Hierarchical environmental classification in a hearing prosthesis

Patent metadata

Field	Value
Publication number	US-11337011-B2
Application number	US-201816755744-A
Country	US
Kind code	B2
Filing date	Oct 10, 2018
Priority date	Oct 17, 2017
Publication date	May 17, 2022
Grant date	May 17, 2022

Abstract

Presented herein are techniques for generating a hierarchical classification of a set of sound signals received at hearing prosthesis. The hierarchical classification includes a plurality of nested classifications of a sound environment associated with the set of sound signals received at hearing prosthesis, including a primary classification and one or more secondary classifications that each represent different characteristics of the sound environment. The primary classification represents a basic categorization of the sound environment, while the secondary classifications define sub-categories/refinements of the associated primary classification and/or other secondary classifications.

First claim

What is claimed is:

1. A method, comprising:
at a hearing prosthesis:
receiving a set of sound signals;
providing the set of sound signals to a first classifier;
determining, based on the first classifier, a primary classification of a current sound environment associated with the sound signals;
conditionally activating a second classifier based on the primary classification; and
determining, based on the activating, a secondary classification of the set of sound signals.

2. The method of claim 1 , further comprising:
generating, at the hearing prosthesis, a hierarchical classification output representing the primary classification and the secondary classification; and
storing the hierarchical classification output as part of a hierarchical classification data set in memory of the hearing prosthesis.

3. The method of claim 1 , further comprising:
adjusting one or more settings of the hearing prosthesis based on the primary classification and the secondary classification.

4. The method of claim 3 , wherein adjusting the one or more settings of the hearing prosthesis based on the primary classification and the secondary classification comprises:
at the hearing prosthesis, automatically adjusting the one or more settings of the hearing prosthesis.

5. The method of claim 3 , wherein the one or more settings comprise at least one of: noise reduction settings, tinnitus masking settings, microphone settings, gain settings, channel dynamic range, maxima selection, or comfort settings.

6. The method of claim 1 , further comprising deriving another secondary classification based on the secondary classification.

7. The method of claim 1 , wherein the primary classification indicates that the set of sound signals represent speech, and wherein determining the secondary classification comprises:
sub-categorizing attributes of the speech.

8. The method of claim 7 , wherein sub-categorizing the attributes of the speech comprises:
determining whether the speech in the set of sound signals is speech of a recipient or external speech.

9. The method of claim 1 , wherein the primary classification indicates that the set of sound signals represent noise, and wherein determining the secondary classification comprises:
sub-categorizing a type of the noise.

10. The method of claim 1 , further comprising:
generating, based on the set of sound signals, stimulation for delivery to a recipient of the hearing prosthesis.

11. The method of claim 10 , wherein generating, based on the set of sound signals, stimulation for delivery to a recipient of the hearing prosthesis comprises:
electrically stimulating the recipient based on the set of sound signals.

12. A hearing device comprising:
one or more input elements configured to receive at least one set of sound signals;
a memory; and
one or more processors coupled to the memory and the one or more input elements, and configured to:
generate a hierarchical classification of the at least one set of sound signals;
convert, based on the hierarchical classification, the at least one set of sound signals into one or more output signals;
deliver, based on the one or more output signals, stimulation to a recipient of the hearing device;
generate a hierarchical classification output representing the hierarchical classification; and
store the hierarchical classification output as part of a hierarchical classification data set in a memory of the hearing device.

13. The hearing device of claim 12 , wherein the one or more processors are further configured to:
determine, from the at least one set of sound signals, a primary classification of the hierarchical classification; and
determine, based on the primary classification and the at least one set of sound signals, one or more secondary classifications that define sub-categories of the primary classification.

14. The hearing device of claim 13 , wherein at least one of the one or more secondary classifications sub-categorizes another of the one or more secondary classifications.

15. The hearing device of claim 13 , wherein the primary classification indicates that the at least one set of sound signals represent speech, and wherein to determine the one or more secondary classifications, the one or more processors are further configured to:
sub-categorize, based on the primary classification, attributes of the speech.

16. The hearing device of claim 13 , wherein the primary classification indicates that the at least one set of sound signals represent noise, and wherein to determine the one or more secondary classifications, the one or more processors are further configured to:
sub-categorize a type of the noise.

17. The hearing device of claim 12 , wherein the one or more processors are further configured to:
adjust one or more settings of the hearing device based on the hierarchical classification.

18. The hearing device of claim 17 , wherein the one or more settings comprise at least one of: noise reduction settings, tinnitus masking settings, microphone settings, gain settings, channel dynamic range, maxima selection, or comfort settings.

19. A method, comprising:
receiving a set of sound signals;
generating a hierarchical classification of the set of sound signals, wherein an attribute of a primary classification of the hierarchical classification is further qualified by a nested secondary classification in the hierarchical classification;
converting, based on the hierarchical classification, the set of sound signals into one or more output signals;
generating a hierarchical classification output representing the hierarchical classification of the set of sound signals; and
storing the hierarchical classification output as part of a hierarchical classification data set in memory of a hearing device.

20. The method of claim 19 , wherein generating a hierarchical classification comprises:
determining, from the set of sound signals, the primary classification; and
determining, based on the primary classification and the set of sound signals, one or more secondary classifications that define sub-categories of the primary classification.

21. The method of claim 20 , further comprising:
subcategorizing one of the one or more secondary classifications; and
determining, based on the subcategorizing, another of the one or more secondary classifications.

22. The method of claim 20 , wherein the primary classification indicates that the set of sound signals represent speech, and wherein determining, from the set of sound signals, one or more secondary classifications that define sub-categories of the primary classification comprises:
generating, based on the primary classification indicating the set of sound signals represent speech, a secondary classification that sub-categorizes attributes of the speech.

23. The method of claim 20 , wherein the primary classification indicates that the set of sound signals represent noise, and wherein determining, from the set of sound signals, one or more secondary classifications that define sub-categories of the primary classification comprises:
sub-categorizing, based on the primary classification, a type of the noise.

24. The method of claim 19 , further comprising:
adjusting one or more settings of the hearing device based on the hierarchical classification data set.

25. The method of claim 24 , wherein the one or more settings comprise at least one of: no

Assignees

• Cochlear Ltd

Inventors

• Goorevich Michael
• Qazi Obaid Ur Rehman
• Puchner Carl

Classifications

• A61N1/36036

  of the outer, middle or inner ear · CPC title

• H04R2225/41

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

• H04R25/50 Primary

  Customised settings for obtaining desired overall acoustical characteristics · CPC title

• H04R25/75

  Electric tinnitus maskers providing an auditory perception · CPC title

• H04R2225/43

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