Tue, December 3, 2024
Mon, December 2, 2024

Improving Acoustic and Bone Conduction Speech Enhancement

  Copy link into your clipboard //science-technology.news-articles.net/content/2 .. stic-and-bone-conduction-speech-enhancement.html
  Print publication without navigation Published in Science and Technology on by Tim Hastings
          🞛 This publication is a summary or evaluation of another publication 🞛 This publication contains editorial commentary or bias from the source
Professor Stephen Xia and his team developed an audio super-resolution model that enhances speech signals using neural networks.
The article from Northwestern University's McCormick School of Engineering discusses a new approach to enhancing speech signals in noisy environments using both acoustic and bone conduction microphones. Researchers have developed a deep learning model that integrates signals from both types of microphones to improve speech intelligibility. Acoustic microphones capture sound through the air, while bone conduction microphones pick up vibrations directly from the skull, which can be particularly useful in noisy conditions. The study, led by Professor Philipos Loizou, found that this dual-microphone system significantly outperforms traditional single-microphone methods in environments with high levels of background noise, such as in vehicles or crowded places. This technology could potentially benefit hearing aid users, telecommunication systems, and voice-controlled devices by providing clearer speech signals in challenging acoustic environments.

Read the Full mccormick.northwestern.edu Article at:
[ https://www.mccormick.northwestern.edu/news/articles/2024/12/improving-acoustic-and-bone-conduction-speech-enhancement/ ]