System and methods of subject classification based on assessed hearing capabilities

• US 9,319,812 B2
• Filed: 08/29/2008
• Issued: 04/19/2016
• Est. Priority Date: 08/29/2008
• Status: Active Grant

• Current Assignee: Cochlear Limited, University of Florida Research Foundation, Incorporated (State University System of Florida)
• Original Assignee: University of Florida Research Foundation, Incorporated (State University System of Florida)
• Inventors: Banerjee, Bonny, Krause, Lee Stanley, Holmes, Alice, Shrivastav, Rahul
• Primary Examiner(s): Cohen, Lee S
• Assistant Examiner(s): LLOYD, EMILY M
• Application Number:
  US12/201,598
• Publication Number:
  US 20100056951A1
• Time in Patent Office: 2,790 Days
• Field of Search: 735/85, 381/329, 381/60, 600/559
• US Class Current: 1/1
• CPC Class Codes: A61B 5/121 evaluating hearing capacity
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: H04R 2225/43 Signal processing in hearing aids to enhance the speech intelligibility
• CPC Class Codes: H04R 2225/55 Communication between hearing aids and external devices via a network for data exchange
• CPC Class Codes: H04R 25/70 Adaptation of deaf aid to hearing loss, e.g. initial electronic fitting

Abstract

A method of assessing hearing characteristics of a subject is provided. The method includes determining a hearing capability of the subject based on responses of the subject to a series of sounds presented to the subject. Each sound corresponds to a presence, absence or irrelevance of a predetermined plurality of features. The method further includes assigning the subject to one of a predetermined plurality of classes based upon the responses of the subject, each of the plurality of classes being derived from hearing tests performed on a plurality of other subjects.

Claims

1. A computer implemented method of assessing hearing characteristics of a person, the method comprising:

providing, by a processor, a series of sounds to an interface configured to present the series of sounds to a person, wherein different sounds in the series of sounds corresponding to at least one of a presence, absence or irrelevance of a predetermined plurality of consonant features, wherein the predetermined plurality of consonant features comprises at least a Nasal feature, a Compact feature, and a Grave feature;

determining, by the processor, a hearing capability of the person based on responses of the person to the series of sounds; and

assigning, by the processor, the person to one of a predetermined plurality of classes based upon the responses of the person, each of the plurality of classes describing errors made primarily with respect to the Nasal, Compact, and Grave consonant features.

2. The method of claim 1, further comprising setting, by the processor, one or more parameter values of a hearing-enhancement device based on the class to which the person is assigned.

3. The method of claim 1, wherein determining the hearing capability comprises identifying one or more of the predetermined plurality of consonant features as contributing more than other consonant features of the predetermined plurality of consonant features to one or more failures to correctly respond to one or more sounds of the series of sounds.

4. The method of claim 3, wherein the one or more failures to correctly respond to the one or more sounds of the series of sounds defines one or more feature errors made with respect to the one or more features corresponding to the one or more sounds of the series of sounds, and further comprising generating a performance measure for the person based upon a computed mean of the one or more feature errors.

5. The method of claim 4, wherein the computed mean of the one or more feature errors equals a weighted mean, and further comprising computing the weighted mean, ξ

, to be equal to

6. The method of claim 5, wherein the assigning the person to one of the predetermined plurality of classes comprises computing a weighted contribution of each feature, the weighted contribution of a feature quantitatively measuring the contribution that each feature makes to the computed mean of feature errors.

7. The method of claim 6, wherein computing the weighted contribution of each feature comprises computing a value equal to

8. The method of claim 1, wherein the plurality of classes describe the errors made by the assigned persons with respect to Nasal, Compact, and Grave consonant features and no other consonant features.

9. A system for tuning a hearing-enhancement device, the system comprising:

an interface for rendering a series of sounds to a person and for receiving from the person a response to each of the sounds rendered, different sounds of the series of sounds correspond to one or more features belonging to a predetermined plurality of consonant features, wherein the plurality of consonant features comprises at last a Nasal feature, a Compact feature, and a Grave feature; and

a processing unit communicatively linked to said interface, the processing unit configured to;

determine a hearing capability of the person based on the received responses of the person to the series of sounds rendered,

assign the person to one of a predetermined plurality of classes based upon received responses, each of the plurality of classes describing errors made by the person primarily with respect to the Nasal, Compact, and Grave consonant features, and

set one or more parameters of the hearing-enhancement device based on the class to which the person is assigned.

10. The system of claim 9, wherein determining the hearing capability of the person comprises identifying one or more of the predetermined plurality of consonant features as contributing more than other of the predetermined plurality of consonant features to one or more failures of the person to correctly respond to one or more sounds of the series of sounds.

11. The system of claim 10, wherein the one or more failures to correctly respond to the one or more sounds of the series of sounds defines one or more feature errors made with respect to the one or more features corresponding to the one or more sounds of the series of sounds, and wherein the processing unit is further configured to measure a hearing performance of the person based on a computed mean of the one or more feature errors.

12. The system of claim 11, wherein the computed mean of the one or more feature errors equals a weighted mean, and wherein the processing unit is further configured to compute the weighted mean, ξ

, to be equal to

13. The system of claim 12, wherein the processing unit is further configured to assign the person to one of the predetermined plurality of classes by computing a weighted contribution of each feature, the weighted contribution of a feature quantitatively measuring the contribution that each feature makes to the computed mean of feature errors.

14. The system of claim 13, wherein the processing unit is further configured to compute the weighted contribution of each feature by determining a value equal to

15. The system of claim 9, wherein the plurality of classes describe the errors made by the assigned persons with respect to Nasal, Compact, and Grave consonant features and no other consonant features.

16. A non-transitory computer-readable storage medium in which computer-readable instructions are embedded, the computer-readable instructions, when executed by a processing unit, cause the processing unit to perform a method comprising:

providing, a series of sounds to an interface configured to present the series of sounds to a person, wherein different sounds in the series of sounds correspond to at least one of a presence, absence or irrelevance of a predetermined plurality of consonant features, wherein the predetermined plurality of consonant features comprises at least a Nasal feature, a Compact feature, and a Grave feature;

determining a hearing capability of the person based on responses of the person to the series of sounds; and

assigning the person to one of a predetermined plurality of classes based on the person'"'"'s responses, each of the plurality of classes describing errors made by the person primarily with respect to the Nasal, Compact, and Grave consonant features.

17. The non-transitory computer-readable storage medium of claim 16, wherein the method further comprises setting one or more parameter values of a hearing-enhancement device based upon the class to which the person is assigned.

18. The non-transitory computer-readable storage medium of claim 16, wherein determining the hearing capability comprises identifying one or more of the predetermined plurality of consonant features as contributing more than other of the predetermined plurality of consonant features to one or more failures to correctly respond to one or more sounds of the series of sounds.

19. The non-transitory computer-readable storage medium of claim 18, wherein the one or more failures to correctly respond to the one or more sounds of the series of sounds identifies one or more feature errors made with respect to the one or more features corresponding to the one or more sounds of the series of sounds, and wherein the method comprises measuring a hearing performance of the person based on a computed mean of feature errors.

20. The non-transitory computer-readable storage medium of claim 19, wherein the computed mean of the one or more feature errors equals a weighted mean, and further comprising computing the weighted mean, ξ

, to be equal to

21. The non-transitory computer-readable storage medium of claim 20, wherein assigning the person to one of the predetermined plurality of classes comprises computing a weighted contribution of each feature, the weighted contribution of each feature quantitatively measuring the contribution that each feature makes to the computed mean of feature errors.

22. The non-transitory computer-readable storage medium of claim 21, wherein computing the weighted contribution of each feature comprises computing a value equal to

23. The non-transitory computer-readable storage medium of claim 16, wherein the plurality of classes describe the errors made by the assigned persons with respect to Nasal, Compact, and Grave consonant features and no other consonant features.