/Patent Tracker
MetaGranted patentAudio & voiceInterest 6/10

Meta patents noise removal that fits within audio frame timing

Meta describes a method for cleaning up audio recordings by breaking them into short segments and using a specialized neural network to remove background noise. The system adjusts the length of these segments to ensure the noise removal process finishes quickly enough for each part.

Why it mattersThis technique could help make voice calls or video recordings clearer on devices with limited processing power by optimizing how fast the software works.

In the filing’s own words

The disclosed computer-implemented method may include capturing, by a computing device, a media clip. The method may also include dividing, by the computing device, the media clip into a set of frames, wherein each frame may include an audio portion of the media clip of a predetermined length of time. Additionally, the method may include performing, by the computing device, a noise suppression process on each frame of the set of frames using a trained neural network model, wherein the trained neural network model is quantized to use input tensors. Finally, the method may include creating, by the computing device, a clean media clip based on the noise suppression process. Various other methods, systems, and computer-readable media are also disclosed.

What exactly they claim (claim 1)

1. A computer-implemented method comprising: capturing, by a computing device, a media clip; dividing, by the computing device, the media clip into a set of frames, wherein each frame comprises an audio portion of the media clip of a predetermined length of time; performing, by the computing device, a noise suppression process on each frame of the set of frames using a trained neural network model, wherein the predetermined length of time for each frame is based at least in part on a duration of the noise suppression process such that the noise suppression process for each frame is able to be completed within the predetermined length of time, and wherein the trained neural network model is quantized to use input tensors by using indirection buffers to point to separate input tensor locations; and creating, by the computing device, a clean media clip based on the noise suppression process.

Facts

Company
Meta (Meta Platforms, Inc.)
Official title
Systems and methods for noise suppression
Patent number
US12725624B2
Application number
18521982
Filed
Nov 28, 2023
Granted
Sep 1, 2026
Inventors
2
Claims
20

Classified under

G10L 21/0232 Physics & computingG10L 25/30 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Meta in Audio & voice

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.