Neural model reduces distress from trigger sounds in misophonia
Trigger Sound Suppression for Misophonia
Sound
Summary
Misophonia is a condition where certain everyday sounds cause strong negative reactions in some people. The authors created a computer system that listens to short bits of sound and selectively removes the specific trigger sounds that cause discomfort, while leaving other sounds intact. They collected common trigger sounds and trained a model to suppress these selectively in real time. A study with adults who have misophonia showed that listening to the modified sounds caused less distress and improved their emotional response.
What this means in practice
- •For hearing aid manufacturers: Integrate selective trigger sound suppression into hearing aids to reduce discomfort for misophonia sufferers without blocking all sound.$Commercial implications: Enables new hearing aids tailored for misophonia patients by selectively suppressing trigger sounds and improving user comfort.
- •For mobile app developers: Create real-time mobile apps that reduce misophonia triggers in everyday sound environments using lightweight neural models.
Authors
Vaishnavi Vidyasagar, Jasmine Zhang, Mahima Uliyar, Seunghyun Oh, Emily Catherine Gates, Mark Zachary Rosenthal, Shyamnath Gollakota
Abstract
Misophonia, a disorder of decreased tolerance to specific sounds, affects 5-20% of the population, yet sufferers have no good options: therapy helps a minority, and earplugs or noise cancellation silence everything. We present a study for neural trigger sound suppression for misophonia, selectively removing trigger sounds. We curate a dataset covering the 10 most common trigger classes. Using streaming dual-path networks operating on 6 ms audio chunks, we explore both one-hot and multi-hot-conditioned models that suppress 1-3 triggers from the acoustic scene. We validate our model outputs in a listening study with 30 adults with clinically elevated misophonia impairment. Participants reported significantly lower distress and arousal, and improved valence, for suppressed audio.