Adaptive Crosstalk Cancellation and Spatialization for Dynamic Group Conversation Enhancement Using Mobile and Wearable Devices

Ryan M. Corey, Manan Mittal, Kanad Sarkar, Andrew C. Singer

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a system to improve the intelligibility of group conversations in noisy environments, such as restaurants, by aggregating signals from the mobile and wearable devices of the participants. The proposed system uses a mobile device placed near each talker to capture a low-noise speech signal. Instead of muting inactive microphones, which can be distracting, adaptive crosstalk cancellation filters remove the speech of other users, including delayed auditory feedback of the listener's own speech. Next, adaptive spatialization filters process the low-noise signals to generate binaural outputs that match the spatial and spectral cues at the ears of each listener. The proposed system is demonstrated using recordings of three human subjects conversing with realistic movement.

Original languageEnglish (US)
Title of host publicationInternational Workshop on Acoustic Signal Enhancement, IWAENC 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665468671
DOIs
StatePublished - 2022
Event17th International Workshop on Acoustic Signal Enhancement, IWAENC 2022 - Bamberg, Germany
Duration: Sep 5 2022Sep 8 2022

Publication series

NameInternational Workshop on Acoustic Signal Enhancement, IWAENC 2022 - Proceedings

Conference

Conference17th International Workshop on Acoustic Signal Enhancement, IWAENC 2022
Country/TerritoryGermany
CityBamberg
Period9/5/229/8/22

Keywords

  • Acoustic sensor network
  • adaptive filters
  • binaural processing
  • hearing aids
  • remote microphones

ASJC Scopus subject areas

  • Signal Processing
  • Acoustics and Ultrasonics

Fingerprint

Dive into the research topics of 'Adaptive Crosstalk Cancellation and Spatialization for Dynamic Group Conversation Enhancement Using Mobile and Wearable Devices'. Together they form a unique fingerprint.

Cite this