US 11,540,063 B2Granted

Hearing device comprising a detector and a trained neural network

AssigneeOticon A/S

InventorsMichael Syskind Pedersen, Asger Heidemann Andersen, Jesper Jensen, Nels Hede Rohde, Anders Brødløs Olsen, Michael Smed Kristensen, Thomas Bentsen, Svend Oscar Petersen

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

A hearing device comprises an input transducer comprising a microphone for providing an electric input signal representative of sound in the environment of the hearing device, a pre-processor for processing electric input signal and providing a multitude of feature vectors, each being representative of a time segment thereof, a neural network processor adapted to implement a neural network for implementing a detector configured to provide an output indicative of a characteristic property of the at least one electric input signal, the neural network being configured to receive said multitude of feature vectors as input vectors and to provide corresponding output vectors representative of said output of said detector in dependence of said input vectors. The hearing device further comprises a transceiver comprising a transmitter and a receiver for establishing a communication link to another part or device or server, at least in a particular adaptation-mode of operation, and a selector for—in said particular adaptation-mode of operation—routing said feature vectors to said transmitter for transmission to said another part or device or server, and—in a normal mode of operation—to route said feature vectors to said neural network processor for use as inputs to said neural network, a neural network controller connected to said neural network processor for—in said particular adaptation-mode of operation—receiving optimized node parameters, and to apply said optimized node parameters to said nodes of said neural network to thereby implement an optimized neural network in said neural network processor, wherein the optimized node parameters have been selected among a multitude of sets of node parameters for respective candidate neural networks according to a predefined criterion in dependence of said feature vectors. A method of selecting optimized parameters for a neural network for use in a portable hearing device is further disclosed. The invention may e.g. be used in hearing aids or headsets, or similar, e.g. wearable, devices.

Claims18

Dependent claims

A hearing device configured to be located at or in an ear, or to be fully or partially implanted in the head, of a user, the hearing device comprising:

an input transducer comprising at least one microphone for providing at least one electric input signal representative of sound in the environment of the hearing device,
a pre-processor for processing said at least one electric input signal and providing a multitude of feature vectors, each being representative of a time segment of said at least one electric input signal,
a neural network processor adapted to implement a neural network for implementing a detector, or a part thereof, configured to provide an output indicative of a characteristic property of the at least one electric input signal, the neural network comprising an input layer and an output layer and a number of hidden layers, each layer comprising a number of nodes, each node being defined by a number of node parameters, the neural network being configured to receive said multitude of feature vectors as input vectors and to provide corresponding output vectors representative of said output of said detector, or a part thereof, in dependence of said input vectors,
a post-processor configured to receive said output vectors, and wherein said post-processor is configured to process said output vectors and to provide a resulting signal,
a transceiver comprising a transmitter and a receiver for establishing a communication link to another part or device or server, said communication link allowing transmission and reception of data to and from, respectively, said another part or device or server, at least in a particular adaptation-mode of operation,
a selector for, in said particular adaptation-mode of operation, routing said feature vectors to said transmitter for transmission to said another part or device or server and,
in a normal mode of operation, to route said feature vectors to said neural network processor for use as inputs to said neural network,
wherein the hearing device is configured to, in said particular adaptation-mode of operation, receive optimized node parameters from said another part or device or server, and to apply said optimized node parameters to said nodes of the neural network to thereby implement an optimized neural network in the neural network processor,
wherein the optimized node parameters have been selected among a multitude of sets of node parameters for respective candidate neural networks according to a predefined criterion in dependence of said feature vectors, and
wherein a user is prompted to speak one or more words forming the basis for at least some of said multitude of vectors, and
said predefined criterion for selecting said optimized node parameters is based on a comparison of output vectors, which are outputted from said candidate neural networks in response to said one or more prompted words spoken by the user.

8 more elements

A method of selecting optimized parameters for a neural network for use in a portable hearing device, the method comprising

providing a portable hearing device to be used by a particular user;
the hearing device comprising a neural network processor adapted to implement a neural network comprising an input layer and an output layer and a number of hidden layers, each layer comprising a number of nodes, each node being defined by a number of node parameters and a non-linear function, the neural network being configured to receive an input vector and to provide an output vector as a specific non-linear function of the input vector,
mounting the hearing device at or on the user;
providing at least one electric input signal representing sound in the environment of the user wearing the hearing device;
processing said at least one electric input signal and providing a multitude of feature vectors, each being representative of a time segment of said at least one electric input signal,
providing a multitude of pre-trained candidate neural networks, where each pre-trained network is considered a candidate for the user, and wherein each pre-trained neural network has been trained on fully or partially different training data;
receiving said feature vector and providing them as input vectors to said multitude of pre-trained candidate neural networks;
determining by said multitude of pre-trained candidate neural networks respective output vectors corresponding to said feature vectors;
comparing said output vectors and selecting one of the multitude of candidate neural networks as the optimized neural network for the hearing device according to a predefined criterion regarding said output vectors;
transmitting node parameters for the selected one of the multitude of candidate neural networks to the neural network processor of the hearing device, and
receiving said node parameters in said neural network processor and applying them to said neural network, and
prompting the user to speak one or more predetermined words forming the basis for at least some of said multitude of feature vectors, and
wherein said predefined criterion for selecting said optimized neural network is based on a comparison of output vectors, which are outputted from said candidate neural networks in response to said one or more predetermined words spoken by the user.

10 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/060,732Filed 1 Oct 2020
Priority: EP 192020028 Oct 2019
Published: US 2021/0105565 A18 Apr 2021
Granted: 27 Dec 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification18 codes

G06N 3/08
Neural networks: learning methods
H04R 25/507
Using digital signal processing: implemented by neural network or fuzzy logic
G06N 3/0464
Architecture, e.g. interconnection topology: convolutional networks [CNN, ConvNet]
G06N 3/063
Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons: using electronic means