Granted Patent B2

US 12,462,828 · App. 18/334,067 · Granted Nov 4, 2025

Inventors: Rasmus Kvist Lund (Ballerup, DK); Pejman Mowlaee (Ballerup, DK)

Assignee: GN AUDIO A/S

G10L21/038G10L19/02G10L19/22G10L2019/0004

Abstract

Claims (39)

1 . A computer-implemented method for training a bandwidth extension model for personalized bandwidth extension, wherein the method comprises:

obtaining an audio dataset comprising one or more first audio signals with a first bandwidth;

obtaining a hearing dataset comprising a hearing profile comprising one or more user profiles including a first user profile for a user of an audio device;

applying a bandwidth extension model to the one or more first audio signals to generate one or more bandwidth extended audio signals with a second bandwidth,

determining one or more perceptual losses associated with the one or more bandwidth extended audio signals based on the first user profile;

determining a masking threshold and a personalized bandwidth based on the hearing dataset;

determining an audible range and audible levels based on the masking threshold and the personalized bandwidth; and

training, based on the one or more perceptual losses, the bandwidth extension model,

wherein the audible range is a personalized bandwidth for the user of the audio device,

wherein the audible levels are used to determine masked and unmasked components of the generated bandwidth extending audio signals,

wherein each of the one or more perceptual losses is a perceptual loss function,

wherein the training of the bandwidth extension model includes training the bandwidth extension model to generate spectral content that is audible within the personalized bandwidth for the user of the audio device.

2 . A method for personalized bandwidth extension in an audio device, wherein the method comprises:

a. obtaining an input microphone signal with a first bandwidth,

b. obtaining a first user parameter comprising at least one of a result of a hearing test carried out on the user of the audio device or physiological information regarding the user of the audio device, including at least one of gender or age,

c. determining, based on the first user parameter, a bandwidth extension model,

wherein the bandwidth extension model comprises a trained neural network, and

wherein the trained neural network is trained according to claim 1 , and

d. generating an output signal with a second bandwidth by applying the determined bandwidth extension model to the input microphone signal.

3 . The method for personalized bandwidth extension in an audio device according to claim 2 , wherein the step c. comprises:

obtaining a codebook comprising a plurality of bandwidth extension models each associated with one or more user parameters,

comparing the first user parameter to the codebook, and

determining, based on the comparison between the codebook and the first user parameter, the bandwidth extension model.

4 . The method for personalized bandwidth extension in an audio device according to claim 2 , comprising:

analysing the input microphone signal to determine the first bandwidth, and

determining, based on the first user parameter and the determined first bandwidth, the bandwidth extension model.

5 . The method for personalized bandwidth extension in an audio device according to claim 2 , wherein the first user parameter is stored on a local storage of the audio device.

6 . The method for personalized bandwidth extension in an audio device according to claim 2 , wherein the step a. comprises:

receiving the input microphone signal from a far-end station, wherein the received input microphone signal from the far-end station is an encoded signal, and

wherein the steps b. to d. is carried out as part of decoding the input microphone signal from the far-end station.

7 . An audio device for personalized bandwidth extension, the audio device comprising:

a processor and

a memory configured to store instructions which, when executed by the processor, causes the processor to:

a. obtain an input microphone signal with a first bandwidth,

b. obtain a first user parameter comprising at least one of a result of a hearing test carried out on a user of the audio device or physiological information regarding the user of the audio device, including at least one of gender or age,

c. determine, based on the first user parameter, a bandwidth extension model,

wherein the bandwidth extension model comprises a trained neural network, and

wherein the trained neural network is trained according to claim 1 , and

d. generate an output signal with a second bandwidth using the determined bandwidth extension model.

Assignments (2)

Priority Claims (1)

Continuity (1)

References Cited (20)