The present invention is directed to a hearing aid which includes a lateral ear canal assembly and a medial ear canal assembly. In embodiments of the invention the medial ear canal assembly may include smart circuitry adapted to control parameters and outputs of the medial ear canal assembly. In embodiments of the invention various methods and circuitry are described, wherein the methods and circuitry are adapted to improve the performance and efficiency of the hearing aid.

A hearing device comprises an input transducer comprising a microphone for providing an electric input signal representative of sound in the environment of the hearing device, a pre-processor for processing electric input signal and providing a multitude of feature vectors, each being representative of a time segment thereof, a neural network processor adapted to implement a neural network for implementing a detector configured to provide an output indicative of a characteristic property of the at least one electric input signal, the neural network being configured to receive said multitude of feature vectors as input vectors and to provide corresponding output vectors representative of said output of said detector in dependence of said input vectors. The hearing device further comprises a transceiver comprising a transmitter and a receiver for establishing a communication link to another part or device or server, at least in a particular adaptation-mode of operation, and a selector for—in said particular adaptation-mode of operation—routing said feature vectors to said transmitter for transmission to said another part or device or server, and—in a normal mode of operation—to route said feature vectors to said neural network processor for use as inputs to said neural network, a neural network controller connected to said neural network processor for—in said particular adaptation-mode of operation—receiving optimized node parameters, and to apply said optimized node parameters to said nodes of said neural network to thereby implement an optimized neural network in said neural network processor, wherein the optimized node parameters have been selected among a multitude of sets of node parameters for respective candidate neural networks according to a predefined criterion in dependence of said feature vectors. A method of selecting optimized parameters for a neural network for use in a portable hearing device is further disclosed. The invention may e.g. be used in hearing aids or headsets, or similar, e.g. wearable, devices.

A system and method for differentially locating and modifying audio sources that includes receiving multiple audio inputs from a set of distinct locations; determining a multi-dimensional audio map from the audio inputs; acquiring a set of positional audio control inputs applied to the audio map, each audio control input comprising a location and audio processing property; and generating an audio output according to the audio control inputs and the audio inputs. The audio control inputs capable of configuration through manual, automatic, computer vision analysis, and other configuration modes.

A method performed by an electronic controller includes determining a charge level of a power supply configured to provide power to a medical device, and estimating, based on the charge level of the power supply, a first power supply life for operating the medical device according to a first mode. Further, the method includes estimating, based on the charge level of the power supply, a second power supply life for operating the medical device according to a second mode. As recited, operating the medical device according to the first mode has a different power use or consumption characteristic from operating the medical device according to the second mode. The method also includes generating a notification indicative of the first power supply life and the second power supply life.

A speaker of a hearing instrument generates a sound that includes a range of frequencies. Furthermore, a microphone of the hearing instrument measures an acoustic response to the sound. A processing system classifies, based on the acoustic response to the sound, a depth of insertion of an in-ear assembly of the hearing instrument into an ear canal of a user. Additionally, the processing system generates an indication based on the depth of insertion of the in-ear assembly of the hearing instrument into the ear canal of the user.

Hearing management, using a portable device or integrated portable devices, can include generating during a hearing diagnostics phase an audiogram based on responses of a user to signals conveyed to the user. In response to detecting ambient noises during the hearing diagnostics phase, noise cancellation can be performed to cancel the ambient noises in conjunction with conveying the signals to the user. During a hearing enhancement phase, sounds can be captured with the portable device. The captured sounds can be enhanced in real-time during the hearing enhancement phase by amplifying select frequencies of the captured sounds using signal gain. The frequencies can be selected, and the signal gain determined based on the audiogram. The captured sounds, now enhanced, can be conveyed to the user as frequency-enhanced sounds.

Broadly speaking, the embodiments disclosed herein describe replacing a current hearing aid profile stored in a hearing aid. In one embodiment, the hearing aid profile is updated by sending a hearing aid profile update request to a hearing aid profile service, receiving the updated hearing aid profile from the hearing aid profile service, and replacing the current hearing aid profile in the hearing aid with the updated hearing aid profile.

A hearing aid system comprises a hearing aid, and a portable auxiliary device' adapted to establish a communication link between them. The hearing aid comprises a microphone providing an electric input signal, a signal processor, and an output unit. The auxiliary device comprises a microphone providing an auxiliary electric input signal, and a user control interface allowing a user to initiate a specific calibration mode of operation of the hearing aid system. The signal processor of the hearing aid is configured to receive corresponding time segments of said electric input signal and said auxiliary electric input signal to provide an estimate of an acoustic transfer function from said microphone of said auxiliary device to said microphone of said hearing aid. A method of operating a hearing aid system is further disclosed. The invention may e.g. be used in various applications related to own voice detection and estimation.

A hearing device comprises an input transducer comprising a microphone for providing an electric input signal representative of sound in the environment of the hearing device, a pre-processor for processing electric input signal and providing a multitude of feature vectors, each being representative of a time segment thereof, a neural network processor adapted to implement a neural network for implementing a detector configured to provide an output indicative of a characteristic property of the at least one electric input signal, the neural network being configured to receive said multitude of feature vectors as input vectors and to provide corresponding output vectors representative of said output of said detector in dependence of said input vectors. The hearing device further comprises a transceiver comprising a transmitter and a receiver for establishing a communication link to another part or device or server, at least in a particular adaptation-mode of operation, and a selector for—in said particular adaptation—mode of operation—routing said feature vectors to said transmitter for transmission to said another part or device or server, and—in a normal mode of operation—to route said feature vectors to said neural network processor for use as inputs to said neural network, a neural network controller connected to said neural network processor for—in said particular adaptation-mode of operation—receiving optimized node parameters, and to apply said optimized node parameters to said nodes of said neural network to thereby implement an optimized neural network in said neural network processor, wherein the optimized node parameters have been selected among a multitude of sets of node parameters for respective candidate neural networks according to a predefined criterion in dependence of said feature vectors. A method of selecting optimized parameters for a neural network for use in a portable hearing device is further disclosed. The invention may e.g. be used in hearing aids or headsets, or similar, e.g. wearable, devices.

A hearing device directly or indirectly connected to a server through a network, the hearing device being provided with: an input unit that acquires sound data from the outside; a communication unit that transmits the sound data to the server, and receives a parameter set generated on the basis of the analysis result obtained by analyzing the sound data in the server; a storage unit that stores the parameter set; and an adjustment unit that, on the basis of the parameter set, adjusts gains of a plurality of prescribed frequencies.