Processing chip for processing audio signals using at least one deep neural network in a hearing device

    公开(公告)号:US12108219B1

    公开(公告)日:2024-10-01

    申请号:US18614362

    申请日:2024-03-22

    Applicant: SONOVA AG

    CPC classification number: H04R25/507

    Abstract: A processing chip for processing audio signals using at least one deep neural network (DNN) in a hearing device comprises a first compute unit having a hardware architecture adapted for processing one or more convolutional neural network layers of the at least one DNN, a second compute unit having hardware architecture adapted for processing one or more recurring neural network layers of the at least DNN, a control unit for directing the first and second compute units when to compute a respective layer of the at least one DNN, a shared memory unit of storing data to be processed in respective layers of the at least one DNN, and a data bus system for providing access to the shared memory unit for each of the first and the second compute unit.

    Hearing device including a battery and an acoustic valve

    公开(公告)号:US11290830B2

    公开(公告)日:2022-03-29

    申请号:US17094615

    申请日:2020-11-10

    Applicant: SONOVA AG

    Abstract: An illustrative hearing device includes a battery having a battery voltage, a microphone for transducing sound into an input signal, a processor configured to be operated with an operating voltage and to generate an output signal from the input signal, a speaker for transducing the output signal to an acoustic signal, and a valve. An acoustic effect of the valve is adjustable by applying a valve voltage, wherein the adjustment is controllable by the processor. The hearing device comprises a voltage regulator configured to generate the operating voltage from the battery voltage, wherein the operating voltage is less than the battery voltage and wherein the valve voltage is greater than the operating voltage.

    Method for operating a hearing device and a hearing device optimized for being powered by a mercury-free battery

    公开(公告)号:US10104479B2

    公开(公告)日:2018-10-16

    申请号:US15038431

    申请日:2013-12-04

    Applicant: Sonova AG

    Abstract: The present invention proposes a method for operating a hearing device 1 which prevents battery leakage, especially in the case when the hearing device 1 is powered by a mercury-free battery 2. The method comprises monitoring a supply voltage of at least one of a plurality of electronic units 7, 8, 9 of the hearing device 1, initiating a low battery leakage shutdown state when a low supply voltage condition is identified based on the monitoring, wherein the initiating a low battery leakage shutdown state includes activating at least one power gate 10 to disconnect at least one of the plurality of electronic units 7, 8, 9 from the power supply when entering the low battery leakage shutdown state, and discharging a buffer capacitor 4 provided for stabilizing the battery voltage. Moreover, a hearing device 1 optimized for being powered by a mercury-free battery 2 is provided.

    Hearing device adapted to perform a self-test and a method for testing a hearing device

    公开(公告)号:US11689866B2

    公开(公告)日:2023-06-27

    申请号:US16643174

    申请日:2017-08-31

    Applicant: Sonova AG

    Inventor: Fethi Cherigui

    Abstract: Hearing devices capable of performing a self-test as well as a method for automatically testing a hearing device. A hearing device includes a measurement bridge circuit connected to the receiver of the hearing device in parallel with the audio amplifier of the hearing device. A method for self-testing a hearing device includes the steps of i) disabling the audio amplifier connected to the receiver, in particular by putting the amplifier in a high impedance state, ii) applying with a measurement bridge circuit a direct current (DC) and/or an alternating current (AC) to the receiver, iii) measuring with the measurement bridge circuit (5) a voltage at the receiver, and iv) detecting a presence or absence of a fault condition based on the measured voltage.

    Systems and methods for using a selectively configurable interface assembly to program a hearing device

    公开(公告)号:US11064305B2

    公开(公告)日:2021-07-13

    申请号:US16588333

    申请日:2019-09-30

    Applicant: SONOVA AG

    Abstract: An exemplary hearing device includes an interface assembly comprising a plurality of contacts and a processor coupled to the contacts. The processor is configured to configure, while a receiver assembly is connected to the interface assembly, the contacts to serve as output contacts; output, based on the configuring, audio signals to the receiver assembly by way of the contacts; detect that a device has been connected to the interface assembly in place of the receiver assembly; measure, in response to the detecting, a direct current resistance (DCR) of the device; determine, based on the DCR, that the device is a programming device; reconfigure, in response to determining that the device is the programming device, the contacts to serve as input contacts; and receive, based on the reconfiguring of the contacts to serve as input contacts, programming instructions from the programming device by way of the contacts.

    A HEARING DEVICE ADAPTED TO PERFORM A SELF-TEST AND A METHOD FOR TESTING A HEARING DEVICE

    公开(公告)号:US20200260194A1

    公开(公告)日:2020-08-13

    申请号:US16643174

    申请日:2017-08-31

    Applicant: Sonova AG

    Inventor: Fethi Cherigui

    Abstract: Hearing devices capable of performing a self-test as well as a method for automatically testing a hearing device. A hearing device includes a measurement bridge circuit connected to the receiver of the hearing device in parallel with the audio amplifier of the hearing device. A method for self-testing a hearing device includes the steps of i) disabling the audio amplifier connected to the receiver, in particular by putting the amplifier in a high impedance state, ii) applying with a measurement bridge circuit a direct current (DC) and/or an alternating current (AC) to the receiver, iii) measuring with the measurement bridge circuit (5) a voltage at the receiver, and iv) detecting a presence or absence of a fault condition based on the measured voltage.

    Processing chip for processing audio signals using at least one deep neural network in a hearing device

    公开(公告)号:US20250016510A1

    公开(公告)日:2025-01-09

    申请号:US18890546

    申请日:2024-09-19

    Applicant: SONOVA AG

    Abstract: A processing chip for processing audio signals using at least one deep neural network in a hearing device includes a first compute unit having a hardware architecture adapted for processing one or more convolutional neural network layers of the at least one deep neural network, a second compute unit having a hardware architecture adapted for processing one or more recurrent neural network layers of the at least one deep neural network, a shared memory unit for storing data to be processed in respective layers of the at least one deep neural network, the shared memory unit comprising a memory controller configured for running on a memory controller clock frequency that is higher than a compute unit clock frequency of both the first compute unit and the second compute unit, and a data bus system for providing access to the shared memory unit.

    Processing chip for processing audio signals using at least one deep neural network in a hearing device

    公开(公告)号:US20240323619A1

    公开(公告)日:2024-09-26

    申请号:US18614362

    申请日:2024-03-22

    Applicant: SONOVA AG

    CPC classification number: H04R25/507

    Abstract: A processing chip for processing audio signals using at least one deep neural network (DNN) in a hearing device comprises a first compute unit having a hardware architecture adapted for processing one or more convolutional neural network layers of the at least one DNN, a second compute unit having hardware architecture adapted for processing one or more recurring neural network layers of the at least DNN, a control unit for directing the first and second compute units when to compute a respective layer of the at least one DNN, a shared memory unit of storing data to be processed in respective layers of the at least one DNN, and a data bus system for providing access to the shared memory unit for each of the first and the second compute unit.

    Systems and Methods for Using a Selectively Configurable Interface Assembly to Program a Hearing Device

    公开(公告)号:US20210099816A1

    公开(公告)日:2021-04-01

    申请号:US16588333

    申请日:2019-09-30

    Applicant: SONOVA AG

    Abstract: An exemplary hearing device includes an interface assembly comprising a plurality of contacts and a processor coupled to the contacts. The processor is configured to configure, while a receiver assembly is connected to the interface assembly, the contacts to serve as output contacts; output, based on the configuring, audio signals to the receiver assembly by way of the contacts; detect that a device has been connected to the interface assembly in place of the receiver assembly; measure, in response to the detecting, a direct current resistance (DCR) of the device; determine, based on the DCR, that the device is a programming device; reconfigure, in response to determining that the device is the programming device, the contacts to serve as input contacts; and receive, based on the reconfiguring of the contacts to serve as input contacts, programming instructions from the programming device by way of the contacts.

Patent Agency Ranking