IP Library Granted Patent US 12,732,739
Granted Patent B2
US 12,732,739 · App. 18/673,192 · Granted Sep 8, 2026

Wearable device with enhanced noise suppression

Inventors: Mikolaj Aleksander Kegler (London, GB); Marko Stamenovic (Truro, MA); Li-Chia Yang (Chelmsford, MA); Alexander D. Pawlicki (Newbury, MA); Bryce Irvin (Brooklyn, NY); Carl Jensen (Waltham, MA); Amir Reza Moghimi (Auburndale, MA); Luke Calvin Walters (Alton, NH)
Assignee: Bose Corporation
H04R1/1083G10K11/175H04R3/005H04R29/001H04R2460/01
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,732,739
App. No.
18/673,192
Filed
May 23, 2024
Granted
Sep 8, 2026
Kind
B2
Art Unit
2695
USPC
381/26
Abstract

Techniques, including devices and systems implementing the techniques, for using enhanced noise suppression to provide optimal denoised output. One example system generally includes a device of a user, a first sensor coupled to the device, a second sensor coupled to the device, and one or more processors coupled to the device. The one or more processors are generally, individually or collectively, configured to receive, at the first sensor, a first audio signal with a first degradation, receive, at the second sensor, a second audio signal with a second degradation, where the first degradation is different than the second degradation, and determine an output audio signal using the first audio signal and the second audio signal.

Claims (44)

1 . A system comprising:

a device of a user;

a first sensor coupled to the device;

a second sensor coupled to the device; and

one or more processors coupled to the device, the one or more processors, individually or collectively, being configured to:

receive, at the first sensor, a first audio signal with a first degradation;

receive, at the second sensor, a second audio signal with a second degradation, wherein the first degradation is different than the second degradation; and

determine an output audio signal by using a trained machine-learning model to determine a first mask for the first audio signal and a second mask for the second audio signal, wherein the first mask is configured to at least partially denoise the first audio signal and the second mask is configured to at least partially denoise the second audio signal.

2 . The system of claim 1 , wherein the first sensor comprises a microphone outside the device and the second sensor comprises:

a feedback microphone;

a voice band accelerometer; or

an inertial measurement unit.

3 . The system of claim 1 , wherein the one or more processors, individually or collectively, are further configured to determine the output audio signal by:

applying the first mask to the first audio signal to produce a denoised first audio signal;

applying the second mask to the second audio signal to produce a denoised second audio signal; and

summing the denoised first audio signal and the denoised second audio signal to produce the output audio signal.

4 . A method for audio signal processing in a device of a user, the method comprising:

receiving, at a first sensor coupled to the device, a first audio signal with a first degradation;

receiving, at a second sensor coupled to the device, a second audio signal with a second degradation, wherein the first degradation is different than the second degradation; and

determining an output audio signal by using a trained machine-learning model to determine a first mask for the first audio signal and a second mask for the second audio signal, wherein the first mask is configured to at least partially denoise the first audio signal and the second mask is configured to at least partially denoise the second audio signal.

5 . The method of claim 4 , wherein the second sensor comprises:

a feedback microphone;

a voice band accelerometer; or

an inertial measurement unit.

6 . The method of claim 5 , wherein the first sensor comprises a microphone outside the device.

7 . The method of claim 4 , wherein determining the output audio signal further comprises:

applying the first mask to the first audio signal to produce a denoised first audio signal;

applying the second mask to the second audio signal to produce a denoised second audio signal; and

summing the denoised first audio signal and the denoised second audio signal to produce the output audio signal.

8 . The method of claim 4 , further comprising preprocessing the second audio signal, wherein the preprocessing comprises effectively removing a non-user speech component of the second audio signal.

9 . The method of claim 4 , wherein the first audio signal and the second audio signal each comprise a speech component originating from the user.

10 . The method of claim 4 , wherein the device comprises a wearable device.

11 . A non-transitory computer-readable medium comprising computer-executable instructions that, when executed by one or more processors of a device of a user, cause the device to perform a method for audio signal processing, the method comprising:

receiving, at a first sensor coupled to the device, a first audio signal with a first degradation;

receiving, at a second sensor coupled to the device, a second audio signal with a second degradation, wherein the first degradation is different than the second degradation; and

determining an output audio signal by using a trained machine-learning model to determine a first mask for the first audio signal and a second mask for the second audio signal, wherein the first mask is configured to at least partially denoise the first audio signal and the second mask is configured to at least partially denoise the second audio signal.

12 . The non-transitory computer-readable medium of claim 11 , wherein the first sensor comprises a microphone outside the device and the second sensor comprises:

a feedback microphone;

a voice band accelerometer; or

an inertial measurement unit.

13 . The non-transitory computer-readable medium of claim 11 , wherein determining the output audio signal further comprises:

applying the first mask to the first audio signal to produce a denoised first audio signal;

applying the second mask to the second audio signal to produce a denoised second audio signal; and

summing the denoised first audio signal and the denoised second audio signal to produce the output audio signal.

Assignments (2)
SECURITY INTEREST Recorded Feb 28, 2025
From: BOSE CORPORATION
To: BANK OF AMERICA, N.A., AS ADMINISTRATIVE AGENT
Reel/Frame 070438/0001 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 19, 2024
From: KEGLER, MIKOLAJ ALEKSANDER; STAMENOVIC, MARKO; YANG, LI-CHIA; PAWLICKI, ALEXANDER D; IRVIN, BRYCE; JENSEN, CARL; MOGHIMI, AMIR REZA; WALTERS, LUKE CALVIN
To: BOSE CORPORATION
Reel/Frame 069749/0377 →
Continuity (1)
Related Publication 20250365527A1 · Nov 27, 2025
References Cited (16)
US 11045123B2 · Honore · 2021 [cited by examiner]
US 11937047B1 · Lovchinsky · 2024 [cited by examiner]
US 12254892B2 · de la Rey · 2025 [cited by examiner]
US 12272369B1 · Chhetri · 2025 [cited by examiner]
US 20180033449A1 · Theverapperuma · 2018 [cited by examiner]
US 20200374647A1 · Cappello · 2020 [cited by examiner]
US 20230162758A1 · Borgstrom · 2023 [cited by examiner]
US 20240129674A1 · Casper · 2024 [cited by examiner]
US 20240194214A1 · Fang · 2024 [cited by examiner]
US 20240331715A1 · Lee · 2024 [cited by examiner]
US 20240331716A1 · Bean · 2024 [cited by examiner]
US 20250048043A1 · Lovchinsky · 2025 [cited by examiner]
US 20250259641A1 · de la Rey · 2025 [cited by examiner]
International Search Report and Written Opinion dated Jul. 7, 2025 for Application No. PCT/US2025/030254, 11 pages. [cited by applicant]
Zhang et al., “A Speech Enhancement Algorithm by Iterating Single- and Multi-Microphone Processing and Its Application to Robust ASR”, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASS… [cited by applicant]
Wang et al., “Multi-Modal Speech Enhancement with Bone-Conducted Speech in Time Domain”, Applied Acoustics, vol. 200, Nov. 2022, 7 pages. [cited by applicant]