Error, canvas is not supported

Larwan Berke

larwan.berke @ mail.rit.edu
Photo of Larwan Berke.
I am a fourth-year Ph.D. candidate in Computing and Information Sciences at the Golisano College of Computing and Information Science (GCCIS), Rochester Institute of Technology (RIT) under the advisement of professor Matt Huenerfauth. I was awarded the National Science Foundation (NSF) Graduate Research Fellowship studying Human-Computer Interaction (HCI) in September 2017.








Research Teams

I am a member of those wonderful teams at RIT:
LATLab Logo Linguistic and Assistive Technologies Laboratory (LATLab)

CAIR Logo Center for Accessibility and Inclusion Research (CAIR)

Research Goal

As the accuracy of Automatic Speech Recognition (ASR) technology improves over time, it may become a viable method for transcribing audio input in real-time. Such technology can provide access to spoken language for people who are Deaf or Hard-of-Hearing (DHH). However, ASR is imperfect and will remain so for a while, thus there is a need for users to cope with errors in the output. Our proposed solution is to add markup to the captioning so the DHH viewer is able to discern when the ASR may be erroneous by utilizing the confidence values in the ASR output. Our goal is to develop an application for a tablet so the DHH user can bring it to one-on-one meetings with hearing people.

Publications / Presentations / Posters

You may also view my Google Scholar Profile or ACM Digital Library Profile.

* Sedeeq Al-khazraji, Larwan Berke, Sushant Kafle, Peter Yeung, Matt Huenerfauth. 2017. "Modeling the Speed and Timing of American Sign Language to Generate Realistic Animations." ACM SIGACCESS Conference on Computers and Accessibility (ASSETS'18). URL:toappear
Award Larwan Berke, Sushant Kafle, Matt Huenerfauth. 2018. "Methods for Evaluation of Imperfect Captioning Tools by Deaf or Hard-of-Hearing Users at Different Reading Literacy Levels." Honorable Mention. ACM Conference on Human Factors in Computing Systems (CHI'18). URL
* Larwan Berke, Christopher Caulfield, Matt Huenerfauth. 2017. "Deaf and Hard-of-Hearing Perspectives on Imperfect Automatic Speech Recognition for Captioning One-on-One Meetings." ACM SIGACCESS Conference on Computers and Accessibility (ASSETS'17). URL
Award Kasmira Patel, Matt Huenerfauth, Larwan Berke. 2017. "Design and Psychometric Evaluation of an American Sign Language Translation of the System Usability Scale." Honorable Mention. ACM SIGACCESS Conference on Computers and Accessibility (ASSETS'17). URL
Award Poster. April 2017. "Displaying Confidence From Imperfect Automatic Speech Recognition For Captioning." Second Place for Best Poster. Effective Access Technology Conference at RIT. URL
* Poster. February 2017. "Creating a Training Dataset for an Automatic Educational Feedback System for American Sign Language Students." AI Retreat “Move 78” at RIT. URL
* Kevin Rathbun, Larwan Berke, Christopher Caulfield, Michael Stinson, Matt Huenerfauth. 2017. "Eye Movements of Deaf and Hard of Hearing Viewers of Automatic Captions." CSUN Assistive Technology Conference (AT'2017). URL
* Souad Baowidan, Natalie Ningshan Guo, Sarah Johnson, Robyn Moncrief, Larwan Berke. May 2017. "A New N-gram Analytics Tool in ELAN and its Application to Improve Automatic Fingerspelling Generation" DePaul School Of Computing Research Symposium. URL
* Speaker. January 2017. "Captioning Meetings with Imperfect Automatic Speech Recognition." NTID Scholarship Symposium at RIT. URL
* Larwan Berke. 2016. "Displaying Confidence From Imperfect Automatic Speech Recognition For Captioning." Doctoral Consortium. ACM SIGACCESS Conference on Computers and Accessibility (ASSETS'16). URL
* John McDonald, Rosalee Wolfe, Jerry Schnepp, Julie Hochgesang, Diana Gorman Jamrozik, Marie Stumbo, Larwan Berke, Melissa Bialek, Farah Thomas. 2015. "An automated technique for real-time production of lifelike animations of American Sign Language." Universal Access in the Information Society (UAIS May 2015). URL
* Rosalee Wolfe, John Mcdonald, Larwan Berke, Marie Stumbo. 2014. "Expanding n-gram analytics in ELAN and a case study for sign synthesis." Language Resources and Evaluation Conference (LREC 2014). URL
Award Poster. February 2014. "Exploring Corpus Analysis for Coarticulation in ASL." Second Place for "Tiki Suarez-Brown Undergraduate Poster Recognition." ACM Richard Tapia Celebration of Diversity in Computing Conference (Tapia 2014). URL
* Poster. October 2013. "Using Corpus Analysis to Improve Legibility of Generated ASL." Grace Hopper Celebration of Women in Computing Conference (GHC 2013). URL
* Larwan Berke. Summer 2013. "Empowering ELAN with N-gram Analytics for Corpora." Distributed Research Experiences for Undergraduates (DREU 2013). URL
* Marie Stumbo, Larwan Berke, Melissa Bialek, Farah Thomas. 2013. "Toward a Real-Time ASL Avatar Utilizing Linguistic Principles for Nonmanual Signals." International Symposium on Sign Language Translation and Avatar Technology (SLTAT 2013). URL
* John McDonald, Rosalee Wolfe, Jerry Schnepp, Julie Hochgesang, Diana Gorman Jamrozik, Marie Stumbo, Larwan Berke. 2013. "Toward Lifelike Animations of American Sign Language: Achieving Natural Motion from the Movement-Hold Model." International Symposium on Sign Language Translation and Avatar Technology (SLTAT 2013). URL