Personalization of algorithm parameters of a hearing device

Abstract

The present application discloses personalization of algorithm parameters of a hearing device, wherein a method of personalizing one or more parameters of a processing algorithm used in a processor of a hearing aid for a specific user comprises: performing a predictive test for estimating the hearing ability of a user when the user listens to test signals having different characteristics; analyzing the results of the predictive test of the user and providing a hearing ability measure of the user; selecting a specific processing algorithm of the hearing aid; selecting a cost-benefit function and / or a key value for the specific processing algorithm related to the hearing ability of the user from one or more related psychometric functions according to the characteristics of the test signals; and determining one or more personalization parameters of the specific processing algorithm for the user according to the hearing ability measure and the cost-benefit function.

Description

Technical Field

[0001] This application relates to the field of hearing devices, such as hearing aids. Background Technology

[0002] Needs and abilities vary greatly among individuals. This high variability stems partly from the diverse causes of hearing loss and partly from the complexity of the brain functions that support our ability to attend to a signal in the presence of other competing sounds. The causes of hearing difficulties are numerous, including a) cochlear damage (i.e., loss of outer hair cells and / or inner hair cells); b) damage to the substantial supporting structures (such as stria vascularis degeneration); c) neural degeneration, damage, and / or atrophy; and d) cognitive differences; these are just a few of the known causes.

[0003] Of the observed differences in speech comprehension among individuals with hearing loss, it has been estimated that only about 50% can be explained by the corresponding audiograms. Therefore, based solely on audiograms, it may be difficult to find the optimal set of hearing aid parameters for a particular user. Furthermore, hearing care professionals (HCPs) have limited time to collect additional data. Therefore, it would be beneficial to find alternative ways to provide information about users and their hearing abilities and / or preferences.

[0004] Furthermore, audible and visible indicators are important means of user interaction for hearing aids, informing users what is happening within the device for a set of usage scenarios, such as program changes or low battery, and they are becoming increasingly useful. However, currently, audible indicators and at least some visible symbols are generally fixed and hard-coded into all hearing aids. Some of the provided sounds / symbols may not be suitable for or understood by the hearing aid user, which can affect (or even disrupt) their daily life. Therefore, it would be beneficial to personalize these indicators to meet the specific needs of each hearing aid user. Summary of the Invention

[0005] This invention relates to the personalization of devices such as hearing aids, for example, configuring and adjusting parameter settings (also referred to as "hearing instrument settings") of one or more processing algorithms for a specific user. Such configuration or adjustment may, for example, be based on patient-specific predictions and assessments of the "costs" and benefits of applying specific processing algorithms such as noise reduction or directional (beamforming) algorithms.

[0006] For example, there is a balance between the benefits and the "costs" of directionality. That is, generally speaking, listeners tend to benefit when the target is in a position that is relatively enhanced by beamforming (such as in front of the listener), and incur "costs" when attention is strongly attenuated by beamforming. In other words, assistive systems such as directional beamforming systems can have "side effects," such as attenuating at least part of the signal that the listener is willing to pay attention to.

[0007] The fact that needs and abilities vary greatly among individuals has important implications for how and when hearing aid "helping" systems truly provide a net benefit to different individuals. This is in... Figure 1 The figure is shown in the image. The lower right portion highlights a key point where “high-performing individuals” with a low Speech Reception Threshold (SRT) are expected to enjoy a net benefit from beamforming at a relatively low Signal-to-Noise Ratio (SNR) compared to “low-performing individuals” with a higher SRT. Specifically, high-performing individuals will incur a net cost of beamforming at the SNR where low-performing individuals enjoy a net benefit. This means that a setting that helps one listener will result in a deficit for another. Individual settings can include any settings in hearing aid signal processing, such as frequency shaping, dynamic range compression, directionality, noise reduction, feedback immunity, etc. Future advanced algorithms, such as deep neural networks for speaker separation and speech enhancement, may also require settings tailored to individual users to provide maximum benefit. Therefore, if we can better individualize how to provide assistance to each listener, we will greatly improve individual outcomes.

[0008] Furthermore, personalizing hearing aids by combining contextual data and acoustic environment information from smartphones (or similar portable devices) with user feedback could be advantageous, as it could automatically change hearing aid (e.g., parameter) settings, for example, based on machine learning techniques such as learning algorithms, supervised or unsupervised learning, including the use of artificial neural networks.

[0009] A method of personalization using one or more parameters of the processing algorithm in the hearing aid.

[0010] In one aspect of this application, a method is provided for personalizing one or more parameters of a processing algorithm used in a processor of a hearing aid for a specific user. This method may include:

[0011] - A predictive test is performed to estimate the user's hearing ability while the user listens to test signals with different characteristics;

[0012] - Analyze the results of the predictive test for the user and provide a measure of the user's auditory ability;

[0013] - Select the specific processing algorithm for the hearing aid.

[0014] The method may further include:

[0015] -Based on the characteristics of the test signal, a specific processing algorithm related to the user's auditory ability selects a cost-benefit function and / or key values ​​from one or more relevant psychometric functions; and

[0016] - For the user, one or more personalized parameters of the specific processing algorithm are determined based on the auditory ability metric and the cost-benefit function.

[0017] This allows for the provision of improved hearing aids for specific users.

[0018] The method may include one or more of the following steps:

[0019] - In addition, the predictive tests can be conducted via smartphones in clinical settings or in everyday life;

[0020] - Test your daily preferences using a smartphone and optimize your settings accordingly;

[0021] - Combining the results of predictive and preference tests provides a better individual setting.

[0022] The method may also include using deep neural networks (DNNs) for signal processing or setting modulation.

[0023] Analysis of the results of the predictive test for the user can be performed in an assistive device communicating with the hearing aid (such as a fitting system, smartphone, or similar device) or in the processor of the hearing device. Determining the user-personalized parameters of the specific processing algorithm based on the hearing ability metric and the cost-benefit function can be performed in an assistive device communicating with the hearing aid (such as a fitting system, smartphone, or similar device) or in the processor of the hearing device.

[0024] Auditory ability measures may include speech intelligibility measures, frequency discrimination measures, amplitude discrimination measures, frequency selectivity measures, or time selectivity measures. Auditory ability measures may vary with frequency and / or level, for example. Speech intelligibility measures may be, for example, the “Speech Intelligibility Index” (see, for example, [ANSI / ASA S3.5; 1997]) or any other suitable speech intelligibility measure such as the STOI measure (see, for example, [Taal et al.; 2010]). Frequency discrimination measures can indicate a user’s ability to distinguish two close frequencies (f1, f2), for example, by enabling the smallest frequency range Δf that distinguishes f1 from f2. disc (=f2-f1) is used for indication. Minimum frequency range Δf discIt can vary with frequency. The amplitude measurement indicates the user's ability to distinguish two close levels (L1, L2), for example, by enabling the minimum level difference ΔL that distinguishes L1 from L2. disc (=L2-L1) is used for marking. Minimum level difference Δf disc It can vary with frequency (and / or level). Amplitude measures may include, for example, amplitude modulation (AM) measurements. Amplitude measures may also include, for example, measurements of the user's auditory threshold (e.g., in the form of audiogram data).

[0025] Different characteristics of the test signal can be represented by one or more of the following:

[0026] - Different signal-to-noise ratios (SNR);

[0027] -Different modulation depths or modulation indices;

[0028] -Different detection thresholds for a tone in broadband, band-limited, or band-stop noise, describing frequency selectivity;

[0029] -Different detection thresholds for time differences in broadband or band-limited noise, describing time selectivity;

[0030] - As a function of the modulation frequency, such as the modulation transfer function, different depths or exponents of amplitude modulation.

[0031] -Different frequencies or depths of spectral modulation;

[0032] - Sensitivity to frequency modulation under varying center frequency and bandwidth;

[0033] - Frequency modulation direction, such as the distinction between the positive and negative phases of Schroeder phase stimulation.

[0034] This method may include selecting a predictive test for estimating a user's level of hearing ability. The predictive test may be selected from the following group:

[0035] -Spectral-time modulation test;

[0036] - Three-number test;

[0037] - Gap detection;

[0038] - Cut noise test;

[0039] -TEN test;

[0040] - Cochlear compression.

[0041] The “Spectro-temporal modulation (STM) test” measures a user’s ability to distinguish the spectral-temporal modulation of a test signal. Performance in the STM test a) can explain a significant portion of a user’s ability to understand speech (speech intelligibility); and especially b) can continue to explain a large share of speech intelligibility differences even after decomposing differences that can be explained by audiograms, see, for example, [Bernstein et al.; 2013; Bernstein et al.; 2016]. STM is determined by modulation depth (the amount of modulation), modulation frequency (fm, cycles per second), and spectral density (Ω, cycles per octave). The specific form of the STM test is the “Audible Contrast Threshold test” (developed by the Interacoustics Research Unit as part of Interacoustics A / S).

[0042] The "Three-Digit Test" is a speech recognition hearing test in noise using combinations of three spoken digits, presented against a noisy background, such as with headphones or a speaker from a hearing aid or a pair of hearing aids, played or relayed from an assistive device such as a smartphone (see, for example, http: / / hearcom.eu / prof / DiagnosingHearingLoss / SelfScreenTests / ThreeDigitTest_en.html). The results are correlated with the user's auditory threshold, such as the speech reception threshold (SRT). A version of the Three-Digit Test forms part of the Danish clinical test of speech recognition in noise, "Dantale." In this test, the Danish digits 0, 1, 2, 3, 5, 6, 7, and 12 are used to form 60 different groups of three arranged in tripartite units. The individual digits are acoustically identical, and the interval between digits in a group of three is 0.5 seconds (see, for example, [Elberling et al.; 1989]). In this specification, the term "three-number test" is used as a general term referring to a test in which the listener is presented with three numbers and has the task of identifying which numbers are presented. This may include a result measure that is a threshold version and a version that measures the percentage or proportion of correctly identified numbers.

[0043] The notch noise test is used to evaluate frequency selectivity. The target tone is presented in the presence of masking noise with notches (i.e., spectral gaps), and the width of the notch varies. The threshold for detecting pure tones is measured as a function of the notch width.

[0044] The TEN (Threshold Equalizing Noise) test is used to identify dead zones in the cochlea. The target is typically a pure tone presented in the suspected dead zone, and masking noise is presented at adjacent frequencies to prevent the target from being detected by listening at the off-frequency.

[0045] The processing algorithm may include one or more of the following: noise reduction algorithm, directionality algorithm, feedback control algorithm, speaker separation and speech enhancement algorithm.

[0046] This method can be incorporated into the fitting process, where the hearing aid is adjusted to the user's needs. This method can be performed, for example, by an audiologist when configuring a specific hearing aid for a particular user, such as adjusting parameter settings to meet the user's specific needs. Different parameter settings may relate to different processing algorithms, such as noise reduction (e.g., making it more or less aggressive), directionality (e.g., activating at higher or lower noise levels), feedback control (e.g., adjusting the fit based on the user's desired acoustic environment), and so on.

[0047] The steps for conducting predictive testing may include:

[0048] -Activate the test mode of the auxiliary device;

[0049] The predictive test is performed via the auxiliary device.

[0050] The assistive device may include a remote control for the hearing aid or a smartphone. The assistive device may form part of a fitting system for configuring the hearing aid (such as processing algorithm parameters) to meet the user's specific needs. The hearing aid and the assistive device are adapted to enable data exchange between them. The assistive device may be configured to run an application (APP) from which predictive tests are initiated. Predictive tests may, for example, be a triadic test or a spectrum-time modulation (STM) test.

[0051] The process of conducting a predictive test can be initiated by the user. Predictive tests can be performed via an application (APP) running on the assistive device. Predictive tests can be performed through a fitting system that communicates with, forms part of, or is constituted by the assistive device. The process of activating the test mode of the assistive device can be performed by the user. Predictive tests can also be initiated by a hearing care specialist (HCP) during the hearing aid fitting process using the fitting system, where the parameters of one or more processing algorithms of the processor are adjusted according to the user's needs.

[0052] Hearing device

[0053] On one hand, the present invention provides a hearing aid configured to be worn on or in a user's ear and / or at least partially implanted in a user's head. The hearing aid may include a forward path for processing an electrical input signal representing sound provided by an input unit and presenting the processed signal, perceptible as sound, to the user via an output unit. The forward path includes a processor for performing said processing by executing one or more configurable processing algorithms. The hearing aid may be adapted to personalize the parameters of said one or more configurable processing algorithms according to the user's specific needs based on the described method.

[0054] Hearing devices may consist of or include air-conduction hearing devices, bone-conduction hearing devices, cochlear implant hearing devices, or combinations thereof.

[0055] Hearing devices may be adapted to provide frequency-varying gain and / or level-varying compression and / or frequency shifting (with or without frequency compression) from one or more frequency ranges to one or more other frequency ranges to compensate for a user's hearing loss. Hearing devices may include a signal processor for amplifying the input signal and providing a processed output signal.

[0056] Hearing devices may include an output unit for providing stimulation, perceived as an acoustic signal by a user, based on processed electrical signals. The output unit may include multiple electrodes of a cochlear implant (for CI-type hearing devices) or a vibrator in a bone conduction hearing device. The output unit may include an output transducer. The output transducer may include a receiver (speaker) for providing the stimulation as an acoustic signal to the user (e.g., in acoustic (air conduction-based) hearing devices). The output transducer may also include a vibrator for providing the stimulation as mechanical vibrations of the skull to the user (e.g., in bone-attached or bone-anchored hearing devices).

[0057] The hearing device may include an input unit for providing an electrical input signal representing sound. The input unit may include an input transducer, such as a microphone, for converting the input sound into an electrical input signal. The input unit may include a wireless receiver for receiving wireless signals that include or represent sound and providing an electrical input signal representing said sound. The wireless receiver may, for example, be configured to receive electromagnetic signals in the radio frequency range (3 kHz to 300 GHz). The wireless receiver may, for example, be configured to receive electromagnetic signals in the optical frequency range (e.g., infrared light 300 GHz to 430 THz or visible light such as 430 THz to 770 THz).

[0058] Hearing devices may include directional microphone systems adapted to spatially filter sound from the environment, thereby enhancing a target sound source among multiple sound sources in the local environment of the user wearing the hearing device. The directional system is adapted to detect (e.g., adaptive detection) the direction from which a specific portion of the microphone signal originates. This can be achieved, for example, in a variety of different ways described in the prior art. In hearing devices, microphone array beamformers are commonly used to spatially attenuate background noise sources. Many beamformer variations can be found in the literature. Minimum variance distortionless response (MVDR) beamformers are widely used in microphone array signal processing. Ideally, an MVDR beamformer keeps the signal from the target direction (also known as the line of sight) unchanged while attenuating sound signals from other directions to the greatest extent possible. A generalized sidelobe canceller (GSC) structure is an equivalent representation of an MVDR beamformer, offering computational and digital representation advantages over a direct implementation of the original form.

[0059] Hearing devices can be portable (i.e., configured to be wearable) devices or integral to them, such as devices that include a local power source, such as a battery, for example a rechargeable battery. Hearing devices can be, for example, lightweight, easy-to-wear devices, such as having a total weight of less than 100g, such as less than 20g.

[0060] A hearing aid may include a forward or signal path between an input unit (such as an input converter, for example a microphone or microphone system and / or a direct electrical input (such as a wireless receiver)) and an output unit such as an output converter. A signal processor is located in this forward path. The signal processor is adapted to provide frequency-varying gain according to the specific needs of the user. The hearing aid may include an analysis path having functionalities for analyzing the input signal (such as determining level, modulation, signal type, acoustic feedback estimate, etc.). Some or all of the signal processing of the analysis path and / or signal path may be performed in the frequency domain. Some or all of the signal processing of the analysis path and / or signal path may be performed in the time domain.

[0061] The hearing device can be configured to operate in different modes, such as a normal mode and one or more specific modes, which may be user-selectable or automatically selected. Operating modes can be optimized for specific acoustic conditions or environments. Operating modes may include low-power modes, in which the functionality of the hearing device is reduced (e.g., for energy saving), such as disabling wireless communication and / or disabling specific features of the hearing device. Operating modes can be directional or omnidirectional.

[0062] The hearing device may include multiple detectors configured to provide status signals relating to the hearing device's current network environment (such as the current acoustic environment), and / or the current state of the user wearing the hearing device, and / or the current state or operating mode of the hearing device. Alternatively or additionally, one or more detectors may form part of an external device that communicates with the hearing device (e.g., wirelessly). The external device may include, for example, another hearing device, a remote control, an audio transmission device, a telephone (e.g., a smartphone), external sensors, etc.

[0063] Hearing devices may include a voice activity detector (VAD) for estimating whether (or with what probability) an input signal (at a specific point in time) includes a voice signal. Hearing devices may also include a self-voice detector for estimating whether (or with what probability) a particular input sound (such as speech) originates from the voice of a user of the hearing device system.

[0064] Multiple detectors may include motion detectors, such as accelerometers. The motion detectors are configured to detect movements of the user's facial muscles and / or bones, such as those caused by speech or chewing (e.g., jaw movements), and provide detector signals that identify the movements.

[0065] The hearing device may include a classification unit configured to classify the current situation based on input signals from (at least partially) a detector and possibly other inputs. In this specification, "current situation" is defined by one or more of the following:

[0066] a) Physical environment (including the current electromagnetic environment, such as the presence of electromagnetic signals (including audio and / or control signals) that are planned or unplanned to be received by the hearing device, or other properties of the current environment that are different from acoustics);

[0067] b) Current acoustic conditions (input level, feedback, etc.); and

[0068] c) The user's current mode or state (movement, temperature, cognitive load, etc.);

[0069] d) The current mode or state of the hearing device and / or another device communicating with the hearing device (selected program, time elapsed since the last user interaction, etc.).

[0070] The classification unit may be based on or include a neural network, such as a trained neural network.

[0071] Hearing devices may include acoustic (and / or mechanical) feedback control (such as suppression) or echo cancellation systems.

[0072] Hearing devices may also include other suitable functions for the applications involved, such as compression and noise reduction.

[0073] Hearing devices may include hearing aids, such as hearing instruments, such as hearing devices adapted to be located at the user's ear or wholly or partially in the ear canal, such as headphones, headsets, ear protection devices, or combinations thereof. Hearing aid systems may include loudspeaker amplifiers (including multiple input converters and multiple output converters, for example, for use in audio conferencing situations), such as including beamforming filter units, such as providing multi-beamforming capabilities.

[0074] application

[0075] On the one hand, applications of the hearing device described in detail in the "Detailed Description" section and defined in the claims are provided. Applications can be provided in systems including one or more hearing aids (such as hearing instruments), headphones, headsets, active ear protection systems, and combinations thereof.

[0076] Computer-readable media or data carrier

[0077] The present invention further provides a tangible computer-readable medium (data carrier) storing a computer program including program code (instructions), which, when the computer program is run on a data processing system (computer), causes the data processing system to perform (implement) at least some (such as most or all) of the steps of the methods described above, in detail in the "Detailed Description" and as defined in the claims.

[0078] By way of example, but not limitation, the aforementioned tangible computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disc storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to execute or store required program code in the form of instructions or data structures and is accessible by a computer. As used herein, disks include compact discs (CDs), laser discs, optical discs, digital multipurpose discs (DVDs), floppy disks, and Blu-ray discs, wherein these disks typically magnetically copy data while simultaneously being optically copied using lasers. Other storage media include those stored in DNA (e.g., in synthetic DNA strands). Combinations of the aforementioned disks should also be included within the scope of computer-readable media. In addition to being stored on tangible media, computer programs may also be transmitted via transmission media such as wired or wireless links or networks such as the Internet and loaded into data processing systems to run at locations other than tangible media.

[0079] Computer program

[0080] In addition, this application provides a computer program (product) including instructions that, when run by a computer, cause the computer to perform the steps of the methods (methods) described above, in detail in the "Detailed Description" section, and as defined in the claims.

[0081] Data processing system

[0082] In one aspect, the present invention further provides a data processing system, including a processor and program code, the program code causing the processor to perform at least some (such as most or all) of the steps of the methods described above, in detail in the "Detailed Description" section, and as defined in the claims.

[0083] Hearing system

[0084] On the other hand, a hearing device and a hearing system including auxiliary devices are provided, including those described above, described in detail in the "Detailed Description" section, and defined in the claims.

[0085] Hearing systems are adapted to establish communication links between hearing devices and assistive devices so that information (such as control and status signals, possibly audio signals) can be exchanged or forwarded from one device to another.

[0086] Auxiliary devices may include remote controls, smartphones, or other portable or wearable electronic devices such as smartwatches.

[0087] The auxiliary device may consist of or include a remote control for controlling the functions and operation of the hearing device. The remote control functions are implemented in a smartphone, which may run an app that enables control of the audio processing device via the smartphone (the hearing device includes a suitable wireless interface to the smartphone, such as Bluetooth or some other standardized or proprietary solution).

[0088] The auxiliary device may be constituted by or include an audio gateway device, which is adapted to receive multiple audio signals (e.g., from an entertainment device such as a TV or music player, from a telephone device such as a mobile phone, or from a computer such as a PC) and to select and / or combine appropriate signals (or combinations of signals) from the received audio signals for transmission to the hearing device.

[0089] The assistive device may constitute or include another hearing device. The hearing system may include two hearing devices suitable for implementing a binaural hearing system, such as a binaural hearing aid system.

[0090] A hearing system may include a hearing aid and an assistive device, the system being adapted to establish a communication link between the hearing aid and the assistive device to enable data exchange or forwarding from one device to another, wherein the assistive device is configured to execute applications that implement a user interface for the hearing aid and predictive tests for estimating the user's hearing ability, which can be initiated by the user and executed through the assistive device, including:

[0091] a) The sound elements of the predictive test are played through a speaker, for example, an auxiliary device; or

[0092] b) Transmitting the sound elements of the predicted test to the hearing aid via the communication link for presentation to the user via the hearing aid's output unit; and

[0093] The user interface is configured to receive user responses to the prediction test, and the auxiliary device is configured to store the user responses to the prediction test.

[0094] Auxiliary devices may include remote controls, smartphones, or other portable or wearable electronic devices such as smartwatches.

[0095] The assistive device includes a fitting system for adjusting the hearing aid to the needs of a particular user, or is part of such a fitting system. The fitting system and the hearing aid are configured to enable the exchange of data between them, such as enabling different (e.g., personalized) parameter settings to be forwarded from the fitting system to the hearing aid (e.g., the hearing aid's processor).

[0096] The assistive device can be configured to estimate the user's speech reception threshold (SRT) from the user's response to a predictive test. The SRT (or speech recognition threshold) is defined as the sound pressure level at which 50% of speech is correctly recognized. It is also possible to perform measurements with targets different from 50% correctness. Other performance levels typically measured include, for example, 70% and 80% correctness.

[0097] The assistive device can be configured to perform a predictive test as a three-digit test, wherein the sound elements of the predictive test include a) digits played with different signal-to-noise ratios, or b) digits played with a fixed signal-to-noise ratio, but with different hearing aid parameters such as different compression or noise reduction settings.

[0098] APP

[0099] On the other hand, the present invention also provides a non-transitory application called an APP. The APP includes executable instructions configured to run on an assistive device to implement a user interface for the hearing device or hearing system described above, in detail in the "Detailed Description," and as defined in the claims. The APP is configured to run on a mobile phone, such as a smartphone, or another portable device enabled to communicate with said hearing device or hearing system.

[0100] Non-transitory applications can be configured to enable users to perform one or more of the following steps:

[0101] - Select and initiate predictive tests to estimate the user's hearing ability when the user listens to test signals with different characteristics;

[0102] - Initiate analysis of the results of the predictive test for the user and provide a measurement of the user's auditory ability;

[0103] - Select the specific processing algorithm for the hearing aid;

[0104] -Based on the different characteristics of the test signal, the algorithm selects a cost-benefit function and / or key value from one or more relevant psychometric functions related to the user's auditory ability; and

[0105] - For the user, one or more personalized parameters of the processing algorithm are determined based on the hearing ability metric and the cost-benefit function.

[0106] Non-transient applications can be configured to allow users to apply personalized parameters to the processing algorithm.

[0107] Non-transitory applications can be configured to enable users to:

[0108] - The results of verifying the personalized parameters when they are applied to the input sound signal provided by the input unit of the hearing aid and when the resulting signal is played back to the user by the output unit of the hearing aid;

[0109] - Accept or reject personalized parameters.

[0110] definition

[0111] In this specification, "hearing aid" as a hearing instrument refers to a device suitable for improving, enhancing, and / or protecting a user's hearing ability, which achieves this by receiving sound signals from the user's environment, generating corresponding audio signals, possibly modifying the audio signals, and providing the possibly modified audio signals as audible signals to at least one of the user's ears. The audible signals may be provided, for example, as sound signals radiating into the user's outer ear, sound signals transmitted as mechanical vibrations through the bone structures of the user's head and / or through parts of the middle ear to the user's inner ear, and electrical signals transmitted directly or indirectly to the user's cochlear nerve.

[0112] Hearing aids can be configured to be worn in any known manner, such as as a unit worn behind the ear (having a tube that directs radiated sound signals into the ear canal or having an output transducer, such as a speaker, arranged close to or located within the ear canal), as a unit wholly or partially arranged in the auricle and / or ear canal, as a unit connected to a fixed structure implanted in the skull, such as a vibrator, or as a connectable unit that is wholly or partially implanted. Hearing aids may include a single unit or several units that communicate with each other (e.g., acoustically, electrically, or optically). The speaker may be housed within the housing along with other components of the hearing aid, or it may be an external unit (possibly combined with a flexible guiding element such as a dome-shaped element).

[0113] More generally, a hearing aid includes an input transducer for receiving sound signals from the user's environment and providing a corresponding input audio signal, and / or a receiver for receiving the input audio signal electronically (i.e., wired or wirelessly); signal processing circuitry (typically configurable) for processing the input audio signal (such as a signal processor, for example including a configurable (programmable) processor, such as a digital signal processor); and an output unit for providing an audible signal to the user based on the processed audio signal. The signal processor may be adapted to process the input signal in the time domain or in multiple frequency bands. In some hearing aids, amplifiers and / or compressors may constitute the signal processing circuitry. The signal processing circuitry typically includes one or more (integrated or separate) storage elements for executing programs and / or for storing parameters used (or potentially used) in the processing and / or for storing information suitable for the hearing aid's functionality and / or for storing information used, for example, in conjunction with an interface to the user and / or an interface to a programming device (such as processed information, for example, provided by the signal processing circuitry). In some hearing aids, the output unit may include an output transducer, such as a loudspeaker for providing airborne sound signals or a vibrator for providing sound signals propagating through structures or fluids. In some hearing aids, the output unit may include one or more output electrodes for providing electrical signals that electrically stimulate the cochlear nerve (e.g., to a multi-electrode array) (cochlear implant hearing aids).

[0114] In some hearing aids, the vibrator may be adapted to transmit structurally propagated sound signals to the skull transdermally or through the skin. In some hearing aids, the vibrator may be implanted in the middle ear and / or inner ear. In some hearing aids, the vibrator may be adapted to provide structurally propagated sound signals to the middle ear bones and / or cochlea. In some hearing aids, the vibrator may be adapted to provide fluid-propagated sound signals to the cochlear fluid, for example, through the oval window. In some hearing aids, the output electrode may be implanted in the cochlea or on the medial side of the skull and may be adapted to provide electrical signals to the hair cells of the cochlea, one or more auditory nerves, the auditory brainstem, the auditory midbrain, the auditory cortex, and / or other parts of the cerebral cortex.

[0115] Hearing aids can be adapted to the specific needs of users, such as those with hearing loss. The configurable signal processing circuitry of a hearing aid can be adapted to apply frequency- and level-variable compression and amplification of the input signal. Customized frequency- and level-variable gain (amplification or compression) can be determined during the fitting process by the fitting system based on the user's hearing data, such as an audiogram, using basic fitting principles (e.g., speech adaptation). This frequency- and level-variable gain can be reflected, for example, in processing parameters, uploaded to the hearing aid via an interface to a programming device (fitting system), and used by a processing algorithm executed by the hearing aid's configurable signal processing circuitry.

[0116] A “hearing system” refers to a system that includes one or two hearing aids. A “binaural hearing system” refers to a system that includes two hearing aids and is adapted to work together to provide audible signals to both of a user’s ears. A hearing system or a binaural hearing system may also include one or more “assistive devices” that communicate with the hearing aids and influence and / or benefit from the functionality of the hearing aids. The aforementioned assistive devices may include at least one of the following: a remote control, a remote microphone, an audio gateway device, an entertainment device such as a music player, a wireless communication device such as a mobile phone (e.g., a smartphone), or a tablet computer, or another device, such as one that includes a graphical interface. Hearing aids, hearing systems, or binaural hearing systems may be used, for example, to compensate for hearing loss in individuals with hearing impairments, enhance or protect the hearing ability of individuals with normal hearing, and / or transmit electronic audio signals to individuals. Hearing aids or hearing systems may, for example, be part of or interact with broadcasting systems, active ear protection systems, hands-free telephone systems, car audio systems, entertainment systems (such as TV, music playback, or karaoke), teleconferencing systems, classroom amplification systems, etc.

[0117] The present invention can be used, for example, in applications such as hearing aids. Attached Figure Description

[0118] Various aspects of the invention will be best understood from the following detailed description taken in conjunction with the accompanying drawings. For clarity, these drawings are schematic and simplified, showing only the details necessary for understanding the invention while omitting other details. Throughout the specification, the same reference numerals are used for the same or corresponding parts. Features of each aspect may be combined with any or all features of other aspects. These and other aspects, features, and / or technical effects will be apparent from and illustrated in the following figures, wherein:

[0119] Figure 1 The upper right curve schematically illustrates how the effect of the directional algorithm can influence speech intelligibility (in this case, speech in the presence of noise) for high-performing and low-performing individuals as a function of signal-to-noise ratio (SNR); and the lower right curve schematically illustrates that high-performing listeners with low SRT can expect to enjoy the net benefit of beamforming at a considerably lower SNR than low-performing listeners with higher SRT.

[0120] Figure 2 The left side shows, as Figure 1 The test scenario shown on the right illustrates different cost-benefit curves as a function of SNR for the directional algorithm (MVDR), demonstrating off-axis "cost" and on-axis "benefit".

[0121] Figure 3The relationship between speech intelligibility (percentage of correct speech [0%; 100%]) and SNR is shown for different hearing scenarios [-10dB; +10dB] for hearing-impaired users: a) using forward beamplotter (DIR front), target in front; b) using auricular-OMNI (P-OMNI), target in front; c) using auricular-OMNI, target on one side; and d) using forward beamplotter (DIR front), target on one side.

[0122] Figure 4 This demonstrates how settings / parameters in hearing aids can be updated, for example, via an assistive device's app;

[0123] Figure 5 An app capable of performing speech intelligibility tests is shown running on an assistive device;

[0124] Figure 6 An embodiment of the scheme according to the invention for personalizing audible or visible indicators in a hearing aid is shown;

[0125] Figure 7 A method for generating a database for training algorithms (such as neural networks) is shown, which is used to adaptively provide personalized parameter settings for processing algorithms of hearing aids;

[0126] Figure 8A A binaural hearing aid system is shown, comprising a pair of hearing aids that communicate with each other and with an assistive device that implements a user interface;

[0127] Figure 8B The implementation in Figure 8A The user interface in the assistive device of a binaural hearing aid system;

[0128] Figure 8C An in-ear receiver hearing aid according to an embodiment of the present invention is illustrated schematically, for example, used in... Figure 8A In the binaural hearing aid system.

[0129] The further applicability of the invention will become apparent from the detailed description given below. However, it should be understood that while the detailed description and specific examples illustrate preferred embodiments of the invention, they are given for illustrative purposes only. Other embodiments of the invention will become apparent to those skilled in the art based on the following detailed description. Detailed Implementation

[0130] The detailed description below, taken in conjunction with the accompanying drawings, serves as a description of various different configurations. This detailed description includes specific details to provide a thorough understanding of several different concepts. However, it will be apparent to those skilled in the art that these concepts can be implemented without these specific details. Several aspects of the apparatus and method are described by various different blocks, functional units, modules, elements, circuits, steps, processes, algorithms, etc. (collectively, “elements”). Depending on the specific application, design constraints, or other reasons, these elements may be implemented using electronic hardware, computer programs, or any combination thereof.

[0131] Electronic hardware may include microelectromechanical systems (MEMS), (e.g., application-specific integrated circuits), microprocessors, microcontrollers, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), gating logic, discrete hardware circuits, printed circuit boards (PCBs) (e.g., flexible PCBs), and other suitable hardware configured to perform the various functions described in this specification, such as sensors for sensing and / or recording the physical properties of the environment, devices, users, etc. Computer programs should be interpreted broadly as instructions, instruction sets, code, code segments, program code, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, programs, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description languages, or other names.

[0132] Figure 1 The left side shows the experimental configuration in which user U is exposed to target signals (“targets”) from three different directions (T1 (front), T2 (left), T3 (right)) and noise signals (“masking signals?”) distributed at multiple different locations around the user. Figure 1 The upper right curve illustrates how the effect of the directional algorithm can influence speech intelligibility (in this case, speech in the presence of noise) for high-performing and low-performing individuals as a function of signal-to-noise ratio (SNR); and the lower right curve schematically shows that high-performing listeners with low SRT can expect to enjoy the net benefit of beamforming at a considerably lower SNR than low-performing listeners with higher SRT. Figure 1 Together, it shows that the targeting system (ideally) should be enabled with different SNRs for different individual users.

[0133] This invention proposes using a cost-benefit function as a way to quantify the costs and benefits of an aid system for each individual. This invention also discloses a method for using predictive metrics to achieve better individualization for each patient.

[0134] Cost-benefit function

[0135] exist Figure 1In the example, the cost-benefit function is estimated as the increase caused by the directionality of the forward target minus the decrease caused by the directionality of the off-axis (lateral) target.

[0136] like Figure 1 As shown, the point at which a listener's net benefit crosses the net "cost" varies from person to person (depending on the individual's hearing ability).

[0137] The cost-benefit function can relate to many aspects of hearing aid outcomes, benefits, or "quality" such as speech intelligibility, sound quality, and listening effort.

[0138] It should be noted that Figure 1 The illustration in the upper right corner shows a simplified representation of the listener's speech comprehension in an omnidirectional situation as a single psychometric function, although in practice, separate psychometric functions may exist for targets coming from the front and from the sides.

[0139] Predictive metrics

[0140] Predictive metrics may include, for example, psychoacoustic testing, questionnaires, assessments by hearing care professionals (HCPs) and / or subjective patient assessments.

[0141] Possible predictive tests include, but are not limited to:

[0142] Spectrum-Time Modulation (STM) Testing;

[0143] Three-number test;

[0144] Personal preference survey;

[0145] Listening preference survey;

[0146] HCP sliders or similar HCP evaluation tools;

[0147] Customer sliders or similar customer self-assessment tools;

[0148] Acceptable noise level test;

[0149] SWIR test;

[0150] Listening effort assessment;

[0151] Reading breadth test;

[0152] Daily attention test;

[0153] Auditory vocabulary learning test;

[0154] Text reception threshold;

[0155] Other cognitive assessment tests;

[0156] Speech testing in noise;

[0157] SNR loss assessment;

[0158] Time-based fine structure sensitivity;

[0159] Time modulation detection;

[0160] Frequency selectivity;

[0161] Critical bandwidth;

[0162] Notch noise bandwidth estimation;

[0163] Threshold equalization noise (TEN) testing (see, for example, [Moore et al.; 2000]);

[0164] Spectral ripple identification;

[0165] Frequency modulation detection;

[0166] Gap detection;

[0167] Cochlear compression estimation;

[0168] Questionnaire: SSQ;

[0169] Questionnaire: Self-reported deficiencies;

[0170] Binaural masking detection;

[0171] Laterality;

[0172] Listen carefully and try your best;

[0173] Spatial awareness test;

[0174] Spatial positioning test;

[0175] Testing the apparent source width;

[0176] Demographic information such as age, gender, and the language spoken by the patient.

[0177] Predictive metrics, for example, are used to estimate an individual patient's need for assistance and adjust patient settings for the corresponding processing algorithm accordingly. The aforementioned assessment can, for example, be performed during the fitting process, where the hearing aid processing parameters are adjusted to the individual's needs.

[0178] An assessment of where the cost-benefit function for an individual patient intersects from net benefit to net cost can be performed according to the present invention.

[0179] Below, various aspects of the invention are illustrated in the context of a directional algorithm. However, this method can also be used in other assistive systems such as noise reduction.

[0180] In this example, benefits and costs are measured in the speech intelligibility (SI) domain (benefits are measured as an increase in SI, and costs are measured as a decrease in SI). Benefits and costs related to speech intelligibility can be measured through specific hearing tests evaluated on a given user wearing a hearing aid with parameter settings representing different operating modes of the orientation system (e.g., at different SNRs).

[0181] However, this method can also be used with a wide range of result metrics, including but not limited to:

[0182] The patient's cognitive load hearing level;

[0183] Listen carefully and try your best;

[0184] Spiritual energy;

[0185] The ability to remember what was said;

[0186] Spatial awareness;

[0187] Spatial perception;

[0188] Patient's perception of sound quality;

[0189] The patient tries hard to perceive sounds through their hearing.

[0190] Figure 2 The left side shows, as Figure 1 The test scenario shown on the right illustrates different cost-benefit curves for the directional algorithm (MVDR) as a function of SNR, displaying off-axis "costs" and on-axis "benefits." The vertical axis represents the relative benefit of the outcome measure, such as the speech intelligibility benefit measured with and without a help system as the percentage of correctly repeated words in the listening test increases.

[0191] In other words, Figure 2 This paper presents a quantitative approach that balances preserving a rich representation of the listener's surrounding sound environment with enhancing focus on the target of interest that the listener may struggle to understand as situations become more challenging. The curves in the figure show that each individual has regions where the function is negative and regions where the function is positive. We can also see that the positive regions are located further to the left along the SNR axis, and the negative regions are located further to the right; that is, the positive regions are always under more unfavorable conditions than the negative regions (in this case, a lower SNR). Furthermore, this method provides analytical tools that we can use to find the intersection of negative and positive (i.e., benefit) for a given individual. It is important to highlight the individual nature of this method: it calculates individualized functions and diagnoses the needs of different listeners differently.

[0192] Figure 2This indicates a modeling approach using off-axis sound. Due to directivity (such as in MVDR beamformers), the beam pattern faces forward (e.g., θ = 0°, see...). Figure 2 (Left side), observed increased speech intelligibility "on-axis" (front), i.e., the target reaches the user from the front, and observed "off-axis" (e.g., θ = +90° or -90°, see...) Figure 2 Reduced speech intelligibility (from the left side), meaning the target reaches the user from one side. At high SNR: negative cost / benefit; at low SNR: positive cost / benefit.

[0193] While the aforementioned methods are valuable for optimizing hearing aid fitting for individuals, limitations in time and the availability of equipment across clinical hearing disorders will most likely necessitate their indirect application via predictive testing, rather than a direct approach of calculating the full cost-benefit function for every patient. The reason for choosing an indirect method (i.e., using predictive testing) is that, in clinical practice, it is nearly impossible to collect the vast amounts of data required to calculate the full cost / benefit function for all patients. Therefore, predictive tests are used that are associated with one or more key characteristics of cost / benefit. This may include, but is not limited to, the zero-crossing point of the cost-benefit function or identifying features of one or more psychometric functions derived from it. This is achieved by collecting data from the test population for the aforementioned cost-benefit analysis and for predictive testing, and then identifying good predictive tests with the help of association analysis. Predictive tests may include, for example, the three-number test, the spectral-time modulation test, and other tests.

[0194] Figure 3 The relationship between speech intelligibility (percentage of correct speech [0%; 100%]) and SNR is shown for different hearing scenarios [-10dB; +10dB] for hearing-impaired users: a) using a forward beammap (DIR front), with the target in front; b) using auricular-OMNI (P-OMNI), with the target in front; c) using auricular-OMNI, with the target on one side; and d) using a forward beammap (DIR front), with the target on one side.

[0195] The SNR range is an exemplary range and may vary depending on the specific application or acoustic situation.

[0196] Measuring thresholds in predictive testing

[0197] Methods for estimating thresholds may include the following steps:

[0198] - Run predictive tests (such as three-number tests and / or spectral-time modulation (STM) tests);

[0199] - Change the input parameters (e.g., the modulation depth of the STM or the SNR of the three-digit test);

[0200] - Find the threshold (e.g., the modulation depth or SNR when a listener achieves a predetermined target performance level, where possible target performance levels could be 50% correct, 80% correct, etc.).

[0201] The three-digit test is sometimes called the "digits in noise" test. The target sound is three digits, such as "2"..."7"..."5". The SNR can be changed by altering one or more "masking sounds", such as modulated noise, the recording scene, etc.

[0202] Map prediction tests to automatic learning

[0203] The goal of this invention is to enable hearing aid users to use the sounds around them without removing sounds when they are not deemed necessary from the perspective of target (speech) signal perception (such as speech intelligibility).

[0204] A 50% intelligibility rate for speech can be considered a key indicator (e.g., defining the speech reception threshold (SRT)). It can also serve as an indicator of how well the listener uses sound, supported by pupillary measurement data. If we use a region of approximately 50% intelligibility, then from... Figure 3 We can consider "a" as the point where the scenario has become challenging enough that the user experiences a significant "loss of use" with targets coming from the side in omnidirectional settings, and "b" as the point where the listener experiences a significant "loss of use" with targets coming from the front in full MVDR. Based on this logic, we propose starting the transition away from omnidirectional settings at "a" or lower, and reaching full MVDR at "b" or higher. The transition (a minus b) indicates the range of dB the listener desires to transition from fully omnidirectional to maximally directional settings.

[0205] 1. Example: Providing personalized data

[0206] Below, we outline alternative or supplementary approaches for collecting data that can be used to fine-tune parameters in hearing instruments, such as for personalization.

[0207] Modern hearing aids do not necessarily consist only of hearing instruments attached to the ear; they may also include or be connected to additional computing power, such as computing power available through assistive devices like smartphones. Other assistive devices, such as tablets, laptops, and other wired or wireless communication devices, can also be used as resources for the hearing instruments. Audio signals can be transmitted (exchanged) between the hearing instruments and assistive devices, and the hearing instruments can be controlled via a user interface on the assistive device, such as a touch-sensitive display.

[0208] The method proposes using training sounds to fine-tune the settings of a hearing aid. Training sounds could represent acoustic scenarios that the listener finds difficult. These scenarios can be recorded via the hearing aid's microphone and wirelessly transmitted to an assistive device. The assistive device can analyze the recorded acoustic scenarios and suggest one or more sets of improved hearing aid parameters. The listener can then listen to sounds processed based on these parameters and compare them to sounds processed based on a previous set of parameters. For example, a set of parameters selected (e.g., by the user) can be replaced with a new set of parameters (e.g., by the hearing aid or assistive device) and compared to a previous set. Thus, based on feedback from the listener, the improved set of processing parameters can be stored in the hearing aid and / or applied when similar acoustic environments are recognized. The final improved set of processing parameters can be fed back to the assistive device so that it can update its recommendation rules based on the user feedback.

[0209] Another proposal is to estimate the hearing aid user's ability to understand speech. Speech intelligibility testing is often too time-consuming to be performed during hearing aid fitting, but speech intelligibility testing and / or other predictive tests can be made available through assistive devices, allowing hearing aid users to determine their speech reception threshold (SRT). Based on the estimated or predicted SRT and audiogram, hearing aid parameters (such as the aggressiveness of the noise reduction system) can be fine-tuned for the individual listener. Such predictive tests (such as the "triple count test" or "spectral-time modulation (STM) test") can be performed using several different types of background noise representing different hearing conditions. In this way, hearing aid settings can be optimized to ensure the best speech intelligibility in many different situations.

[0210] Other proposals include measuring a listener’s ability to locate sound sources simulated by a hearing aid, or their preference for noise suppression and / or reverberation suppression, or their ability to separate several sound sources.

[0211] Figure 4 This illustrates how settings / parameters in hearing aids can be updated, for example, via an assistive device's app. See [link / reference] whenever the listener finds a sound scenario difficult. Figure 4 (1) is used to selectively record, transmit, and store segments (time periods) of sound from all preferred hearing aid microphones in the assistive device (alternatively, the hearing aid continuously transmits sound to the assistive device, which is stored in a buffer such as a circulating (first-in, first-out (FIFO)) buffer). Based on the stored sound, a new set of settings will be proposed to the hearing aid, and the listener will be prompted to choose between listening to the sound processed by the new settings and listening to the sound processed by the current settings. The listener can then choose the proposed settings to take precedence over the current settings, see [link to relevant documentation]. Figure 4 (2) The current settings will be updated whenever the new settings are selected first. This process can be repeated several times; see (see section 2). Figure 4In steps (3) and (4), the listener will be able to choose between the current setting and the new setting each time until the user is satisfied. This can be used as a general setting in the hearing instrument, or these settings can be recalled whenever a similar acoustic scenario is detected. Processing with these settings can occur in the hearing instrument, where sound fragments are transmitted back to the hearing instrument; or the processing can occur in an auxiliary device that mimics the processing of the hearing instrument. In this way, only the processed signal is transmitted to the hearing instrument and presented directly to the listener.

[0212] Figure 5 This demonstrates an app running on an assistive device that performs speech intelligibility tests. The tests can be of many types, but very directly related to... Figure 5 One type of use of diagrams is, for example, a digit recognition test (such as a "three-number test"), in which the listener must repeat different digits (in... Figure 5 The numbers ('4,8,5', '3,1,0', and '7,0,2', respectively) can be wirelessly transmitted to a hearing aid and presented to the listener at different signal-to-noise ratios (via an output unit, such as the hearing aid's speaker). Different numbers can also be played through the assistive device's speaker and picked up by the hearing aid's microphone. This allows for the estimation of the speech reception threshold (SRT) and psychometric functions, which, along with hearing... Figure 1 It can be used to fine-tune hearing aid settings. As an alternative to playing numbers with different signal-to-noise ratios, it is also possible to consider presenting these numbers with a fixed signal-to-noise ratio, but with different hearing aid parameters such as different compression or noise reduction settings, thereby fine-tuning the hearing instrument fitting.

[0213] Personalized decisions can be based on supervised learning (such as neural networks). Personalization parameters (such as the amount of noise reduction) can be determined, for example, by a trained neural network, where the input features are a set of predictive metrics (such as measured SRT, audiograms, etc.).

[0214] (e.g., press) Figure 4 The combined input / preferred settings (as illustrated in the example) and other user-specific parameters obtained elsewhere (such as SRT, audiogram data, etc.) can be used as a training set for the neural network to predict personalized settings.

[0215] and Figure 4 Regarding this invention, one aspect relates to a hearing aid (or app) configured to store a period of input signal, such as the last 20 seconds, in a buffer. Whenever the listener finds the situation difficult (or it may contain too much processing of unnatural signals), the sound can be repeated with a more aggressive setting / less aggressive setting. In this way, over time, the hearing aid can learn the user's preferred settings for different situations.

[0216] 2. Example: Personalization of hearing aid indicators

[0217] A scheme to enable hearing aid users to select and personalize the sounds / patterns of their hearing aids according to their preferences is proposed below. This can be done during hearing aid fitting for the user (e.g., at a hearing care specialist (HCP)) or after fitting, for example via a mobile phone or other processing device (e.g., a computer). The set of sounds and LED patterns can be made available to the user (e.g., in the cloud or on a local device). The user can browse, select, and try several different options (sound and LED patterns) before choosing a preferred option. The selected sound and LED pattern is then stored in the user's hearing aid, replacing possible default values. The user may also be allowed to create and generate their own audio (e.g., sound patterns, music, or speech clips) and / or visible (e.g., LED patterns). This approach allows the user to select a set of indicators of personal interest along with personalized indicator patterns, and further leads to more use cases than currently known, such as, but not limited to:

[0218] - Configure and personalize indicators for health alerts or other notifications (using information from hearing instrument sensors or AI predictive information (AI = Artificial Intelligence));

[0219] - Integration with "If...Then..." (IFTTT) enables personalized event-triggered indicators.

[0220] Figure 6 An embodiment of the scheme according to the invention for personalizing audible or visible indicators in a hearing aid is illustrated schematically. Figure 6 An example of a general solution with partial use cases is shown, where key operations are marked with square brackets, such as [Get Indicators] which refers to the hearing aid user U or hearing care specialist (HCP) retrieving a "dictionary" of audio and / or visual indicators (e.g., stored on a server, such as in the "cloud"). Figure 6 (referred to as "cloud data storage" in Chinese, or stored locally) downloaded to its computer or device (AD).

[0221] 3. Example: Adaptive personalization of hearing aid parameters using contextual information.

[0222] Hearing aid fitting can be personalized, for example, by defining general preferences for low, medium, or high ambient sound attenuation, and thus determining auditory focus and noise reduction based on questionnaire input and / or hearing tests (such as the triad test or STM test). However, these settings do not adapt to the user's cognitive abilities throughout the day. For example, the ability to separate speech during a meeting may be better in the morning, or the need for background noise reduction may increase in challenging acoustic environments at night. These thresholds are rarely personalized due to a lack of clinical resources in hearing health care, although it is known that patients' ability to understand speech in noise (e.g., across specific time periods, such as a day) can vary by up to 15 dB. Furthermore, hearing aids are calibrated based on pure-tone audiograms, which do not capture the large differences in loudness functions (such as loudness growth functions) between users. The logic for converting audiograms to frequency-specific amplification (VAC+, NAL) is based on the average loudness function (or loudness growth function), while in reality, patients can vary by up to 30 dB in how they perceive the loudness of sound in both ears. Combining internet-connected hearing aids with a smartphone app makes it possible to dynamically adjust the beamforming threshold or modify the gain based on each user's perceived loudness.

[0223] While it's possible to define "if...then..." (IFTTT) rules for changing the programming on a hearing aid connected to a smartphone via Bluetooth, in such a configuration, there's no feedback loop to assess whether the user is satisfied with the hearing aid settings in a given context. The hearing aid also doesn't learn from data to automatically adjust its settings for changing contexts.

[0224] Furthermore, the personalization of hearing impairment treatment has so far been based on predictive methods, such as questionnaires or hearing tests. While this can be a good starting point, it is possible to expect more accurate estimates of individual abilities to be achieved through the determination of individual preference profiles in multiple different sound environments. In addition, estimates of an individual's speech reception threshold (SRT) or full psychometric function may be possible through the determination of client preference profiles in the client's "real" sound environment.

[0225] Based on the above, it becomes possible to use information other than audiograms for better individualized adjustment of hearing instruments.

[0226] Hearing aids capable of storing alternative fitting profiles as programs or other sets of settings enable the adjustment of auditory focus and noise reduction settings based on context and time of day. Context-based enabling models user behavior as time-series parameters, i.e., “trigger A,” “location B,” “event C,” “time D,” and “sound environment type F,” are defined based on, for example, hearing aid detection including SNR and levels, such as sound environment, smartphone location, and calendar data (IFTTT triggers: iOS location, Google Calendar events, etc.). These are associated with preferred hearing aid actions “set low / medium / high” as illustrated below:

[0227] ['Left','Mikkelborg','Bicycle','Morning','High','SNR value (dB)']

[0228] ['Entered','Eriksholm','Office','Morning','Low','SNR value (dB)']

[0229] ['Calendar','Eriksholm','Lunch','Afternoon','Midday','SNR value (dB)']...

[0230] In addition to low-level signal parameters such as SPL or SNR, we classify soundscapes based on audio spectrograms generated through hearing aid signal processing. This enables not only environmental recognition such as "office," but also the differentiation of intentions such as "conversation" (2-3 people, self-voice) and "ignoring speech" (2-3 people, no self-voice detected). The app can be configured to:

[0231] 1) Automatically adjusts low / medium / high thresholds (SPL, SNR) to define when beamforming and attenuation should take effect; and

[0232] 2) By adjusting the frequency-specific amplification based on the predicted environment and intentions, the relevant logical basis (VAC+, NAL) is dynamically personalized.

[0233] The app can combine the soundscape "environment + intent" classification with the user's selected preferences to predict when to modify the logic basis by generating an amplified deviation, such as + / - 6dB. This is added to or subtracted from the average logic basis across, for example, 10 frequency bands from 200Hz to 8kHz, as illustrated below:

[0234] ['Office','Conversation',-2dB,-1dB,0dB,+2dB,+2dB,+2dB,+2dB,+2dB,+2dB,+2dB']

[0235] ['Café','Social',+2dB,+2dB,+1dB,0dB,0dB,0dB,0dB,-1dB,-2dB,-2dB,-2dB']

[0236] That is, based on the "environment + intent" classification, the app can personalize the logical basis (VAC+, NAL) through overwriting, thereby...

[0237] 1) Gain shaping based on phrases like "office + conversation" enhances high-frequency gain, thus improving speech intelligibility; or

[0238] 2) Modify the gain of the loudness function of an individual learning based on preferences such as "coffee shop + social interaction" to reduce the perceived loudness of a given environment.

[0239] Modeling user behavior as time-series parameters (“trigger A”, “location B”, “event C”, “time D”, “setting low / medium / high”) provides the basis for training decision tree algorithms to predict the optimal settings when encountering new locations or event types.

[0240] Applying machine learning techniques to contextual data by using parameters as input for training a classifier enables the prediction of corresponding changes in hearing aid settings or other sets of settings (IFTTT action). Subsequently, implementing the trained classifier as an "if...then..." algorithm (decision tree) in a smartphone app will facilitate the prediction and automatic selection of the optimal setting in the face of changing context. That is, even when encountering new locations or events, the algorithm will predict the most likely settings based on previously learned behavioral patterns. As a result, this can improve individual general preferences for hearing aids and / or enhance the objective benefits of individual hearing aid use, such as speech intelligibility (SI).

[0241] In addition, the app will provide a simple feedback interface (accept / reject), allowing users to indicate whether the settings are satisfactory to ensure parameters are continuously updated and the classifier is retrained. Even with limited training data, the app will be able to adjust hearing aid settings based on the user's cognitive abilities and the changing sound environment throughout the day. Similarly, the generated data and user feedback can provide valuable insights, such as in which contexts to choose which hearing aid settings. Such information is useful for further optimizing the signal processing capabilities embedded in the hearing aid.

[0242] Figure 7 An embodiment of a method for generating a database for training algorithms (such as neural networks) is illustrated schematically, which is used to adaptively provide personalized parameter settings for processing algorithms of hearing aids. The method may include, for example, the following steps:

[0243] S1, which installs a ready-to-use hearing aid on the user's body;

[0244] S2 connects the hearing aid to an app on an assistive device such as a smartphone or similar processing device.

[0245] S3, (through hearing aids and / or assistive devices) picks up and analyzes the sound signals of the user's current acoustic environment;

[0246] S4 extracts relevant parameters of the acoustic environment (average sound level, noise level, SNR, music, single speaker, multiple speakers, dialogue, speech, no speech, estimated speech intelligibility, etc.);

[0247] S5 can extract parameters of the physical environment (such as time of day, location, temperature, and wind speed).

[0248] S6 may extract parameters of the user's status (such as cognitive load, exercise pattern, body temperature, etc.);

[0249] S7 automatically stores the corresponding values ​​of the parameters (related to the acoustic environment, physical environment, and user status) along with the hearing aid's user-changeable settings (such as volume, program, etc.).

[0250] The database can be generated during the hearing aid's learning mode, where the user encounters various acoustic situations (environments) in multiple different states (e.g., different times of day). In learning mode, the user is allowed to influence the processing parameters of the selected algorithm, such as noise reduction (e.g., a threshold for attenuating noise) or directionality (e.g., a threshold for applying directionality).

[0251] Algorithms (such as artificial neural networks, like deep neural networks) can be trained, for example, during the iterative process using a database of “ground truth” data as outlined above, for example, by applying a value function. Training can be performed, for example, using numerical optimization methods, such as (iterative) stochastic gradient descent (or ascent) or adaptive moment estimation (Adam). The trained algorithm can be applied to the hearing aid’s processor during normal use. Alternatively or additionally, the trained (potentially continuously updated) algorithm can be available during normal use of the hearing aid, for example via a smartphone, or, for example, in the cloud. Possible latency due to partial processing in another device (or via a network on a server, such as the “cloud”) is likely acceptable because it is not necessary to apply corrections (personalization) to the hearing aid’s processing within milliseconds or seconds.

[0252] During normal use, the data mentioned in steps S3-S6 can be generated and fed back to the trained algorithm, whose output can be (estimated) volume and / or program settings and / or personalized parameters of the processing algorithm for a given environment and user mental state.

[0253] Figure 8AAn implementation of a hearing system according to the invention is shown, such as a binaural hearing aid system. This hearing system includes left and right hearing aids that communicate with assistive devices such as remote control devices, communication devices such as mobile phones, or similar devices capable of establishing a communication link to one or both of the left and right hearing aids. Figure 8B An auxiliary device is shown, configured to execute an application (APP) that implements the user interface of the hearing system, from which the functions of the hearing system, such as the operating mode, can be selected.

[0254] Figure 8A , 8B Together, we illustrate an embodiment of a binaural hearing aid system according to the present invention, comprising a first (left) and a second (right) hearing aid (HD1, HD2), and an application scenario of the assistive device AD. The assistive device AD ​​includes mobile phones such as smartphones. Figure 8A In some embodiments, the hearing aid and assistive device are configured to establish a wireless link (WL-RF) between them, such as a digital transmission link conforming to Bluetooth standards (e.g., Bluetooth Low Energy or equivalent). Alternatively, these links can be implemented in any other convenient wireless and / or wired manner and conform to any suitable modulation type or transmission standard, which may vary for different audio sources. Figure 8A , 8B Assistive devices (such as smartphones) include user interfaces (UIs) that provide remote control functionality for hearing aids or hearing systems, such as for changing programs or operating modes or parameters (such as volume) in the hearing aid. Figure 8B The user interface (UI) shows the app (denoted as the "Personalized App") used to select the operating mode of the hearing system (between "Normal Mode" and "Learning Mode"). In "Learning Mode" (in... Figure 8B In the example, it is assumed that the selection is made (as shown in bold italics), and the personalization of processing parameters can be performed by the user, as described in this invention. The selection between multiple prediction tests can be made via a "personalized app" (here, choosing between "3D test" and "spectral-time modulation" (STM test)). Figure 8B In this example, 3D testing has been selected. Another option for choosing the processing algorithm to be personalized is via the user interface (UI). Figure 8B In this example, users can choose between a "noise reduction" algorithm and a "directional" algorithm; the directional algorithm has been selected. The screen also includes a "start" button.

[0255] - "Start Test" is used to begin the selected prediction test (here, "Three-Number Test," see also: [link to relevant documentation]). Figure 5 );

[0256] - "Determine Personalization Parameters" is used to begin calculating the personalization parameters of the selected processing algorithm (here, the directional algorithm) based on auditory ability metrics extracted from the selected predictive test (here, the "three-number test") and a cost-benefit function (or its subcomponents) for the selected processing algorithm and the user; and

[0257] - "Application Parameters" are used to store personalized parameters determined for the selected processing algorithm for future use in the hearing aids of the users involved.

[0258] The app may also include, for example, screens or functions that allow users to evaluate them before accepting determined personalized parameters (via the app parameters button), such as in conjunction with... Figure 4 As shown in the figure.

[0259] Hearing aids (HD1, HD2) in Figure 8A The device shown is installed at the user's ear (behind the ear), for example, see [link to example]. Figure 8C Other types can also be used, such as those that are completely located in the ear (e.g., in the ear canal), or completely or partially implanted in the head. For example... Figure 8A As shown, each hearing aid may include a wireless transceiver to establish an interaural IA-WL between hearing aids, such as based on inductive communication or RF communication (such as Bluetooth technology). Each hearing aid also includes a transceiver for establishing a wireless link WL-RF (e.g., based on radiated field (RF)) to the assistive device AD, for at least receiving and / or transmitting signals, such as control signals, information signals, and, for example, audio signals. The transceivers are identified by RF-IA-Rx / Tx-1 and RF-IA-Rx / Tx-2 in the right (HD2) and left (HD1) hearing aids, respectively.

[0260] In this embodiment, the remote control app is configured to interact with a single hearing aid (rather than with a binaural hearing aid system).

[0261] exist Figure 8A , 8B In this embodiment, the auxiliary device is described as a smartphone. However, the auxiliary device can be embodied in other portable electronic devices, such as an FM transmitter, a dedicated remote control, a smartwatch, a tablet computer, etc.

[0262] Figure 8C An in-ear receiver type hearing aid (so-called BTE / RITE type hearing aid) is shown according to an embodiment of the present invention (BTE = behind the ear, RITE = in-ear receiver). Figure 8CAn exemplary hearing aid, such as an air conduction hearing aid, includes a BTE section (BTE) adapted to be located at or behind the user's ear and an ITE section (ITE) adapted to be located in or within the user's ear canal and includes a receiver (= speaker, SPK). The BTE section and the ITE section are connected (e.g., electrically) via a connecting element IC and internal wiring in the ITE and BTE sections (see wiring Wx in the BTE section, for example). Alternatively, the connecting element may consist entirely or partially of a wireless link between the BTE section and the ITE section. Of course, other types may also be used, such as the ITE section including a custom earmold adapted to the user's ear and / or ear canal, or a type consisting of a custom earmold.

[0263] exist Figure 8C In the hearing aid embodiment, the BTE section includes two input transducers (such as microphones) (M BTE1 M BTE2 The input unit of the input transducer is used to provide a representation of the input audio signal (S). BTE The input unit also includes two wireless receivers (WLR1, WLR2) (or transceivers) for providing corresponding directly received auxiliary audio and / or control input signals, and / or enabling the transmission of audio and / or control signals to other devices such as remote controls or processing devices, telephones, or another hearing aid. The processing capabilities of the assistive device and / or server connected to a network (such as the “cloud”) can be provided via one of the wireless transceivers (WLR1, WLR2). The hearing aid HD includes a substrate SUB on which multiple electronic components are mounted, including a memory MEM, which stores, for example, various hearing aid programs (e.g., user-specific data such as audiogram-related data or parameter settings derived therefrom, such as personalized ones), or is provided via a personalized app (see [link to app]). Figure 2 For example, determining the aforementioned (user-specific) procedure, or other parameters of the algorithm such as beamformer filter weights and / or gradient parameters, and / or hearing aid configuration such as input source combination (M BTE1 M BTE2 (M ITE (WLR1, WLR2), for example, optimized for multiple different listening conditions. The memory MEM may also include a database of personalized parameter settings according to the invention for different acoustic environments (and / or different processing algorithms). In a specific operating mode, two or more electrical input signals from the microphone are combined to provide a beamforming signal, which is provided by applying appropriate (e.g., complex) weights to (at least partially) the corresponding signals. The beamformer weights are preferably personalized as proposed in the invention.

[0264] The substrate SUB also includes a configurable signal processor (DSP, such as a digital signal processor), for example, a processor for applying gain that varies with frequency and level, such as providing beamforming, noise reduction, filter bank functions, and other digital functions implementing the features of the hearing aid according to the invention. The configurable signal processor DSP is adapted to access a memory MEM, for example, to select appropriate parameters for the current configuration or operating mode and / or hearing condition and / or to write data to the memory (such as algorithm parameters, for example, for recording user behavior), and / or to access a database of personalized parameters according to the invention. The configurable signal processor DSP is also configured to process one or more electrical input audio signals and / or one or more directly received auxiliary audio input signals based on the currently selected (activated) hearing aid program / parameter settings (e.g., automatically selected, such as based on one or more sensors, or based on input from the user interface). The mentioned functional units (and other elements) may be divided into circuits and components according to the application involved (e.g., for size, power consumption, analog-to-digital processing, acceptable latency, etc.), for example, integrated in one or more integrated circuits, or as a combination of one or more integrated circuits with one or more individual electronic components (such as inductors, capacitors, etc.). A configurable signal processor (DSP) provides the processed audio signal, which is intended to be presented to the user. The substrate also includes a front-end IC (FE) for interfacing the configurable DSP with input and output converters, typically including interfaces between analog and digital signals (e.g., interfaces to microphones and / or speakers, and possibly to sensors / detectors). The input and output converters can be separate components or integrated with other electronic circuitry (e.g., MEMS-based).

[0265] Hearing aids (HD) also include output units (such as output converters) for providing stimuli that can be perceived as sound by the user, based on processed audio signals from or derived from a processor. Figure 8C In the hearing aid embodiment, the ITE portion includes at least a portion of an output unit in the form of a speaker (also called a receiver) SPK for converting electrical signals into acoustic (airborne) signals, which (when the hearing aid is mounted on the user's ear) are guided to the eardrum to provide a sound signal there. ED The ITE section also includes guide elements such as the dome-shaped DO (dot) to guide and position the ITE section within the user's ear canal. Figure 8C In some embodiments, the ITE portion also includes another input converter such as a microphone M. ITE Used to provide the input sound signal S representing the location of the ear canal. ITE The electrical input audio signal. Sound S ITE The sound travels from the environment through the semi-open dome (DO) via a direct acoustic pathway to the residual cavity at the eardrum. Figure 8CThe direct path is indicated by a dashed arrow. Sound propagates directly (through the sound field S). dir (Identification) and the sound from the HD audio system (via sound field S) HI (Indicated) The sound field S at the eardrum is mixed. ED The ITE component may include (potentially customized) earmolds to provide a relatively tight fit to the user's ear canal (thus minimizing sound leakage directly toward the eardrum and from the speaker to the environment). The earmold may include ventilation channels to provide (controlled) leakage of sound from the residual cavity between the earmold and the eardrum (thus managing the occlusion effect).

[0266] (from input converter M) BTE1 M BTE2 M ITE The electrical input signal can be processed in the time domain or (time-)frequency domain (or partly in the time domain and partly in the frequency domain, if deemed advantageous for the application in question).

[0267] All three microphones (M BTE1 M BTE2 M ITE ) or two of the three microphones (M BTE1 M ITE (This can be included in the "personalization" process according to the invention.) The "front" BTE microphone M BTE1 It can be selected as a reference microphone.

[0268] exist Figure 8C In one embodiment, the connector IC includes electrical conductors for connecting electrical elements to the BTE and ITE portions. The connector IC may include an electrical connector CON to connect a cable to a mating connector in the BTE portion. In another embodiment, the connector IC is a sound tube, with the speaker SPK located within the BTE portion. In yet another embodiment, the hearing aid does not include a BTE portion; instead, the entire hearing aid is enclosed within an earmold (ITE portion).

[0269] Figure 8CThe illustrated hearing aid HD embodiment is a portable device that includes a battery BAT, such as a rechargeable battery, based on lithium-ion battery technology, for example, to power electronic components in the BTE and ITE sections. In embodiments, the hearing aid is adapted to provide frequency-varying gain and / or level-varying compression and / or frequency shifting (with or without frequency compression from one or more frequency ranges to one or more other frequency ranges), for example, to compensate for the user's hearing loss. The BTE section may include, for example, a connector (such as a DAI or USB connector) for connecting a "shoe" with additional functionality (such as an FM shoe or an additional battery), or a programming device (such as a fitting system), or a charger to the hearing aid HD. Alternatively or additionally, the hearing aid may include a wireless interface for programming and / or charging the hearing aid.

[0270] In this invention, schemes for personalizing settings have been described within the framework of processing algorithms (such as directional or noise reduction algorithms) using predictive testing. However, these types of tests can also be used for prescribing physical acoustics, which include, for example, ventilation channels (“vents”).

[0271] When appropriately replaced by a corresponding process, the structural features of the apparatus described above, in detail in the "Detailed Description" section, and as defined in the claims can be combined with the steps of the method of the present invention.

[0272] Unless explicitly stated otherwise, the singular forms “a” and “the” used herein include the plural forms (i.e., meaning “at least one”). It should be further understood that the terms “having,” “comprising,” and / or “including” as used in the specification indicate the presence of the stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof. It should be understood that, unless explicitly stated otherwise, when an element is referred to as “connected” or “coupled” to another element, it may be a direct connection or coupling to the other element, or there may be intermediate inserting elements. The term “and / or” as used herein includes any and all combinations of one or more of the listed related items. Unless explicitly stated otherwise, the steps of any method disclosed herein do not necessarily have to be performed in the exact order disclosed.

[0273] It should be understood that references to "an embodiment," "an embodiment," "an aspect," or "may" in this specification mean that a particular feature, structure, or characteristic described in connection with that embodiment is included in at least one embodiment of the invention. Furthermore, particular features, structures, or characteristics may be suitably combined in one or more embodiments of the invention. The foregoing description is provided to enable those skilled in the art to implement the various aspects described herein. Various modifications will be apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects.

[0274] The claims are not limited to the aspects shown herein, but encompass the full scope consistent with the language of the claims, wherein, unless expressly stated, an element referred to in the singular does not mean "one and only one," but rather "one or more." Unless expressly stated, the term "some" means one or more.

[0275] The scope of this invention should be determined based on the claims.

[0276] References

[0277] ·Bernstein, JGW, Mehraei, G., Shamma, S., Gallun, FJ, Theodoroff, SM, and Leek, MR (2013). “Spectrotemporal modulation sensitivity as a predictor of speech intelligibility for hearing-impaired listeners,” J. Am. Acad. Audiol., 24, 293–306. doi:10.3766 / jaaa.24.4.5.

[0278] ·[ANSI / ASA S3.5;1997]"American National Standard Methods for theCalculation of the Speech Intelligibility Index,"ANSI / ASA S3.5,1997Edition,June6,1997.

[0279] ·[Taal et al.; 2010] Cees H.Taal; Richard C.Hendriks; Richard Heusdens; Jesper Jensen, "A short-time objective intelligibility measure for time-frequency weighted noisy speech", ICASSP 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp.4214-4217.

[0280] ·[Moore et al.;2000]Moore,B.C.J.,Huss,M.,Vickers,D.A.,Glasberg,B.R.,and Alcantara,J.I.(2000).“A test for the diagnosis of dead regions in thecochlea,”Br.J.Audiol.,doi:10.3109 / 03005364000000131.doi:10.3109 / 03005364000000131.

[0281] ·[Elberling et al.;1989]C.Elberling,C.Ludvigsen and P.E.Lyregaard,”DANTALE:A NEW DANISH SPEECH MATERIAL”,Scand.Audiol.18,pp.169-175,1989.

[0282] ·[Bernstein et al.;2016]Bernstein,J.G.W.,Danielsson,H., M.,Stenfelt,S., J.,&Lunner,T.,“Spectrotemporal Modulation Sensitivityas a Predictor of Speech-Reception Performance in Noise With Hearing Aids”,Trends in Hearing,vol.20,pp.1-17,2016.

Claims

1. A method for personalizing one or more parameters of a processing algorithm used in a hearing aid processor for a specific user, the method comprising: - A predictive test is performed to estimate the user's hearing ability while the user listens to test signals with different characteristics; - Analyze the results of the user's predictive test and provide the user's auditory ability measure based on the analysis of the results of the user's predictive test, wherein the auditory ability measure includes speech intelligibility measure; - Select the specific processing algorithm for the hearing aid, including the directionality algorithm; - Estimate the cost-benefit function of the specific processing algorithm based on the auditory ability metric, wherein the cost-benefit function is estimated as the change in speech intelligibility metric - signal-to-noise ratio caused by the directionality of on-axis targets minus the change in speech intelligibility metric - signal-to-noise ratio caused by the directionality of off-axis targets, wherein the on-axis targets are targets that arrive at the user from the front, and the off-axis targets are targets that arrive at the user from one of the sides; - For the user, one or more personalized parameters of the specific processing algorithm are determined based on the auditory ability metric and the cost-benefit function.

2. The method according to claim 1, wherein, The different characteristics of the test signal are represented by one or more of the following: - Different signal-to-noise ratios (SNR); -Different modulation depths or modulation indices; -Different detection thresholds for a tone in broadband, band-limited, or band-stop noise, describing frequency selectivity; -Different detection thresholds for time differences in broadband or band-limited noise, describing time selectivity; - Different depths or exponents of amplitude modulation as a function of modulation frequency; -Different frequencies or depths of spectral modulation; - Sensitivity to frequency modulation under varying center frequency and bandwidth; - Frequency modulation direction.

3. The method according to claim 1, wherein, The method includes selecting a predictive test to estimate the user's level of hearing ability.

4. The method according to claim 1, wherein, The prediction test is selected from the following group: --Spectral-time modulation test; --Three-number test; --Gap detection; --Cut notch noise test; --TEN test; -- Cochlear compression.

5. The method according to claim 1, wherein, The processing algorithm includes one or more of the following: noise reduction algorithm, feedback control algorithm, speaker separation and speech enhancement algorithm.

6. The method according to claim 1, wherein, The method forms part of a fitting process in which the hearing aid is adjusted to meet the user's needs.

7. The method according to claim 1, wherein, The steps for conducting predictive testing include: -Activate the test mode of the auxiliary device; The predictive test is performed via the auxiliary device.

8. The method according to claim 7, wherein, The process of conducting predictive testing is initiated by the user.

9. The method according to claim 1, wherein, For orientation algorithms that represent off-axis costs and on-axis benefits, the cost-benefit function is expressed as a function of the signal-to-noise ratio.

10. A computer-readable storage medium storing thereon a non-transitory application called an APP, the APP including executable instructions configured to execute on an assistive device to implement a user interface for a hearing system including a hearing aid, wherein the APP is configured to enable a user to perform one or more of the following steps: - Select and initiate predictive tests to estimate the user's hearing ability when the user listens to test signals with different characteristics; - Initiate analysis of the results of the predictive test for the user and provide the user's auditory ability measure based on the analysis of the results of the predictive test for the user, wherein the auditory ability measure includes speech intelligibility measure; - Select the specific processing algorithm for the hearing aid, including the directionality algorithm; - Estimate the cost-benefit function of the specific processing algorithm based on the auditory ability metric, where... The cost-benefit function is estimated as the change in speech intelligibility metric - signal-to-noise ratio (SNR) due to the directionality of on-axis targets minus the change in speech intelligibility metric - SNR due to the directionality of off-axis targets, wherein the on-axis target is a target arriving at the user from the front, and the off-axis target is a target arriving at the user from one of the sides; and - For the user, one or more personalized parameters of the processing algorithm are determined based on the hearing ability metric and the cost-benefit function.

11. The computer-readable storage medium according to claim 10, wherein, The app is configured to allow users to apply the personalized parameters to the processing algorithm.

12. The computer-readable storage medium according to claim 11, wherein, The app is configured to enable users to: - The results of verifying the personalized parameters when they are applied to the input sound signal provided by the input unit of the hearing aid and when the resulting signal is played back to the user by the output unit of the hearing aid; - Accept or reject personalized parameters.

Images