A hearing system performs nonlinear processing of signals received from a plurality of microphones using a neural network to enhance a target signal in a noisy environment. In various embodiments, the neural network can be trained to improve a signal-to-noise ratio without causing substantial distortion of the target signal. An example of the target sound includes speech, and the neural network is used to improve speech intelligibility.

A hearing system comprises a hearing device worn on the head, or fully or partially implanted in the head, of a user, and external audio transmitters. The hearing system allows wireless communication to be established between the hearing device and the audio transmitters. The hearing device comprises microphones providing respective electric input signals; a beamformer filter providing a beamformed signal from the electric input signals; and an output unit. The hearing system further comprises a selector/mixer for selecting and possibly mixing one or more of the electric input signals or the beamformed signal and external electric signals from the audio transmitters, and providing a current input sound signal based thereon for presentation to the user. The selector/mixer is controlled by a source selection processor, which determines the source selection control signal based on a comparison of the beamformed signal and the external electric sound signals or processed versions thereof.

Disclosed is a hearing device configured to be worn in an ear of a user. The hearing device is configured to provide an audio signal to the user. The hearing device comprises a circuit assembly. The circuit assembly comprises a printed circuit board assembly. The printed circuit board assembly comprises: a first circuit board; a second circuit board; and a third circuit board interconnected with the first circuit board and the second circuit board. The circuit assembly comprises a battery, and an output transducer for providing the audio signal, wherein the printed circuit board assembly is folded about the battery and the output transducer.

A hearing aid, comprising a microphone configured to produce a microphone output signal representing sounds transduced by the microphone; an earphone speaker configured to convert an equalized output electrical signal into acoustic waves; a Bluetooth wireless transceiver; and an automated processor configured to spot a plurality of different keywords; and selectively control a Bluetooth communication partner dependent on the spotted keyword.

An apparatus includes a housing and a circuit including an inductor and at least one capacitor in electrical communication with the inductor. The circuit has a resonance frequency and bounds a non-electrically-conductive region of the housing. The circuit is configured to be operable as an antenna.

A hearing device, e.g. a hearing aid or a headset, configured to be worn by a comprises an input unit for providing at least one electric input signal in a time-frequency representation; and a signal processor comprising a target signal estimator for providing an estimate of the target signal; a noise estimator for providing an estimate of the noise; and a gain estimator for providing respective gain values in dependence of said target signal estimate and said noise estimate. The gain estimator comprises a trained neural network, wherein the outputs of the neural network comprise real or complex valued gains, or separate real valued gains and real valued phases. The signal processor is configured—at a given time instance t—to calculate changes Δx(i,t)=x(i,t)−{circumflex over (x)}(i,t−1), and Δh(j,t−1)=h(j,t−1)−ĥ(j,t−2) to an input vector x(t) and to the hidden state vector h(t−1), respectively, from one time instance, t−1, to the next, t, and where {circumflex over (x)}(i,t−1) and ĥ(j,t−2) are estimated values of x(i,t−1) and h(j,t−2), respectively, where indices i, j refers to the i.sup.th input neuron and the j.sup.th neuron of the hidden state, respectively, where 1≤i≤N.sub.ch,x and 1≤j≤N.sub.ch,oh, wherein N.sub.ch,x and N.sub.ch,oh is the number of processing channels of the input vector x and the hidden state vector h, respectively, and wherein the signal processor is further configured to provide that the number of updated channels among said N.sub.ch,x and said N.sub.ch,oh processing channels of the modified gated recurrent unit for said input vector x(t) and said hidden state vector h(t−1), respectively, at said given time instance t is limited to a number of peak values N.sub.p,x, and N.sub.p,oh, respectively, where N.sub.p,x is smaller than N.sub.ch,x, and N.sub.p,oh, is smaller than N.sub.ch,oh.

A hearing device is disclosed. The hearing device comprises a plurality of antennas. The hearing device comprises electronic components including a first electronic component. The plurality of antennas comprises a first antenna and a second antenna. The first antenna may comprise a coil part coiled along a first antenna axis. The first antenna may be configured for magnetic induction communication. The second antenna may be configured for communication in a frequency band in the GHz range. The second antenna may comprise a shielding part configured to shield the first antenna.

Described are systems, methods, apparatuses, and computer program products for wireless in-ear-monitoring (IEM) of audio. A system includes transmitter(s) configured to map orthogonal sub-carriers of a digital signal to narrowband receivers to form receiver-allocated audio channels, modulate the digital signal, and transmit the signal as an ultra-high frequency (UHF) analog carrier wave comprising the orthogonal sub-carriers to the nearby receiver. A narrowband receiver is configured to demodulate and sample the sub-carriers allocated to the receiver. Sub-carriers can be positioned orthogonal to one another in adjacent sub-bands of the frequency domain and beacon symbols and pilot signals can be iteratively provided in the same portion of the frequency domain for each channel. The receiver can use non-data-aided and data-aided approaches for synchronization of the time domain and frequency domain waveforms of the received signal to the transmitted signal prior to sampling the allocated sub-carriers.

The flexible attachable tip is manufactured to repeatedly connect as well as disconnect to a body of a hearing assistance device. The flexible attachable tip is manufactured to have two or more offset layers of flexible earmolds. The tip has a dome-shaped earmold that is separated by an air gap from offset layers of inner earmolds. Each layer of ear mold has multiple bendable members with an air vent constructed into the bendable members for that earmold. Air space is formed in between each of the individual bendable members making up the flexible earmold for a given layer of the offset layers. The flexible earmolds including their bendable members bend to a deformed state in order to secure the hearing assistance device in position inside an ear canal, which prevents the device from falling out of an ear, while still providing both a sound path and an airflow path through the ear canal.

Method for setting parameters for individual adaptation of an audio signal, including: performing a first listening test with the substeps: playing a plurality of first audio signals having different levels; obtaining feedback per frequency range from an individual which of the plurality of first acoustic signals is above an individual listening threshold; and using the lowest level of the different levels for which feedback is available as a level for the individual listening threshold per frequency range; performing adaptation of a second audio signal with the substeps: playing the second audio signal according to a total volume level considering a sound adaptation characteristic map; and varying the sound adaptation characteristic wherein the levels for the individual listening thresholds are used as minimum output levels in the sound adaptation characteristic map.