In some embodiments, the electronic device includes a speaker, a microphone, a memory, a digital signal processor (DSP), a driver, and a processor. The processor is configured to: obtain a first sound signal by combining a first signal, a second signal, and a first anti-phase signal; extract, from a second sound signal related to the first sound signal, a first DPOAE signal; obtain a third sound signal by combining a fourth signal, a fifth signal, and a second anti-phase signal; extract, from a fourth sound signal related to the third sound signal, a second DPOAE signal; obtain a user hearing profile based on the first and second DPOAE signals; and perform, based on the user hearing profile, at least one of a sound volume change and an equalization (EQ) change of a sound to be output.

The disclosure generally relates to a method, system and apparatus to improve a user's understanding of speech in real-time conversations by processing the audio through a neural network contained in a hearing device. The hearing device may be a headphone or hearing aid. In one embodiment, the disclosure relates to an apparatus to enhance incoming audio signal. The apparatus includes a controller to receive an incoming signal and provide a controller output signal; a neural network engine (NNE) circuitry in communication with the controller, the NNE circuitry activatable by the controller, the NNE circuitry configured to generate an NNE output signal from the controller output signal; and a digital signal processing (DSP) circuitry to receive one or more of controller output signal or the NNE circuitry output signal to thereby generate a processed signal; wherein the controller determines a processing path of the controller output signal through one of the DSP or the NNE circuitries as a function of one or more of predefined parameters, incoming signal characteristics and NNE circuitry feedback.

An optimization system for testing a patient's hearing comprises a controller, an ear piece, and a memory. The controller: provides a series of tones to the ear piece; receives feedback from the patient between each tone; generates a data point to be used in an audiogram after receiving each feedback; after each data point is generated, computes a statistical distribution based on the generated data points; identifies an area of the statistical distribution most in need of additional data; and selects a subsequent tone to provide in the series of tones. Each feedback indicates whether the respective tone was detected or not detected, and each data point is based on the respective feedback. Each subsequent tone provided in the series of tones is a tone represented in the area of the statistical distribution most in need of additional data at the time of selection.

Disclosed herein, among other things, are systems and methods for a user adjustment interface using remote computing resources. Specifically, a system can include a mobile device in communication with a hearing assistance device or a remote server. The mobile device can interpret an acoustic environment and send information about the environment to a remote server. The remote server can determine and send information to the mobile device for use in a user interface. The mobile device can receive a user selection of hearing assistance parameter information to be sent to the hearing assistance device.

A method of defining and setting a nonlinear signal processing of a hearing device, e.g. a hearing aid, by machine learning is provided. The hearing device being configured to be worn by a user at or in an ear or to be fully or partially implanted in the head at an ear of the user, the method comprising providing at least one electric input signal representing at least one input sound signal from an environment of a hearing device user, determining a normal-hearing representation of said at least one electric input signal based on a normal-hearing auditory model, determining a hearing-impaired representation of said at least one electric input signal based on a hearing-impaired auditory model, determining optimised training parameters by machine learning, where determining optimised training parameters comprises iteratively adjusting the training parameters, and comparing the normal-hearing representation with the hearing-impaired representation to determine a degree of matching between the normal-hearing representation and the hearing-impaired representation, until the degree of matching fulfils predetermined requirements, and, when the degree of matching fulfils the predetermined requirements, determining corresponding signal processing parameters of the hearing device based on the optimised training parameters. A hearing device is further provided.

A method including obtaining data based on a current and/or anticipated future state of a hearing prosthesis and adjusting a set gain margin of the hearing prosthesis based on the current or anticipated future state of the hearing prosthesis.

A system comprises an auditory device processor, an auditory device output mechanism, an auditory input sensor, a database including a reference bank of environmental sounds and corresponding sound profiles, and a memory. The auditory device processor is configured to: while the auditory input sensor is detecting a first environmental sound, receive a sound selection from the user, wherein the sound selection is associated with the first environmental sound; store a first sound profile in the reference bank corresponding to the first environmental sound; receive a second environmental sound detected by the auditory input sensor; analyze a frequency content of the second environmental sound; compare the frequency content of the second environmental sound with the reference bank of environmental sounds and corresponding sound profiles stored in the database; in response to the comparison, select one of the sound profiles corresponding to the second environmental sound; and automatically adjust the parameter settings.

Hearing aid system comprising at least one hearing aid is provided. The hearing aid system further comprising an input unit for receiving an input sound signal from an environment of the hearing aid user and providing at least one electric input signal representing said input sound signal, an output unit for providing at least one set of stimuli perceivable as sound to the hearing aid user based on processed versions of said at least one electric input signal, a processing unit connected to said input unit and to said output unit and comprising signal processing parameters to provide said processed versions of said at least one electric input signal, at least one photoplethysmogram (PPG) sensor configured to provide a PPG signal of the hearing aid user, and a listening effort determination unit configured to provide at least one PPG morphology parameter value based at least on the PPG signal, compare the at least one PPG morphology parameter value with at least one corresponding reference PPG morphology parameter value and determine a morphology comparison measure, and determine a listening effort of the hearing aid user. A hearing aid is further provided.

Disclosed herein are systems and methods for automatic correction of real ear measurements (REMs). A sound signal is produced through a receiver of a hearing device, and a sound pressure signal is sensed using a microphone placed inside the ear canal. The sound pressure signal is transformed to obtain a frequency response signal, a local minimum of the frequency response signal is detected above a programmable frequency level, and a spectral flatness of the frequency response signal is calculated in a selected frequency band surrounding the local minimum. If the spectral flatness is greater than a selected threshold value, acoustic correction is applied to the frequency response in the selected frequency band using an estimated transfer function to obtain a corrected sound pressure frequency response. The corrected sound pressure frequency response is used to modify, or make a recommendation to modify, a physical or operational characteristic of the hearing device.

Cochlear implant systems can comprise a cochlear implant system comprising a cochlear electrode, a stimulator, an input source, and an implantable battery and/or communication module. The signal processor may be programmed with a transfer function and be configured to receive input signals from the input source and output a stimulation signal to the stimulator based on the received input signals with the transfer function. The system may be configured to receive a status indicator signal indicative of whether an external auditory aid device is active and update the transfer function of the signal processor if the external auditory aid device is active. For example, the signal processor can operate programmed with a first transfer function if the external auditory aid device is not active and with a second transfer function if the external auditory aid device is active.