公开(公告)号：US20230292074A1

公开(公告)日：2023-09-14

申请号：US17927239

申请日：2021-05-18

Applicant: STARKEY LABORATORIES, INC.

Inventor： Daniel Marquardt ,  Deepak Kadetotad ,  Tao Zhang

IPC: H04S7/00

CPC classification number: H04S7/30 ,  G06N3/08

Abstract: An ear-wearable device stores a plurality of neural network data objects each defining a respective neural network. A sound signal received from a microphone of the ear-wearable device is digitized. An ambient environment of the digitized sound signal is classified into one of a plurality of classifications. Based on the classification, one of the neural network data objects is selected to enhance the digitized sound signal. An analog signal is formed based on the enhanced digitized sound signal. The analog signal is reproduced via a receiver of the ear-wearable device.

公开(公告)号：US20230362559A1

公开(公告)日：2023-11-09

申请号：US18027314

申请日：2021-08-25

Applicant: Starkey Laboratories, Inc.

Inventor： Achin Bhowmik ,  Daniel Marquardt ,  Deepak Kadetotad

IPC: H04R25/00 ,  G10L25/30 ,  G10L21/0208

CPC classification number: H04R25/507 ,  G10L25/30 ,  G10L21/0208 ,  H04R2225/43 ,  H04R2225/41

Abstract: An audio processing path receives an audio signal from a microphone of an ear-wearable device and reproduces the audio signal at a receiver that is placed within an ear of a user. A deep neural network (DNN) is coupled to the audio processing path that performs speech enhancement on the audio signal. An audio feature detector is operable to detect an audio change via the processing path that triggers a change of state of the DNN. The change of state affects resource consumption by the DNN. The change of state is applied to the DNN, and the DNN performs the speech enhancement in the changed state.

公开(公告)号：US12302084B2

公开(公告)日：2025-05-13

申请号：US17927239

申请日：2021-05-18

Applicant: STARKEY LABORATORIES, INC.

Inventor： Daniel Marquardt ,  Deepak Kadetotad ,  Tao Zhang

IPC: H04S7/00 ,  G06N3/08 ,  H04R25/00

Abstract: An ear-wearable device stores a plurality of neural network data objects each defining a respective neural network. A sound signal received from a microphone of the ear-wearable device is digitized. An ambient environment of the digitized sound signal is classified into one of a plurality of classifications. Based on the classification, one of the neural network data objects is selected to enhance the digitized sound signal. An analog signal is formed based on the enhanced digitized sound signal. The analog signal is reproduced via a receiver of the ear-wearable device.