Associate Professor, Toyota Technological Institute at Chicago
20 Dec 2018
15:30 pm
Karen Livescu is an Associate Professor at TTI-Chicago. She completed her PhD and post-doc in electrical engineering and computer science at MIT and her Bachelor’s degree in physics at Princeton University. Her main research interests are in the intersection of speech and language processing and machine learning. Her recent work includes multi-view representation learning, acoustic word embeddings, visually grounded speech modeling, and automatic sign language recognition. Her recent professional activities include serving as a member of the IEEE Spoken Language Technical Committee, an associate editor for IEEE Transactions on Audio, Speech, and Language Processing, a technical co-chair of ASRU 2015 and 2017, and a program co-chair of ICLR 2019.
Invited Speech
Acoustic (and acoustically grounded) word embeddings
Abstract:
Word embeddings have become a ubiquitous tool in natural language processing. The analogue for spoken language—acoustic word embeddings—refers to a function that maps a spoken word (or more generally a speech segment of arbitrary length) to a fixed-dimensional vector. Closely related are acoustically grounded embeddings of written words, that is embeddings that represent the way a written word sounds by training on paired acoustic and textual data. Such embeddings can be useful for speeding up or improving performance on a number of speech tasks. This talk will present recent work on both acoustic and acoustically grounded word embeddings, including several learning approaches and applications in speech recognition and search.
