I am a lecturer in E&E engineering at Stellenbosch University, South Africa. Before moving (back) to South Africa, I did a postdoc at TTI-Chicago with Karen Livescu and Greg Shakhnarovich on multi-modal machine learning models combining speech and vision. I obtained my PhD in 2016 from the University of Edinburgh, where I was supervised by Sharon Goldwater, Aren Jansen and Simon King; I worked on unsupervised speech processing, and played around with unsupervised Bayesian and neural models.
My main research interests are in machine learning, speech and language processing, and computer vision. I am particularly interested in machine learning methods that can learn from small amounts of labelled data, and in unsupervised methods that can learn directly from raw unlabelled data. Can an algorithm find meaningful units and structures in a corpus of speech audio, with only minimal guidance? How much supervision is required to build a useful speech processing or computer vision system? These questions are central when building language, speech and vision systems in low- and zero-resource settings.