« All Events

  • This event has passed.

Embeddings for spoken words – talk by Karen Livescu from TTIC

December 22, 2019 @ 12:00 pm - 1:00 pm IST

Event canceled

Title:  Embeddings for 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 segments corresponding to words, or other linguistic units, as fixed-dimensional vectors.  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.
Bio:  Karen Livescu is an Associate Professor at TTI-Chicago.  She completed her PhD in electrical engineering and computer science at MIT.   Her main research interests are in 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 2015/2017/2019, and a program co-chair of ICLR 2019.

Details

Date:
December 22, 2019
Time:
12:00 pm - 1:00 pm IST

Venue

Gonda Building (901), Room 101

Leave a Comment