• Bio
  • Google Scholar
  • Projects
  • Bio
  • Google Scholar
Project 1 Image

Deep Neural Networks for Speech Enhancement on Resource-Constrained Devices

Design, train, optimize and deploy deep neural network models in pytorch and tensorflow for noise suppression with low latency for embedded devices (hearing aid devices)

Read more on Google Scholar
Project 1 Image

Audio-Based Cough Detection in Clinic Waiting Rooms

Cough detector for clinic waiting rooms using deep learning techniques using tensorflow to identify coughs sounds and estimates the number of patients who report cough as a symptom during their clinic visit as a surveillance tool for respiratory disease outbreak.

Read more on Google Scholar
Project 2 Image

Personalizing over-the-counter hearing aids using pairwise comparisons

Developed optimization technique of hearing aid configurations based on patients’ feedback and multi-arm bandit algorithms

Read more on Google Scholar

Published Papers

  • Audio-Based Cough Detection in Clinic Waiting Rooms. In 2022 IEEE 10th International Conference on Healthcare Informatics (ICHI)
  • Personalizing over-the-counter hearing aids using pairwise comparisons. Smart Health, 23
  • Robots in healthcare: A survey. In Advances in Computer Vision: Proceedings of the 2019 Computer Vision Conference (CVC)
  • Wearable sensors and a multisensory music and reminiscence therapies application: To help reduce behavioral and psychological symptoms in person with dementia

My YouTube Videos



My Medium Articles

  • Client-Side Audio Stream Cache Reload in Node.js and React
  • Enhancing the Facebook Demucs-based Denoiser: Incorporating Learning Rate Warm-Up

yumna-anwar@uiowa.edu