Abstract: A signal processing device for processing audio signals is described. The signal processing device has an input interface for receiving an input signal and an output interface for outputting an output signal. Moreover, the signal processing device has at least one neural network for separating one or more audio signals from the input signal. The number of audio signals separated from the input signal by using the at least one neural network is variable.

Abstract: A hearing system having a hearing device, including a receiver antenna assembly with a receiver core having a relatively high magnetic permeability and a receiver coil wound around the receiver core, operably connected to a rechargeable power source, and a hearing device charger, including a transmitter antenna assembly, with a transmitter core having a relatively high magnetic permeability and a transmitter coil wound around the transmitter core, operably connected to a power supply. The respective configurations of the hearing device and the hearing device charger may be such that when the hearing device is in a charging position on the hearing device charger, the receiver core and the transmitter core together provides a closed loop path for magnetic flux.

Abstract: An exemplary hearing device is configured to receive, from a source, a data packet, the data packet including a plurality of frames including a first frame and a second frame. The hearing device determines that the data packet has an invalid checksum. The hearing device accesses, in response to the determining that the data packet has the invalid checksum, a first frame checksum for the first frame and a second frame checksum for the second frame. The hearing device determines that the first frame checksum is invalid and that the second frame checksum is valid. The hearing device discards, based on the first frame checksum being invalid, the first frame and stores, based on the second frame checksum being valid, the second frame.

Abstract: An illustrative method for checking a usability of an impression model of a human ear includes determining an estimated shape model of the human ear by adapting a statistical shape model to the impression model, wherein the statistical shape model has been determined from a plurality of impression models of a plurality of human ears and wherein the statistical shape model has at least one impression feature, which is mapped to an estimated impression feature of the estimated shape model; determining a feature classification from the estimated impression feature; and when the feature classification is within an allowed feature classification range, rating the impression model as usable.

Abstract: Described herein are a protective element configured to be connected to an electroacoustic transducer or a sound tube included in a hearing device, the protective element comprising a 3D-shaped membrane that has two or more first portions having a first thickness that are configured to transmit sound and two or more second portions having a second thickness. The first thickness is less than the second thickness such that a rigidity of the 3D-shaped membrane is greater at the two or more second portions than at the two or more first portions. At least two of the two or more second portions are spaced from one another along a circumference of the 3D-shaped membrane by at least one of the two or more first portions.

Abstract: A hearing device sizer tool in accordance with at least one of the present inventions includes a shaft defining a medial end and a lateral end, and an in-the-canal (ITC) hearing device seal associated with the medial end of the shaft. A hearing device sizer tool system in accordance with at least one of the present inventions includes a plurality of hearing device sizer tools with differently sized ITC hearing device seals.

Abstract: An exemplary hearing system includes a hearing device, a memory storing instructions and one or more processors communicatively coupled to the memory and configured to execute the instructions to perform a process comprising: accessing operating service tier data that associates a first operating service tier with a first set of hearing device functions and a second operating service tier with a second set of hearing device functions; detecting, while the hearing device operates in accordance with the first set of hearing device functions associated with the first operating service tier, a satisfaction of a condition associated with the second operating service tier; and directing, based on the detecting the satisfaction of the condition, the hearing device to switch from operating in accordance with the first set of hearing device functions to operating in accordance with the second set of hearing device functions.

Abstract: An exemplary system includes a memory storing instructions and one or more processors communicatively coupled to the memory and configured to execute the instructions to perform a process comprising: accessing fitting data representative of fitting parameters set by a fitting application to fit a hearing device to a user; determining user behavior data indicative of a hearing intention of the user in an auditory scene where the user is located; determining auditory scene data representative of information about the auditory scene; and implementing, based on the fitting data, the user behavior data, and the auditory scene data, a sound processing delay scheme for use by the hearing device.

Abstract: An illustrative hearing system may be configured to receive, from an inertial sensor included in a hearing device configured to be worn by a user, inertial sensor data representative of at least one of motion of the hearing device or orientation of the hearing device. The hearing system may further be configured to determine, based on the inertial sensor data, an activity state of the user and to determine, based on the activity state, a cardiorespiratory quality index representative of a quality level of a measurement of a cardiorespiratory property of the user.

Abstract: An exemplary hearing device is configured to concurrently maintain a first link with a source and a second link with a second hearing device. The hearing device scans, while not receiving data via the first link, the second link for a preamble of a binaural data packet for a first time period. Based on whether the preamble is detected, the hearing device selectively: receives the binaural data packet and ignores the first link while receiving the binaural data packet if the preamble of the binaural data packet is detected during the first time period; and scans the first link for a preamble of a data packet for a second time period if the preamble of the binaural data packet is not detected during the first time period.

Abstract: An illustrative hearing device may be at least partially inserted into an ear canal and may include an acoustic transducer having a membrane configured to generate sound waves, a housing enclosing a first chamber and a second chamber acoustically coupled by the membrane, a sound outlet configured to release sound waves from the first chamber into the ear canal, an acoustic port acoustically coupling the second chamber to an ambient environment outside the ear canal, and a mechanical resonator configured to resonate with sound waves at a resonance frequency. The second chamber may be acoustically coupled to the mechanical resonator.

Abstract: There is provided a method for streaming a multichannel audio signal comprising a first channel (L) and a second channel (R) from an audio source device to a binaural hearing system comprising a first hearing device worn at first ear of a user and a second hearing device worn at a second ear of the user.

Abstract: A hearing device plug connector may include a first connector component and a second connector component, wherein the hearing device plug connector includes a latching mechanism for securing the first connector component and the second connector component against unintended disconnection, wherein the latching mechanism includes a catch and a complementary latch component which are in latching engagement when the first connector component and the second connector component are connected, wherein the catch is moveable against a spring force from a latching position into a release position when connecting or disconnecting the first connector component and the second connector component, and wherein in the latching position the catch can engage with the complementary latch component and in the release position the catch can disengage from the complementary latch component.

Abstract: There is provided a system for estimating a total acoustic attenuation of a hearing protection device including an interface at a distal end and a sound canal extending from the interface to a sound opening at a medial end of the hearing protection device. The system comprises: a measurement unit including a loudspeaker and a microphone and being attachable to the interface in such a manner that, when the hearing protection device is worn in an ear canal of a user, the loudspeaker and the microphone are in acoustic communication, via the sound canal of the hearing protection device; a control unit configured to provide the loudspeaker with test audio signals to generate test sounds in the occluded ear canal volume and to receive test response audio signals captured by the microphone from the test sounds; and an evaluation unit configured to estimate a leakage acoustic impedance.

Abstract: The disclosure relates to a method of operating a hearing system comprising an ear unit wearable at an ear of a user, an output transducer included in the ear unit, and a detector arrangement comprising a plurality of spatially separated sound detectors and configured to provide audio data representative of the detected sound.

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.

Abstract: A customized in-ear hearing device includes a light source, photodetector, light emission window, and light transmission window. The light source and the photodetector together function as a physiological sensor by emitting light from the light source through the light emission to the skin of a user's ear canal, and detecting at the photodetector light reflected by the skin that passes through the light detection window. The light emission window and light detection window are located at a customized portion of the sidewall of the device that contacts the skin in the ear canal.

Abstract: System and methods are presented for detecting an authentic copy of a deep neural network in a device without reverse engineering the device. For example, the device can be a hearing device. A method is presented that includes providing audio signals to a deep neural network located in a hearing device, receiving signals from the deep neural network that are triggered by the transmitted audio signals, and determining whether the received signals were the expected signals. Specifically, the system can determine that an unauthorized entity embedded an unauthorized copy of the deep neural network in a hearing device.

Abstract: A cable for a hearing device, comprising a plurality of conductors, comprising conductors arranged in twisted pairs (TP1 to TP4) wound around a plastically deformable core wire (FW).

Abstract: An exemplary system includes a memory storing instructions and a processor communicatively coupled to the memory and configured to execute the instructions to perform a process. The process may comprise accessing a hearing loss profile of a user of a hearing device, determining, based on the hearing loss profile of the user, one or more acoustic parameters for voice notifications, and directing the hearing device to apply the one or more acoustic parameters to a voice notification to be presented to the user by way of the hearing device.