Work

SPECTRA: Personalizable Sound Recognition for Deaf and Hard of Hearing Users through Interactive Machine Learning

Year: 2025

Type: conference-paper

Abstract: Record soundsTrain personalized model Iteratively test Figure 1: Overview of the SPECTRA pipeline.In an interactive machine learning training workfow, users collect audio data samples (left), flter their data into a training dataset (center), and assess their model's performance in a live environment (right).The design includes key elements to support the needs of DHH users during this process, including spectrogram and waveform audio visualizations of audio, data annotating to save useful contextual information, and an interactive clustering visualization of their dataset.

Source: CHI Conference on Human Factors in Computing Systems

DOI: 10.1145/3706598.3713294

Authors: Steven M. Goodman, Emma J McDonnell, Jon E. Froehlich, Leah Findlater

Institution: University of Washington

Language: English

Topic: Assistive Technology in Communication and Mobility

Subfield: Occupational Therapy

Field: Health Professions

Domain: Health Sciences

Open Access status: hybrid

Funders: National Science Foundation, University of Washington

Awards: CHS: Medium: Collaborative Research: Wearable Sound Sensing and Feedback Techniques for Persons who are Deaf or Hard of Hearing, G653274256, Graduate Research Fellowship Program (GRFP)