A hearing assistance system comprises an input unit for providing electric input sound signals u.sub.i, each representing sound signals U.sub.i from a multitude n.sub.u of sound sources S.sub.i, an electroencephalography (EEG) system for recording activity of the auditory system of the user's brain and providing a multitude n.sub.y of EEG signals y.sub.j, and a source selection processing unit receiving said electric input sound signals u.sub.i and said EEG signals y.sub.j, and in dependence thereof configured to provide a source selection signal Ŝ.sub.x indicative of the sound source S.sub.x that the user currently pays attention to using a selective algorithm that determines a sparse model to select the most relevant EEG electrodes and time intervals based on minimizing a cost function measuring the correlation between the individual sound sources and the EEG signals, and to determine the source selection signal Ŝ.sub.x based on the cost functions obtained for said multitude of sound sources.

The disclosure presents a method and an amplifier system for minimizing variation in an acoustical signal caused by variation in gain of an amplifier, comprising a battery for providing a supply voltage to the amplifier, a digital signal processor for providing the acoustical signal to the amplifier, a controller unit receiving an enablement signal when the supply voltage is in an offset mode, and based on the enablement signal requesting a measured voltage during a time period, and a first analog-to-digital converter configured for measuring the supply voltage to the amplifier when receiving the request from the controller unit or the first analog-to-digital converter is configured for measuring the supply voltage to the amplifier continuously, and where variations in the measured voltage relates to variations in the supply voltage during the time period. Furthermore, the controller unit is configured to predict offset modes (i.e. changes) in the supply voltage based on the enablement signals and a fitting of the measured voltages, and wherein the controller unit is configured to generate a compensating signal based on the fitting and transmit the compensating signal to the digital signal processor, the digital signal processor is then configured to minimize variation in the acoustical signal at the output of the amplifier by compensating the variation in gain of the amplifier based on the compensating signal.

Presented herein are techniques for training a hearing prosthesis to classify/categorize received sound signals as either including a recipient's own voice (i.e., the voice or speech of the recipient of the hearing prosthesis) or external voice (i.e., the voice or speech of one or more persons other than the recipient). The techniques presented herein use the captured voice (speech) of the recipient to train the hearing prosthesis to perform the classification of the sound signals as including the recipient's own voice or external voice.

A method and apparatus for sound enhancement are provided in this invention. The method comprises: obtaining sound signals and converting the sound signals into digital signals; decomposing the digital signals to obtain a plurality of IMFs or pseudo-IMFs; selectively amplifying the amplitudes of the IMFs and pseudo-IMFs; reconstituting the selectively amplified IMFs or pseudo-IMFs to obtain reconstituted signals and converting the reconstituted signals into analog signals. The present invention is based on the Hilbert-Huang transform. Through the present invention, the sound can be selectively amplified, and only the high-frequency consonants in the sound are amplified without vowel, which effectively improves the clarity of the enhanced sound. The present invention overcomes the problems in the current sound enhancement method which makes the sound louder without increasing the clarity.

In a method for direction-dependent noise rejection for a hearing system, first and second input transducers are used to generate an interference signal and a target signal from a sound from the surroundings. The interference signal and/or the target signal are referenced to a useful signal source arranged in a target direction. The target signal is generated with a target directivity pattern. For each of a first plurality of frequency bands, an acoustic characteristic of the target signal is compared with a corresponding acoustic characteristic of the interference signal, and the comparison is used to ascertain a provisional weighting factor. The provisional weighting factor is used to form for the frequency band a weighting factor for the respective frequency bands. An input signal to be processed is weighted on a frequency-band-by-frequency-band basis using the respective weighting factor, and the weighted input signal is used to generate an output signal.

A reverberation condition is detected affecting an electronic hearing device. The hearing device receives sound from a microphone and provides amplified sound to an in-ear receiver. The reverberation condition is predicted to impact clarity of the amplified sound. A sound processing capability is determined that will affect the reverberation. The sound processing capability is applied to the amplified sound and includes one or more of expansion, compression, and directionality processing. In response to detecting the reverberation condition, at least one of the following is performed: enabling the sound processing capability with a reverberation mitigation setting if the sound processing capability is currently disabled; or changing the sound processing capability to the reverberation mitigation setting from a default setting if the sound processing capability is currently enabled. The reverberation mitigation setting is removed when the reverberation condition is no longer detected.

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.

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.

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.

Hearing device and method of power estimation and/or pulse detection in a hearing device is disclosed. The method comprises obtaining a pulse input signal; determining if the pulse input signal satisfies a first rising criterion; in accordance with the input signal satisfying the first rising criterion, increasing a threshold; determining if the pulse input signal satisfies a first down count criterion; in accordance with the pulse input signal satisfying the first down count criterion, initializing a down counter; determining if the down counter satisfies a second down count criterion; in accordance with the down counter satisfying the second down count criterion, decreasing the down counter; determining if the down counter satisfies a pulse detection criterion; and in accordance with the down counter satisfying the pulse detection criterion, outputting a pulse output signal indicative of detection of a pulse.