Jennifer Drexler

Graduate Student

Jennifer received her B.S.E. degree in Computer Science from Princeton University in 2009. Before starting at MIT in 2013, she worked in the Human Language Technology Group at MIT Lincoln Laboratory, focusing mainly on machine translation. Jennifer's current research focuses on low- and no-resource speech processing, with the goal of enabling speech technologies in low-resource languages. Her projects include unsupervised speech segmentation, analysis of audio-visual models, and joint learning across multiple levels of linguistic hierarchy.



Unsupervised Speech Processing

All humans process vast quantities of unannotated speech and manage to learn phonetic inventories, word boundaries, etc., and can use these abilities to acquire new word. Why can't ASR technology have similar capabilities? Our goal in this research project is to build speech technology using unannotated speech corpora.
Jim Glass