Feature extraction in hearing prostheses

Patent metadata

Field	Value
Publication number	US-12022262-B2
Application number	US-202318175024-A
Country	US
Kind code	B2
Filing date	Feb 27, 2023
Priority date	Dec 8, 2017
Publication date	Jun 25, 2024
Grant date	Jun 25, 2024

Abstract

Presented herein are techniques for extracting features from sound signals received at a hearing prosthesis at least partially based on an environmental classification of the sound signals. More specifically, one or more sound signals are received at a hearing prosthesis and are converted in to stimulation control signals for use in delivering stimulation to a recipient of the hearing prosthesis. The hearing prosthesis determines an environmental classification of the sound environment associated with the one or more sound signals and is configured to use the environmental classification in the determination of a feature-based adjustment for incorporation into the stimulation control signals.

First claim

What is claimed is:

1. A method, comprising:
receiving one or more input signals at a hearing device;
determining, from the one or more input signals, an environmental classification of a current ambient environment associated with the one or more input signals; and
performing one or more feature-extraction operations to extract at least one signal feature from the one or more input signals,
wherein the one or more feature-extraction operations are controlled at least partially based on the environmental classification of the current ambient environment.

2. The method of claim 1 , further comprising:
generating, from the one or more input signals, stimulation control signals for use in stimulating a recipient of the hearing device; and
incorporating at least one feature-based adjustment into the stimulation control signals, wherein the at least one feature-based adjustment is based on the at least one signal feature extracted from the one or more input signals.

3. The method of claim 2 , wherein incorporating the at least one feature-based adjustment into the stimulation control signals comprises:
executing one or more feature-based adjustment operations to determine the at least one feature-based adjustment for incorporation into the stimulation control signals, wherein the one or more feature-based adjustment operations are adjusted at least partially based on the environmental classification of the current ambient environment.

4. The method of claim 1 , wherein performing the one or more feature-extraction operations to extract the at least one signal feature from the one or more input signals comprises:
performing one or more feature-extraction pre-processing operations on the one or more input signals to generate one or more pre-processed signals;
extracting the at least one signal feature from the one or more pre-processed signals; and
adjusting the one or more feature-extraction pre-processing operations at least partially based on the environmental classification of the current ambient environment.

5. The method of claim 4 , further comprising:
generating, from the one or more input signals, stimulation control signals for use in stimulating a recipient of the hearing device,
wherein the one or more feature-extraction pre-processing operations and the extracting of the at least one signal feature are performed separate from the generating of the stimulation control signals.

6. The method of claim 5 , wherein generating the stimulation control signals for use in stimulating the recipient of the hearing device comprises:
executing sound processing operations; and
adjusting one or more of the sound processing operations at least partially based on the environmental classification of the current ambient environment.

7. The method of claim 6 , wherein a first environmental classifier is configured to adjust the one or more of the sound processing operations, and a second classifier, which operates independently from the first environmental classifier, is configured to adjust the one or more feature-extraction pre-processing operations.

8. The method of claim 6 , wherein a single classifier is configured to both adjust the one or more of the sound processing operations and to adjust the one or more feature-extraction pre-processing operations.

9. The method of claim 4 , further comprising:
receiving one or more user inputs; and
adjusting the one or more feature-extraction pre-processing operations at least partially based on the environmental classification of the current ambient environment and at least partially based on the one or more user inputs.

10. The method of claim 1 , wherein extracting the at least one signal feature from the one or more input signals based on the environmental classification of the current ambient environment comprises:
extracting at least one measure of fundamental frequency (F0) from the one or more input signals.

11. A method, comprising:
receiving at least one input signal at a hearing device;
determining, from the at least one input signal, an environmental classification of a current ambient environment associated with the at least one input signal;
converting the at least one input signal into stimulation control signals for use in stimulating a recipient of the hearing device;
extracting, using a feature extraction process, one or more signal features from the at least one input signal, wherein one or more parameters of the feature extraction process are controlled based on the environmental classification of the current ambient environment; and
determining at least one feature-based adjustment for incorporation into the stimulation control signals, wherein the at least one feature-based adjustment is based on at least one of the one or more signal features extracted from the at least one input signal.

12. The method of claim 11 , wherein determining the at least one feature-based adjustment for incorporation into the stimulation control signals comprises:
executing one or more feature-based adjustment operations to determine the at least one feature-based adjustment for incorporation into the stimulation control signals, wherein one or more parameters of the one or more feature-based adjustment operations are controlled based on the environmental classification of the current ambient environment.

13. The method of claim 11 , wherein extracting, using the feature extraction process, the one or more signal features from the at least one input signal comprises:
performing one or more feature-extraction pre-processing operations on the at least one input signal to generate one or more pre-processed signals;
extracting the one or more signal features from the one or more pre-processed signals; and
adjusting one or more parameters of the one or more feature-extraction pre-processing operations based on the environmental classification of the current ambient environment.

14. The method of claim 13 , wherein the one or more feature-extraction pre-processing operations and the extracting of the one or more signal features are performed separate from the converting the at least one input signal into the stimulation control signals.

15. The method of claim 13 , further comprising:
receiving one or more user inputs; and
adjusting the one or more parameters of a feature-based adjustment one or more feature-extraction pre-processing operations based on the environmental classification of the current ambient environment and based on the one or more user inputs.

16. The method of claim 11 , wherein converting the at least one input signal into the stimulation control signals for use in stimulating the recipient of the hearing device comprises:
executing sound processing operations; and
adjusting one or more parameters of one or more of the sound processing operations based on the environmental classification of the current ambient environment.

17. The method of claim 11 , wherein extracting, using the feature extraction process, the one or more signal features from the at least one input signal comprises:
extracting at least one measure of fundamental frequency (F0) from the at least one input signal.

18. A method, comprising:
receiving at least one sound signal at an implantable microphone of an implantable medical device;
classifying the at least one sound signal into a selected one of a plurality of categories; and
extracting one or more signal features from the at least one sound signal based on the selected one of the plurality of categories.

19. The metho

Assignees

• Cochlear Ltd

Inventors

• Goorevich Michael
• Brown Matthew
• Vandali Andrew

Classifications

• H04R2225/67

  Implantable hearing aids or parts thereof not covered by H04R25/606 · CPC title

• H04R2225/43

  Signal processing in hearing aids to enhance the speech intelligibility · CPC title

• H04R2225/41

  Detection or adaptation of hearing aid parameters or programs to listening situation, e.g. pub, forest · CPC title

• A61N1/36038

  Cochlear stimulation · CPC title

• H04R2225/61

  Aspects relating to mechanical or electronic switches or control elements, e.g. functioning · CPC title