Skip to main navigation Skip to search Skip to main content

Privacy Preserving Radio Frequency Speech Sensing with Deep Learning Towards Improved Hearing Aids

  • Michaela Reay
  • , Hira Hameed
  • , Muhammad Ali Imran
  • , Qammer H. Abbasi
  • University of Glasgow

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Hearing loss is a profound public health issue typically addressed with microphone sensing hearing aids calibrated to compensate for an individual's hearing loss pattern. However, microphones often generate low sound quality in noisy environments resulting in low device adoption. This paper explores use of noise resistant Radio Frequency (RF) radar speech sensing micro-Doppler (μD) shifts generated from a speaker's vocal tract with Deep Learning (DL) speech classification for audio replay. It extends earlier work using a vowels dataset to whole sentences to train and test seven DL model types that gave encouraging accuracy results ranging from 75% to 91%. Model training time typically took 4 minutes and no more than 20 epochs to converge with loss rates suggesting potential viability of RF μD sensing for more complex vocabularies.

Original languageEnglish
Title of host publication2024 IEEE International Symposium on Antennas and Propagation and INC/USNCURSI Radio Science Meeting, AP-S/INC-USNC-URSI 2024 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2387-2388
Number of pages2
ISBN (Electronic)9798350369908
DOIs
StatePublished - 2024
Externally publishedYes
Event2024 IEEE International Symposium on Antennas and Propagation and INC/USNCURSI Radio Science Meeting, AP-S/INC-USNC-URSI 2024 - Florence, Italy
Duration: 14 Jul 202419 Jul 2024

Publication series

NameIEEE Antennas and Propagation Society, AP-S International Symposium (Digest)
ISSN (Print)1522-3965

Conference

Conference2024 IEEE International Symposium on Antennas and Propagation and INC/USNCURSI Radio Science Meeting, AP-S/INC-USNC-URSI 2024
Country/TerritoryItaly
CityFlorence
Period14/07/2419/07/24

Fingerprint

Dive into the research topics of 'Privacy Preserving Radio Frequency Speech Sensing with Deep Learning Towards Improved Hearing Aids'. Together they form a unique fingerprint.

Cite this