Hearing aids and methods and apparatus for audio fitting thereof

• US 7,650,004 B2
• Filed: 01/16/2002
• Issued: 01/19/2010
• 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): Faulk; Devona E
• Application Number:
  US10/051,757
• Publication Number:
  US 20030133578A1
• Time in Patent Office: 2,925 Days
• Field of Search: 381/314, 381/323, 381/312, 381/60, 381/313, 381/324, 600/559, 706/13
• US Class Current: 381/312
• 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. An apparatus for fitting a hearing aid by its wearer, comprising:

a memory adapted to store a first population comprising a plurality of parent sets;

a toggle device adapted to toggle between a pair of the plurality of parent sets;

a select indicator for selecting a preferred one set of the pair;

a communications link adapted to connect with the hearing aid; and

a processor adapted to provide signals to the hearing aid to change operation of the hearing aid based on each parent set, to allow the wearer to select one preferred set for each pair of parent sets, to record a ranking of parent sets, assign probabilities of selection of parent sets, crossover and/or mutate at least one parent set, and replace weakest parent sets with a child set.

2. The apparatus according to claim 1, wherein the processor ranks a hierarchy of the plurality of parent sets. probability of selection by the select indicator to the sets of the plurality of pairs and the another pair.

3. The apparatus according to claim 2, wherein the processor assigns a probability of selection by the select indicator to the sets of the plurality of pairs and the another pair.

4. The apparatus according to claim 3, wherein the genetic algorithm decides which of the plurality of parent sets becomes the first and second sets for each the plurality of pairs.

5. A hearing aid fitted by the apparatus according to claim 1.

15. The apparatus of claim 1, wherein each parent set of the plurality of parent sets comprises more than one parameter.

16. The apparatus of claim 1, wherein the communications link is a wireless link.

17. The apparatus of claim 1, further comprising a flash memory for storing a hierarchy of the plurality of parent sets.

18. The apparatus of claim 1, wherein the toggle device toggles between a second pair of sets selected from the second population.

6. A method of fitting a hearing aid, comprising the steps:

preparing a first population of a plurality of parent sets;

presenting a first pair from the parent sets, the first pair comprising a first and second set and being presented with assistance of the hearing aid;

selecting a first preference between the first and second sets of the first pair;

operating on at least one set of the plurality of parent sets to obtain a child set, the child set being one of a mutation and crossover;

replacing one of the plurality of parent sets of the first population with the child set to form a second population;

presenting a second pair, the second pair comprising the child set and a third set, the third set being selected from the second population but not being the child set;

selecting a second preference between the child set and the third set of the second pair; and

converging on a solution set, the solution set being one of the first, second, third and child sets.

7. The method according to claim 6, further comprising the step of ranking a hierarchy of the plurality of parent sets.

8. The method according to claim 6, further comprising the step of assigning a probability of selection in one of the selecting steps to the first, second, third and child sets.

9. The method according to claim 6, further comprising the step of deciding which set of the plurality of parent sets becomes the first and second sets of the first pair.

10. A method of fitting a hearing aid, comprising the steps:

providing a hearing aid having an initial prescription;

preparing a population of a plurality of parent sets, each of the parent sets having at least one parent parameter;

presenting a first pair of sets from the parent sets, the first pair comprising a first and second set and being presented with assistance of the hearing aid;

selecting a first preference between the first and second sets of the first pair;

presenting a second pair of sets from the parent sets, the second pair comprising a third and fourth set;

selecting a second preference between the third and fourth sets of the second pair;

operating on one set of the plurality of parent sets to obtain a child set, the child set being one of a mutation and crossover of the one set, the child set having at least one child parameter;

replacing one of the plurality of parent sets of the first population with the child set to form a second population;

presenting a third pair of sets, the third pair comprising the child set and a fifth set, the fifth set being selected from the second population but not being the child set;

selecting a third preference between the child set and the fifth set;

converging on a solution set, the solution set being one of the first, second, third, fourth, fifth and child sets; and

updating the initial prescription with one of the at least one parent and child parameters.

19. The method according to claim 10, further comprising the step of ranking a hierarchy of the plurality of parent sets.

20. A computer readable medium having executable instructions for performing the steps of claim 10.

11. A method of using a genetic algorithm in a hearing aid, having a first population of a plurality of parent sets, comprising the steps;

presenting a first pair of sets from the parent sets, the first pair comprising a first and second set, the genetic algorithm selecting which of the parent sets becomes the first and second set, the first paid being presented with assistance of the hearing aid;

indicating a preference to the genetic algorithm between the first and second sets of the first pair;

operating on at least one set of the plurality of parent sets with a genetic algorithm operator to obtain a child set, the child set being one of a mutation and crossover;

replacing one of the plurality of parent sets of the first population with the child set to form a second population;

presenting a second pair, the second pair comprising the child set and a third set, the third set being selected from the second population but not being the child set, the genetic algorithm selecting which set of the second population becomes the third set;

indicating a second preference to the genetic algorithm between the child set and the third set of the second pair; and

converging on a solution set, the solution set being one of the first, second, third and child sets.

12. A computer readable medium having executable instructions for performing the steps of claim 11.

13. A method of perceptually tuning a hearing aid using a genetic algorithm, comprising the steps:

providing a system an initial setting;

preparing a population of a plurality of parent sets, each of the parent sets having at least one parent parameter;

presenting a first pair of sets from the parent sets, the first pair comprising a first and second set, the genetic algorithm selecting which of the plurality of parent sets becomes the first and second set, the first paid being presented with assistance of the hearing aid;

indicating a first preference to the genetic algorithm between the first and second sets of the first pair;

presenting a second pair of sets from the parent sets, the second pair comprising a third and fourth set, the genetic algorithm selecting which of the plurality of parent sets becomes the third and fourth sets;

indicating a second preference to the genetic algorithm between the third and fourth sets of the second pair;

operating on one set of the plurality of parent sets with a genetic algorithm operator to obtain a child set, the child set being one of a mutation and crossover of the one set, the child set having at least one child parameter;

replacing one of the plurality of parent sets of the first population with the child set to form a second population;

presenting a third pair of sets, the third pair comprising the child set and a fifth set, the fifth set being selected from the second population but not being the child set, the genetic algorithm selecting which set of the second population becomes the fifth set;

indicating a third preference to the genetic algorithm between the child set and the fifth set;

converging on a solution set, the solution set being one of the first, second, third, fourth, fifth and child sets; and

updating the initial setting with one of the at least one parent and child parameters selected from the solution set.

14. A computer readable medium having executable instructions for performing the steps of claim 13.