Kwang Kim
Purdue University, IN·Neuroscience
Stuttering, a disorder of speech fluency that begins in childhood, affects about 5–8% of children and 1% of adults. Many adults who stutter use earpieces that change how they hear their own voice, by adding a slight delay or shifting its pitch.
- Fields
Neuroscience
Biomedical Engineering
Medicine & Clinical Research
- Topics
stuttering
speech fluency
altered auditory feedback
- Grants
- 1 known grant, through Jun 2029
What they work on
- Train and validate machine learning classifiers that predict upcoming stuttering moments from electroencephalography (EEG), brain-wave recordings, collected while adults who stutter are speaking.
- Optimize altered auditory feedback, changes to how speakers hear their own voice such as delays and pitch shifts, so it reduces stuttering nearly as well as choral speech, building on the lab's pilot data.
- Build and test a proof-of-concept closed-loop system in which EEG-based classifiers control, in real time, when optimized altered auditory feedback is delivered to the speaker.
More about the research
These changes often reduce stuttering at first. But users report that the benefit fades, and the always-on effect is hard to tolerate. These devices also work far less well than choral speech, speaking in unison with another person, which reduces stuttering by about 90%.
Why it matters
This work could lead to a new generation of wearable devices for adults who stutter. Such devices would combine small EEG sensors, machine learning and everyday hardware such as smartphones. Because they would deliver feedback only when needed, they may reduce stuttering more effectively than current always-on devices and be easier to tolerate.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Ayoub Daliri
Arizona State University Campus Immersion, AZ·Neuroscience
Evaluate how exposure to auditory errors alters predictive sensorimotor processes in children and adults who stutter, using behavioral and neurophysiological recordings to test whether stuttering involves inaccurate speech predictions across the lifespan.
Chung Yin Joseph Lau
Northwestern University, IL·Neuroscience
Test whether the balance between top-down expectation signals and local speech representations is disrupted in autism, using EEG to measure context-dependent processing of speech sounds.
Phuc Nguyen
University of Massachusetts, MA·Computer Science·Early-career
Build computational models that translate jaw movement and faint facial vibrations, captured by an ear-worn sensor, into speech sounds and commands so users can control devices silently.
The school
Purdue University: 43 labs on PI Pages, $932M a year on research, 833 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.