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.

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 method for directional signal processing of signals of a microphone array, including first and second microphones generating first and second input signals from an ambient sound, uses the first input signal to form a reference signal transformed into the frequency domain, thereby generating a frequency-space reference signal. The first and second input signals are transformed into the frequency domain, and a first frequency-space directional signal is formed in the frequency domain using the transformed first and second input signals. A frequency-resolved comparison of the frequency-space reference signal with the first frequency-space directional signal or signal derived therefrom in the frequency domain, is used to generate frequency-dependent first gain factors to generate a time filter in the time domain. The reference signal is filtered by the time filter and an output signal is generated from the reference signal filtered by the time filter.

A system for indicating a direction to a user is disclosed. The system may include a first unit and a second unit to be worn proximate to a first ear and a second ear of the user respectively. The system may indicate a direction to the user through tactile sensations delivered proximate to the ears of the user by the first and second units. The system may also include microphones to aid in determining the direction of a source of a sound and the system may indicate the determined direction, thereby allowing the user to localize the sound. The system may also function as hearing aids. The system may aid individuals with hearing disabilities by alerting them to the direction of the source of a sound.

Systems and methods for providing augmented arrays for audio playback are disclosed. An example playback device includes a first transducer configured to output audio along a first acoustic axis and a second transducer configured to output audio along a second acoustic axis. The playback device is configured to receive a source stream of audio content including at least a first input channel and a second input channel. The device plays back first audio output via the first transducer based on the first input channel and directed along the first acoustic axis, and plays back second audio output via the second transducer based on the second input channel and directed along the second acoustic axis, wherein the second audio output at least partially cancels the first audio output along a first spatial region offset from the first acoustic axis.

A system (20) includes a plurality of microphones (22), configured to generate different respective signals in response to acoustic waves (36) arriving at the microphones, and a processor (34). The processor is configured to receive the signals, to combine the signals into multiple channels, which correspond to different respective directions relative to the microphones by virtue of each channel representing any portion of the acoustic waves arriving from the corresponding direction with greater weight, relative to others of the directions, to calculate respective energy measures of the channels, to select one of the directions, in response to the energy measure for the channel corresponding to the selected direction passing one or more energy thresholds, and to output a combined signal representing the selected direction with greater weight, relative to others of the directions. Other embodiments are also described.

A hearing aid system for generating processed audio signals may include at least one processor. The processor may be configured to receive an audio signal representative of the sounds captured by the at least one microphone; generate a processed audio signal based on analysis of the audio signal; determine a quality degradation of at least one aspect of the processed audio signal; and provide an auditory cue to the user indicating the quality degradation.

A method for rejecting inherent noise of a microphone arrangement that includes a first microphone and a second microphone. The first microphone generates a first microphone signal from an ambient sound signal and the second microphone generates a second microphone signal from the ambient sound signal. A measure of correlation between the first microphone signal and the second microphone signal is ascertained, and inherent noise of the first microphone and/or of the second microphone in the first or second microphone signal is rejected on the basis of the measure of correlation.

A system, such as an ear-wearable device or a hearing aid, can receive multiple audio signals representing a same audio content, can cross-correlate the multiple audio signals to determine relative delays between the audio signals, can apply the determined delays to at least one of the audio signals to form multiple synchronized audio signals, and can mix at least two of the synchronized audio signals in time-varying proportions to form an output audio signal. The system can optionally adjust the mix proportions, in real time, to increase or optimize the signal-to-noise ratio of the output audio signal. The system can optionally perform the cross-correlation repeatedly, at regular or irregular time intervals, to update the relative delays. The system can optionally divide the audio signals into frequency bands, and apply these operations to each frequency band, independent of the other frequency bands.