Hearing aids and methods and apparatus for audio fitting thereof

• US 9,049,529 B2
• Filed: 12/31/2009
• Issued: 06/02/2015
• Est. Priority Date: 11/15/2001
• Status: Active Grant

• Current Assignee: Starkey Laboratories Incorporated
• Original Assignee: Starkey Laboratories Incorporated
• Inventors: Durant, Eric A.
• Primary Examiner(s): Paul, Disler
• Application Number:
  US12/651,154
• Publication Number:
  US 20100172524A1
• Time in Patent Office: 1,979 Days
• Field of Search: 381/323, 381/312, 381/314, 381/60, 600/559, 706/13
• US Class Current: 1/1
• CPC Class Codes: G06N 3/126 Evolutionary algorithms, e.g. genetic algorithms or genetic programming
• CPC Class Codes: H04R 25/505 using digital signal processing
• CPC Class Codes: H04R 25/70 Adaptation of deaf aid to hearing loss, e.g. initial electronic fitting

Abstract

A field ready, unsupervised-use ready, method and apparatus for audio fitting a hearing aid is described in a hand held configuration having paired comparisons (hearing selections) stored in and derivable from a memory therein. The paired comparisons are presented one at a time to a user and a preferred selection for each paired comparison is made by a select indicator after the user toggles back and forth between the selections for as many times necessary in determining their preferences. A genetic algorithm converges all the preferences upon a single solution. Crossover and mutation genetic algorithm operators operate on a linear range of indexes representative of parametric values of the pairs. A fully integrated hearing aid having all the above described features incorporated therein is also presented.

Claims

1. A method of audio fitting a hearing aid for a user using a genetic algorithm mutation operator on at least one parent set in a system population, the one parent set having a plurality of parent parameters, each the parent parameter being represented by a parent index, the method comprising:

arranging the parent indexes in a range from a low the parent index to a high the parent index using input received from the user based on a paired comparison between parent sets;

creating a mutation set having a plurality of mutation indexes;

summing the mutation indexes and the parent indexes to form a summation set having a plurality of summation indexes; and

fitting the hearing aid at least in part by reproducing at least one of the plurality of summation indexes in a child set.

2. The method according to claim 1, wherein one of the summation indexes is one of larger than the high parent index and smaller than the low parent index, wherein reproducing the summation indexes in the child set further comprises rounding the one of the summation indexes to one of the high parent index and the low parent index.

3. The method according to claim 1, wherein creating the mutation set further comprises generating the mutation indexes by generating a plurality of random variables and rounding each the random variable to a closest integer.

4. The method according to claim 3, wherein generating the plurality of random variables further comprises creating a normal distribution for the random variables.

5. The method of claim 1, wherein using a genetic algorithm mutation operator includes using the operator that does not operate directly on a parameter value.

6. The method of claim 1, wherein using a genetic algorithm mutation operator includes using the operator as part of a genetic algorithm to converge user preferences upon a single solution.

7. The method of claim 1, wherein using a genetic algorithm mutation operator includes using the operator for tuning a hearing aid.

8. The method of claim 1, wherein the range is linear.

9. A non-transitory computer readable medium having executable instructions for performing the steps of claim 1.

10. The computer readable medium of claim 9, wherein the medium includes at least one of a ROM, RAM, EEPROM, CD or other optical storage device, or floppy disk or other magnetic disk storage device.

11. The computer readable medium of claim 9, wherein the medium is included in a hearing aid.

12. A method of using a genetic algorithm operator on at least one parent set in a system population, the one parent set having a plurality of parent parameters, each parent parameter being represented by a parent index, the method comprising:

receiving an input from a user of a hearing aid, wherein the input includes a user selection from a paired comparison by the user between parent sets;

arranging the parent indexes in a linear range from a low parent index to a high parent index using the received input;

operating on the parent indexes, not on the parent parameters, with the genetic algorithm operator to obtain a child set, the child set having a child index position and at least one child parameter; and

tuning the hearing aid at least in part by using the operator as part of a genetic algorithm to converge user preferences upon a single solution using the child set and the at least one parent set.

13. The method of claim 12, further comprising replacing one of the plurality of parent sets of the system population with the child set to form a second population.

14. The method of claim 12, wherein the genetic algorithm operator includes a genetic crossover operator.

15. The method of claim 12, wherein the genetic algorithm operator includes a genetic mutation operator.

16. The method of claim 12, wherein using a genetic algorithm operator includes using the operator for tuning a parameter of the hearing aid.

17. The method of claim 16, wherein using the operator for tuning a parameter of the hearing aid includes tuning gain of the hearing aid.

18. The method of claim 16, wherein using the operator for tuning a parameter of the hearing aid includes tuning compression ratio of the hearing aid.

19. The method of claim 16, wherein using the operator for tuning a parameter of the hearing aid includes tuning noise reduction of the hearing aid.

20. The method of claim 16, wherein using the operator for tuning a parameter of the hearing aid includes tuning feedback cancellation of the hearing aid.

21. A method of audio fitting a hearing aid using a genetic algorithm mutation operator on at least one parent set in a system population, the one parent set having a plurality of parent parameters, each the parent parameter being represented by a parent index wherein the parent indexes can be arranged in a range from a low the parent index to a high the parent index, comprising:

creating a mutation set having a plurality of mutation indexes;

summing the mutation indexes and the parent indexes to form a summation set having a plurality of summation indexes; and

fitting the hearing aid at least in part by reproducing the summation indexes in a child set,

wherein one of the summation indexes is one of larger than the high parent index and smaller than the low parent index, wherein forming the summation indexes include rounding the one of the summation indexes to one of the high parent index and the low parent index.