Joseph (Yossi) Keshet

Illinois Speech Day 2012  will be held @ TTI-Chicago on May 7, 2012

Symposium on Machine Learning in Speech and Language Processing @ Interspeech 2012 on September 14, 2012

 

Research Assistant Professor

TTI-Chicago

About Me


Since 2009 I have been a Research Assistant Professor at  TTI-Chicago, a philanthropically endowed academic computer science institute located on the University of Chicago campus. Previously I was a postdoctoral research scientist at IDIAP Research Institute, Switzerland, where I worked with Samy Bengio and Hynek Hermansky. I completed my Ph.D. at The School of Computer Science and Engineering at The Hebrew University under the supervision of Yoram Singer in 2007.


My research focuses on developing and analyzing statistical machine learning algorithms for complex and structured tasks. Much of my research is driven by problems in speech and language processing, where typically each problem has a very large number of training examples, is highly structured, and has a unique measure of performance. 


My CV can be downloaded here (PDF).

News

  1. • I am co-organizing the 2nd Symposium on Machine Learning in Speech and Language Processing co-located with Interspeech 2012 in Portland, ON on September 14, 2012 with  Karen Livescu, David Chiang, Fei Sha and Mark Hasegawa-Johnson.

  2. • I am organizing Illinois Speech Day 2012 at TTI-Chicago on May 7, 2012.

  3. • I am co-organizing the 1st Symposium on Machine Learning in Speech and Language Processing co-located with collocated with ICML 2011 and ACL-HLT 2011 in Bellevue, WA on June 27, 2011 with Geoffrey Zweig, Dan Roth, and Hal Daume III.

  4. • I founded the ISCA special interest group on machine learning for speech and language (SIGML)

  5. • I am organizing Illinois Speech Day 2011 at TTI-Chicago on May 7, 2012.

Office

TTI-Chicago, Room 533

6045 S Kenwood Ave,

Chicago, IL 60637

Phone: (773) 834 6850

Fax: (773) 834-9881

Recent Papers


  1. • Morgan Sonderegger and Joseph Keshet, Automatic Discriminative Measurement of Voice Onset Time, Journal of the Acoustical Society of America, 132: 3965−3979, 2012.

  2. • Rohit Prabhavalkar, Joseph Keshet, Karen Livescu and Eric Fosler-Lussier, Discriminative Spoken Term Detection with Limited Data, 2nd Symposium on Machine Learning in Speech and Language Processing, Portland, Oregon, 2012.

  3. • Katharine Henry, Morgan Sonderegger and Joseph Keshet, Automatic Measurement of Positive and Negative Voice Onset Time, The 13th Annual Conference of the International Speech Communication Association (Interspeech), Portland, Oregon, 2012.

  4. • Hao Tang, Joseph Keshet, and Karen Livescu, Discriminative Pronunciation Modeling: A Large-Margin, Feature-Rich Approach, The 50th Annual Meeting of the Association of Computational Linguistics (ACL), 2012.

  5. • David McAllester and Joseph Keshet, Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss, The 25th Annual Conference on Neural Information Processing Systems (NIPS), 2011 (full oral presentation).

  6. • Joseph Keshet, Chih-Chieh Cheng, Mark Stoehr, and David McAllester, Direct Error Rate Minimization of Hidden Markov Models, The 12th Annual Conference of the International Speech Communication Association (Interspeech), Florence, Italy, 2011.

Email: jkeshet@ttic.edu

Student Collaborators


Rohit Prabhavalkar (Ohio State University, CSE, PhD)

Katharine Henry (U. of Chicago, CS & Linguistics, BA)

Hao Tang (TTI-Chicago, CS, PhD)

Chih-Chieh Cheng (UCSD, CSE, PhD)

Mark Stoehr (U. of Chicago, Math, BS)

Andrew Cotter (TTI-Chicago, CS, PhD)

Morgan Sonderegger (U. of Chicago, CS, PhD)