Associate Professor, Toyota Technological Institute at Chicago
University of Chicago
Seminar: Learning to embed spoken words
Abstract: Word embeddings have become a ubiquitous tool in natural language processing. These embeddings represent the meanings of written words. On the other hand, for spoken language it may be more important to represent how a written word *sounds* rather than (or in addition to) what it means. For some applications it can also be helpful to represent variable-length acoustic signals corresponding to words, or other linguistic units, as fixed-dimensional vectors, or acoustic word embeddings. 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 applications. This talk will present work on both acoustic word embeddings and acoustically grounded written word embeddings, including their applications for improved speech recognition and search in English and across languages.
About the speaker: Professor Livescu's main research interests are in speech and language processing, as well as related aspects of machine learning. She is an Associate Professor at TTI-Chicago, a philanthropically endowed academic computer science institute located on the University of Chicago campus. She completed her PhD in 2005 at MIT in the Spoken Language Systems group of the Computer Science and Artificial Intelligence Laboratory. In 2005-2007 she was a post-doctoral lecturer in the MIT EECS department. In Feb.-Aug. 2008 she was a Research Assistant Professor at TTI-Chicago.
Host: Nikos Sidiropoulos, Louis T. Rader Professor and Chair, Electrical and Computer Engineering