Oticon A/s

Rasmus Jones

David Thorn Blix

Zuzana Jelcicová

Michael Syskind Pedersen

Jesper Bruun Jensen

Asger Heidemann Andersen

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&#x2014;at a given time instance t&#x2014;to calculate changes &#x394;x(i,t)=x(i,t)&#x2212;{circumflex over (x)}(i,t&#x2212;1), and &#x394;h(j,t&#x2212;1)=h(j,t&#x2212;1)&#x2212;&#x125;(j,t&#x2212;2) to an input vector x(t) and to the hidden state vector h(t&#x2212;1), respectively, from one time instance, t&#x2212;1, to the next, t, and where {circumflex over (x)}(i,t&#x2212;1) and &#x125;(j,t&#x2212;2) are estimated values of x(i,t&#x2212;1) and h(j,t&#x2212;2), respectively, where indices i, j refers to the iinput neuron and the jneuron of the hidden state, respectively, where 1&#x2264;i&#x2264;Nand&#x2264;j&#x2264;N, wherein Nand Nis 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 Nand said Nprocessing channels of the modified gated recurrent unit for said input vector x(t) and said hidden state vector h(t&#x2212;1), respectively, at said given time instance t is limited to a number of peak values N, and N, respectively, where Nis smaller than N, and N, is smaller than N.

Hearing device comprising a recurrent neural network and a method of processing an audio signal

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 Nprocessing channels of the Peak GRU for said input vector x(t) and said hidden state vector h(t&#x2212;1) at said given time instance t is limited to a number of peak values N, where Nis smaller than N. A method of operating a hearing device is further disclosed.

Growing community of inventors

København NV, Denmark

Rasmus Jones