Hearing device adjustment based on categorical perception

1. A computer-implemented method for tuning a hearing device, the method comprising:

synthesizing, using a computing device, at least a first speech stimulus and a second speech stimulus, the first speech stimulus and the second speech stimulus being selected so as to fall in different phonemic categories on either side of an expected categorical perception breakpoint;

presenting, using a hearing device, the first speech stimulus and the second speech stimulus to a listener;

receiving, using a user interface, a response from the listener for the first speech stimulus and the second speech stimulus indicating whether the first speech stimulus and the second speech stimulus are perceived to be the same or different from each other, wherein an indication of difference indicates at least one characteristic of a listener's categorical perception;

comparing, using the computing device, the at least one characteristic of the listener's categorical perception against at least one characteristic of the expected categorical breakpoint;

applying, by the computing device, at least one algorithm selected from the group consisting of regression, constraint-based reasoning, graph theory, and ensemble learning to a result of the comparison of the at least one characteristic of the listener's categorical perception against the at least one characteristic of the expected categorical breakpoint to generate at least one parameter for adjusting the hearing device; and

adjusting, using the computing device, a hearing device based on the at least one generated parameter.

2. The method of claim 1 wherein the first speech stimulus and second speech stimulus are selected from the group consisting of stimuli that vary in: the time domain, the frequency-domain, voice onset time, spectral center of gravity, stop burst frequency, spectral slope, duration, rise time, spectrum moments, fall time, signal-to-noise ratio, spectral characteristics, waveform characteristics, and parameters derived from any of the foregoing.

3. The method of claim 1 further comprising:

synthesizing at least a third speech stimulus and a fourth speech stimulus upon the computing device receiving a response indicating the first speech stimulus and the second speech stimulus are perceived to be different, and

presenting the third speech stimulus and the fourth speech stimulus using the hearing device.

4. The method of claim 1 wherein synthesizing at least the first speech stimulus and the second speech stimulus includes leveraging at least one of an audiogram, Fletcher index, hearing screening results, and user device volume.

5. The method of claim 1 wherein comparing the at least one characteristic of the listener's categorical perception against the at least one characteristic of the expected categorical breakpoint includes comparing a shift in frequency of the perceived categorical breakpoint and a shift in frequency of the expected categorical breakpoint.

6. The method of claim 1 further comprising assigning a weight to each of the at least one generated parameter for adjusting the hearing device.

7. The method of claim 6 wherein the weight is based on at least one of the user's age and the user's primary language.

8. The method of claim 6 further comprising synthesizing at least a third speech stimulus and a fourth speech stimulus.

9. The method of claim 1 further comprising repeating the steps of:

synthesizing the first speech stimulus and the second speech stimulus,

presenting the first speech stimulus and the second speech stimulus,

receiving a response for the first speech stimulus and the second speech stimulus,

comparing the at least one characteristic of the listener's categorical perception against at least one characteristic of the expected categorical breakpoint,

generating the at least one parameter until at least one predetermined criteria is achieved; and

adjusting, using the computing device, the hearing device based on the at least one generated parameter.

10. The method of claim 9 wherein the predetermined criteria includes at least one of a listener performance metric, a temporal duration metric for completing a categorical perception test, and a number of stimuli tested.

11. The method of claim 1 wherein the at least one characteristic of the listener's categorical perception relates to a slope associated with multiple detected categorical perception judgments.

12. The method of claim 1 wherein the at least one characteristic of the listener's categorical perception relates to a mid-point between multiple detected categorical perception judgments.