US 12,230,289 B2
Device and method for machine-learning based noise suppression
Jesus F. Corretjer, Chicago, IL (US)
Assigned to MOTOROLA SOLUTIONS, INC., Chicago, IL (US)
Filed by MOTOROLA SOLUTIONS, INC., Chicago, IL (US)
Filed on Aug. 29, 2022, as Appl. No. 17/897,287.
Prior Publication US 2024/0070524 A1, Feb. 29, 2024
Int. Cl. G10L 21/0208 (2013.01); G06N 20/00 (2019.01); G10K 11/16 (2006.01); G10L 19/00 (2013.01); G10L 25/30 (2013.01); H04R 1/32 (2006.01); H04R 1/40 (2006.01); H04R 3/00 (2006.01)
CPC G10L 21/0208 (2013.01) [G06N 20/00 (2019.01); G10K 11/16 (2013.01); G10L 19/00 (2013.01); G10L 25/30 (2013.01); H04R 1/326 (2013.01); H04R 1/406 (2013.01); H04R 3/005 (2013.01); H04R 2410/01 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A device comprising:
a microphone;
an output device;
a noise suppression engine configured to receive audio data from the microphone; and
a machine-learning noise suppression engine configured to:
receive the audio data from the noise suppression engine or the microphone;
apply one or more machine learning algorithms to the audio data to generate machine-learning based noise suppression parameters; and
provide the machine-learning based noise suppression parameters to the noise suppression engine,
the noise suppression engine further configured to:
prior to receiving the machine-learning based noise suppression parameters:
apply non-machine-learning based noise suppression to the audio data to generate noise-suppressed audio data; and
provide the noise-suppressed audio data to the output device; and
after receiving the machine-learning based noise suppression parameters:
apply the machine-learning based noise suppression parameters to the noise-suppressed audio data to generate updated noise-suppressed audio data; and
provide the updated noise-suppressed audio data to the output device.