaces has made voice enabling of telecommunications, automotive, and consumer electronics devices nearly ubiquitous. Commercially available automated intelligent assistants have been developed to guide customers through problem solving scenarios. The […]

Deep neural networks (DNNs) for automatic speech recognition (ASR) require large amounts of labelled data, which can be difficult and expensive to collect. However, recent research has shown that some features learned by DNNs are highly transferable to other tasks and datasets. Here we propose to design a multi-lingual training procedure to leverage large amounts […]