Contact: Joseph Keshet, jkeshet at

UIUC contact: Mark Hasegawa-Johnson

Northwestern contact: Janet Pierrehumbert

We continue the tradition of Illinois Speech Day at TTI-Chicago. Illinois Speech Day is a day-long meeting consisting of presentations and discussion on the theme of computational models of speech. Presenters are faculty, postdocs, and students at University of Chicago, Northwestern, UIUC, and TTI-Chicago. Presentations include completed and ongoing work, with the goal of fostering interaction among the sites. Previous Illinois Speech Days were at 2009, 2010, and 2011.

Please contact Joseph Keshet to register. Space is limited.

9:30 light breakfast

10:00 Keynote: Entrainment in Conversational Speech

Julia Hirschberg, Columbia university

10:50 The Tale of Two Sensory Goals in Speech

Sazzad Nasir, Northwestern

11:20 Symbolic Representations of Motor Function for Automatic Language Acquisition

Steve Levinson, UIUC

11:50 coffee break

12:10 Abstraction and Phonetic Detail in Prosody Perception

Jennifer Cole, UIUC

12:40 Idiolects, Dialects, and Languages: Acoustic and Lexical Models that

Bridge the Barriers

Mark Hasegawa-Johnson, UIUC

1:10 lunch (catered)

2:00 Potential Roles for Audiomotor Integration and Tone Discrimination in

Learning Mandarin Phonetic Contrasts

Li Hsin Ning, UIUC

2:30 Effect of Time Stretching on Speech Perception in Attentionally Demanding Tasks

Valeriy Shafiro, Rush University

3:00 Discriminative Pronunciation Modeling: A Large-margin, Feature-rich Approach

Hao Tang, TTI-Chicago

3:30 - 4:30 poster session:

4:30 Multiview Acoustic Feature Learning using Articulatory Measurements

Raman Arora, TTI-Chicago

5:00 Individual differences in coarticulated speech

Alan Yu, University of Chicago

5:30 Learning Pronunciations from Untranscribed Speech

Sravana Reddy, University of Chicago

6:00 Automatic Measurement of Positive and Negative Voice Onset Time

Katharine Henry, University of Chicago

6:30 go out for dinner

Talker and Language Variation in the LTASS of  English, Mandarin & Mandarin-accented English

Lisa Hesterberg, Lauren Ackerman and Ann Bradlow, Northwestern

Pinky Extension Coarticulation in ASL Fingerspelling

Jonathan Keane, Diane Brenatri, and Jason Riggle, University of Chicago

Fingerspelling Recognition with Linguistic Features

Taehwan Kim, TTI-Chicago

Replacing Neural Networks with Nearest Neighbors for Speech Tasks

Arild Brandrud Næss, Norwegian University of Science and Technology  and TTI-Chicago

Discriminatively Learning Factorized Finite State Pronunciation Models from DBNs

Preethi Jyothi, Ohio State University

Discriminative Articulatory Feature-based Models for Keyword Spotting

Rohit Prabhavalkar, Ohio State University

Plagiarism Detection in Polyphonic Music using Monaural Signal Separation

Soham De

3:30 - 4:30 poster session (cont.):

A Biomimetic Model of the Human Auditory System

Sarah Elizabeth King, UIUC

F0 and the Perception of Prominence in American English

Tim Mahrt, Jennifer Cole, Margaret Fleck, Mark Hasegawa-Johnson, UIUC


Illinois Speech Day 2012

May 7, 2012

TTI-Chicago, Rooms 526-530

6045 S Kenwood Ave, Chicago, IL