IP Library › Granted Patent US 12,483,844
Granted Patent B2
US 12,483,844 · App. 18/632,844 · Granted Nov 25, 2025

Neural network-driven feedback cancellation

Inventors: Kelly Fitz (Eden Prairie, MN); Carlos Renato Calcada Nakagawa (Eden Prairie, MN); Tao Zhang (Eden Prairie, MN)
Assignee: Starkey Laboratories, Inc.
H04R25/507H04R3/005H04R25/453H04R25/558H04R2225/023
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 12,483,844
App. No.
18/632,844
Granted
Nov 25, 2025
Kind
B2
Abstract

Disclosed herein, among other things, are apparatus and methods for neural network-driven feedback cancellation for hearing assistance devices. Various embodiments include a method of signal processing an input signal in a hearing assistance device to mitigate entrainment, the hearing assistance device including a receiver and a microphone. The method includes performing neural network processing to identify acoustic features in a plurality of audio signals and predict target outputs for the plurality of audio signals, and using the trained neural network to control acoustic feedback cancellation of the input signal.

Claims (25)

1 . A hearing device, comprising:

a microphone configured to receive an input signal, the input signal being sound picked up by the microphone; and

a processor configured to process the input signal to correct for a hearing impairment of a wearer, the processor further configured to use a machine learning algorithm to govern adaptive feedback cancellation on the input signal, the machine learning algorithm trained to learn and improve feedback cancellation parameters through analysis of input signals.

2 . The hearing device of claim 1 , further comprising an adaptive feedback cancellation filter to provide the adaptive feedback cancellation on the input signal.

3 . The hearing device of claim 1 , wherein the machine learning algorithm comprises a trained neural network.

4 . The hearing device of claim 1 , wherein the machine learning algorithm is trained to identify acoustic features in the input signal.

5 . The hearing device of claim 4 , wherein the machine learning algorithm is trained to predict target parameters for the input signal using the identified acoustic features.

6 . The hearing device of claim 5 , wherein the processor is configured to use the target parameters predicted by the trained algorithm to govern the adaptive feedback cancellation on the input signal.

7 . The hearing device of claim 1 , wherein the machine learning algorithm is trained offline from data collected during normal use of the hearing device.

8 . The hearing device of claim 7 , wherein the training is performed on an external device.

9 . The hearing device of claim 8 , wherein the training is performed based on data collected from wearers stored on a server connected to the hearing device by a communication network.

10 . The hearing device of claim 9 , wherein neural network processing runs on the server and is configured to update parameters of feedback cancellation on the hearing device.

11 . The hearing device of claim 8 , wherein the training is performed on a mobile device.

12 . The hearing device of claim 11 , wherein neural network processing runs on the mobile device and updates parameters of feedback cancellation on the hearing device.

13 . The hearing device of claim 1 , wherein the hearing device is a hearing aid.

14 . A method of signal processing an input signal of a hearing device including a microphone and a processor, the method comprising:

receiving, by the processor, the input signal based on sound picked up by the microphone;

processing, by the processor, the input signal to correct for a hearing impairment of a wearer; and

using, by the processor, a machine learning algorithm to govern adaptive feedback cancellation on the input signal, the machine learning algorithm trained to learn and improve feedback cancellation parameters through analysis of input signals.

15 . The method of claim 14 , wherein using the machine learning algorithm includes using a trained neural network.

16 . The method of claim 14 , wherein using the machine learning algorithm to govern adaptive feedback cancellation includes using an adaptive feedback cancellation filter of the hearing device to provide the adaptive feedback cancellation on the input signal.

17 . The method of claim 16 , further comprising training the machine learning algorithm to identify a relationship between data available in online operation of the hearing device and an optimal configuration of runtime parameters of the adaptive feedback cancellation filter.

18 . The method of claim 14 , further comprising using the machine learning algorithm to control subband acoustic feedback cancellation of the input signal.

19 . The method of claim 14 , further comprising using the machine learning algorithm to control output phase modulation (OPM) for the hearing device.

20 . The method of claim 14 , further comprising using the machine learning algorithm to mitigate entrainment and to modify adaptive behavior to avoid self-correlated input for the hearing device.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 20, 2024
From: FITZ, KELLY; NAKAGAWA, CARLOS RENATO CALCADA; ZHANG, TAO
To: STARKEY LABORATORIES, INC.
Reel/Frame 067788/0226 →
Continuity (4)
Continuation 18120665 · Mar 13, 2023
Continuation 17249581 · Mar 5, 2021
Continuation 15133896 · Apr 20, 2016
Related Publication 20240348994A1 · Oct 17, 2024
References Cited (88)
US 5282261A · Skeirik · 1994 [cited by applicant]
US 5533120A · Staudacher · 1996 [cited by applicant]
US 5604812A · Meyer · 1997 [cited by applicant]
US 5621724A · Yoshida · 1997 [cited by examiner]
US 5636285A · Sauer · 1997 [cited by examiner]
US 5754661A · Weinfurtner · 1998 [cited by examiner]
US 6035050A · Weinfurtner et al. · 2000 [cited by applicant]
US 6044163A · Weinfurtner · 2000 [cited by applicant]
US 6674867B2 · Basseas · 2004 [cited by examiner]
US 7149320B2 · Haykin et al. · 2006 [cited by applicant]
US 7187778B2 · Basseas · 2007 [cited by applicant]
US 7400738B2 · Niederdrank et al. · 2008 [cited by applicant]
US 7742608B2 · Truong et al. · 2010 [cited by applicant]
US 7769702B2 · Messmer et al. · 2010 [cited by applicant]
US 7889879B2 · Dillon et al. · 2011 [cited by applicant]
US 8199948B2 · Theverapperuma · 2012 [cited by applicant]
US 8681999B2 · Theverapperuma et al. · 2014 [cited by applicant]
US 9094769B2 · Bisgaard et al. · 2015 [cited by applicant]
US 9648430B2 · Dittberner et al. · 2017 [cited by applicant]
US 10097930B2 · Nakagawa et al. · 2018 [cited by applicant]
US 10575103B2 · Fitz et al. · 2020 [cited by applicant]
US 11606650B2 · Fitz · 2023 [cited by examiner]
US 11985482B2 · Fitz · 2024 [cited by examiner]
US 20030133521A1 · Chen et al. · 2003 [cited by applicant]
US 20030185411A1 · Atlas et al. · 2003 [cited by applicant]
US 20050047620A1 · Fretz · 2005 [cited by applicant]
US 20050105750A1 · Frohlich et al. · 2005 [cited by applicant]
US 20060126872A1 · Allegro-Baumann et al. · 2006 [cited by applicant]
US 20070297627A1 · Puder · 2007 [cited by applicant]
US 20080095389A1 · Theverapperuma · 2008 [cited by applicant]
US 20080130927A1 · Theverapperuma · 2008 [cited by examiner]
US 20090067651A1 · Klinkby et al. · 2009 [cited by applicant]
US 20100027820A1 · Kates · 2010 [cited by applicant]
US 20100166200A1 · Truong et al. · 2010 [cited by applicant]
US 20120230503A1 · Theverapperuma · 2012 [cited by applicant]
US 20130195297A1 · Burns · 2013 [cited by applicant]
US 20140355798A1 · Sabin · 2014 [cited by applicant]
US 20160255446A1 · Bernardi et al. · 2016 [cited by applicant]
US 20160284346A1 · Visser et al. · 2016 [cited by applicant]
US 20160309267A1 · Fitz et al. · 2016 [cited by applicant]
US 20170148444A1 · Bocklet et al. · 2017 [cited by applicant]
US 20170311091A1 · Nakagawa · 2017 [cited by applicant]
US 20170311095A1 · Fitz et al. · 2017 [cited by applicant]
US 20190034791A1 · Busch et al. · 2019 [cited by applicant]
US 20190042881A1 · Lopatka et al. · 2019 [cited by applicant]
US 20210195345A1 · Fitz et al. · 2021 [cited by applicant]
US 20220256294A1 · Diehl et al. · 2022 [cited by applicant]
US 20230328463A1 · Fitz et al. · 2023 [cited by applicant]
WO WO2014094866A1 · 2014 [cited by applicant]
“U.S. Appl. No. 15/133,896, Advisory Action mailed Feb. 18, 2020”, 3 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Advisory Action mailed Oct. 25, 2018”, 3 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Final Office Action mailed Aug. 8, 2018”, 22 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Final Office Action mailed Sep. 21, 2017”, 17 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Final Office Action mailed Nov. 29, 2019”, 20 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Final Office Action mailed Dec. 10, 2020”, 21 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Non Final Office Action mailed Jan. 12, 2018”, 20 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Non Final Office Action mailed Mar. 10, 2017”, 23 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Non Final Office Action mailed May 23, 2019”, 21 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Non Final Office Action mailed Jun. 19, 2020”, 20 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Response filed Jan. 29, 2020 to Final Office Action mailed Nov. 29, 2019”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Response filed Mar. 2, 2020 to Advisory Action mailed Feb. 18, 2020”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Response filed Apr. 12, 2018 to Non Final Office Action mailed Jan. 12, 2018”, 8 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Response filed Jun. 12, 2017 to Non Final Office Action mailed Mar. 10, 2017”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Response filed Sep. 17, 2020 to Non Final Office Action mailed Jun. 19, 2020”, 11 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Response Filed Oct. 3, 2018 to Final Office Action mailed Aug. 8, 2018”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Response filed Nov. 21, 2017 to Final Office Action mailed Sep. 21, 2017”, 7 pgs. [cited by applicant]
“U.S. Appl. No. 15/133,896, Response filed Aug. 22, 2019 to Non-Final Office Action mailed May 23, 2019”, 10 pgs. [cited by applicant]
“U.S. Appl. No. 17/249,581, Advisory Action Before Filing of an Appeal Brief mailed Oct. 25, 2022”, 3 pgs. [cited by applicant]
“U.S. Appl. No. 17/249,581, Final Office Action mailed Aug. 12, 2022”, 15 pgs. [cited by applicant]
“U.S. Appl. No. 17/249,581, Non Final Office Action mailed Apr. 27, 2022”, 14 pgs. [cited by applicant]
“U.S. Appl. No. 17/249,581, Notice of Allowance mailed Nov. 7, 2022”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 17/249,581, Response filed Jul. 26, 2022 to Non Final Office Action mailed Apr. 27, 2022”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 17/249,581, Response filed Oct. 11, 2022 to Final Office Action mailed Aug. 12, 2022”, 9 pgs. [cited by applicant]
“U.S. Appl. No. 17/249,581, Supplemental Notice of Allowability mailed Feb. 10, 2023”, 2 pgs. [cited by applicant]
“U.S. Appl. No. 18/120,665, Non Final Office Action mailed Sep. 22, 2023”, 17 pgs. [cited by applicant]
“U.S. Appl. No. 18/120,665, Notice of Allowance mailed Jan. 9, 2024”, 10 pgs. [cited by applicant]
“U.S. Appl. No. 18/120,665, Preliminary Amendment filed Jun. 28, 2023”, 6 pgs. [cited by applicant]
“U.S. Appl. No. 18/120,665, Response filed Dec. 19, 2023 to Non Final Office Action mailed Sep. 22, 2023”, 7 pgs. [cited by applicant]
“European Application No. 17167360.1, Extended European Search Report mailed Aug. 24, 2017”, 9 pgs. [cited by applicant]
“European Application Serial No. 17167360.1, Response filed Apr. 24, 2018 to Communication pursuant to Rules 70(2) and 70a(2)/Rule 39(1) mailed Oct. 25, 2017”, 28 pgs. [cited by applicant]
“European Application Serial No. 20153888.1, Office Action Mailed Sep. 27, 2022”, 6 pgs. [cited by applicant]
Chen, J., et al., “A Feature Study for Classification-Based Speech Separation at Low Signal-to-Noise Ratios”, IEEE/ACM Trans. Audio Speech Lang. Process., 22, (2014), 1993-2002. [cited by applicant]
Gerhard, David, “Audio Signal Classification: History and Current Techniques”, Department of Computer Science University of Regina, Technical Report TR-CS 2003-07, (Nov. 2003), 38 pgs. [cited by applicant]
Gil-Cacho, J.M., et al., “Wiener variable step size and gradient spectral variance smoothing for double-talk-robust acoustic echo cancellation and acoustic feedback cancellation”, Signal Processing, 104, (Jun. 7, 2013),… [cited by applicant]
Healy, Eric W., et al., “An algorithm to improve speech recognition in noise for hearing- impaired listeners”, Journal of the Acoustical Society of America, 134, (2013), 3029-3038. [cited by applicant]
Ji, et al., “An Efficient Adaptive Feedback cancellation using by Independent component analysis for hearing aids”, Engineering in Medicine and Biology Society, 27th Annual International Conference of the Shanghai, (Jan… [cited by applicant]
Manders, Alastair J, et al., “Objective Prediction of the Sound Quality of Music Processed by an Adaptive Feedback Canceller”, IEEE Transactions on Audio, Speech and Language Processing, IEEE, vol. 20, No. 6, (Aug. 1, 1… [cited by applicant]
Shiva, Gholami-Boroujeny, et al., “Neural network-based adaptive noise cancellation for enhancement of speech auditory brainstem responses”, Signal, Image and Video Processing, vol. 10, No. 2, (Feb. 17, 2015), 389-395. [cited by applicant]