Our research group investigates machine learning models and methodologies for spoken language and audio processing. We are particularly interested in multi-modal learning (for example, audio-visual), as well as approaches based on unsupervised/self-supervised learning for low-resource languages and domains. See our Research page for more details.
We are part of the Computer Science department at The University of Texas at Austin, and are located near the heart of campus in the beautiful and bright Gates-Dell Complex.
We are always on the lookout for motivated students interested in joining the lab!
Current UT students (Ph.D., M.S., and undergraduate) interested in joining our lab should email David Harwath directly. Please include some information about yourself, including a copy of your CV/resume and a description of your background relevant to our research.
Prospective graduate students should apply directly to the Computer Science department’s graduate program. You can find more information here.