This research program is aimed at developing modern machine learning methods that lead to improved performance of audio processing algorithms (e.g., for hearing aids). In particular, our approach is to study computational models of learning and adaptation in brains and apply these ideas to the design of personalization of audio processing applications. Key areas of interest include Bayesian machine learning, probabilistic graphical models (factor graphs), computational neurosciences and signal processing. We develop our own toolbox (see
http://forneylab.org) for Bayesian inference and learning, so you should have a strong interest and background in professional code development.
Please browse our web page
http://biaslab.org for more information on our research goals.