November 12, 2017
RIT has a longstanding commitment in education and research in access technologies, and the university has become an international leader in the field of computer accessibility for people with disabilities. Earlier this month, the work of RIT faculty and students was featured at the leading research conference in this field, The 19th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS'17), held this year at the Sheraton Inner Harbor hotel in Baltimore, MD.
RIT was exceptionally well-represented at conference, with over 13 faculty and students attending the conference, and with seven of the plenary talks given at the conference being presented by RIT researchers (approximately one sixth of all podium presentations). An additional five research papers from RIT authors were presented during the poster sessions of the conference.
The majority of research presented from RIT was from faculty and students in the B. Thomas Golisano College of Computing and Information Sciences (GCCIS) and from the National Technical Institute for the Deaf (NTID). GCCIS is home to several degree programs (e.g. human computer interaction, human centered computing) and research centers (e.g. the Center for Accessibility and Inclusion Research), which conduct work in the field of computing accessibility. NTID has a long history of conducting research on communications and collaboration technologies for DHH students.
A major theme of the research presented this year was on the topic of technologies for people who are Deaf of Hard of Hearing (DHH), including work on using automatic speech recognition software to provide captioning during meetings between DHH individuals and their hearing colleagues. In fact, all of the full-length technical papers presented during the session on "Sign Language and Captioning" at the conference were by RIT authors.
ASSETS is the most prestigious research conference in the field of computing accessibility, and it has become extremely selective, with only 25% of research papers submitted for peer-review ultimately being accepted for presentation at the event. Each year, 5% of the top papers are identified as nominees for the Best Paper Award, and one paper is selected as the highest quality research submission to the conference.
RIT authors took home the Best Paper Award: PhD student Sushant Kafle and GCCIS faculty Matt Huenerfauth presented their research on inventing a new method of automatically evaluating the quality of speech recognition accuracy to predict whether the text transcript produced would be understandable for DHH individuals who were reading captions based on this technology.
A second paper by RIT authors was among the six remaining finalists for this award - joint work by Huenerfauth and other GCCIS students Larwan Berke and Kasmira Patel. "A major goal of our research is to promote greater inclusion of people who are deaf or hard of hearing in research studies or evaluations of technology. In both of our ASSETS papers this year, we present tools that other researchers can use to create or evaluate new communication technologies" said Matt Huenerfauth, GCCIS faculty in the Department of Information Sciences and Technologies.
RIT is home to the National Technical Institute for the Deaf (NTID), and there are over 1,300 DHH students on the RIT campus. Given the longstanding focus of RIT on higher education for DHH students, much of the research presented by RIT authors focused on tools to support communication or collaboration, especially in education settings. For instance, research by NTID faculty Lisa Elliot, Michael Stinson, James Mallory and others has investigated the use of speech recognition technology to support communication during group meetings or in workplace settings with DHH students.
Peer-Reviewed Papers by RIT Authors, Published in the Proceedings of the ASSETS'17 Conference:
Papers Accepted for Presentation as Plenary Talks:
Best Paper Award winner: "Evaluating the Usability of Automatically Generated Captions for People who are Deaf or Hard of Hearing" by Sushant Kafle (RIT student) and Matt Huenerfauth (RIT GCCIS faculty).
Best Paper Award nominee: "Design and Psychometric Evaluation of an American Sign Language Translation of the System Usability Scale" by Matt Huenerfauth (RIT GCCIS faculty), Kasmira Patel (RIT student), and Larwan Berke (RIT student).
"Deaf and Hard-of-Hearing Perspectives on Imperfect Automatic Speech Recognition for Captioning One-on-One Meetings" by Larwan Berke (RIT student), Christopher Caulfield (RIT student), and Matt Huenerfauth (RIT GCCIS faculty).
"Interviews and Observation of Blind Software Developers at Work to Understand Code Navigation Challenges" by Khaled Albusays (RIT student), Stephanie Ludi, and Matt Huenerfauth (RIT GCCIS faculty).
"Personal Perspectives on Using Automatic Speech Recognition to Facilitate Communication between Deaf Students and Hearing Customers" by James Mallory (RIT NTID faculty), Michael Stinson (RIT NTID faculty), Lisa Elliot (RIT NTID faculty), and Donna Easton (RIT researcher).
"Cyborg Pride: Self-Design in e-NABLE" by Peregrine Hawthorn and Daniel Ashbrook (RIT GCCIS faculty).
"Deaf, Hard of Hearing, and Hearing perspectives on using Automatic Speech Recognition in Conversation" by Raja Kushalnagar, Abraham Glasser (RIT student), and Kesavan Kushalnagar (RIT student).
Papers Accepted for Presentation as Scientific Posters:
"CollabAll: Inclusive Discussion Support System For Deaf and Hearing Students" by Anthony Peruma (RIT student), Yasmine El-Glaly (RIT GCCIS faculty)
"Feasibility of Using Automatic Speech Recognition with Voices of Deaf and Hard-of-Hearing Individuals" by Abraham Glasser (RIT student), Kesavan Kushalnagar (RIT student), Raja Kushalnagar
"Teaching Inclusive Thinking in Undergraduate Computing" by Nidhi Palan (RIT student), Matt Huenerfauth (RIT GCCIS faculty), Stephanie Ludi, Vicki Hanson (RIT GCCIS faculty)
"User Experiences When Testing a Messaging App for Communication Between Individuals who are Hearing and Deaf or Hard of Hearing" by Lisa Elliot (RIT NTID faculty), Michael Stinson (RIT NTID faculty), Syed Ahmed (RIT student), Donna Easton (RIT researcher)
"Using Automatic Speech Recognition to Facilitate Communication Between an Individual who is Hearing and One who is Deaf or Hard of Hearing" by Michael Stinson (RIT NTID faculty), Syed Ahmed (RIT student), Lisa Elliot (RIT NTID faculty), Donna Easton (RIT researcher)