Various implementations include systems for processing audio signals to remove artifacts introduced by a machine learning system in challenging environments. In particular implementations, a method includes generating a processed audio signal for a hearing assistance device in which the processed audio signal is intended to perceptually dominate a user auditory experience, including: processing an unprocessed audio signal received by the hearing assistance device, wherein the processing includes utilizing a machine learning (ML) system to generate an ML enhanced audio signal; determining a mixing coefficient from an environmental noise assessment; mixing the ML enhanced audio signal with the unprocessed audio signal using the mixing coefficient to generate the processed audio signal; and outputting the processed audio signal.

A hearing system to activate an auditory system using cerebrospinal fluids includes at least one processor configured to receive an audio signal captured using a sound sensor (e.g., a microphone), extract temporal and spectral features from the audio signal, and create modulated ultrasound signals in a range of 20 Hz to 20 kHz with ultrasound carrier frequencies in the range of 50 kHz to 4 MHz, which are ultrasound frequencies that are well-suited to reach the cerebrospinal fluids (e.g., can pass across the skull/bones to reach the cerebrospinal fluids). The system further includes at least one ultrasonic transducer which receives the modulated signal and delivers the modulated signal to the body and activates the auditory system via vibration of cerebrospinal fluids that vibrate cochlear fluids, bypassing the normal conductive pathway that uses middle ear bones and minimizing bone conduction and distortion through the skull.

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.

A hearing device configured to be worn at an ear of a user may include a sensor unit configured to provide sensor data, the sensor unit comprising a sound detector configured to provide sound data included in the sensor data; and a processor configured to determine a physiological parameter from the sensor data, the physiological parameter indicative of a physiological property of the user. The processor is configured to determine whether the physiological parameter fulfills a condition, and provide, depending on whether the physiological parameter fulfills the condition, output data based on the sensor data.

A method performed by an electronic hearing device with an earpiece configured to be worn in an ear, includes: engaging a hearing mode wherein a compensated output signal is based on current hearing compensation data. Performing a first fitting procedure including: obtaining first hearing compensation data via audiometric measurements; emitting an otoacoustic stimulation signal and capturing an acoustic signal including otoacoustic emissions. In response to receiving a first input signal, performing a first monitoring procedure including: emitting an otoacoustic stimulation signal and capturing an acoustic signal including otoacoustic emissions, if any. Determining a deviation value based on the second acoustic signal and the third acoustic signal; and determining whether the deviation value satisfies a first criterion. In accordance with a determination that the deviation value satisfies the first criterion, communicating a first notification signal indicative of the deviation from the hearing device.

An integrated circuit for digital signal routing. Signal routing is achieved with a multiply-accumulate block, which takes data from one or more data sources and, after any required scaling, generates output data for a data destination. Data from a data source is buffered for an entire period of a data sample clock so that the multiply-accumulate block can retrieve the data at any point in the period, and output data of the multiply-accumulate block is buffered for an entire period of the data sample clock so that the data destination can retrieve the data at any point in the period. The multiply-accumulate block operates on a time division multiplexed basis, so that multiple signal paths can be processed within one period of the sample clock.

An ear-worn electronic system comprise a plurality of discrete devices configured for deployment at one ear of a wearer. The system comprises a first device configured for placement at least partially within an ear canal of the wearer. The first device comprises at least a first processor, one or more first microphones, a first speaker, a first rechargeable battery, and first charging circuitry. The system comprises a second device configured for placement at the wearer's ear proximal of the first device in an outer ear direction. The second device comprises at least a second processor, a second rechargeable battery, and second charging circuitry. The first device is configured to operate autonomously when operating in an independent mode relative to the second device. The first and second devices are configured to operate cooperatively when operating in a communicatively coupled mode.

The present disclosure relates to a binaural hearing aid system comprising hearing aids for placement at, or in, a user's left and right ear, the hearing aids each comprising a microphone arrangement, a wireless communications unit, a receiver, and a sound channel with a valve, which is movable from an open state to an closed state and from a closed state to an open state. The binaural hearing aid system further comprises a signal processing arrangement adapted for generating a beamformed signal based on microphone signals supplied by either or both of the microphone arrangement(s) and for applying the beamformed signal to either or both of the receiver(s), and a valve control arrangement configured to asymmetrically control the valves in each hearing aid by moving the valves into positions wherein one of the valves is opened more than the other.

Disclosed is a system and method for individualized hearing aid prescription which consists of a test procedure that enables the fitting of an individualized estimation of the SII model to individual listeners efficiently and an optimization process which translates the resulting individualized model to the prescribed gains across frequencies for programming into the user's hearing aids. The test involves the recognition of one or more words presented in background noise, which better approximates the daily listening experiences of hearing-aid users compared to the pure-tone detection in a silent environment task which is commonly utilized during conventional audiometric testing. In the estimated SII model, five parameters describe in a custom fashion the relative weights of speech information across the five frequency bands for a given listener. The results from the speech test is used to determine the desirable amount of gain for each frequency region to optimize the user's aided speech intelligibility. The resulting gains for the individual may then be programmatically applied to the individual's prescribed hearing aid device(s).

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.