JP2001238294A - Optimal solution determination method and hearing aid fitting device using the same - Google Patents

Abstract

(57) [Summary] [Problem] To propose an optimal solution determination method for efficiently and quickly determining a final optimal value reflecting user's preference from optimal values corresponding to a plurality of conditions. . SOLUTION: Based on a plurality of optimal n-dimensional solution vector candidates, a solution vector obtained by an optimal solution determining method for determining one optimal n-dimensional solution vector is converted into an adjustment parameter value of the programmable hearing aid 4, and the programmable hearing aid is converted. 4, a parameter writing unit 2c for writing to the hearing aid parameter storage unit 5, a sound source storage unit 1a for storing a sound source, and a sound source presentation unit 1d for presenting the sound source to the programmable hearing aid 4.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a quantitative evaluation criterion because the evaluation criterion is subjective and unclear, including adjustment of acoustic characteristics and image characteristics according to personal preferences. The present invention relates to an optimum solution determining method for obtaining an optimum adjustment result based on an optimum value under a plurality of conditions and a subjective evaluation of an individual with respect to a problem that cannot be adjusted based on the condition, and a hearing aid fitting device using the same.

[0002]

2. Description of the Related Art When adjusting acoustic characteristics, image characteristics, and the like in accordance with personal preferences, the evaluation criteria for the characteristics are extremely subjective and unclear. There is a problem that the adjustment result cannot be quantitatively evaluated and expressed because the tendency of the preference for each characteristic greatly differs from user to user in many cases. In addition, usually, there are a plurality of parameters for adjusting the target acoustic characteristics and image characteristics, and the interaction of these parameter values greatly affects the subjective evaluation of the user. It is more difficult to determine a suitable adjustment result.

In order to solve such a problem, for example, Japanese Patent Application Laid-Open No. 9-54765 proposes an optimization adjustment method using an interactive genetic algorithm. In this method, an n-dimensional vector having n adjustment parameters as elements is used as a solution vector (chromosome), and a sound signal or an image signal processed according to each solution vector is presented to a user. A genetic algorithm is implemented based on the user's evaluation value to estimate an optimal solution vector. According to such a method, the characteristic that the user himself / herself perceives to be the most audible is calculated not only by individually calculating the optimum value of each adjustment value but also by considering the interaction between the adjustment values. Can be calculated.

Further, a method for determining an optimal image for a certain problem has been proposed (SIGGRAPH Conf. Pro).
c., Vol.1997, pp389-400,1997). This is an n-dimensional solution vector (n>) having the characteristic adjustment value of the target image as an element.
2), each solution vector is mapped on a two-dimensional space and shown to the user, and when the user specifies an arbitrary coordinate in the two-dimensional space, the solution vector corresponding to the coordinate is set as an adjustment value. This is a system where images are presented to the user. In this method, each solution vector is converted to a Multidimensional Sca (MDS) based on the Euclidean distance between the vectors.
The optimal value can be determined while mapping to a two-dimensional space using a ling) method or the like, and allowing the user to image the distance in the multi-dimensional space on the two-dimensional space.

[0005] As an example of the problem to be determined in the present invention for determining acoustic characteristics, image characteristics, and the like according to personal preferences, fitting of a hearing aid can be considered. The hearing characteristics of a hearing-impaired person vary from person to person, and the taste for sound also differs from person to person. Many hearing aids have multiple adjustment functions (eg, volume adjustment, frequency response adjustment, output limit adjustment,
Automatic gain control adjustment).

[0006] Hearing aid fitting is the work of setting the degree of adjustment (adjustment value) of each of these adjustment functions to an optimum value for each individual with hearing impairment. Usually, a value such as an audiogram or the like is set to a known formula for fitting. Is performed by substituting into Japanese Patent Application Laid-Open No. 9-54765 proposes a method of constructing the n-dimensional solution vector using the adjustment values of the respective adjustment functions and performing fitting of the hearing aid using an interactive genetic algorithm.

[0007]

However, in the above-mentioned interactive genetic algorithm, since a single optimal value is determined for a single condition for a certain problem, the condition
That is, there is a problem that an optimum value specialized for the condition used for the adjustment is determined. For this reason, in a problem in which a plurality of conditions may exist, an interactive genetic algorithm is performed on each condition to determine an optimal value specific to each condition, and then a final single optimal The value has to be determined separately, and this final optimum value has been determined by a subjective evaluation of the coordinator or a calculation formula determined independently of individual user's preference.

For example, in the case of the hearing aid fitting, if any single sound source (for example, an audio signal) is used to execute the interactive genetic algorithm, an optimum value specific to the sound source is determined. There is a problem.

A hearing aid is a device used in various environments, and it is necessary to provide a comfortable listening state to a hearing-impaired person in any environment. , A plurality of environmental sounds), it is necessary to determine the final optimum value after determining the optimum value for each condition by executing the interactive genetic algorithm. However, there is a problem that this final optimum value must be determined by a subjective evaluation of the coordinator or a calculation formula determined without regard to individual user's preference.

In the above method of mapping a multidimensional solution vector to a two-dimensional space and allowing a user to determine an optimum value, if the number of dimensions of the solution vector and / or the number of bits of a component (gene) of the solution vector is large, Second, there is a problem in that the number of optimal solution vector candidates illustrated in a two-dimensional space increases, the time required for determining the optimal solution becomes extremely long, and the burden on the user increases.

[0011] For example, when the method of mapping the multi-dimensional solution vector into a two-dimensional space and determining the optimum value by the user is performed in the hearing aid fitting, the number of adjustment functions of the hearing aid and / or the adjustment value of each adjustment function is adjusted. Depending on the number of bits, the number of optimal solution vector candidates illustrated for a hearing-impaired person becomes enormous, the time required for fitting becomes extremely long, and the burden on the hearing-impaired user increases.

SUMMARY OF THE INVENTION The present invention has been made in view of the above-mentioned problems of the prior art, and an object of the present invention is to reflect user's preference from optimal values corresponding to a plurality of conditions. An object of the present invention is to propose an optimum solution determining method for efficiently determining a final optimum value in a short time and a hearing aid fitting device using the same.

[0013]

According to a first aspect of the present invention, there is provided an apparatus for determining one optimal n-dimensional solution vector based on optimal n-dimensional solution vector candidates corresponding to a plurality of conditions. For the problem, the optimal n
A first step in which the positions of the two-dimensional solution vector candidates are illustrated in a two-dimensional space, a second step in which a user selects arbitrary coordinates in the two-dimensional space, and a two-dimensional space of the plurality of n-dimensional solution vector candidates Coordinates above and multiple n obtained in advance
A third step of calculating an n-dimensional solution vector corresponding to an arbitrary coordinate selected by the user based on the evaluation value of the user with respect to the two-dimensional solution vector; This is to determine one optimal n-dimensional solution vector.

According to a second aspect of the present invention, in the optimal solution determining method according to the first aspect, user evaluation values for the plurality of n-dimensional solution vectors are obtained by an interactive genetic algorithm.

According to a third aspect of the present invention, in the optimal solution determining method according to the first or second aspect, the n-dimensional solution vector is used as an adjustment parameter of a hearing aid.

According to a fourth aspect of the present invention, in the optimal solution determining method according to the first or second aspect, the n-dimensional solution vector is used as an image adjustment parameter.

According to a fifth aspect of the present invention, in the optimal solution determining method according to the first, second or third aspect, the plurality of optimal n-dimensional solution vector candidates are set as optimal n-dimensional solution vectors for a plurality of sound sources. is there.

The invention according to claim 6 is the invention according to claims 1, 2, 3
Or parameter writing means for converting an n-dimensional solution vector obtained by the optimal solution determination method into an adjustment parameter value of a hearing aid and writing the adjusted parameter value in a hearing aid parameter storage section of the hearing aid, sound source storage means for storing a sound source, and Is provided with a sound source presenting means for presenting to the user.

The invention according to claim 7 is the invention according to claims 1, 2, and 3
Or parameter writing means for converting an n-dimensional solution vector obtained by the optimal solution determination method into an adjustment parameter value of a hearing aid and writing the adjusted parameter value in a hearing aid parameter storage section of the hearing aid, sound source storage means for storing a sound source, and And a display means for displaying a visual figure based on the adjustment parameter values of the hearing aid and / or the acoustic information represented by the n-dimensional solution vector.

According to an eighth aspect of the present invention, in the hearing aid fitting device according to the seventh aspect, the visual figure is a frequency characteristic of the acoustic information.

According to a ninth aspect of the present invention, in the hearing aid fitting device according to the seventh aspect, the visual figure is an input / output characteristic of the acoustic information.

According to a tenth aspect of the present invention, in the hearing aid fitting device according to the seventh aspect, the visual figure is a time waveform of the acoustic information.

According to an eleventh aspect of the present invention, in the hearing aid fitting device according to the seventh aspect, the visual figure is a sound spectrogram of the acoustic information.

According to a twelfth aspect of the present invention, in the hearing aid fitting apparatus according to any one of the sixth to eleventh aspects, an n-dimensional solution vector corresponding to an arbitrary coordinate selected by a user is used as an adjustment parameter value of the hearing aid. The plurality of sound sources are converted and written into the hearing aid parameter storage unit of the hearing aid, and the plurality of sound sources are sequentially presented to the user.

[0025]

Embodiments of the present invention will be described below with reference to the accompanying drawings. Here, FIG. 1 is a configuration diagram of a hearing aid fitting apparatus according to the present invention, FIG. 2 is a flowchart for previously acquiring optimum values for three environmental sounds and evaluation values for a plurality of solution vectors, and FIG. 3 is shown in FIG. Flowchart for determining a single final optimal fitting value based on the results obtained by the method, FIG. 4 shows an example of a two-dimensional space used in the method shown in FIG. 3,
FIG. 5 is another flowchart for determining a single final optimal fitting value based on the results obtained by the method shown in FIG. 2, and FIG. 6 shows an example of a two-dimensional space used in the method shown in FIG. FIG.

As shown in FIG. 1, the hearing aid fitting device according to the present invention comprises a sound source processing unit 1, a parameter creation unit 2, and a two-dimensional space display unit 3. Reference numeral 4 denotes a so-called programmable hearing aid, and reference numeral 6 denotes a speaker that presents to the programmable hearing aid 4 the hearing-processed sound, environmental sound, and the like.

The sound source processing unit 1 includes a sound source storage unit 1a, a sound source signal conversion unit 1b, a sound source signal selection unit 1c, and a sound source presentation unit 1d. The parameter creation unit 2 includes a coordinate acquisition unit 2a, a solution vector calculation unit 2b, From the writing unit 2c, the two-dimensional space display unit 3 includes an optimal solution vector acquisition unit 3a, a two-dimensional coordinate calculation unit 3b, and a display unit 3c.

The programmable hearing aid 4 includes a microphone 4a, an amplifier 4b, a hearing aid processing unit 4c, an earphone 4d,
It comprises a parameter storage unit 5. Here, the parameter writing unit 2 c is connected to the parameter storage unit 5 of the programmable hearing aid 4.

The sound source storage unit 1a stores a plurality of environmental sound files in which environmental sounds used for fitting are digitally recorded and one calibration sound file. Here, the environmental sound and the calibration sound file are constituted by digital data in a WAVE file format, for example.

The sound source signal conversion unit 1b includes a sound source signal selection unit 1
In addition to having a function of calling an environmental sound file stored in the sound source storage unit 1a based on a control signal from the control unit c, a function of converting digital data stored in the environmental sound file into an analog environmental sound signal.

The sound source presentation unit 1d amplifies or attenuates the sound source signal (analog environmental sound signal) output from the sound source signal conversion unit 1b to a predetermined level, and presents the amplified sound signal to the programmable hearing aid 4 using the speaker 6 or the like. I do.

The coordinate acquisition unit 2a acquires arbitrary two-dimensional coordinates in the two-dimensional space displayed by the display unit 3c, selected by the user. The solution vector calculation unit 2b includes a coordinate acquisition unit 2a
Calculates an n-dimensional solution vector composed of the adjustment values of the respective adjustment functions of the hearing aid from the two-dimensional coordinates acquired by.

The parameter writing section 2c has a function of writing the solution vector calculated by the solution vector calculation section 2b into the parameter storage section 5 of the programmable hearing aid 4 as a parameter of the adjustment function of the programmable hearing aid 4.

The optimal solution vector acquiring unit 3a is a unit that determines a user's optimal fitting value for each environmental sound, that is, an optimal solution vector and a user's evaluation value for each optimal solution vector, and / or an arbitrary value, which is predetermined before the fitting by the present system. To obtain a plurality of solution vectors and their evaluation values.

The two-dimensional coordinate calculation unit 3b calculates the coordinates of the two-dimensional space shown to the user from the solution vector and the evaluation value obtained by the optimum solution vector obtaining unit 3a.

The display unit 3c displays the two-dimensional space to the user based on the coordinates of the two-dimensional space calculated by the two-dimensional coordinate calculation unit 3b, and displays the coordinates of the two-dimensional space calculated by the two-dimensional coordinate calculation unit 3b. Parameter values (eg, acoustic gain: GAIN, output limitation: MOP, breakpoint of input / output characteristics: TK, etc.) and acoustic information (frequency characteristic diagram, input / output characteristic diagram, time waveform diagram, Sound spectrogram) can be displayed.

A sound source storage unit 1a, a sound source signal conversion unit 1b, a sound source signal selection unit 1c, a coordinate acquisition unit 2a, a solution vector calculation unit 2b, and a two-dimensional space Optimal solution vector acquisition section 3a, two-dimensional coordinate calculation section 3b, and display section 3c that constitute display section 3
Can be constituted by a personal computer.

That is, a built-in hard disk and / or memory of the personal computer has the function of the sound source storage unit 1a, and the CPU and a predetermined program include a sound source signal conversion unit 1b, a sound source signal selection unit 1c, a solution vector calculation unit 2b,
The keyboard and / or mouse function as the dimensional coordinate calculation unit 3b, and the coordinate acquisition unit 2a and the optimal solution vector acquisition unit 3a
, And the display performs the function of the display unit 3c.

The operation of the hearing aid fitting device according to the present invention configured as described above will be described with reference to the flowcharts shown in FIGS. In FIG. 2, first,
In step SP1, prior to the fitting, the sound source signal selection unit 1c is operated to call up a calibration sound file from the sound source storage unit 1a, and presented from the sound source presentation unit 1d, in order to calibrate the presentation sound pressure level when presenting the sound source. . Step SP
In step 2, the presented sound pressure level is calibrated by manipulating the amplification and attenuation of the sound source presentation unit 1d using a sound level meter or the like.

Next, in step SP3, the audiogram of the hearing-impaired person is measured, and in step SP4,
Using the measured audiogram, a tentative fitting value is calculated according to a known hearing aid fitting formula.

After initial setting (i = 1, k = 1) in steps SP5 and SP6, step SP7
In, the environmental sound file is called. As the environmental sound file to be used here, for example, "the environment in which the hearing aid is used most frequently" is previously heard from the subject, and a file that is considered to be closest to the environment is used. In the embodiment of the present invention, the environmental sound is the home noise S ₁ , the office noise S ₂ ,
Are three types of factory noise S _3.

Next, in step SP8, the fitting values composed of the adjustment values of the respective adjustment functions of the programmable hearing aid 4 are converted into solution vectors. Here, the solution vector set is represented by p _ik (i = 1, 2, 3,..., M, k = 1,
2,3..., N), and in the embodiment of the present invention, m =
3, n = 20.

Next, at step SP9, the solution vector p _ik specified by the parameter writing section 2c is converted into parameters of the programmable hearing aid 4, and at step SP10, the parameters are written to the parameter storage section 5 of the programmable hearing aid 4.

Next, in step SP11, the sound source signal conversion section 1b and the sound source presentation section 1d reproduce the environment sound file called out earlier and present it to the programmable hearing aid 4 through the speaker 6. The subject listens to the output sound of the programmable hearing aid 4 (that is, the environmental sound subjected to hearing aid processing according to the solution vector p _ik ).

In step SP12, the presented sound
In other words, to obtain an evaluation value E _ik of the subject to the solution vector p _ik at that time. The evaluation value E _ik is comfort for the presented sound,
It is a numerical value representing the subject's subjective evaluation based on clarity or the like. Here, five levels of 1 to 5 are set, 1 is the lowest evaluation, and 5 is the highest evaluation.

[0046] In step SP13, it is determined whether all of the evaluation values up E _i20 is acquired, the process proceeds to step SP14 if not acquired, repeat the above operation. Here, in step SP14, the subject's subjective evaluation of the current fitting value is heard, and the fitting value is adjusted or changed in consideration of the content and the evaluation value _Eik .

This adjustment and change can be made, for example, by "noisy".
If it is evaluated, the content is such that the values of volume adjustment and output restriction are reduced. On the other hand, if all the evaluation values up to E _i20 have been obtained, in step SP16, the solution vector p _ik that has obtained the highest evaluation value so far is set as the optimal fitting value F _i for the environmental sound.

[0048] Then, in step SP17, the operation determines whether or not made up factory noise S _3, if performed until factory noise S ₃ ends fitting work, if not carried out step SP18 for factory noise S ₃ of the above-mentioned operation proceed to repeat until the fitting operation is completed.

Next, was determined by the flow chart shown in FIG. 2, the evaluation value E _ik for optimum fitting values F _1, F _2, F ₃ and various fitting values for the 3 kinds of sound sources S _1, S _2, S ₃ The method used to determine the final fitting value is shown in the flowchart of FIG.

First, in step SP21, the optimum fitting values F ₁ , F ₂ , and F ₃ obtained by the method shown in FIG. 2 are obtained by the optimum solution vector obtaining section 3a, and the optimum fitting values F ₁ and F _{2 are obtained.} , it calculates the Euclidean distance d _12, d _13, d ₂₃ each between F _3.

At step SP22, a two-dimensional coordinate calculator
Euclidean distance d by 3b₁₂, D₁₃, D_{twenty three}On three sides
Assuming a triangle that has₁, F_Two,
F_ThreeCoordinate x in two-dimensional space₁, X_Two, X_ThreeIs calculated. This
Here, these coordinates x₁, X _Two, X_ThreeIs a triangle
E-click as shown in the appropriate size on the screen.
Distance d₁₂, D₁₃, D_{twenty three}To the Euclidean distance d₁₂,
d₁₃, D_{twenty three}While maintaining the ratio between
You may ask.

The Euclidean distances d ₁₂ , d ₁₃ , d ₂₃
Is a relation in which a triangle having three sides cannot be created (for example, d ₁₂ + d ₁₃ <d ₂₃ ), the coordinates x ₁ , x ₂ , x ₃ may be calculated. In this case, for example, the figure to be shown is not a triangle but a line segment, and a distance in a two-dimensional space between a coordinate x ₁ and a coordinate x ₂ connecting a coordinate x ₂ and a coordinate x ₃ and a coordinate x ₁ and a coordinate x X ₁ may be arranged at coordinates such that the ratio of the distances in the two-dimensional space ₃ is d ₁₂ : d ₁₃ , or the coordinates x ₂ on the line segment
Distance from may illustrate two points such as the distance from the coordinate x ₃ is a d ₁₃ as both coordinates x ₁ at d _12.

Next, at step SP23, the display unit 3
illustrating the position of the coordinates x _1, x _2, x ₃ on the screen at c. Here, FIG. 4 shows an example of the two-dimensional space illustrated on the screen.

In step SP24, the user designates an arbitrary position in the two-dimensional space with reference to the positions of the three vertices in the two-dimensional space shown in FIG. Then, the coordinate obtaining unit 2a obtains the coordinates x ₄ of the designated position on the two-dimensional space.
To win. For example, a user who uses the hearing aid at the office and the hearing aid mainly in the office and at home after returning home specifies the position as point A in FIG.

Next, in step SP25, the coordinates x ₁ ,
The distance d ₁₄ between x ₂ , x ₃ and the coordinate x ₄ in a two-dimensional space,
d ₂₄ and d ₃₄ are calculated, and in step SP26, the solution vector candidate P such that the ratio of the Euclidean distance to the optimum fitting values F ₁ , F ₂ and F ₃ is d ₁₄ : d ₂₄ : d ₃₄ respectively. _{Find h} .

Here, the ratio d of the Euclidean distance₁₄: D
_{twenty four}: D₃₄Contains (d₁₄+ A): (d _{twenty four}+ A): (d₃₄+
a) or (d)₁₄× a): (d_{twenty four}× a): (d₃₄×
An arbitrary width may be provided as in a). For example,
Solution vector candidate P_hIf you increase the number of h
d₁₄: D_{twenty four}: D₃₄As well as (d₁₄+
a): (d_{twenty four}+ A): (d₃₄+ A), a = −1.
P for three ratios of 0,0,1.0_hSolve all
Let it be a candidate for a vector. The number of h is the distance d₁₄, D_{Two Four},
d₃₄And the value of a and the adjustment value of each adjustment function (solution vector
The number of bits of each element).

[0057] Then, in step SP27, among the solution vector p _ik determined by the flow chart shown in FIG. 2, the solution vector p _ik (E _ik> 3 in this example) Evaluation was high, each solution vector candidate P _h To obtain a similarity Q _ikh .
Here, the similarity is an index representing the similarity of the solution vector P _h and p _ik, in this example, is the reciprocal of both Euclidean distance.

Next, at step SP28, the similarity Q
By multiplying the evaluation value E _ik in _Ikh, performs weighting by the evaluation of the user acquired in advance with respect to the calculated similarity, determining the solution vector candidate P _h where Q _ikh × E _ik is maximized.

Next, at step SP29, Q
converted to the parameters of the programmable hearing aid 4 by the parameter writing unit 2c of the solution vector candidate P _{h to Ikh} × E _ik is maximum as fitting value, step SP3
0, the parameter is set to the programmable hearing aid 4
Is written to the parameter storage unit 5.

Next, in steps SP31 and SP32, the sound source signal conversion section 1b and the sound source presentation section 1d use the environmental sound (home noise S ₁ ) corresponding to the optimum fitting value F _1.
Is reproduced and presented to the programmable hearing aid 4 from the speaker 6. Subject listens output sound of the programmable hearing aid 4 (i.e., the solution vector candidate P _h domestic noise S ₁ which is hearing aid processing in accordance with).

When the subject examines step SP32 to step S
In P35, the output sound of the programmable hearing aid 4 is set to 3
After finished hearing the type of environment sounds S _1, S _2, S ₃ all, in step SP36, if the subject is satisfied with the current fitting value P _h fitting ends, if not satisfied, returns to step SP24 To repeat the above operation.

[0062] In this case, any of the coordinate x ₄ is, for example, the user of the current fitting value P _h, if easy to hear at home in the noise S ₁ under but the feel and difficult to hear under the noise S ₂ office B is the location, such as a point, domestic noise S ₁ under, easy to listen to ₂ under both the noise S office, but as the point C if feel like to be able to listen a little more comfortable even under the noise S ₃ factory Place.

Next, was determined by the flow chart shown in FIG. 2, the evaluation value E _ik for optimum fitting values F _1, F _2, F ₃ and various fitting values for the 3 kinds of sound sources S _1, S _2, S ₃ Another method for determining the final fitting value will be described with reference to the flowchart shown in FIG.

First, steps SP41 to SP4
9 corresponds to step SP in the flowchart shown in FIG.
Since the contents are the same as the contents of 21 to SP29, the description is omitted.

[0065] Then, in step SP50, as shown in FIG. 6, the programmable hearing aid 4 corresponding to the coordinates x ₄ in the two-dimensional spatial adjustment parameters (e.g., acoustic gain:
GAIN = 5, output limitation: MOP = 3, breakpoint of input / output characteristics: TK = 2, etc.) and acoustic characteristic diagram (for example, frequency characteristic diagram for each input / output sound pressure level) are displayed on the screen of the display unit 3c. To be displayed.

As described above, on the screen of the display unit 3c,
By displaying an adjustment parameter value and the acoustic characteristics of the programmable hearing aid 4 view corresponding to the coordinate x ₄ in the two-dimensional space, even for the subject, since the visually grasp the adjustment degree of the hearing aid also for adjustment operator parameters ,
Optimal hearing aid adjustment parameter values can be set efficiently and accurately.

[0067] In FIG. 6, the visual graphic to be displayed on the screen of the display unit 3c, although the frequency characteristic caused by the solution vector P _h corresponding to x _4, in this case figure of the solution vector P _h A graphic based on the acoustic information to be represented may not be a frequency characteristic. For example, if the hearing aid is of a type that can change the input / output characteristics of sound (so-called AGC hearing aid or non-linear hearing aid), the input / output characteristics may be represented as a visual figure.

Further, the graphic displayed on the screen of the display unit 3c is displayed when a specific sound signal is input to the hearing aid.
The time waveform of the output sound of the hearing aid may be used. As the input sound in this case, a sound source used in the genetic algorithm may be used, or another sound signal may be used.

The graphic displayed on the screen of the display unit 3c is displayed when a specific sound signal is input to the hearing aid.
It may be a sound spectrogram of the output sound of the hearing aid. As the input sound in this case, a sound source used in the genetic algorithm may be used, or another sound signal may be used.

Further, steps SP51 to SP5
7 are the contents of step SP in the flowchart shown in FIG.
The description is omitted because it is the same as the contents of step 30 to step SP36.

In the embodiment of the present invention, fitting is performed using three types of environmental sounds S ₁ , S ₂ , and S ₃ , but the fitting may be performed using two or more types of environmental sounds. good.

In the embodiment of the present invention, the position of each multidimensional vector is illustrated in a two-dimensional space using the ratio of the Euclidean distance between the multidimensional vectors.
It may be illustrated on a two-dimensional space using the DS method or the self-organizing mapping technique.

In the embodiment of the present invention, the similarity Q
The _ikh, but are asking only for the solution vector p _ik of E _ik> 3, the conditions of the solution vector p _ik may be a condition other than the E _ik> 3, the similarity for all of the solution vector p _ik without the conditions _You may ask for Q _ikh . In addition, candidates for the solution vector to determine the similarity Q _Ikh need not be limited to p _ik, for example, may each solution vector p _ik and Euclidean distance for all of the solution vector p _ik close as solution vector candidate P _h.

In the embodiment of the present invention, the similarity Q
Although simply as the reciprocal of the Euclidean distance of the solution vector p _ik the solution vector candidate P _h a _Ikh, the similarity may be any index that can represent the similarity of the two vectors, for example, elements of the solution vector p _ik May be a reciprocal of the Euclidean distance after a specific weighting is performed.

In the above-described embodiment of the present invention, the method for obtaining the optimum fitting values for various sound sources and the evaluation values for various fitting values by using the flowchart shown in FIG. 2 has been described. However, acquisition of these values may be performed using an interactive genetic algorithm.

In the interactive genetic algorithm, an optimum value specific to a sound source is obtained, and in addition, evaluation values for various solution vectors are obtained in the process of determining the optimum value. The method can be used as it is.

In other words, the interactive genetic algorithm is performed in which the sound sources are domestic noise S ₁ , office noise S ₂ , and factory noise S _3, and the optimal solution vectors F ₁ , F ₂ , F ₃ for each sound source are executed. And at the same time, _pik multiple solution vectors obtained during the evolution of the interactive genetic algorithm.
Then, the present invention is implemented with the evaluation value for these as _Eik .

In the embodiment of the present invention, only the hearing aid fitting is described. However, the application of the system optimizing method is not limited to the hearing aid fitting. For example, the visual acuity using eyeglasses, contact lenses, or the like is used. The evaluation criteria are subjective and unclear, and quantitative evaluation, including adjustment of acoustic and image characteristics according to personal preferences, such as correction and design of products such as interiors that match personal preferences. The present invention can be applied to any problem that cannot be adjusted based on a criterion, and in which an optimal value and a subjective evaluation of an individual under a plurality of conditions can be obtained in advance.

Further, although the embodiment of the present invention is described only with respect to the hearing aid fitting, the present optimum solution method can also be used to create an image according to the user's preference. In this case, for example, when the resolution and brightness of the target image are set to different values for each coordinate on the screen to perform optimal image adjustment, the resolution and brightness of each coordinate are used as an element. The present invention can be implemented by creating a solution vector as follows.

[0080]

As described above, according to the first aspect of the present invention, the evaluation criterion is not an optimal value specialized for a specific condition but a plurality of evaluation criteria for an unclear problem. It is possible to efficiently and accurately obtain a single optimum value in consideration of the conditions while reflecting the user's preference.

According to the second aspect of the present invention, the optimum value for a plurality of conditions and the evaluation value for a plurality of solution vectors can be obtained efficiently and accurately, so that a single optimum value considering a plurality of conditions is obtained. The value can be determined more efficiently and accurately.

According to the third aspect of the present invention, it is possible to perform a hearing aid fitting that reflects the individual's preference for sound of a hearing-impaired user.

According to the fourth aspect of the present invention, it is possible to obtain an optimum single image adjustment value while reflecting an individual user's preference for an image.

According to the fifth aspect of the present invention, by providing a plurality of environmental sounds as sound sources to be presented, it is possible to perform fitting suitable for various sound environments instead of fitting specific to a specific sound environment. it can.

According to the sixth aspect of the present invention, it is possible to perform hearing aid fitting suitable for various sound environments by reflecting the individual's preference for sound for the hearing-impaired user.

According to the seventh aspect of the present invention, the hearing aid fitting suitable for various sound environments is reflected by reflecting the taste of the individual hearing-impaired user to the sound, and the adjustment parameter value of the hearing aid displayed on the display means and / or This can be performed while referring to a visual figure based on acoustic information.

According to the eighth aspect of the present invention, since the frequency characteristic of the acoustic information is given as a visual figure, the evaluation value given by the user to the past solution vector can be easily stored. The optimum solution can be obtained efficiently and accurately with the evaluation fluctuation kept to a minimum.

According to the ninth aspect of the present invention, since the input / output characteristic of acoustic information is given as a visual figure, the evaluation value given by the user to the past solution vector can be easily stored. In addition, the fluctuation of the evaluation can be minimized, and the optimum solution can be obtained efficiently and accurately.

According to the tenth aspect of the present invention, since the time waveform of the acoustic information is given as the visual figure, the evaluation value given by the user to the past solution vector can be easily stored. The optimum solution can be obtained efficiently and accurately with the evaluation fluctuation kept to a minimum.

According to the eleventh aspect of the present invention, since the sound spectrogram of the acoustic information is given as a visual figure, the evaluation value given by the user to the past solution vector can be easily stored. The optimum solution can be obtained efficiently and accurately with the evaluation fluctuation kept to a minimum.

According to the twelfth aspect, each hearing-impaired user can determine the optimal fitting value while checking the hearing aid effect of the fitting value selected by himself / herself in various sound environments.

[Brief description of the drawings]

FIG. 1 is a configuration diagram of a hearing aid fitting device according to the present invention.

FIG. 2 is a flowchart for obtaining in advance optimal values for three environmental sounds and evaluation values for a plurality of solution vectors.

FIG. 3 is a flowchart for determining a single final optimal fitting value based on the results obtained by the method shown in FIG. 2;

FIG. 4 is a diagram showing an example of a two-dimensional space used in the method shown in FIG.

FIG. 5 is another flowchart for determining a single final optimal fitting value based on the results obtained by the method shown in FIG. 2;

FIG. 6 is a diagram showing an example of a two-dimensional space used in the method shown in FIG.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Sound source processing part, 1a ... Sound source storage part, 1b ... Sound source signal conversion part, 1c ... Sound source signal selection part, 1d ... Sound source presentation part, 2 ...
Parameter creation unit, 2a coordinate acquisition unit, 2b solution vector calculation unit, 2c parameter writing unit, 3D two-dimensional space display unit, 3a optimal solution vector acquisition unit, 3b two-dimensional coordinate calculation unit, 3c display Section, 4 ... programmable hearing aid, 5 ... parameter storage section, 6 ... speaker.

Claims (12)

[Claims] 1. For a problem in which a user determines one optimal n-dimensional solution vector based on optimal n-dimensional solution vector candidates corresponding to a plurality of conditions, the positions of the plurality of optimal n-dimensional solution vector candidates are set to 2 A first step illustrated in a two-dimensional space, a second step in which a user selects arbitrary coordinates in the two-dimensional space, and coordinates in the two-dimensional space of the plurality of n-dimensional solution vector candidates obtained in advance. A third step of calculating an n-dimensional solution vector corresponding to an arbitrary coordinate selected by the user based on the evaluation values of the user with respect to the plurality of n-dimensional solution vectors; An optimal n-dimensional solution vector on the basis of an optimal n-dimensional solution vector. 2. The optimal solution determination method according to claim 1, wherein the user evaluation values for the plurality of n-dimensional solution vectors are obtained by an interactive genetic algorithm. 3. The optimal solution determination method according to claim 1, wherein the n-dimensional solution vector is used as an adjustment parameter of a hearing aid. 4. The optimal solution determination method according to claim 1, wherein the n-dimensional solution vector is used as an image adjustment parameter. 5. The plurality of optimal n-dimensional solution vector candidates are set as optimal n-dimensional solution vectors for a plurality of sound sources.
The optimal solution determination method according to claim 1, 2 or 3. 6. Parameter writing means for converting an n-dimensional solution vector determined by the optimal solution determination method according to claim 1, into an adjustment parameter value of a hearing aid, and writing the adjusted parameter value in a hearing aid parameter storage unit of the hearing aid. A hearing aid fitting device, comprising: sound source storage means for storing a sound source; and sound source presentation means for presenting the sound source to a hearing aid. 7. Parameter writing means for converting an n-dimensional solution vector determined by the optimal solution determination method according to claim 1, into an adjustment parameter value of a hearing aid, and writing the adjusted parameter value in a hearing aid parameter storage unit of the hearing aid. Sound source storage means for storing a sound source, sound source presentation means for presenting a sound source to a hearing aid, and a display for displaying a visual figure based on adjustment parameter values of the hearing aid and / or acoustic information represented by the n-dimensional solution vector. Hearing aid fitting device characterized by comprising means. 8. The hearing aid fitting device according to claim 7, wherein the visual figure is a frequency characteristic of the acoustic information. 9. The hearing aid fitting device according to claim 7, wherein the visual figure is an input / output characteristic of the acoustic information. 10. The hearing aid fitting according to claim 7, wherein the visual figure is a time waveform of the acoustic information. 11. The hearing aid fitting according to claim 7, wherein the visual figure is a sound spectrogram of the acoustic information. 12. The method according to claim 1, wherein an n-dimensional solution vector corresponding to an arbitrary coordinate selected by the user is converted into an adjustment parameter value of the hearing aid, written into a hearing aid parameter storage unit of the hearing aid, and the plurality of sound sources are sequentially presented to the user. 6 to claim 1
A hearing aid fitting device according to any one of the preceding claims.