Midwest
Speech and
Language Days
2013
May 2-3, 2013
Toyota Technological Institute at Chicago
6045 S. Kenwood Ave, Chicago, IL

Midwest Speech and Language Days (MSLD) is a 2-day meeting held at TTI-Chicago that continues and expands upon the tradition of Illinois Speech Day. This year, in addition to speech, we will have presentations on research in linguistics and natural language processing. Presenters and attendees come from Midwest universities and research institutions. The goal of the workshop is to increase awareness of speech and language research going on in the region and to foster collaboration among sites. We will also be welcoming TTIC's new president, Sadaoki Furui, who will be speaking at the workshop.

Please contact the organizers for more information or to register.

Organizers:

Kevin Gimpel, TTIC
Karen Livescu, TTIC


Details:

Talks   Talk slots are 25 minutes and include 20 minutes for the talk and 5 for questions.
Posters   Posters can be at most 4 feet by 6 feet.
Parking   A limited number of parking passes are available for TTIC's parking lot. Please contact the organizers to reserve one. Park in the building's parking lot and get your parking pass from the security guard in the lobby. There is also free parking in the commuter parking lot at 60th St and Stony Island Ave and free street parking on many streets near TTIC (just beware of "permit parking" signs!).
Accommodations   For students and those interested in staying within close walking distance of TTIC, we recommend International House at the University of Chicago. There are also many reasonable options in downtown Chicago, such as Hotel Felix.


Invited Speakers:

Jim Glass, MIT
Yotaro Kubo, NTT


Schedule:

Thursday, May 2

9:00-10:00    Breakfast provided at TTIC

10:00-11:50    Keynote session
10:00-10:55     Sadaoki Furui, TTIC - Data-intensive automatic speech recognition based on machine learning
10:55-11:50     Jim Glass, MIT - Towards unsupervised speech processing

11:50-12:05    Break

12:05-1:20    Talk session
12:05-12:30     Jon Keane, U. Chicago - Developing an articulatory model of handshape
12:30-12:55     Li-Hsin Ning, UIUC - Tongue shape of Mandarin "retroflex" consonants: Real-time Magnetic Resonance Imaging data
12:55-1:20     Chilin Shih, UIUC - Multi-dimensional adaptive pronunciation training

1:20-2:15    Lunch provided at TTIC

2:15-3:55    Talk session
2:15-2:40     Micha Elsner, OSU - Information structure prediction for visual-world referring expressions
2:40-3:05     Yonatan Bisk, UIUC - An HDP model for inducing combinatory categorial grammars
3:05-3:30     Doug Downey, Northwestern - Scaling information extraction to the Web

3:30-3:45    Break

3:45-5:15    Poster session
BriAnne Amador & Diane Brentari, U. Chicago - Variation in American Sign Language (ASL) Narratives: Evidence for a Black ASL Prosodic Register
Raman Arora, TTIC - Multi-view learning of acoustic features for speech recognition
Kristen Cortese, Rush - Effect of pitch training on speech perception
Kwang-Sung Jun, UW-Madison - Collecting conversations in Twitter
Hyunjung Lee, U. Chicago - Evidence for sound change in Kyungsang Korean: The case of stop consonants
Torrey Loucks and Li-Hsin Ning, UIUC - Linguistically specific sensorimotor responses in second language learning
Tim Mahrt, UIUC - Similarity of prosodic phonetic detail between imitated vs. repeated speech
Arjun Mukherjee, UIC - What Yelp fake review filter might be doing?
John Novak and Jason Archer, UIC - On-line audio dilation for interactive speech communication
Junming Sui, UW-Madison - Socioscope: Spatio-temporal signal recovery from social media
Hao Tang, TTIC - A comparison of losses for training segmental models
Marten Van Schijndel, OSU - An analysis of frequency- and memory-based processing costs


Friday, May 3

9:00-9:30    Breakfast provided at TTIC

9:30-10:30    Invited talk
Yotaro Kubo, NTT - Integration of structured classification and deep neural networks for automatic speech recognition

10:30-11:20    Talk session
10:30-10:55     Barbara Di Eugenio, UIC - Multimodal dialogue processing in the ROBOHELPER project
10:55-11:20     Kevin Gimpel, TTIC - Phrase dependency grammars for machine translation

11:20-11:35    Break

11:35-12:50    Talk session
11:35-12:00     Micah Hodosh, UIUC - Image description as ranking
12:00-12:25     Bing Liu, UIC - Sentiment analysis and modeling of online discussions
12:25-12:50     Karen Livescu, TTIC - Low-resource spoken term detection with discriminative articulatory models

12:50-1:45    Lunch provided at TTIC

1:45-3:25    Talk session
1:45-2:10     Peter Baumann, Northwestern - Using resource-rich languages as a resource for under-resourced languages: high-precision morphological analysis of Tagalog
2:10-2:35     Janet Pierrehumbert, Northwestern - The evolutionary dynamics of words
2:35-3:00     Steve Levinson, UIUC - Mental representations of motor function for language understanding
3:00-3:25     Shinji Watanabe, MERL - Structural Bayesian linear regression for hidden Markov models

3:30-5:00    Poster session
Sara Finley, Waldorf - Adult learning of novel phonological patterns
Lisa Hesterberg, Northwestern - Morphological generalization in Arabic
Amjad Abu Jbara, UM-Ann Arbor - Mining multiple perspectives from threaded discussions
Rahul Jha, UM-Ann Arbor - Surveyor: A system for summarizing scientific topics starting from keywords
Preethi Jyothi, OSU - Discriminatively training WFST factors with an application to pronunciation modeling
Taehwan Kim, TTIC - American Sign Language fingerspelling recognition with semi-Markov conditional random fields
Ben King, UM-Ann Arbor - Labeling the languages of words in mixed-language documents using weakly supervised methods
Tatiana Luchkina, UIUC - Speaker- and reader-based account of discourse prominence in a free word order language
Preethi Raghavan, OSU - Temporal ordering of medical events in longitudinal clinical narratives




Participants (* denotes presenter):

Deema AlShamaa, UW-Madison
*BriAnne Amador, U. Chicago
*Jason Archer, UIC
*Raman Arora, TTIC
*Peter Baumann, Northwestern
*Yonatan Bisk, UIUC
*Diane Brentari, U. Chicago
Damir Cavar, EMU
Malgorzata E. Cavar, EMU
Lin Chen, UIC
Jennifer Cole, UIUC
*Kristen Cortese, Rush
*Barbara Di Eugenio, UIC
*Doug Downey, Northwestern
*Micha Elsner, OSU
*Sara Finley, Waldorf
Margaret Fleck, UIUC
*Sadaoki Furui, TTIC
Vikas Garg, TTIC
*Kevin Gimpel, TTIC
*Jim Glass, MIT
Matt Goldrick, Northwestern
Nick Green, UIC
Scott Hajek, UIUC
Mark Hasegawa-Johnson, UIUC
Katie Henry, U. Chicago
*Lisa Hesterberg, Northwestern
*Micah Hodosh, UIUC
Dave Howcroft, OSU
*Amjad Abu Jbara, UM-Ann Arbor
*Rahul Jha, UM-Ann Arbor
*Kwang-Sung Jun, UW-Madison
*Preethi Jyothi, OSU
*Jon Keane, U. Chicago
*Taehwan Kim, TTIC
Amelia Kimball, UIUC
*Ben King, UM-Ann Arbor
Sarah Elizabeth King, UIUC
*Yotaro Kubo, NTT
Alice Lai, UIUC
*Hyunjung Lee, U. Chicago
*Steve Levinson, UIUC
*Bing Liu, UIC
*Karen Livescu, TTIC
*Torrey Loucks, UIUC
*Tatiana Luchkina, UIUC
*Tim Mahrt, UIUC
Daniel Margoliash, U. Chicago
David McAllester, TTIC
Agathe Merceron, Beuth
*Arjun Mukherjee, UIC
Ryan Musa, UIUC
Jeremy Needle, Northwestern
*Li-Hsin Ning, UIUC
Bahador Nooraei, TTIC
*John Novak, UIC
*Janet Pierrehumbert, Northwestern
*Preethi Raghavan, OSU
Jason Riggle, U. Chicago
Dan Roth, UIUC
Valeriy Shafiro, Rush
Stan Sheft, Rush
*Chilin Shih, UIUC
Ryan Shosted, UIUC
Paris Smaragdis, UIUC
Mark Stoehr, U. Chicago
*Junming Sui, UW-Madison
*Hao Tang, TTIC
*Marten Van Schijndel, OSU
*Shinji Watanabe, MERL
Di Wu, UIUC
Alan Yu, U. Chicago