The present disclosure relates to compact hearing aids, components thereof, and support systems therefor, as well as methods of insertion and removal thereof. The compact hearing aids generally include a sensor, such as a microphone, an actuation mass, an energy source for providing power to the compact hearing aid, a processor, and an actuator enclosed in a housing that is designed to be inserted through the tympanic membrane during a minimally-invasive outpatient procedure. In operation, the microphone receives sound waves and converts the sound waves into electrical signals. A processor then modifies the electrical signals and provides the electrical signals to the actuator. The actuator converts the electrical signals into mechanical motion, which actuates the actuation mass to modulate the velocity or the position of the tympanic membrane.

Methods and systems for signal processing an audio signal in a hearing device to detect when feedback path change occurs and controlling an adaptive feedback canceler to remove the feedback are provided. The hearing device includes a receiver and a microphone. An exemplary method includes detecting whether a tonal signal is caused by a feedback path change by estimating a product of a subband error signal and a subband output signal generated in response to a subband audio input signal; estimating a fast metric based on the estimated product and estimating a slow metric; and applying or maintaining an adaptation rate to the adaptive feedback canceler of the hearing device, wherein the adaptation rate applied or maintained is selected based upon a value of the difference between the fast and slow metrics compared to a threshold value.

An illustrative radio frequency (RF) power control system includes an RF transmitter configured to operate external to a recipient, a cochlear implant configured to operate internal to the recipient based on RF power received from the RF transmitter, and a processor that, while operating in a power adaptation mode during which the cochlear implant applies stimulation to the recipient: 1) receives an audio signal, 2) directs the RF transmitter to provide the RF power to the cochlear implant at a power level determined based on the audio signal and based on a power level mapping function, 3) determines an error value representing a difference between a target metric and a measured metric associated with receipt of the RF power at the cochlear implant, and 4) updates the power level mapping function based on the error value. Corresponding systems and methods are also disclosed.

The hearing aid includes an end wall having end face adapted to face outwards of an ear canal when the hearing aid is placed in the ear canal, and the hearing aid includes an antenna extending from the end face and having two legs inserted into the end wall and electrically coupled to wireless circuitry arranged inside the hollow housing. Each leg of the antenna is provided with a first coupling part releasably engaging a corresponding second coupling part of the hollow housing, and at least one locking part is movable between a locking position in which the first coupling parts are locked to the corresponding second coupling parts and a release position in which the first coupling parts are free to be removed from the corresponding second coupling parts.

A completely-in-canal hearing aid, including a housing, a receiver, a chip, a battery, a flexible circuit board and a microphone, wherein the housing includes a front section and a rear section; the receiver and the chip are located in the front section; the battery is located in the rear section; the rear section has two opposite surfaces and two opposite side surfaces; the front section has a first central axis parallel to the length of the front section; the rear section has a second central axis located between the two opposite surfaces and between the two opposite side surfaces; the first central axis and the second central axis are different straight lines. The completely-in-canal hearing aid is fine and compact in structure, reasonable and ingenious in design, diversified in function and comfortable to wear.

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

The present disclosure describes examples of systems and methods of wireless remote control of appliances using a canal hearing device upon manual activation of a switch placed in the concha cavity behind the tragus. In some examples, the lateral end comprises one or more manually activated switches, a wireless antenna, and a battery cell. In some examples, the wireless electronics include low energy Bluetooth capability. The appliance may be any device with wireless control capability, for example an electronic lock, a thermostat, an electronic lighting, a telephone, a kitchen appliance, a medical alert system, a television, a medical device, and a smart glass. The inconspicuous and secure wear of the canal hearing device may allow a hearing device user to enjoy a normal lifestyle, including exercise, and to discretely interact with wirelessly controlled devices.

A hearing aid electrical contact structure and a hearing aid are provided. The hearing aid electrical contact structure includes: a housing, wherein the housing includes a front section and a rear section connected to each other; the rear section is used for accommodating a battery and at least a part of a flexible circuit board; an outer side surface of the rear section has at least two side holes; a conductive contact sheet is assembled in each of the at least two side holes, and the conductive contact sheet is electrically connected to a pad of the flexible circuit board; an outer surface of the conductive contact sheet realizes a transition with the outer side surface of the rear section. The hearing aid electrical contact structure has a smooth surface without any groove structure or convex structure.

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.

Disclosed herein, among other things, are apparatus and methods for tonality-driven feedback canceler adaptation for hearing devices. Various embodiments include a method of signal processing an input signal in a hearing device to mitigate entrainment, the hearing device including a receiver and a microphone. The method includes detecting strength of tonality of the input signal by estimating a second derivative of subband phase of the input signal, and adjusting parameters of an adaptive feedback canceler of the hearing device based on the detected tonality.