Malihe Alikhani
Northeastern University, MA·Computer Science
Many scientific ideas have no standard sign in American Sign Language (ASL). In a biology class, one deaf student may fingerspell a term, another may use a sign they invented, and a third may use a different sign entirely.
- Fields
Computer Science
Education Research
- Topics
American Sign Language
deaf education
sign language recognition
- Grants
- 1 known grant, through Aug 2027
What they work on
- Build an AI tool that recognizes ASL signs used in classroom conversation and shows related scientific terms in real time through augmented reality, signing avatars and English captions.
- Develop sign recognition and sign generation systems that adapt to differences between learners and include facial expressions and prosodic features, the rhythm and emphasis of signing.
- Co-design and prototype-test the tool with deaf students, then run an experimental study of how it affects collaboration and learning in university biology classes.
- Examine how adaptive supports for lexical alignment, meaning settling on shared terms, relate to group collaboration processes and learning outcomes among deaf students.
More about the research
Without shared vocabulary, it is hard for deaf students to work together on problems. Group problem-solving is known to deepen understanding of complex concepts, but most classroom supports are built for hearing students. Deaf people are also strongly underrepresented in science.
Why it matters
Deaf students in science courses often lack shared signs for technical terms, which makes group learning harder and may contribute to their underrepresentation in science. A real-time tool that shows and aligns scientific signs could help deaf undergraduates join biology group work more fully. If it works, the approach could extend to other settings where deaf students collaborate and support career paths for deaf scientists and trainees.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Abraham Glasser
Gallaudet University, DC·Computer Science
Test whether a digital assistant that recognizes only single signs, using about 100 signs serving as stand-ins for common voice queries, can meet Deaf users' needs in Wizard-of-Oz experiments.
Jee Woong Park
University of Nevada-Las Vegas, NV·Engineering
Develop computer vision AI algorithms that detect workplace hazards in photographs that trainees take on their own construction sites.
Lap Fai Yu
George Mason University, VA·Computer Science
Investigate how artificial intelligence techniques can be integrated with mixed reality headsets to assist first responders during tasks such as firefighting and search and rescue.
The school
Northeastern University: 27 labs on PI Pages, $347M a year on research, 251 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.