Method and system for use of hearing prosthesis for linguistic evaluation

Patent metadata

Field	Value
Publication number	US-10842995-B2
Application number	US-201715784723-A
Country	US
Kind code	B2
Filing date	Oct 16, 2017
Priority date	May 13, 2013
Publication date	Nov 24, 2020
Grant date	Nov 24, 2020

Abstract

A method and system to help determine the extent to which a hearing prosthesis recipient is exposed to speech. The hearing prosthesis will log data regarding audio input, optimally in correspondence with times when the hearing prosthesis is in a stimulation-on mode in which the hearing prosthesis is set to stimulate a physiological system of the recipient in accordance with received audio input, so as to facilitate identification of speech to which the recipient is exposed. Further, as the hearing prosthesis itself receives the audio input, the hearing prosthesis may analyze the audio input to determine one or more linguistic characteristics of the audio input, such as a quantity of speech by the recipient and/or by others, and the hearing prosthesis may output data representing the determined one or more linguistic characteristics. Advantageously, the data may then be used to help facilitate rehabilitation of the recipient.

First claim

What is claimed is:

1. A hearing prosthesis, comprising:
one or more microphones configured to receive audio inputs representing an audio environment of the hearing prosthesis, wherein the hearing prosthesis is configured to selectively stimulate a physiological system of a recipient in accordance with one or more of the audio inputs;
one or more stimulus outputs;
a processing unit configured to:
determine, based on the audio inputs, one or more linguistic characteristics of the audio environment,
generate data representing the one or more linguistic characteristics; and
output the data from the hearing prosthesis.

2. The hearing prosthesis of claim 1 , wherein the one or more linguistic characteristics comprise a measure of speech produced by the recipient.

3. The hearing prosthesis of claim 2 , wherein the measure of speech produced by the recipient comprises a measure of quantity of speech by the recipient.

4. The hearing prosthesis of claim 2 , wherein the measure of speech produced by the recipient comprises at least one characteristic selected from the group consisting of:
a measure of proportion of time spent by the recipient speaking,
a measure of quantity of conversational turns by the recipient,
a measure of quantity of conversations initiated by the recipient,
a measure of quantity of phonetic features produced by the recipient, and
a measure of length of utterances by the recipient.

5. The hearing prosthesis of claim 1 , wherein the one or more linguistic characteristics comprise a measure of speech produced by one or more people other than the recipient.

6. The hearing prosthesis of claim 5 , wherein the measure of speech produced by one or more people other than the recipient comprises a measure of quantity of speech produced by the one or more people other than the recipient.

7. The hearing prosthesis of claim 1 , wherein the one or more linguistic characteristics comprise a measure of quantity of speech interaction between the recipient and one or more people other than the recipient.

8. The hearing prosthesis of claim 1 , wherein the one or more linguistic characteristics comprise a measure of speech quality.

9. The hearing prosthesis of claim 1 , wherein the linguistic characteristics comprise (i) a measure of quantity of speech by the recipient and (ii) a measure of quantity of speech by one or more people other than the recipient.

10. The hearing prosthesis of claim 1 , wherein the hearing prosthesis is configured to selectively operate in a stimulation-on mode in which the processing unit is configured to convert the audio inputs into stimulation signals for delivery to the physiological system of the recipient via the one or more stimulus outputs and a stimulation-off mode in which the processing unit does not convert the audio inputs into stimulation signals.

11. The hearing prosthesis of claim 10 , wherein the processing unit only generates the data representing the one or more linguistic characteristics when the hearing prosthesis is in the stimulation-on mode.

12. The hearing prosthesis of claim 10 , wherein to generate data representing the one or more determined linguistic characteristics, the processing unit is configured to:
log the one or more linguistic characteristics separately for (i) when the hearing prosthesis is in the stimulation-on mode and (ii) when the hearing prosthesis is in the stimulation-off mode.

13. The hearing prosthesis of claim 12 , wherein the data output by the hearing prosthesis associates the one or more linguistic characteristics with specified times when the hearing prosthesis was operating in the stimulation-on mode.

14. The hearing prosthesis of claim 10 , wherein to output the data from the hearing prosthesis, the processing unit is configured to:
output separate sets of data (i) corresponding with when the hearing prosthesis was in the stimulation-on mode and (ii) corresponding with when the hearing prosthesis was in the stimulation-off mode.

15. The hearing prosthesis of claim 10 , wherein the hearing prosthesis is switchable between the stimulation-on mode and the stimulation-off mode by the recipient.

16. The hearing prosthesis of claim 1 , wherein the hearing prosthesis comprises a hearing aid and wherein the one or more stimulus outputs comprise a receiver configured to output an amplified acoustic signal.

17. The hearing prosthesis of claim 1 , wherein the hearing prosthesis comprises a cochlear implant, and wherein the one or more stimulus outputs comprise one or more cochlear electrodes configured to deliver electrical stimulation signals to the recipient.

18. The hearing prosthesis of claim 1 , wherein the hearing prosthesis comprises a vibrationally-coupled hearing prosthesis configured to deliver vibrations to the recipient in accordance with the audio inputs.

19. The hearing prosthesis of claim 1 , wherein the processing unit is configured to:
determine the one or more linguistic characteristics of the audio environment, generate the data representing the one or more linguistic characteristics, and output the data in real-time as the hearing prosthesis receives the audio input.

20. The hearing prosthesis of claim 1 , wherein the processing unit is configured to output the data from the hearing prosthesis to a computing system for presentation to a user.

21. The hearing prosthesis of claim 1 , wherein the hearing prosthesis receives a plurality of audio inputs, and wherein the processing unit is configured to:
record times when one or more of the plurality of audio inputs causes the hearing prosthesis to stimulate the physiological system of the recipient;
use the recorded times to determine a selected one or more of the plurality of audio inputs that caused the hearing prosthesis to stimulate a physiological system of the recipient; and
determine the linguistic characteristics based only the one or more of the plurality of audio inputs.

22. The hearing prosthesis of claim 1 , further comprising:
a plurality of microphones configured to receive the audio inputs, and wherein the processing unit is configured to:
determine based at least in part on audio inputs received by the plurality of microphones whether the audio inputs represent speech by the recipient or rather represent speech by a person other than the recipient.

Assignees

• Cochlear Ltd

Inventors

• Banna Rami
• Case Alexander
• Hubert-Brierre Florent
• Kendrick Andrew

Classifications

• H04R25/606

  acting directly on the eardrum, the ossicles or the skull, e.g. mastoid, tooth, maxillary or mandibular bone, or mechanically stimulating the cochlea, e.g. at the oval window · CPC title

• H04R25/407

  Circuits for combining signals of a plurality of transducers · CPC title

• A61N1/36038 Primary

  Cochlear stimulation · CPC title