this is the webpage of austin waters. i'm a ph.d. candidate in the department of computer science at the university of texas at austin. i work with Risto Miikkulainen in the neural networks research group. my primary research interests are statistical machine learning and topic models. i am particularly interested in the extension of topic models and other statistical methods to non-text domains such as images, sounds, or videos.
i also have a not-so-secret fascination with the phenomenon of human auditory perception. i am interested in combining computational models of auditory physiology with results from psychoacoustics to create machines that can better understand sound. this is a field sometimes called computational auditory scene analysis or machine hearing. here, my focus is on methods for sound source separation and, in particular, speech enhancement.