Hearing aid system

Abstract

To provide a hearing aid system having a new configuration.SOLUTION: A hearing aid system 1 includes: an acquisition section 301 for acquiring information data related to information of a user of a hearing aid and state data measured by using the hearing aid while the hearing aid is mounted on the user; a database 302 for storing the information data and the state data acquired by the acquisition section 301 by association; and an identification processing section 303 for executing identification processing by using the information data and the state data stored in the database 302. The identification processing section 303 compares the state data in a first situation (point of sale) with the state data in a second situation (time of state confirmation) based on the information data as the identification processing, so as to execute determination processing to determine whether the hearing aid 100 is correctly mounted.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a hearing aid system. [Background technology]

[0002] 2. Description of the Related Art As a conventional technique, an audio processing device is known (for example, Patent Document 1). The audio processing device of Patent Document 1 compares determined values ​​of one or more features of an acoustic signal with preset values ​​of the one or more features, and determines whether a user earpiece is positioned at a user's ear based on the result of the comparison. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2019-523581 Summary of the Invention [Problem to be solved by the invention]

[0004] Although the above-mentioned documents exist as prior art, a hearing aid system having a novel configuration is desired.

[0005] Therefore, an object of the present invention is to provide a hearing aid system having a novel configuration. [Means for solving the problem]

[0006] The present invention employs the following solutions to solve the above problems. Note that the following solutions are merely examples, and the present invention is not limited thereto.

[0007] Solution 1: The hearing aid system of this solution is a hearing aid system that includes an acquisition means for acquiring information data on information of a hearing aid user and condition data measured using the hearing aid while the user is wearing the hearing aid, a storage means for storing the information data acquired by the acquisition means in association with the condition data, and a specific processing execution means for executing a specific processing using the information data and the condition data stored in the storage means. The specific processing is processing that includes at least one of processing such as a processing for determining how well the hearing aid is worn, a processing for calculating parameters of the hearing aid, a processing related to machine learning, a processing related to deep learning, and a statistical processing.

[0008] According to this solution, the system utilizes information data that does not change depending on the measurement conditions and status data that changes depending on the measurement conditions, so that specific processing can be performed using two types of data of different nature, and various processing related to hearing aids (processing for determining how well the hearing aid is worn, processing for calculating hearing aid parameters, processing related to machine learning, etc.) can be performed.As a result, a hearing aid system with a novel configuration can be provided.

[0009] Solution 2: The hearing aid system of this solution is a hearing aid system characterized in that, in any of the solutions described above, the status data is data generated based on a sound input to the microphone of the hearing aid while a test sound is being generated from an earphone of the hearing aid.

[0010] According to this solution, the status data is based on sound output from a hearing aid and input to the hearing aid, and therefore can be data that reflects the status of the hearing aid.

[0011] Solution 3: The hearing aid system of this solution is a hearing aid system characterized in that, in any of the solutions described above, the acquisition means acquires the status data of a first situation, the storage means links and stores the information data and the status data of the first situation, the acquisition means acquires the status data of a second situation different from the first situation, and the specific processing execution means executes, as the specific processing, a determination process for determining whether or not the hearing aid is being worn correctly by comparing the status data of the first situation with the status data of the second situation based on the information data.

[0012] According to this solution, status data of a first situation (at the time of sale, a situation in which the hearing aid is worn correctly, first scene) is compared with status data of a second situation (when checking the status, a situation in which it is unclear whether the hearing aid is worn correctly, second scene) to determine whether the hearing aid is worn correctly or not, so that by checking the determination result, the user can easily check for themselves whether the hearing aid is worn correctly or not.

[0013] Solution 4: The hearing aid system of this solution is a hearing aid system characterized in that, in any of the solutions described above, the acquisition means is capable of acquiring data of multiple users as the status data for the first situation, the storage means is capable of storing data of multiple users as the status data for the first situation, the information data includes multiple items, the status data for the first situation stored in the storage means has a normal range defined for each item or combination of items, and the judgment process is a process of judging whether or not the hearing aid is being worn correctly based on the normal range.

[0014] According to this solution, whether or not a hearing aid is being worn correctly is determined based on the normal range, making it easier to perform the determination process.

[0015] Solution 5: The hearing aid system of this solution is a hearing aid system characterized in that, in any of the solutions described above, the acquisition means is capable of acquiring data of multiple users as the status data, the storage means is capable of storing data of multiple users as the status data, the information data includes multiple items, and the status data stored in the storage means is subjected to the specific processing for each item or combination of items.

[0016] According to this solution, a plurality of status data collected from a plurality of users can be listed for each item or for each combination of items by specific processing. Effect of the Invention

[0017] According to the present invention, a hearing aid system having a novel configuration is provided. [Brief description of the drawings]

[0018] [Figure 1] 1 is a block diagram showing a hearing aid system 1 of a first embodiment. [Diagram 2] 1 is a diagram showing an example of variation in measurement data when the hearing aid 100 is put on and taken off. [Diagram 3] 1 is a sequence diagram showing the flow of processing during measurement at a retail store in the hearing aid system 1 of the first embodiment. [Figure 4] 4 is a sequence diagram showing the flow of processing when checking the state of the hearing aid 100 in the hearing aid system 1 of the first embodiment. FIG. [Diagram 5] 1 is a block diagram showing the configuration of a hearing aid 100 of a first embodiment and a conceptual diagram showing a feedback transfer function. [Figure 6] FIG. 11 is a sequence diagram showing the process flow when checking the state of the hearing aid 100 in the hearing aid system 1-2 of the second embodiment. [Figure 7] FIG. 11 is a sequence diagram showing the process flow when checking the state of the hearing aid 100 in the hearing aid system 1-3 of the third embodiment. [Figure 8]FIG. 11 is a block diagram showing the configuration of a hearing aid 100-4 of a fourth embodiment. [Figure 9] FIG. 13 is a sequence diagram showing the flow of processing during measurement in the hearing aid system 1-5 of the fifth embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] [First embodiment] Hereinafter, a first embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing a hearing aid system 1 of the first embodiment. As shown in FIG. 1, the hearing aid system 1 of the first embodiment is a system that uses a hearing aid 100 as one component, and includes the hearing aid 100, a terminal 200, and a server 300.

[0020] The hearing aid 100 and the terminal 200 can communicate with each other via a communication means such as Bluetooth (registered trademark), and the terminal 200 and the server 300 can communicate with each other via a communication means such as the Internet. The hearing aid 100 and the server 300 may also be able to communicate with each other via a communication means such as the Internet. Each communication means may be a wired communication means.

[0021] The hearing aid 100 is a device worn by a user (a wearer) and is used by being worn on the user's ear. The hearing aid 100 includes a microphone 50 to which sound is input, an earphone 80 from which sound is output, and the like. Terminal 200 is an information processing device that can be used by a user, a sales clerk, etc., and is, for example, a smartphone, a remote control for hearing aid 100, a personal computer (PC), etc. An application 201 (fitting software, controller, etc.) related to hearing aid system 1 is installed in terminal 200. The fitting software and controller, etc. may be implemented in the same terminal 200, or may be implemented in separate terminals.

[0022] Server 300 is a device managed by the operator of hearing aid system 1, and includes acquisition unit 301 (acquisition means), database 302 (storage means), and specific processing unit 303 (specific processing execution means). Server 300 may perform processing, or may simply store data.

[0023] The acquisition unit 301 is a part that acquires information data on information of the user of the hearing aid 100, and status data measured using the hearing aid 100 while the user is wearing the hearing aid 100. The status data is data generated based on a sound input to the microphone of the hearing aid 100 while a test sound is being generated from the earphone of the hearing aid 100. The acquisition unit 301 can acquire status data of a first situation (data measured in a first scene) and status data of a second situation (data measured in a second scene) different from the first situation. The acquisition unit 301 can acquire data of multiple users as status data of the first situation. Details of the various data will be described later. The acquisition unit 301 may be provided on the hearing aid 100 side or the terminal 200 side.

[0024] Database 302 is a part that stores information data and status data acquired by acquisition unit 301 in association with each other. Database 302 can store information data and status data of a first situation in association with each other. Database 302 can store data of a plurality of users as status data of the first situation.

[0025] The identification processing unit 303 is a part that executes identification processing using the information data and status data stored in the database 302. As identification processing, various processes related to the hearing aid (processing for determining the wearing condition of the hearing aid, processing for calculating parameters of the hearing aid, processing related to machine learning, etc.) can be executed, but in the first embodiment, as the identification processing, a determination process is executed for determining whether the hearing aid 100 is being worn correctly by comparing status data of a first situation with status data of a second situation based on the information data.

[0026] 2 is a diagram showing an example of the variation in measurement data due to the insertion and removal of the hearing aid 100. In the diagram, the vertical axis indicates the relative level [dB], and the horizontal axis indicates the frequency [Hz]. When hearing aid 100 is worn, sound is emitted from the earphones of hearing aid 100, and a judgment is made as to whether or not hearing aid 100 is being worn correctly based on the sound input to the microphone of hearing aid 100. When making such a judgment, a standard is required for judging whether the obtained result is normal or not, but there are large differences between individuals depending on the model of hearing aid 100, the type of ear tip, the gender and age of the user, etc., and there is also large variation when worn even by the same user.

[0027] FIG. 2 shows an example of the variation (lines L1 to L20) of the feedback transfer function when the same person repeatedly puts on and takes off the hearing aid 100 20 times using the same ear tip. The first measurement result L1 to the twentieth measurement result L20 follow roughly the same trajectory from left to right on the graph, but the 15th measurement result L15 is a measurement result at a higher level than the other measurement results, and the third measurement result L3, the fourth measurement result L4, the sixth measurement result L6, the seventh measurement result L7, the fourteenth measurement result L14, the sixteenth measurement result L16, and the eighteenth measurement result L18 are measurement results at a lower level than the other measurement results. In this way, even if the same user performs measurements under exactly the same conditions, the measurement results will vary. For this reason, in this embodiment, the normal range is determined using state data (measured values) measured in the correct state at the time of adjustment at a retail store or the like. An example of the procedure of the first embodiment will be described below.

[0028] [Example of procedure in the first embodiment] The procedure example of the first embodiment is an example in which the hearing aid 100 and the terminal 200 communicate with the server 300 to determine whether the hearing aid 100 is being worn correctly. (1) Transmit status data and information data in the first situation (at the time of sale) to the server 300. The status data in the first situation is data (impulse response, feedback transfer function, data obtained by Fourier transformation, etc.) measured using the hearing aid 100 at a store or the like. The feedback transfer function (impulse response) can be measured by outputting sound (sine wave, sweep sound, impulse, etc.) from the worn earphone and obtaining it from the sound input to the microphone of the hearing aid by an adaptive filter of the hearing aid 100. The coefficient of the adaptive filter can be made to correspond to the impulse response, and the impulse response converted into a frequency response can be made to correspond to the feedback transfer function. The status data in the first situation is data measured by a certified hearing aid technician at a store while the user is wearing the hearing aid 100 correctly, and therefore is data indicating a state in which the hearing aid 100 is being worn correctly.

[0029] The information data includes items such as the model of the user's hearing aid 100, the user's age, the user's gender, the sound source (the sound source used during measurement at a store, etc.), and the type of ear tip. The server 300 links the status data of the first situation and the information data and stores them in the database 302. Note that in cases where user registration or the like is performed when the hearing aid system 1 is started to be used and the information data is stored in advance in the database 302 of the server 300, instead of transmitting the information data directly, the server 300 may transmit a symbol that can be matched with the information data (for example, the serial number of the hearing aid 100 or the login ID of the application 201) together with the status data of the first situation.

[0030] The server 300 predefines a plurality of categories (model, gender, etc., and combinations of categories (model and gender, model, age and gender, etc.)) as categories based on one item in the information data or combinations of a plurality of items in the information data, and retrieves (references) and lists (creates a table) corresponding status data for each category from the database 302. In other words, the server 300 can create a table in the database for each predefined category (for each item) or for each combination of categories (for each combination of items).

[0031] The categories are "model", "gender", etc. For example, the first category is "model: A", the second category is "model: B", the third category is "gender: male", and the fourth category is "gender: female". A category combination is a combination of "model", "gender", etc. For example, a first combination category is "model: A, gender: male", a second combination category is "model: A, gender: female", a third combination category is "model: B, gender: male", and a fourth combination category is "model: B, gender: female". In addition, category combinations can be, for example, "age: 50s, model: A" or "gender: female, model: B," or they can also be "male, 30s" or "male, 40s."

[0032] (2) The server 300 performs statistical processing (specific processing) of the status data of the first situation for each category or for each combination of categories in the specific processing unit 303, and sets a normal range (normal range data) of the status data of the first situation from the results. The statistical processing is a method using "average and variance" or a method using a frequency distribution. The normal range may be, for example, a range of the average value ±2σ (a range in which about 95% of the data from the average falls) calculated by calculating "average and variance", or a frequency distribution table is created to find the value with the highest frequency, and a range whose magnitude is 1 / 5 of the highest frequency is set as the normal range. The normal range may be set by the server 300 performing the above calculation, or may be set manually by an administrator. Up to this point, the flow of processing has been described for the time of sale, and from this point onwards, the flow of processing has been described for the time of status confirmation.

[0033] (3) After the user puts on the hearing aid 100, the user operates the terminal 200 to check the wearing condition.

[0034] (4) When worn, instructions are sent from terminal 200 to hearing aid 100, and hearing aid 100, upon receiving the instructions, outputs a test sound (a test sound such as white noise, a sweep sound, or an impulse) from the earphone of hearing aid 100, acquires the sound leaking through a microphone, and obtains status data of the second situation (when checking the status) using an adaptive filter or the like of hearing aid 100. Status data of the second situation is data measured using hearing aid 100 during actual use (impulse response, feedback transfer function, data obtained by Fourier transformation, etc.). Status data of the second situation is data measured while the user is wearing hearing aid 100, and therefore is data indicating a state in which it is unclear whether hearing aid 100 is being worn correctly.

[0035] (5) The hearing aid 100 transmits status data of the second situation to the terminal 200, and the terminal 200 transmits the information data and the status data of the second situation to the server 300. The status data of the second situation may be transmitted by the hearing aid 100 itself to the server 300 together with the information data. Also, instead of transmitting the information data together with the status data of the second situation, a symbol that can be matched with the information data by the server 300 may be transmitted together with the status data of the second situation.

[0036] (6) Server 300 extracts the normal range from database 302 based on the information data, compares the status data of the second situation with the normal range, and notifies the result. Specifically, server 300 checks whether the obtained status data of the second situation is within the normal range. If the status data is outside the normal range, it is assumed that hearing aid 100 may not be worn correctly, and notifies terminal 200 of the wearing status data (OK, NG, etc.) relating to the judgment result.

[0037] (7) Terminal 200 issues warnings and notifications based on the notified wearing condition data. Specifically, terminal 200 displays the wearing condition (information on whether the hearing aid is worn properly or not) and the possibility of a malfunction on a display screen, terminal 200 notifies hearing aid 100 of the determination result, and hearing aid 100 outputs the determination result by voice or the like.

[0038] (8) Machine learning may be used to determine the wearing condition and malfunction. By learning the state data of the first situation as data when the hearing aid is worn correctly and data when the hearing aid is not worn correctly or is malfunctioning as abnormal state data, it is possible to determine whether the hearing aid 100 is worn correctly or whether the hearing aid 100 is malfunctioning, regardless of the normal range. (9) The determination of the wearing condition or malfunction may be performed by the server 300 and the determination results may be notified to the hearing aid 100 or the terminal 200, or the terminal 200 may perform the determination and notify the hearing aid 100, or the hearing aid 100 may perform the determination.

[0039] Instructions for the hearing aid 100 are given by operating the terminal 200. Warnings and notifications may be given on the screen of the terminal 200, or may be displayed by a lamp on the terminal 200 or a lamp on the hearing aid 100, or the terminal 200 or the hearing aid 100 may notify by voice or the like.

[0040] FIG. 3 is a sequence diagram showing the flow of processing during measurement at a retail store in the hearing aid system 1 of the first embodiment. The terminal 200 starts measuring state data (e.g., impulse response) of the first situation (S10). Specifically, the terminal 200 transmits a measurement start instruction to the hearing aid 100. The measurement start instruction can be transmitted using the application 201 of the terminal 200.

[0041] When the hearing aid 100 receives the measurement start instruction, the hearing aid 100 changes to a measurement mode (S11). The hearing aid 100 is switchable between a normal mode and a measurement mode. The normal mode is a mode in which the hearing aid 100 is used for hearing assistance, and the measurement mode is a mode in which the hearing aid 100 is used to measure status data.

[0042] The hearing aid 100 starts measuring the condition data of the first situation (S12), thereby enabling the hearing aid 100 to obtain the condition data of the first situation. When the measurement of the state data of the first situation is completed, the hearing aid 100 returns to the normal mode (S13). The hearing aid 100 transmits status data of the first situation to the terminal 200 (S14).

[0043] The terminal 200 receives the status data of the first situation (S15). The terminal 200 transmits status data of the first situation to the server 300 (S16). At this time, the terminal 200 also transmits information data. The information data may be stored in the hearing aid 100 or in the terminal 200. If the hearing aid 100 stores the information data, the terminal 200 acquires the information data from the hearing aid 100 and transmits it to the server 300. If the terminal 200 stores the information data, the terminal 200 transmits the information data to the server 300.

[0044] The server 300 receives the status data and information data of the first situation (S17). The server 300 associates the status data and the information data of the first situation and stores them in the database 302 (customer database) (S18). The server 300 executes statistical processing (statistical calculation) (S19). The server 300 defines normal ranges for each category or combination of categories from the database 302 (S20).

[0045] FIG. 4 is a sequence diagram showing the flow of processing when checking the state of the hearing aid 100 in the hearing aid system 1 of the first embodiment. The terminal 200 starts measuring state data (e.g., impulse response) of the second situation (S30). Specifically, the terminal 200 transmits a measurement start instruction to the hearing aid 100. The measurement start instruction can be transmitted using the application 201 of the terminal 200.

[0046] When the hearing aid 100 receives the measurement start instruction, the hearing aid 100 changes to the measurement mode (S31). The hearing aid 100 starts measuring condition data of the second situation (S32), thereby enabling the hearing aid 100 to obtain condition data of the second situation. When the measurement of the condition data of the second situation is completed, the hearing aid 100 returns to the normal mode (S33). The hearing aid 100 transmits status data of the second situation to the terminal 200 (S34).

[0047] The terminal 200 receives the status data of the second situation (S35). The terminal 200 transmits the status data of the second situation to the server 300 (S36). At this time, the terminal 200 also transmits information data. The method of transmitting the information data is the same as that when the measurement is performed at the store.

[0048] The server 300 receives the status data and information data of the second situation (S37). The server 300 compares the status data of the second situation with the normal range (S38). The server 300 identifies a category based on data such as gender and age in the information data, and compares the status data of the second situation with the normal range corresponding to the identified category. Note that, if there are multiple categories corresponding to the information data, the comparison may be performed with only one category, or with all categories. Server 300 transmits data on the wearing state based on the determination result to terminal 200 (S39). The wearing state data includes OK information (information indicating that the hearing aid is being worn correctly) or NG information (information indicating that the hearing aid is not being worn correctly). The terminal 200 receives the data on the wearing state (S40). The terminal 200 performs a notification based on the data on the wearing state (S41). This notification enables the user to check whether or not the hearing aid 100 is being worn correctly.

[0049] 5 is a block diagram showing the configuration of the hearing aid 100 of the first embodiment and a conceptual diagram showing a feedback transfer function. Here, the feedback transfer function is used as the state data. As shown in FIG. 5(A), the hearing aid 100 includes a feedback estimation unit 10, a microphone 50, a hearing aid processing unit 60, an amplifier unit 70, an earphone 80, and a test sound input unit 90. The hearing aid 100 also includes a battery (not shown) that serves as a power supply source, and a communication unit (not shown) for communicating with the terminal 200. Of the components of the hearing aid 100, the components other than the microphone 50 and the earphone 80 can be implemented, for example, by signal processing using a DSP (Digital Signal Processor). The feedback estimation unit 10 includes, for example, an adaptive filter 11, a subtraction unit 12, a coefficient update unit 13, a delay processing unit 15, and the like. The feedback estimation unit 10 employs the NLMS algorithm as an adaptation algorithm. Note that the occurrence of acoustic feedback requires the presence of both a means for outputting sound and a means for inputting sound, and therefore the microphone 50 and the earphone 80 can also be regarded as part of the feedback estimation unit 10.

[0050] In addition to a mixture of desired sounds such as voice and environmental sounds (hereinafter referred to as "external sounds"), the microphone 50 also receives sound x(n) output from the earphone 80 that leaks from the ear canal and is fed back (hereinafter referred to as "feedback sound"; see FIG. 5(B)). The relationship between the leaked sound and the sound input to the microphone 50 is represented by the feedback transfer function F(z). The microphone 50 converts the feedback sound f(n) into an electrical signal and outputs a signal d(n) that has passed through the transfer characteristics specific to the microphone 50.

[0051] The adaptive filter 11 adaptively estimates a transfer function W(z) corresponding to the feedback transfer function F(z) using coefficients updated by a coefficient update unit 13 described later, and outputs a signal y(n) obtained by passing a signal u(n) input to the adaptive filter 11 through the transfer function W(z). In other words, the signal y(n) corresponds to an estimate of the component of the feedback sound fed back from the earphone 80 to the microphone 50. The subtraction unit 12 subtracts the output signal y(n) of the adaptive filter 11 from the output signal d(n) of the microphone 50, and outputs the error signal e(n) obtained by this to the hearing aid processing unit 60 and the coefficient update unit 13.

[0052] The test sound b(n) is output to the amplifier 70 and a delay processing unit 15 described later. The test sound input unit 90 can also output the test sound V(n) to the amplifier 70 and the delay processing unit 15. The amplifier 70 amplifies the test sound b(n) with a predetermined gain, and outputs a signal that has passed through a transfer characteristic specific to the amplifier 70 to the earphone 80. The earphone 80 converts the output signal of the amplifier 70 into a sound x(n) that has passed through a transfer characteristic specific to the earphone 80, and outputs the sound. Then, a part of the sound output from the earphone 80 is fed back to the microphone 50 as described above.

[0053] Meanwhile, delay processing unit 15 outputs the post-hearing-aid processing signal with a predetermined delay in order to compensate for delays occurring in hearing aid 100, i.e., delays associated with hearing aid processing and delays when feedback sound reaches microphone 50 from earphone 80. Specifically, delay processing unit 15 outputs the post-hearing-aid processing signal that was input a predetermined time ago to adaptive filter 11 and coefficient update unit 13 as post-delay processing signal u(n).

[0054] Then, the coefficient update unit 13 uses the NLMS algorithm to update the coefficients of the adaptive filter 11 so as to minimize the error signal.

[0055] In the above example configuration, the amplifier 70 is provided, but instead, it is possible to configure the hearing aid processor 60 to perform gain amplification in addition to various hearing aid processes without providing the amplifier 70. This also applies to the following embodiments.

[0056] As described above, according to the first embodiment, the following effects are obtained. (1) By comparing the condition data of the second situation with the normal range, it is possible to check whether the hearing aid 100 is being worn correctly. In addition, if the condition data is out of the normal range by a predetermined value or more, it can also be used to determine whether the microphone or earphone is broken. (2) Large amounts of state data, such as feedback transfer functions listed by category, are valuable when conducting actual verification in product development and research.

[0057] (3) The various data stored in database 302 can be used as learning data for deep learning, K-means algorithm, and SVM (support vector machine), and the learned results can be used to control the step size of an adaptive filter, a feedback canceller, etc. (4) If the hearing aid 100 is equipped with an in-ear microphone, data acquired by the server 300 and data calculated from that data can also be used as an ANC (active noise canceling) coefficient for each individual.

[0058] (5) According to the first embodiment, the system utilizes information data that does not change depending on the measurement situation and status data that changes depending on the measurement situation (status data for the first situation, status data for the second situation). This makes it possible to perform specific processing (processing for determining the fit of the hearing aid) using two types of data of different nature. As a result, it is possible to provide a hearing aid system 1 with a novel configuration.

[0059] (6) According to the first embodiment, the status data (status data for the first situation, status data for the second situation) is based on sound output from hearing aid 100 and input to hearing aid 100 depending on the state in which the hearing aid is being worn. Therefore, by performing input and output using the same device, the data can reflect the state of hearing aid 100.

[0060] (7) According to the first embodiment, the status data of the first situation is compared with the status data of the second situation to determine whether or not the hearing aid 100 is being worn correctly. Therefore, by checking the determination result, the user can easily check for himself or herself whether or not the hearing aid 100 is being worn correctly.

[0061] (8) According to the first embodiment, whether or not a hearing aid is being worn correctly is determined based on the normal range, making it easier to perform the determination process.

[0062] (9) According to the first embodiment, the status data of multiple first situations collected from multiple users is listed by category (by item) or by combination of categories (by combination of items) through statistical processing, making it easier to perform the judgment process.

[0063] (10) The hearing aid 100 is adjusted in a store by a certified hearing aid technician or the like to suit the hearing characteristics of the individual user. The adjustment by the certified hearing aid technician is performed after the hearing aid 100 is properly fitted to the user. Therefore, in order for the user to obtain the correct hearing aid effect, it is important that the hearing aid 100 is properly worn. However, it is difficult for the wearer to check for himself / herself whether the hearing aid 100 is properly worn. In addition, the technology of Patent Document 1 described in the prior art document does not allow the wearer to check whether the hearing aid is properly worn. In this regard, according to the first embodiment, the user can easily check whether the hearing aid 100 is properly worn by himself / herself.

[0064] Second Embodiment Next, a second embodiment of the present invention will be described with reference to the drawings. In the following description, the same contents as those in the first embodiment will be omitted as appropriate.

[0065] [Example of procedure in the second embodiment] The procedure example of the second embodiment is an example in which the hearing aid 100 determines whether the hearing aid 100 is being worn correctly. The hearing aid 100 of the second embodiment has the functions of the specific processing unit 303 of the first embodiment. Also, steps (1) to (4) of the procedure example of the second embodiment are similar to steps (1) to (4) of the procedure example of the first embodiment, and therefore will not be described.

[0066] (5) The hearing aid 100 obtains the normal range based on the information data stored in the hearing aid 100, and compares the state data of the second situation with the normal range stored in the hearing aid 100 to determine whether the hearing aid 100 is being worn correctly. In the second embodiment, the information data and normal range data are stored in the hearing aid 100. The information data and normal range data are stored in the hearing aid 100 at the time of sale. (6) Hearing aid 100 issues a warning or notification based on the determination result. Specifically, hearing aid 100 notifies terminal 200 of the determination result, and terminal 200 displays the wearing status (information on whether or not it is worn properly) and the possibility of a malfunction on a display screen, or hearing aid 100 outputs the determination result as a sound or the like. (7) Machine learning may be used to determine the wearing condition and malfunction. This is the same as in the first embodiment. (8) The judgment data (normal range data) stored in the hearing aid 100 is updated by the server 300 as necessary.

[0067] FIG. 6 is a sequence diagram showing the flow of processing when checking the state of the hearing aid 100 in the hearing aid system 1-2 of the second embodiment. The process from S30 to S33 is the same as the process described in Fig. 4, and therefore the description will be omitted. Also, the process flow during measurement at the store is the same as the process described in Fig. 3, and therefore the description will be omitted.

[0068] The hearing aid 100 compares the condition data of the second situation with the normal range (S50). The hearing aid 100 transmits data on the wearing state based on the determination result to the terminal 200 (S51). The terminal 200 receives the data on the wearing state (S52). The terminal 200 performs a notification based on the data on the wearing state (S53). This notification enables the user to check whether the earphones of the hearing aid 100 are being worn correctly.

[0069] The server 300 transmits update data (data for updating the normal range) to the terminal 200 (S54). The update data can be transmitted to the terminal 200 at any timing (for example, when a certain period of time has passed, when a certain number of pieces of status data of the first situation have been stored in the server 300, etc.) (the same applies to the following embodiments). The terminal 200 receives the update data (S55). The terminal 200 transmits the update data to the hearing aid 100 (S56). The hearing aid 100 receives the update data (S57). The hearing aid 100 executes a process for updating the normal range based on the update data (S58).

[0070] As described above, according to the second embodiment, in addition to the effects of the first embodiment, the hearing aid 100 performs the judgment process, so there is no need to transmit data to the server 300, and the user can check the judgment result more quickly.

[0071] Third Embodiment Next, a third embodiment of the present invention will be described with reference to the drawings. In the following description, the same contents as those in the first embodiment will be omitted as appropriate.

[0072] [Example of procedure of the third embodiment] The procedure example of the third embodiment is an example in which the terminal 200 determines whether the hearing aid 100 is worn correctly. The terminal 200 of the third embodiment has the function of the specific processing unit 303 of the first embodiment. Steps (1) to (4) of the procedure example of the third embodiment are similar to steps (1) to (4) of the procedure example of the first embodiment, and therefore will not be described.

[0073] (5) The hearing aid 100 transmits the information data of the hearing aid 100 and the measured status data of the second situation to the terminal 200. Instead of transmitting the information data together with the status data of the second situation, a symbol that can be matched with the information data by the terminal 200 or the server 300 may be transmitted together with the status data of the second situation. Note that in the third embodiment, the information data is stored in the hearing aid 100, and normal range data is stored in the terminal 200. (6) Terminal 200 obtains the normal range based on the transmitted information data, compares the status data of the second situation with the normal range stored in terminal 200, and determines whether hearing aid 100 is attached properly. This process can be executed by starting a determination program built into the application.

[0074] (7) Terminal 200 issues a warning or notification based on the result of the determination. Specifically, terminal 200 displays the wearing status (information on whether the hearing aid is worn properly or not) and the possibility of a malfunction on a display screen, terminal 200 notifies hearing aid 100 of the result of the determination, and hearing aid 100 outputs the result of the determination by voice or the like. (8) Machine learning may be used to determine the wearing condition and malfunction. This is the same as in the first embodiment. (9) The determination data (data within the normal range) stored in the terminal 200 is updated by the server 300 as necessary.

[0075] FIG. 7 is a sequence diagram showing the flow of processing when checking the state of the hearing aid 100 in the hearing aid system 1-3 of the third embodiment. The process from S30 to S35 is the same as the process described in Fig. 4, and therefore the description will be omitted. Also, the process flow during measurement at the store is the same as the process described in Fig. 3, and therefore the description will be omitted.

[0076] The terminal 200 compares the status data of the second situation with the normal range (S60). The terminal 200 performs a notification based on the data on the wearing state (S61). This notification enables the user to check whether or not the hearing aid 100 is being worn correctly.

[0077] The server 300 transmits the update data to the terminal 200 (S62). The terminal 200 receives the update data (S63). The terminal 200 executes a process of updating the normal range based on the update data (S64).

[0078] As described above, according to the third embodiment, in addition to the effects of the first embodiment, since the terminal 200 executes the determination process, not only is there no need to transmit data to the server 300, but the determination process is executed by the terminal 200, which has a high processing speed, so the user can check the determination result more quickly. Furthermore, according to the third embodiment, since the terminal 200 executes the determination process, the processing load on the hearing aid 100 can be reduced.

[0079] [Fourth embodiment] Next, a fourth embodiment of the present invention will be described with reference to the drawings. In the following description, the same contents as those in the first embodiment will be omitted as appropriate.

[0080] FIG. 8 is a block diagram showing the configuration of a hearing aid 100-4 according to the fourth embodiment. In a hearing aid system 1-4 of the fourth embodiment, the hearing aid 100 of the first embodiment is changed to a hearing aid 100-4. Also, in the hearing aid 100-4, the feedback estimator 10 of the first embodiment is changed to a feedback canceller 10-4.

[0081] As shown in FIG. 8, the hearing aid 100-4 includes a feedback canceller 10-4, a microphone 50, a hearing aid processor 60, an amplifier 70, and an earphone 80. The hearing aid 100-4 also includes a battery (not shown) that serves as a power supply source, and a communication unit (not shown) for communicating with the terminal 200. Of the components of the hearing aid 100-4, the components other than the microphone 50 and the earphone 80 can be implemented, for example, by signal processing using a DSP (Digital Signal Processor). The feedback canceller 10-4 is also composed of, for example, an adaptive filter 11, a subtractor 12, a coefficient updater 13, an initial value storage unit 14, a delay processor 15, and the like. The feedback canceller 10-4 employs the NLMS algorithm as an adaptive algorithm. Note that the occurrence of acoustic feedback is premised on the existence of both a means for outputting sound and a means for inputting sound, and therefore the microphone 50 and the earphone 80 can also be regarded as part of the feedback canceller 10-4.

[0082] In addition to a mixture of desired sounds such as voice and environmental sounds (hereinafter referred to as "external sounds"), the microphone 50 also receives a sound x(n) output from the earphone 80 that leaks from the ear canal and is fed back (hereinafter referred to as "feedback sound"; see FIG. 5(B)). The relationship between the leaked sound and the sound input to the microphone 50 is represented by a feedback transfer function F(z). The microphone 50 converts a composite sound of the input external sound s(n) and the feedback sound f(n) into an electrical signal, and outputs a signal d(n) that has passed through the transfer characteristics unique to the microphone 50.

[0083] The adaptive filter 11 adaptively estimates a transfer function W(z) corresponding to the feedback transfer function F(z) using the coefficients updated by the coefficient update unit 13, and outputs a signal y(n) obtained by passing a signal u(n) input to the adaptive filter 11 through the transfer function W(z). In other words, the signal y(n) corresponds to an estimate of the feedback sound component fed back from the earphone 80 to the microphone 50. The subtraction unit 12 subtracts the output signal y(n) of the adaptive filter 11 from the output signal d(n) of the microphone 50, and outputs the error signal e(n) obtained by this to the hearing aid processing unit 60 and the coefficient update unit 13.

[0084] The hearing aid processor 60 performs hearing aid processing G(z) on the error signal e(n), and outputs a post-hearing aid processing signal b(n) to the amplifier 70 and a delay processor 15, which will be described later. The amplifier 70 amplifies the post-hearing aid processing signal b(n) with a predetermined gain, and outputs the signal that has passed through a transfer characteristic specific to the amplifier 70 to the earphone 80. The earphone 80 converts the output signal of the amplifier 70 into a sound x(n) that has passed through a transfer characteristic specific to the earphone 80, and outputs the sound. Then, a portion of the sound output from the earphone 80 is fed back to the microphone 50, as described above.

[0085] Meanwhile, delay processing unit 15 outputs the post-hearing-aid processing signal with a predetermined delay in order to compensate for delays occurring in hearing aid 100, i.e., delays associated with hearing aid processing and delays when feedback sound reaches microphone 50 from earphone 80. Specifically, delay processing unit 15 outputs the post-hearing-aid processing signal that was input a predetermined time ago to adaptive filter 11 and coefficient update unit 13 as post-delay processing signal u(n).

[0086] Then, the coefficient update unit 13 uses the NLMS algorithm to update the coefficients of the adaptive filter 11 so as to minimize the error signal. Specifically, the coefficient update unit 13 updates the coefficients of the adaptive filter 11 based on the input error signal e(n) and the delayed signal u(n), as well as the coefficient Wo of the initial transfer function measured at the time of initial fitting of the hearing aid, which is pre-stored in the initial value storage unit 14. This update process is different from that in the first embodiment.

[0087] As described above, according to the fourth embodiment, the following effects are obtained. (1) State data of the second situation measured when worn (such as statistical values ​​of the feedback transfer function) can be used as a reference filter (coefficient Wo of the initial transfer function of the initial value memory unit 14 shown in Figure 8) of the adaptive feedback canceller 10-4 of the hearing aid 100-4. (2) Furthermore, according to the fourth embodiment, the present invention can also be applied to a hearing aid 100-4 that includes a feedback canceller 10-4.

[0088] Fifth embodiment Next, a fifth embodiment of the present invention will be described with reference to the drawings. In the following description, the same contents as those in the first embodiment will be omitted as appropriate.

[0089] [Example of procedure of the fifth embodiment] The procedure example of the fifth embodiment is an example of determining the step size of an adaptive filter using data obtained by machine learning that has been trained using a database stored in the server 300 as part of the teacher data. The identification processing unit of the first embodiment performed a process to determine the fit of the hearing aid, but the identification processing unit of the fifth embodiment performs a process to calculate the parameters of the hearing aid and a process related to machine learning as the identification process. Step (1) of the procedure example of the fifth embodiment is similar to step (1) of the first embodiment, and therefore will not be described.

[0090] (2) The output of the earphone or data equivalent thereto is input to a feedback transfer function included in the state data, and the output of the feedback transfer function is used as learning data for machine learning. Then, by performing deep learning using the transfer function that is the correct answer for the adaptive filter according to this learning data as teacher data, a neural network that determines an appropriate step size for the adaptive filter built into the hearing aid 100 can be constructed.

[0091] FIG. 9 is a sequence diagram showing the flow of processing during measurement in the hearing aid system 1-5 of the fifth embodiment. The processes from S10 to S18 are the same as those described in FIG. 3, and therefore the description will be omitted. In FIG. 3, the process is performed using the state data of the first situation, but in FIG. 8, the process may be performed using the state data of the first situation, or the process may be performed using the state data of the second situation. For this reason, in FIG. 8, the two state data are simply described as "state data" without distinguishing between them. In the database 302, the state data of the first situation and the state data of the second situation may be stored separately, or the state data of the first situation and the state data of the second situation may be stored as state data without distinguishing between them. In addition, in the fifth embodiment, since the state of the hearing aid 100 is not checked, there is no sequence diagram corresponding to FIG. 4 of the first embodiment, but the process corresponding to FIG. 4 of the first embodiment may be executed.

[0092] The server 300 executes a process of inputting the output data of the earphone to a feedback transfer function included in the state data (S70). The server 300 executes a process of using the output of the feedback transfer function as learning data for machine learning (S71). The server 300 executes a deep learning process based on the learning data, and updates variable data (e.g., data related to the weights of the neural network) of the neural network for determining an appropriate step size of the adaptive filter (S72). Note that the variable data is not limited to data related to the weights of the neural network, and may be data related to other items (parameters) of the neural network.

[0093] The server 300 transmits the learned and updated variable data to the terminal 200 (S73). The terminal 200 receives the variable data (S74). The terminal 200 transmits the variable data to the hearing aid 100 (S75). The hearing aid 100 receives the variable data (S76). If the server 300 and the hearing aid 100 are capable of communicating with each other, the server 300 may transmit the variable data to the hearing aid 100 without going through the terminal 200. The hearing aid 100 applies the received variable data (e.g., weights) as coefficients of its own neural network to update or construct a neural network that determines an appropriate step size for the adaptive filter, and executes a process to determine an appropriate step size for the adaptive filter (S77). Note that such machine learning may be executed for each category or for each combination of categories based on the acquired information data. That is, in the fifth embodiment, it is preferable that the status data stored in the server 300 (database) is subjected to a specific process (machine learning process or deep learning process) for each item or each combination of items.

[0094] As described above, according to the fifth embodiment, by performing machine learning using the state data stored in database 302, hearing aid 100 can calculate an appropriate step size for the adaptive filter of hearing aid 100. Then, by adopting the calculated appropriate step size for the adaptive filter in the adaptive filter of hearing aid 100, the quality of the adaptive filter of hearing aid 100 can be further improved.

[0095] In addition, according to the fifth embodiment, the system utilizes information data that does not change depending on the measurement conditions and status data that changes depending on the measurement conditions, so that specific processing (calculation processing of hearing aid parameters, processing related to machine learning, etc.) can be performed using two types of data of different nature, and as a result, a hearing aid system 1-5 having a novel configuration can be provided.

[0096] Furthermore, according to the fifth embodiment, multiple status data collected from multiple users are listed by category (by item) or by combination of categories (by combination of items) through machine learning processing or deep learning processing, making it easier to perform processes such as calculating step sizes and data analysis.

[0097] The present invention is not limited to the above-described embodiments, and can be practiced in various modified forms. (1) In the first embodiment, an example has been described in which status data of a first situation is stored in database 302 at the time of sale, but status data of a second situation may also be stored in database 302 at the time of status confirmation. In this way, more status data can be collected and used as important data during development. In this case, acquisition unit 301 can acquire data of multiple users as status data of the first situation and status data of the second situation, and database 302 can store data of multiple users as status data of the first situation and status data of the second situation.

[0098] (2) Regarding the distinction between the status data of the first situation and the status data of the second situation, by adding information (identification information) that distinguishes between the two, it is possible to determine whether to store the status data on the server 300 side or to compare and determine the status data on the server 300 side. On the other hand, by not adding identification information to the status data, the server 300 side may both store the status data and compare and determine the status data both at the time of sale and at the time of status confirmation.

[0099] (3) The specific processing unit 303 may be implemented inside the server 300, or may be implemented in an external device of the server 300. In addition, some of the processes described as being executed by the server 300 may be executed by an external device. (4) In the first embodiment, an example was described in which the status data in the second situation was compared to the normal range, but the status data in the first situation may be compared to the status data in the second situation. In this case, it is possible to check whether the hearing aid 100 is being worn correctly based on the degree to which the status data in the second situation deviates from the status data in the first situation (by checking whether there is a difference of more than a predetermined value).

[0100] (5) In comparing the status data of the second situation with the normal range, depending on the extent to which it deviates from the normal range (for example, outside the first range, or outside a second range wider than the first range), information may be provided as to whether the hearing aid is simply not being worn correctly or whether there is a malfunction of the device (e.g., hearing aid). The information provided can be classified as first information indicating that the hearing aid is not being worn correctly, or second information indicating that there is a malfunction of the device. In addition, the information provided (first information or second information) can be displayed or notified on the terminal or the hearing aid. (6) Categories and normal ranges may be set as necessary, and may not be set depending on the situation. (7) The information data may be stored in the hearing aid 100, the terminal 200, or the server 300. (8) The first to fifth embodiments can be used in combination with each other. (9) The application 201 may be a web application or a cloud application. (10) In the fifth embodiment, an example has been described in which the hearing aid 100 calculates the step size, but the terminal 200 or the server 300 may calculate the step size. Also, an example has been described in which the processes of S70 to S72 in Fig. 8 are executed by the server 300, and the process of S77 in Fig. 8 is executed by the hearing aid 100, but the subject of the processes is not limited to this. The processes of S70 to S72 in Fig. 8 and the process of S77 in Fig. 8 can be executed by one device alone of the hearing aid 100, the terminal 200, or the server 300, or by multiple devices working together. [Explanation of symbols]

[0101] 1, 1-2, 1-3, 1-4, 1-5 Hearing aid system 10 Feedback Estimation Unit 10-4 Feedback Canceller 11 Adaptive Filters 12 Subtraction section 13 Coefficient update section 14 Initial value storage section 15 Delay Processing Section 50 Microphone 60 Hearing aid processor 70 Amplification section 80 Earphones 90 Measurement sound input section 100, 100-4 Hearing aids 200 terminals 201 Applications 300 Servers 301 Acquisition Department 302 Database 303 Specific Processing Department

Claims

1. An acquisition means for acquiring information data relating to information on a user of the hearing aid and condition data measured using the hearing aid while the user is wearing the hearing aid; a storage means for storing the information data and the status data acquired by the acquisition means in association with each other; a specific process execution means for executing a specific process using the information data and the status data stored in the storage means; A hearing aid system comprising:

2. 2. The hearing aid system of claim 1, A hearing aid system, characterized in that the status data is data generated based on a sound input to a microphone of the hearing aid while a test sound is being generated from an earphone of the hearing aid.

3. In the hearing aid system according to claim 1 or 2, The acquiring means acquires the status data of a first situation, The storage means stores the information data and the status data of the first situation in association with each other, the acquiring means acquires the status data of a second status different from the first status, The hearing aid system is characterized in that the specific processing execution means executes, as the specific processing, a determination process for determining whether the hearing aid is worn correctly by comparing the status data of the first situation with the status data of the second situation based on the information data.

4. 4. The hearing aid system of claim 3, the acquiring means is capable of acquiring data of a plurality of users as the status data of the first situation, the storage means is capable of storing data of a plurality of users as the status data of the first situation, The information data includes a plurality of items, The state data of the first situation stored in the storage means has a normal range defined for each of the items or each combination of the items, A hearing aid system, wherein the judgment process is a process of judging whether or not the hearing aid is being worn correctly based on the normal range.

5. 2. The hearing aid system of claim 1, the acquiring means is capable of acquiring data of a plurality of users as the status data, the storage means is capable of storing data of a plurality of users as the status data, The information data includes a plurality of items, A hearing aid system, characterized in that the status data stored in the storage means is subjected to the specific processing for each of the items or each combination of the items.

Images