公开(公告)号：US11330378B1

公开(公告)日：2022-05-10

申请号：US17153168

申请日：2021-01-20

Applicant: Oticon A/S

Inventor： Zuzana Jel{hacek over (c)}icová ,  Rasmus Jones ,  David Thorn Blix

IPC: H04R25/00 ,  G10L25/78 ,  G06N3/04 ,  G06N3/08

Abstract: A hearing device, e.g. a hearing aid or a headset, 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 comprises an input unit for providing at least one electric input signal in a time-frequency representation and a signal processor comprising a neural network configured to provide respective gain values G(k,t) in said time-frequency representation for reducing noise components in said at least one electric input signal. The neural network comprises at least one layer defined as a modified gated recurrent unit, termed Peak GRU, comprising memory in the form of a hidden state vector h, and wherein an output vector o is provided by said Peak GRU in dependence of an input vector x and said hidden state vector h, wherein an output o(j,t) of the Peak GRU at a given time step t is stored as said hidden state h(j,t) and used in the calculation of the output o(j,t+1) in the next time step t+1. The signal processor is configured to provide that the number of updated channels among Nch processing channels of the Peak GRU for said input vector x(t) and said hidden state vector h(t−1) at said given time instance t is limited to a number of peak values Np, where Np is smaller than Nch. A method of operating a hearing device is further disclosed.

公开(公告)号：US11696079B2

公开(公告)日：2023-07-04

申请号：US17580493

申请日：2022-01-20

Applicant: Oticon A/S

Inventor： Zuzana Jel{hacek over (c)}icová ,  Rasmus Jones ,  David Thorn Blix ,  Michael Syskind Pedersen ,  Jesper Jensen ,  Asger Heidemann Andersen

IPC: H04R25/00

CPC classification number: H04R25/453 ,  H04R25/405

Abstract: 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 ith input neuron and the jth neuron of the hidden state, respectively, where 1≤i≤Nch,x and 1≤j≤Nch,oh, wherein Nch,x and Nch,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 Nch,x and said Nch,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 Np,x, and Np,oh, respectively, where Np,x is smaller than Nch,x, and Np,oh, is smaller than Nch,oh.