David Harwath (original) (raw)

My research interests are in the area of machine learning for speech, language, and sound processing. I am particularly interested in multimodality and unsupervised/self-supervised approaches that can benefit low-resource languages and domains. At UT, I lead the Speech, Audio, and Language Technologies (SALT) Lab.

Prior to joining UT, I worked as a research scientist at MIT CSAIL from 2018 to 2020. I recieved my PhD in 2018 from the Spoken Language Systems Group at MIT CSAIL, under the supervision of Jim Glass.

Research

Publications

Please visit the SALT Lab website to find my group's publications. You can also visit my Google Scholar page.

Datasets

Please visit this website to download all of the spoken caption corpora I have collected (as well as modeling code).