Karen Livescu

			Karen Livescu `klivescu at ttic.edu` Professor Toyota Technological Institute at Chicago My main research interests are in speech and language processing, as well as related aspects of machine learning. I am a Professor at TTI-Chicago, a philanthropically endowed graduate institute for computer science located on the University of Chicago campus. I am also a courtesy faculty member in Computer Science, and Affiliated Scholar at the Data Science Institute, at U. Chicago. TTIC is recruiting students to our PhD program, as well as additional faculty, including in speech and language-related areas (more on Speech and Language at TTIC). I completed my PhD in 2005 at MIT in the Spoken Language Systems group of the Computer Science and Artificial Intelligence Laboratory. In 2005-2007 I was a post-doctoral lecturer in the MIT EECS department. In 2008 I was a Research Assistant Professor at TTI-Chicago.

News Speech&Language@TTIC Students/Postdocs Publications Teaching CV Misc

News (see more news on the SL@TTIC page):
Note: I do not use this space for news about awards, talks, or paper acceptances; if you are looking for these, I try to keep my CV reasonably up to date.

The Multilingual SUPERB 2.0 challenge for language- and dialect-robust speech recognition is open for submissions!

Grad students:
Marcelo Beramendi Caballero
Chung-Ming Chien
Ju-Chieh Chou
Ankita Pasad
Jessica Yang
Tianyang (Sally) Xu

Visiting/external students:
Shester Gueuwou (Kwame Nkrumah University of Science and Technology)
Yanhong Li (U. Chicago)
Tejes Srivastava (U. Chicago)

Past grad students/post-docs:
Freda Shi (co-advised with Kevin Gimpel) (PhD 2024 → faculty at U. Waterloo)
Shane Settle (PhD 2023 → Google)
Bowen Shi (PhD 2023 → Meta)
Qingming Tang (PhD 2023 → Amazon)
Shubham Toshniwal (co-advised with Kevin Gimpel) (PhD 2022 → NVIDIA)
Puyuan Peng (co-advised with Mei Wang) (U. Chicago Stats MS 2021 → UTAustin PhD program)
Hao Tang (PhD 2017 → post-doc at MIT → faculty at U. Edinburgh)
Herman Kamper (post-doc 2017 → faculty at Stellenbosch U.)
Weiran Wang (post-doc 2014-2016 → Amazon → Google)
Taehwan Kim (PhD 2016 → post-doc at Caltech → faculty at UNIST)
Arild Brandrud Næss (NTNU PhD 2015, co-advised with Torbjørn Svendsen → faculty at NTNU Business School)
Bahador Nooraei (MS 2015)
Raman Arora (post-doc 2011-2013 → faculty at JHU)
Louis Terry (Northwestern CSE PhD 2011, co-advised with Aggelos Katsaggelos)
John Labiak (U. Chicago Stats MS 2010, co-advised with Yali Amit and Partha Niyogi)

Past visiting/external students:
Hadas Benisty (Technion EE)
Sujeeth Bharadwaj (UIUC ECE)
Sam Bowman (U. Chicago Linguistics BA)
Yang Chen (U. Chicago)
Soham De (Jadavpur University CSE)
Dhivya Eswaran (IIT Madras CSE BTech)
Victoria Evelkin (Technion EE BS)
Matt Faytak (U. Chicago Linguistics BA)
Wanjia He (U. Chicago PSD MS)
Katie Henry (U. Chicago Computer Science BA)
Yushi Hu (U. Chicago)
Shuning Jin (UMN Duluth/UMD)
Preethi Jyothi (Ohio State CSE PhD)
Herman Kamper (U. Edinburgh CS PhD)
Jack Huang (U. Chicago BS)
Gabrielle Knight (Northwestern Integrated Sciences BS)
Kalpesh Krishna (IIT Bombay BS)
Ang Lu (Tsinghua University Automation BS)
Raci Lynch (Stanford SS BS)
Pranava Swaroop Madhyastha (UPC Barcelona CS PhD)
Anna Margolis (U. Washington CS PhD)
Jon Michaux (U. Chicago PhD)
Katie Mock (U. Chicago Linguistics BA)
Puyuan (Jason) Peng (U. Chicago Stats MS)
Mindi Porebsky (UIUC Linguistics BA)
Rohit Prabhavalkar (Ohio State CSE PhD)
Mark Stoehr (U. Chicago Math BS/CS PhD)
Naohiro Tawara (Waseda U.)
Trang Tran (U. Washington EE PhD)
John Wieting (UIUC CS PhD)

Teaching:
Spring 2025 ... TTIC 31110 (CMSC 35110): Speech Technologies
Spring 2023 ... TTIC 31220: Unsupervised learning and data analysis
Spring 2022 ... TTIC 31110 (CMSC 35110): Speech Technologies
Winter 2021 ... TTIC 31220: Unsupervised learning and data analysis
Spring 2020 ... TTIC 31110 (CMSC 35110): Speech Technologies
Winter 2019 ... TTIC 31220: Unsupervised learning and data analysis
Spring 2018 ... TTIC 31110 (CMSC 35110): Speech Technologies
Spring 2017 ... TTIC 31220: Unsupervised learning and data analysis
Spring 2016 ... TTIC 31110: Speech Technologies
Spring 2015 ... TTIC 31090: Signals, Systems, and Random Processes
Winter 2014 ... TTIC 31110: Speech Technologies
Spring 2013 ... TTIC 31090: Signals, Systems, and Random Processes
Spring 2012 ... TTIC 31110: Speech Technologies
Spring 2011 ... TTIC 31090: Signals, Systems, and Random Processes
Winter 2011 ... 20114231: Introduction to Speech Recognition (Weizmann Institute)
Autumn 2009 ... CMSC 35900: Topics in Artificial Intelligence: Speech Technologies
Autumn 2007, Autumn & Spring 2006, Autumn 2005 ... 6.003: Signals and Systems (MIT)
Spring 2007 ... 6.345: Automatic Speech Recognition (MIT)

Technical reports, theses:

K. Livescu, O. Cetin, M. Hasegawa-Johnson, S. King, C. Bartels, N. Borges, A. Kantor, P. Lal, L. Yung, A. Bezman, S. Dawson-Haggerty, and B. Woods, "Articulatory Feature-based Methods for Acoustic and Audio-Visual Speech Recognition: 2006 JHU Summer Workshop Final Report." Center for Language and Speech Processing, Johns Hopkins University.

K. Livescu, "Feature-Based Pronunciation Modeling for Automatic Speech Recognition." Ph.D. Thesis, MIT Department of Electrical Engineering and Computer Science, September 2005.

M. Hasegawa-Johnson, J. Baker, S. Greenberg, K. Kirchhoff, J. Muller, K. Sonmez, S. Borys, K. Chen, A. Juneja, K. Livescu, S. Mohan, E. Coogan, and T. Wang,"Landmark-based Speech Recognition: Report of the 2004 Johns Hopkins Summer Workshop," Johns Hopkins University 2004 Summer Workshop final report.

J. Bilmes, G. Zweig, T. Richardson, K. Filali, K. Livescu, P. Xu, K. Jackson, Y. Brandman, E. Sandness, E. Holtz, J. Torres, and B. Byrne, "Discriminatively Structured Graphical Models for Speech Recognition." Johns Hopkins University 2001 Summer Workshop final report.

K. Livescu, "Analysis and Modeling of Non-Native Speech for Automatic Speech Recognition." S.M. Thesis, MIT Department of Electrical Engineering and Computer Science, August 1999.

K. Livescu, "Analysis of Human and Parrot Phonation Using an Energy Operator and Energy Separation Algorithm." A.B. Thesis, Princeton Department of Physics, April 1996.

Some neat speech links:

Listen to the sounds of the IPA chart

Why is it hard to understand the lyrics in high soprano singing? (It is not because they are singing in Middle High German)

An interactive vocal tract demo

A formant synthesis demo

Personal