Audio and Video

CES 2024: Using AI to remove background noise from speech signals

04 January 2024

Skyworks Solutions Inc. will introduce its latest software to remove unwanted background noise from speech signals.

The company will demonstrate the solution for the first time at the upcoming Consumer Electronics Show (CES) 2024 trade show.

The real-time solution for separating speech from noise in communications and recording systems received a 2024 Innovation Award Honoree. The technology enables users to increase speech intelligibility, preserve quality and reduce listener fatigue when using handsets, headsets, conference systems, automotive telematics, wireless microphones and audio-visual systems.

The software uses artificial intelligence (AI) based on a feed-forward neural network that requires less than 250 kilobytes of memory while adding no latency when integrated into existing audio processing path.

Market research firm Astute Analytica said the edge AI market is forecast to grow to $8 million in 2027 up from just $1.4 million in 2021. Much of this will be from the internet of things, wearables and 5G devices and networks.

Additional features of the software include:

  • Requires less than 10% CPU load
  • Runs at 48 kHz
  • No large cloud server connections needed
  • No tethering to desktop or mobile devices
  • Does not interfere with original speech signals
To contact the author of this article, email PBrown@globalspec.com


Powered by CR4, the Engineering Community

Discussion – 0 comments

By posting a comment you confirm that you have read and accept our Posting Rules and Terms of Use.
Engineering Newsletter Signup
Get the GlobalSpec
Stay up to date on:
Features the top stories, latest news, charts, insights and more on the end-to-end electronics value chain.
Advertisement
Weekly Newsletter
Get news, research, and analysis
on the Electronics industry in your
inbox every week - for FREE
Sign up for our FREE eNewsletter
Advertisement