Procedure for environmentally dependent operation of a hearing aid

Abstract

The invention relates to a method for the environment-dependent operation of a hearing system (1), wherein, in a training phase (10), values ​​for a first plurality of environmental data (15) of a first user of the hearing system (1) are determined at a plurality of data collection times (T1, T2, T3), and based on the values ​​of the environmental data (15), a feature vector (M1, M2, M3) is formed for each of the data collection times (T1, T2, T3) in a feature space (18) of at least four dimensions, in particular at least six dimensions, each of the feature vectors (M1, M2, M3) is mapped to an associated representative vector (R1, R2, R3) in a representation space (20) of at most three dimensions, in particular two dimensions, and based on a spatial distribution of a subgroup of representative vectors (R1, R2, R3), a first region (24) in the representation space (20) is defined for a first environmental situation. (25) of the hearing system (1) is defined,wherein at least one value of a setting (26) for a signal processing of the hearing system (1) is specified for the first environmental situation (25), and wherein in an application phase (30) at an application time (T4) values ​​for the first plurality of environmental data (15) of the first user or a second user of the hearing system (1) are determined and on the basis of the values ​​of the environmental data (15) a corresponding feature vector (M4) for the application time (T4) is formed, on the basis of the first region (24) of the representation space (20) and on the basis of the feature vector (T4) for the application time (T4) the presence of the first environmental situation (25) is recognized, and the at least one value of the signal processing of the hearing system (1) is set according to its specification for the first environmental situation (25), in particular automatically, and the hearing system (1) is operated with the at least one value set in this way.

Description

[0001] The invention relates to a method for the environment-dependent operation of a hearing system, wherein in a training phase, values ​​for a first plurality of environmental data of a first user of the hearing system are determined at a plurality of collection times, and based on the values ​​of the environmental data for each of the collection times, a feature vector is formed in a feature space, wherein for a first environmental situation, at least one value of a setting for signal processing of the hearing system is specified, and wherein in an application phase, at an application time, values ​​for the first plurality of environmental data of the first user or a second user of the hearing system are determined and based on the values ​​of the environmental data, a corresponding feature vector is formed for the application time, and the at least one value of the signal processing of the hearing system is set according to its specification for the first environmental situation,and the hearing system is operated with at least one value set in this way.

[0002] In hearing systems, a user is provided with a sound signal to hear. This sound signal is generated on the basis of an electrical audio signal, which in turn represents the user's acoustic environment. An important example of a hearing system is a hearing aid, which is intended to correct the user's hearing impairment as far as possible through frequency-band-dependent signal processing of the audio signal, in order to make useful signals in ambient noise more audible to the user. Hearing aids can be available in various designs, e.g. BTE, ITE, CIC, RIC or other forms. A similar type of hearing system is a hearing aid such as a cochlear implant or bone conduction hearing aid.Other hearing systems can also be provided by PSADs (Personal Sound Amplification Devices: hearing aid systems used by people with normal hearing) as well as headsets or headphones, especially with active noise cancellation.

[0003] Environment-dependent operation of a hearing system is particularly well-known for hearing aids. This involves setting the audio signal processing settings based on a specific listening situation, where listening situations are defined by standardized groups of acoustic environments with certain comparable acoustic characteristics. If the audio signal detects that one of the standardized groups is present, the audio signal is processed using the corresponding settings predefined for this group of acoustic environments.

[0004] The definition of listening situations is often done in advance according to predefined criteria for individual acoustically measurable characteristics, e.g., at the factory. For the given listening situations, presets for the corresponding signal processing are often provided, which can then be individually adjusted by the user.

[0005] However, the acoustic recognition of individual listening situations is, on the one hand, a complex and potentially error-prone matter, since an acoustic environment may not exactly exhibit the acoustic characteristics that the corresponding listening situation would actually require (e.g., a "cocktail party" outdoors near a road, etc.). On the other hand, due to the multitude of characteristics that are evaluated to distinguish individual acoustic environments from one another and to assign the listening situations accordingly, it is simply hardly possible for a user to meaningfully define listening situations that are ideally suited to their everyday life. As a result, the user is usually dependent on the predefined definitions of listening situations.

[0006] JP 2005 203 981 A discloses a method for signal analysis for a hearing aid. During a learning phase, a plurality of learning signals are transferred to a self-organizing map, which assigns each sample or frame to a planar coordinate system at the relevant time. The assignment of the respective coordinates for a learning signal can vary over time. Based on this assignment, individual signals are then grouped together, and different signal processing parameters are defined for different groups.

[0007] US 2014 / 0 355 798 A1 describes a hearing aid device that can execute a hearing assistance algorithm based on signal processing parameters. For this purpose, a set of audiological values ​​for a population group can be identified, which has a first number of dimensions. The set of audiological values ​​is converted into a reduced data set, which has a second number of dimensions that is smaller than the first number of dimensions. A processor calculates a trajectory for the reduced data set. The trajectory provides signal processing parameters for the hearing aid device.

[0008] US 2015 / 0 124 984 A1 discloses a hearing aid configured to classify a sound environment based on a pattern in a daily routine, to categorize sound information using sound environment categories based on the pattern in the daily routine, and to control an output of the sound information based on the classified sound environment.

[0009] The invention is therefore based on the object of specifying a method by means of which a user can operate a hearing system depending on the environment, but the environments can be adapted to the user as individually as possible.

[0010] The stated object is achieved according to the invention by a method for the environment-dependent operation of a hearing system, wherein in a training phase, values ​​for a first plurality of environmental data of a first user of the hearing system are determined at a plurality of collection times, and based on the values ​​of the environmental data for each of the collection times, a feature vector is formed in an at least four-dimensional, in particular at least six-dimensional feature space, each of the feature vectors is mapped to an associated representative vector in a maximum three-dimensional, in particular two-dimensional, representation space, and based on a spatial distribution of a subgroup of representative vectors, a first region in the representation space for a first environmental situation of the hearing system is defined,wherein at least one value of a setting for signal processing of the hearing system is specified for the first environmental situation.,

[0011] It is provided that in an application phase, at a time of use, values ​​for the first plurality of environmental data of the first user or a second user of the hearing system are determined and, based on the values ​​of the environmental data, a corresponding feature vector for the time of use is formed; based on the first region of the display space and based on the feature vector for the time of use, the presence of the first environmental situation is recognized, in particular automatically; and the at least one value of the signal processing of the hearing system is set, in particular automatically, in accordance with its specification for the first environmental situation; and the hearing system is operated with the at least one value thus set. Advantageous and, in part, inventive embodiments are the subject of the dependent claims and the following description.

[0012] During the training phase, the first environmental situation is defined based on the environmental data, and it is determined how the first environmental situation can be differentiated from other environmental situations based on the environmental data. Furthermore, a signal processing setting is specified that is to be applied to an audio signal from the hearing system for the first environmental situation. During the application phase, the currently available values ​​for the corresponding environmental data are determined, and based on these environmental data values, it can now be determined whether the first environmental situation exists. If this is the case, the hearing system is operated with the corresponding specified signal processing setting.

[0013] During the training phase, the values ​​of the environmental data are determined at different sampling times so that the feature vectors, which are created based on the environmental data values ​​determined at the individual sampling times, are representative of as many acoustic environments as possible. Environmental data includes acoustic environmental data on acoustic environmental variables such as the frequencies of a background noise, the stationarity of a sound signal, sound levels, modulation frequencies, and the like. Furthermore, environmental data in the broader sense also includes "non-acoustic" data, for example, on accelerations or other movement variables of a hearing system's motion sensor, as well as biometric data, which can be recorded using EEG, EMG, PPG (photoplethysmogram), ECG, or similar.

[0014] The aforementioned variables can be measured by a hearing device of the hearing system, e.g., a hearing aid, and / or by another device of the hearing system, e.g., a smartphone, a smartwatch, or another suitable device with appropriate sensors. The determination of the environmental data values ​​from the measured variables can take place in the respective device itself—i.e., in the hearing aid, smartphone, or similar—or after transmission, e.g., from the hearing aid or a headset to the smartphone or a similar device of the hearing system. The variables are preferably measured continuously or quasi-continuously (i.e., at very short intervals, e.g., in the range of seconds), preferably over a longer period of time, e.g., a week or similar, so that the environments typically encountered by the user are recorded as completely as possible and thus, so to speak, "mapped."

[0015] As values ​​of the environmental data, the determined values ​​of the aforementioned or other corresponding variables can either be entered directly into the respective feature vectors, or the values ​​entered into the feature vectors are formed by calculating the mean and / or mean passage rate and / or variance or comparable statistical methods based on the respective variables. In the latter case, a feature sector preferably consists of individual entries, each of which is obtained in the manner described using statistical methods from the aforementioned acoustic environmental variables, movement variables and / or biometric data. In this case, the temporal mean or the mean passage rate or the variance of individual values ​​of a variable since the previous collection time can be calculated at a given time of collection and entered into the feature vector as the corresponding value of the environmental data.

[0016] At each collection point, a total of values ​​for at least four different characteristics, i.e., individual statistical characteristics of various environmental, movement, and / or biometric variables, are determined. Preferably, values ​​for at least six characteristics are determined. Particularly preferably, the same statistical characteristics, as described above, e.g., mean, mean-transmission rate, and variance, are determined as values ​​of the environmental data for each individual variable.

[0017] In order to give a user the opportunity to individually define individual environmental situations based on the determined "features", i.e. the corresponding feature vectors, the individual feature vectors, which contain the "features" at individual collection points in time, are first mapped to the respective corresponding representative vector in the representation space.

[0018] The representation space is at most three-dimensional, preferably two-dimensional, so that the representative vectors for defining the first environmental situation can be visualized for the user via the first region. Such a visualization of the representation space can be carried out in particular on a suitable visualization device of the hearing system, e.g., on a smartphone screen, which in this case becomes part of the hearing system through its integration into the method. A two-dimensional representation space can be represented directly as a "map," while a three-dimensional representation space can be represented, for example, by two-dimensional sectional planes or three-dimensional "point clouds," or similar, between which the user can switch, zoom, or move.

[0019] The mapping of the feature vectors of the feature space to the representative vectors of the representation space is preferably carried out in such a way that "similar feature vectors," i.e., feature vectors that are comparatively close to one another in the feature space due to a relative similarity of their features, are also comparatively close to one another in the representation space (relative to, for example, the overall size of the space used). Representative vectors (or groups of representative vectors) that are clearly separated from one another in the representation space preferably allow inference to separate feature vectors (or corresponding groups of feature vectors) in the feature space, thus enabling differentiation. Conversely, distinguishing between groups of feature vectors becomes more difficult with increasing overlap of the associated, corresponding groups of their respective representative vectors in the representation space.

[0020] Using individual representative vectors that are as close to one another as possible, a first region can now be defined in the representation space. This definition can be carried out, in particular, by the user of the hearing system or by an assistant to the user (e.g., a caregiver, nurse, etc.). A visualization of the representation space is preferably used for the definition. In particular, individual representative vectors can be provided with an additional marking, e.g., via a color representation, which can preferably correspond to an additional marking of the respective recording time for the underlying feature vector by the user, depending on the everyday / daily situation or similar. This can simplify the assignment of the representative vectors for the user.The time of collection can be marked, for example, by an input from the user which globally defines a specific situation in his daily routine, e.g. at home, in the car (on the way to / from work), in the office, in the canteen, during sports, in the garden, etc.

[0021] A subset of representative vectors is now used to define the first region based on their spatial distribution, in particular based on the area enclosed by them (i.e., by their corresponding endpoints in the representation space). This subset of representative vectors corresponds to a group of feature vectors in the feature space, so that the first environmental situation is defined via the corresponding value ranges of the features.

[0022] For the first environmental situation thus defined, which preferably relates to a situation in the user's daily routine, but can also be characterized by other features, particularly acoustic features (e.g., different acoustic environments in the office or at home, etc.), at least one value of the setting for the hearing system's signal processing is now specified. This is preferably done by the user of the hearing system (or, for example, by a technically skilled companion or caregiver). The user preferably enters the corresponding environment (e.g., in a moving car, indoors at home, outdoors in the garden, in the office / at work, etc.) and then modifies the signal processing settings, particularly "by ear," e.g., using a sound scale to adjust the treble or bass emphasis or so-called adaptive parameters for wind or background noise suppression.In principle, however, fine-tuning of any parameters typically used by a fully or semi-professionally trained acoustician is also possible. It is also possible for such an acoustician to perform the environment-specific signal processing settings, and thus define the settings for the initial environment, in a remote fitting session.

[0023] The training phase can thus be systematically divided into an analysis phase and a definition phase, whereby the analysis phase comprises the continuous measurement of the relevant quantities, the determination of the individual corresponding feature values ​​at the respective collection times and a mapping of the feature vectors into the representation space, while in the definition phase the first environmental situation and the associated at least one value of the setting for the signal processing are defined using the representative vectors.

[0024] During an application phase, the definitions of the first environmental situation and the associated at least one signal processing setting of the hearing system are integrated into the operation of the hearing system. For this purpose, at a point in time during the application phase, the hearing system, in particular also a hearing device of the hearing system, initially measures the same environmental and / or movement and / or biometric variables that were also measured in the training phase to determine the values ​​of environmental data. In an analogous manner, the values ​​for the same types of environmental data and a corresponding feature vector are formed from the measured variables as in the training phase.

[0025] The feature vector for the application time is then mapped into the representation space. This is preferably done using the same algorithm as the corresponding mappings from the training phase, or using an approximation method that is as consistent as possible with said algorithm, which, in particular, maps the feature vector of the application time to a representative vector in the representation space, for which representative vectors of its immediate surroundings are based on those feature vectors from the training phase that also form the immediate surroundings of the feature vector of the application time in the feature space.

[0026] If the representative vector thus formed for the time of application lies in the first region of the representation space, it can be concluded that the first environmental situation is present, and accordingly the at least previously defined setting of the signal processing in the operation of the hearing system can be used, i.e., for example, a corresponding, possibly frequency band-dependent amplification and / or dynamic compression, speech signal enhancement, etc. can be applied to an audio signal of the hearing system.

[0027] Alternatively, those regions can be identified in the feature space that correspond to the feature vectors whose representative vectors in the representation space are encompassed by the first region. The recognition of the first environmental situation can then also be performed based on said regions in the feature space if the feature vector for the time of application lies within such a region.

[0028] In particular, for the formation of the feature vector of the application time, a short-term temporal notification (e.g. in the range of a few seconds to a few minutes) or other statistical processing can be carried out, preferably of the same type as in the formation of the feature vectors of the training phase.

[0029] The described method allows the definitions of individual environmental situations to be specifically adapted to individuals or special groups of hearing aid wearers, and this definition can also be carried out by (technically skilled) persons without audiological or scientific training, whereby only a comparatively small effort is required by the hearing system (or an assisting person) for the definitions of the environmental situations, since this can be done directly via the visualization of the preferably two-dimensional display space.

[0030] This makes it possible to address the needs of small user groups in particular, for whom a manufacturer (or other solution provider) would find it too costly to specifically define environmental situations for automatic adjustment of the hearing system. This allows hearing systems to provide environmental classifiers that more specifically satisfy the needs of such user groups than the previously known 'stereotypical' classes of environmental situations. Universalized classes such as 'in the car' or 'in front of the television' were defined precisely because the overwhelming majority of hearing system users find themselves in such situations.

[0031] Since the method is also suitable for use by technically skilled people without audiological or scientific training, it opens up the possibility for not only a hearing system manufacturer (e.g. hearing aid manufacturers), but also other market participants or users to create their own definitions, e.g. hearing aid acousticians or similar, companions of people in specific professions (e.g. dentists, musicians, hunters) or even individual technically skilled users. This makes the use of the method relevant for a larger number of users, since there are generally few hearing system users who are willing to provide extensive information (e.g. inputs in smartphone apps), whereas there are many users who would like to provide as little information as possible beyond selecting a specific function and only make an input if they find a hearing impression unpleasant or in need of improvement.

[0032] In particular, it is also possible for the first environmental situation to be defined by a first user of the hearing system during the training phase, while this definition is used by a second user during the application phase. Thus, a first user can make the environmental situations they have defined available to other users for use with corresponding feature vectors. The definition of the signal processing settings associated with the first environmental situation is preferably performed by the user who uses the hearing system during the application phase.

[0033] Preferably, in the training phase, information on a current usage situation of the hearing system is stored by means of a user input, in particular depending on a defined situation in a daily routine of the first user of the hearing system, wherein the respective information on the usage situation is linked to the feature vectors and / or the associated representative vectors, which are formed on the basis of the values ​​of the environmental data collected during a specific user situation. The usage situation preferably describes a specific situation in the user's daily routine, e.g. at home, in the car (on the way to / from work), in the office, in the canteen, during sports, in the garden, etc. By additionally marking the feature vector or the associated representative vector, the user can also assign the first environmental situation with regard to the usage situation.

[0034] Conveniently, at least a subregion of the display space is visualized, in particular by means of a screen, and at least a subset of the representative vectors is displayed, wherein the first region in the display space is defined based on a user input, in particular with regard to a grouping of visualized representative vectors. The screen is in particular integrated into a corresponding auxiliary device of the hearing system, such as a smartphone, tablet, or similar device that can be connected to the hearing device, in particular wirelessly. The user can then view the individual representative vectors directly on the touchscreen in a two- or possibly three-dimensional representation (in the 3D case, via corresponding sectional planes) and group them accordingly to form the first region.

[0035] In particular, for at least some of the representative vectors, the respective information on the usage situation is visualized, at least in response to an action by the first user. This can be done via a corresponding color representation or by displaying a label on the respective representative vector.

[0036] Advantageously, at least during the training phase, the mapping of the feature vectors to the respective representative vectors is carried out in such a way that the distance relations of at least three feature vectors in the feature space are at least approximately preserved for the distance relations of the corresponding three representative vectors in the representation space as a result of the mapping. This means, in particular, that for each of the three feature vectors mv1, mv2, mv3 with the following distance relation in the feature space: mv1 − mv2 > mv1 − mv3 > mv2 − mv3 , the corresponding representative vectors rv1 (to mv1), rv2 (to mv2), rv3 (to mv3) in the representation space the distance relation rv1 − rv2 > rv1 − rv3 > rv2 − rv3 This maps groups of "similar" feature vectors, which differ only slightly from each other with respect to the entire area covered in the feature space, to "similar" representative vectors, which also differ only slightly from each other with respect to the entire area covered in the representation space.

[0037] Preferably, the mapping of the feature vectors to the respective corresponding representative vectors is carried out using a principal component analysis (PCA) and / or a locally linear embedding (LLE) and / or an isomap mapping and / or a Sammon mapping and / or preferably using a t-SNE algorithm and / or preferably using a self-organizing Kohonen network and / or preferably using a UMAP mapping. The aforementioned methods fulfill the aforementioned property with regard to distance relations and can be implemented efficiently.

[0038] Advantageously, in the application phase, values ​​for the first plurality of environmental data are determined at a plurality of successive application times, and corresponding feature vectors for the successive application times are formed on the basis of the values ​​of the environmental data, wherein the presence of the first environmental situation is recognized on the basis of the first region and on the basis of said feature vectors for the successive application times, in particular on the basis of a polygonal line made up of said feature vectors or a polygonal line made up of the representative vectors which correspond to said feature vectors in the representation space. In particular, machine learning can also be used to identify areas for feature or representative vectors outside the relevant polygonal line in which a corresponding feature or representative vector can be found for an application time.Representative vector leads to the presence of the first environmental situation.

[0039] For example, the five most recent representative vectors (from past application times) are always taken, and a polygonal line is constructed that encompasses all representative vectors (some or all of the representative vectors or their endpoints then represent the corner points of the polygonal line). The hearing system is only assigned to the first environmental situation, and the corresponding signal processing settings are activated, if at least a predefined percentage of the area of ​​the polygonal line (e.g., 80%) lies within the first region in the display space. This prevents a single "outlier" of a single feature, which is attributable to a random but possibly atypical occurrence for an environment, from leading to a changed classification with regard to the environmental situation.

[0040] According to the invention, for the first plurality of environmental data, acoustic environmental data is determined based on a signal from at least one electroacoustic input transducer, in particular a microphone, and / or movement-related environmental data is determined based on at least one signal from an acceleration sensor, in particular one with multidimensional resolution, and / or a gyroscope and / or a GPS sensor. Preferably, for the first plurality of environmental data, further location-related environmental data is determined based on at least one signal from a GPS sensor and / or a WLAN connection, and / or biometric environmental data is determined based on an ECG sensor and / or an EEG sensor and / or a PPG sensor and / or an EMG sensor. In particular, a sensor for generating biometric environmental data can be arranged on an auxiliary device designed as a smartwatch.The sensors mentioned are particularly suitable for the most comprehensive possible characterization of the environmental situation of a hearing system.

[0041] For the acoustic environmental data, the signal of the at least one electroacoustic input transducer is preferably analyzed with regard to a speech activity of the first or second user of the hearing system and / or with regard to an occurrence of wind at the electroacoustic input transducer and / or with regard to a spectral center of gravity of a noise background and / or with regard to a noise background in at least one frequency band and / or with regard to a stationarity of a sound signal of the environment and / or with regard to an autocorrelation function and / or with regard to a modulation depth at a given modulation frequency, which is preferably 4 Hz and a maximum of 10 Hz, and / or with regard to an onset of a speech activity, in particular the user's own speech activity.

[0042] Advantageously, a mean value and / or a variance and / or a mean value passage rate and / or a value range and / or a median of the respective environmental data are determined as values ​​of the environmental data for a collection time and / or the application time, in particular with respect to a period between the respective collection time and an immediately preceding collection time or to a period between the application time and an immediately preceding application time. Using this data, the environmental situation of a hearing system can be characterized particularly comprehensively.

[0043] Preferably, during a sampling time, a recording of a sound signal from the environment is made using the at least one electroacoustic input transducer, and the recording is assigned to the feature vector and the corresponding representative vector for the sampling time. Upon user input, the recording is played back via at least one output transducer of the hearing system, in particular via a loudspeaker. This allows the user to additionally identify which specific acoustic event—i.e., which noise—underlies a representative vector and use this to define the first region.

[0044] Advantageously, individual vector projections of the feature vectors of the collection times are formed into an acoustic feature space on the basis of the acoustic environmental data, wherein the vector projections of the acoustic feature space are each mapped onto acoustic representative vectors in a maximum three-dimensional, in particular two-dimensional, acoustic representation space, wherein a second region for the first environmental situation of the hearing system is defined in the acoustic representation space, and wherein the presence of the first environmental situation is additionally detected on the basis of the second region of the acoustic representation space, in particular by a comparison with a mapping of the feature vector of the application time into the acoustic representation space.

[0045] The hearing aid user may be in an environment where certain short sounds bother them, so they prefer signal processing settings that attenuate these sounds. A typical example is the sound of a spoon hitting a coffee cup or, comparable, the shrill clatter of dishes. There are various options for this, such as slightly reducing the gain of high frequencies, increasing dynamic compression in the high frequency range, or activating signal processing that specifically attenuates sudden sound peaks.

[0046] If the user now marks a representative vector, which is based on the suddenly occurring sound peak of the spoon hitting the coffee cup, the user can find the marking of the corresponding representative vector in a visualized representation.

[0047] This is to be expected in the area of ​​the display space where the representative vectors of a usage situation at home lie, but not in usage situations such as 'office' or 'in the car'. The user could now specify one of the aforementioned changes for the usage situation at home, e.g., increased dynamic compression in the high frequency range. Before doing this, it is advisable to check whether there are other, similar sounds that might also sound different due to the modified signal processing settings.

[0048] In this case, the user can benefit from a representation of the corresponding acoustic representative vector, which represents a projection of the corresponding acoustic feature vector of the acoustic features, in the acoustic representation space in order to be able to make the first environmental situation in addition to or solely on the basis of the representation of the purely acoustic environment in the acoustic representation space of the corresponding second area.

[0049] Preferably, the representation space can be visualized simultaneously, e.g. side by side, with appropriate highlighting of the representative vector relevant for the sound event, as well as the acoustic representation space with the corresponding acoustic representative vector.

[0050] This representation offers the user the advantage that, in the representation of the acoustic representative vectors, sound events (i.e., noises) can be recognized that are very similar to the marked feature ("doorbell") – precisely due to the relative proximity of the corresponding acoustic representative vectors. The "full" representative vectors (which are additionally based on non-acoustic data) of both sound events ("spoon on coffee cup" and "doorbell") are also presumably located in the same region of the representation space and, in particular, are assigned to the same usage situation ("at home").

[0051] If the user now for the first second area of ​​the display space or the acoustic display space and thus for the thus defined first

[0052] If the user adjusts the signal processing in response to a specific environmental situation, whereby spontaneously occurring, bright-sounding sounds ("coffee cup") are attenuated, for example, then the user can recognize, as a result of the acoustic representation space, that similar sounds ("doorbell" or "smoke detector") are also attenuated, whereby the user can make a weighing decision as to whether to implement the attenuation completely in order not to miss such sounds.

[0053] It has proven to be further advantageous if the first environmental situation is additionally defined on the basis of a first usage situation, and a first value of the setting for the signal processing of the hearing system is specified for the first environmental situation, and a second environmental situation is defined on the basis of a second usage situation, and a corresponding second value of the said setting is specified, wherein in particular the second region which corresponds to the first environmental situation in the acoustic representation space, at least partially overlaps with the second region which corresponds to the second environmental situation in the acoustic representation space, wherein the presence of the first or the second environmental situation is recognized on the basis of the presence of the first or second usage situation, and then the first or second value of the signal processing of the hearing system is determined in accordance with its specification for the first or second usage situation.second environmental situation is set.

[0054] In particular, this means that the user is able to identify similar sounds that were created in different environments and, in particular, different usage situations. Depending on the usage situation, the hearing system user may prefer different signal processing settings for certain similar sounds.

[0055] As an example, consider a hunter who may find the rustling of a newspaper unpleasantly loud, but would like to hear every rustle in the leaves while hunting. During the training phase, the rustling of the newspaper is marked as unpleasant, but the rustling in the leaves is not. If the sounds are acoustically very similar but otherwise distinguishable, the user can define different environmental situations and thus different signal processing settings. A desire for different treatment of different "rustles" can arise, for example, in different usage situations "at home" (e.g., reading a newspaper) or "work / office" (a colleague leafing through documents) vs. "outdoors" (relaxing in the forest).

[0056] The possibility of different treatment is then provided in particular by determining feature vectors in the training phase from all sensors of the hearing aid, i.e. based on the recorded audio signals (microphones) and also other sensor signals, which are then mapped into the representation space; acoustic feature vectors are determined from the recorded audio signals and then mapped into the acoustic representation space.

[0057] Based on a marked acoustic representative vector, the user can recognize that they desire a different signal processing (e.g., "rustling newspaper" is marked), but receives information from the acoustic representation space that there are other very similar sounds (here: rustling leaves). The marked acoustic representative vector for the sound "rustling newspaper" can, in particular, form a first subgroup of the acoustic representative vectors and thus a first region in the acoustic representation space, while another acoustic representative vector for the sound "rustling leaves" can form the second region.

[0058] The user can then select such a similar sound in the visualization and is then shown the marked representative vector as well as the corresponding, acoustically similar representative vector in the ("full") display space. Based on their positions, they can determine whether they lie in distinguishable regions. One region then represents the situation "at home," the other, for example, in the forest. If this distinguishability exists beyond the acoustic similarity, then the signal processing is specifically adapted for one environmental situation ("at home") but not for the other environmental situation ("in the forest").

[0059] Preferably, a hearing system is used which has a hearing device, in particular a hearing aid and / or a hearing aid and / or a headset, as well as a computing unit and in particular a visualization device.

[0060] Preferably, the first region for the first environmental situation is defined during the training phase by the first user of a hearing system and stored on a cloud server. During the application phase, the second user of a hearing system that is comparable in terms of application, particularly with regard to the hearing device, downloads said definition from the cloud server to the hearing system. This makes individual environmental situations encountered by users usable for other users.

[0061] Preferably, in the application phase, a correction is made to the definition of the first region and / or to the specification for the at least one value of a signal processing setting of the hearing system by means of a user input, wherein the corrected first region or the corrected value of the signal processing setting is then used in the application phase. This allows the user, on the one hand, to subsequently adapt the definition of the at least one signal processing setting previously made for a first environmental situation and, on the other hand, to subsequently assign, for example, a sound to an environmental situation or even subsequently delete such an assignment.

[0062] Advantageously, each of the feature vectors is mapped to a corresponding representative vector in a one-dimensional representation space, whereby a first interval in the representation space is defined as the first region for the first environmental situation of the hearing system based on a spatial distribution of the endpoints of a subset of representative vectors. A one-dimensional representation space can be particularly advantageous for a comparatively small number of features (e.g., a six-dimensional feature space).

[0063] The invention further relates to a hearing system comprising a hearing device, in particular a hearing aid, hearing aid device, or headphones, and an auxiliary device with a computer unit, in particular a processor unit of a smartphone or tablet, wherein the hearing system is configured to carry out the method described above. The hearing system according to the invention shares the advantages of the method according to the invention. The advantages stated for the method and its further developments can be applied analogously to the hearing system.

[0064] The hearing system preferably comprises a visualization device and / or an input device for user input. In particular, the visualization device and the input device are implemented by a touchscreen of a smartphone or tablet, which can be connected to the hearing device for data transmission.

[0065] In a preferred embodiment, the hearing system comprises the following parts: A hearing device, preferably provided by a hearing aid, in particular configured to record an audio signal by means of at least one built-in microphone, and preferably with one or more sensors such as an acceleration sensor and / or gyroscope, which record "non-acoustic" environmental data. The hearing device is preferably configured to create the feature vector from the environmental data and in particular to create an acoustic feature vector from the acoustic environmental data. An auxiliary device, which comprises the visualization device and the input device, and is preferably provided by a smartphone or a tablet. In particular, the auxiliary device comprises further sensors for determining environmental data (e.g.Localization data based on GPS), wherein the auxiliary device is preferably configured to transmit this environmental data to the hearing device or to receive the environmental data of the hearing aid and to create the said feature vectors by means of a wireless connection.

[0066] Furthermore, individual modular functions or components are preferably implemented in the hearing system, which enable the implementation of the method described above. These modular functions include, in particular, A software input module that provides a user interface where the user can create specific environmental situations, but also usage situations, and label them accordingly ("at home," "in the car," "in the office," "in the cafeteria," "watching TV," "riding a bike," "in the music room"), indicate that they are currently in or leaving one of the defined usage situations, create specific events and label them ("dentist's drill," "vacuum cleaner," "rustling newspaper," "playing musical instruments"), and indicate whether a defined event is about to occur; a dimensionality reduction module that maps the feature vectors collected in the training phase into the 2-dimensional (or 3-dimensional, or even 1-dimensional) representation space.The dimensionality reduction module can be implemented in various ways, namely via an implementation of the t-SNE optimization method, as UMAP, PCA, or as a Kohonen network, which receives the high-dimensional feature vectors on the input side and outputs 2-dimensional (or 3-dimensional) representative vectors on the output side. The dimensionality reduction module can be implemented on the hearing aid, on a smartphone as an auxiliary device, or on an additional computer such as a PC / laptop.

[0067] When using the t-SNE optimization method, it is advantageous to implement the dimensionality reduction module, preferably on the smartphone as an auxiliary device, or on a PC / laptop, as these devices have powerful processors available for computation. The Kohonen network can be implemented either as specialized hardware on an ASIC of the hearing aid or on a neuromorphic chip of the hearing aid, which is configured as a Kohonen network but can also be configured for other tasks. The Kohonen network can also be implemented on the auxiliary device; a feature editor for displaying vectors of a particularly 2-dimensional space as points or arrows in a surface on a display or screen, for highlighting points according to a marking of the displayed vector, e.g. by appropriate coloring, for textual display of properties of individual points, e.g. by corresponding text fields directly next to a point, and for displaying two particularly 2-dimensional spaces next to each other (a display space and an acoustic display space of the corresponding representative vectors).

[0068] The coloring of points can correspond to markings assigned to individual feature vectors. If the markings indicate a usage situation or an environmental situation, the coloring reflects this accordingly.

[0069] As soon as the user selects a point (representative vector) of the acoustic representation space, the corresponding point of the ("full" representation space) can be visually highlighted. The user can thus recognize whether two similar acoustic events, e.g., rustling newspaper and rustling leaves, which are close to each other in the acoustic feature space, can be assigned to distinguishable environmental situations through dimensionality reduction, taking into account additional environmental features, e.g., "at home" or "in the forest," because then the corresponding representative vectors of the representation space lie in different regions. The feature editor can, in particular, be implemented on the auxiliary device. A mapping module that maps feature vectors into the 2- or 3-dimensional representation space during the application phase. The mapping module is preferably implemented in the hearing aid itself, but can also be implemented on the auxiliary device (preferably a smartphone) and transmits the result of said mapping to the hearing aid. If the dimensionality reduction module uses a t-SNE method, a feature vector is mapped into the representation space using an approximation function. If the dimensionality reduction works using a Kohonen network, the mapping can be performed by the same Kohonen network.

[0070] An exemplary embodiment of the invention is explained in more detail below with reference to a drawing. The drawing shows schematically: Fig. 1 in a block diagram a method for the environment-dependent operation of a hearing system

[0071] In Fig. 1A method for the environment-dependent operation of a hearing system 1 is shown schematically in a block diagram, wherein the hearing system is formed in the present case by a hearing device 3 designed as a hearing aid 2 and an auxiliary device 5 designed as a smartphone 4. The hearing device 3 has at least one electro-acoustic input transducer 6, which is designed in the present case as a microphone and generates an audio signal 7 from ambient sound. Furthermore, the hearing device 3 has further sensors 8, which generate additional sensor signals 9. The sensors 8 can comprise, for example, an acceleration sensor or a temperature sensor.

[0072] In a training phase 10 of the method, environmental data is determined for a plurality of acquisition times T1, T2, T3, each based on the audio signal 7 and the sensor signal 9. This is done here by continuously generating acoustic environmental data 12 from the audio signal 7. The acoustic environmental data 12 include: a 4 Hz modulation; an onset mean; an autocorrelation function; a level for low and mid frequencies of a noise background and a centroid of the noise background; a stationarity; wind activity; a broadband maximum level; and the individual's own vocal activity. Likewise, movement-related environmental data 14 is continuously generated from the sensor signal 9, which includes the measured instantaneous accelerations in the three spatial directions.Further types of acoustic environmental data 12 and / or movement-related environmental data 14 or other, particularly location-related and / or biometric environmental data are generally included as environmental data 15, for example, magnetic field sensors, other mobile phone and / or smartwatch sensors, a gyroscope, a heart rate measurement, a PPG measurement (photoplethysmogram), an electrocardiogram (ECG), stress detection via the measurement of the heart rate and its variation, a light sensor, a barometer, auditory effort or auditory activity (for example, via "auditory attention" using an EEG measurement), a measurement of eye or head movements via muscle activity (EMG), location information via GPS, WLAN information, geo-fencing, or Bluetooth beacons for the current location or area.

[0073] For the acoustic environmental data 12 (in this case, ten different types of data) and the (in this case) three motion-related environmental data 14, buffering 16 is performed for the period between two sampling times T1, T2, T3 (for a sampling at sampling time T1, the aforementioned signals are buffered from a starting time T0). Subsequently, a mean value Mn, a variance Var, and a mean transit rate MCR are calculated for each individual type of acoustic environmental data 12 and the motion-related environmental data 14.The aforementioned statistical quantities Mn, Var, MCR of the individual acoustic environmental data 12 and the movement-related environmental data 14 over the buffered period between two collection times T1, T2, T3 form environmental features 16 for the collection time T1, T2, T3 at the end of the buffering period, and are each mapped to a high-dimensional feature vector M1, M2, M3 in a high-dimensional feature space 18. The high dimensionality, e.g., 39D for three statistical features each from ten acoustic and three movement-related environmental data, is indicated here only by the number of axes in the diagrams of the feature space 18 for the individual feature vectors M1, M2, M3.

[0074] Each of the feature vectors M1, M2, M3 is now mapped from the feature space 18 to a corresponding representative vector R1, R2, R3 in a two-dimensional representation space 20. The mapping is performed, for example, using a t-SNE optimization method (t-Distributed Stochastic Neighbor Embedding).

[0075] The optimization procedure is briefly described below (see, for example, "Visualizing Data using t-SNE", 2008, Laurens van der Maaten and Geoffrey Hinton).

[0076] A so-called perplexity parameter defines the number of effective neighbors of the feature vectors. This parameter determines how many neighbors influence the final position of the corresponding representative vector in the two-dimensional representation space (in this case, this parameter can be set to a value of 50, for example, or on the order of 1 / 100 of the number of feature vectors). Then, for all pairs of high-dimensional feature vectors, probability measures are calculated once to determine whether two respective feature vectors can be identified as the nearest neighbors in the high-dimensional feature space. This represents an initial situation.

[0077] For the two-dimensional representation space, random, Gaussian-distributed random numbers Y are assumed as the starting value. The current similarity relationships in Y are then calculated in individual iterations. To optimize the mapping of the similarity relationships, a similarity between the feature space and the representation space is determined using a Kullback-Leibler divergence. Using a gradient of said divergence, the representative vectors (or their endpoints) in the representation space are shifted over T iterations.

[0078] A possible representation of the algorithm is: Feature space the high-dimensional feature vectors X = {x 1 ; x 2 ; ... ; x n }, with n being the number of all available feature vectors (in this case, e.g., n = 4016) Cost function parameters: "perplexity" Perp: determines the number of effective neighbors by choosing the variance σ ifor each point by a binary search (strong influence on Y) Optimization parameters: Specify a number of iterations t of T (e.g. 500), a learning rate h (e.g. 1000), and a momentum a(t) (e.g. 0.5 for t < 250, otherwise a(t) = 0.8) Result: two-dimensional representation space Y = {y 1 ; y 2 ​​; ... ; y n }, - Start of the procedure:

[0079] Calculating the probability measure for all feature vector pairs p ij in high-dimensional space: p j i = p ˜ j i ∑ k ≠ i p ˜ k i mit p ˜ j i = exp − x i − x j 2 / 2 σ i Set p ij = p j i + p i j 2n "Random drawing" of n two-dimensional Gaussian distributed random numbers to initialize Y Optimization of the r mapping into the representation space: o counting loop the optimization for t=1 to T: ▪ Calculate the current probability measure in two-dimensional space: q ij = 1 + y i − y j 2 − 1 ∑ k ≠ l 1 + y k − y l 2 − 1 ▪ Measure the similarity between X and Y (Kullback-Leibler divergence) C = ∑ j ∑ i p ij log p ij q ij ▪ Calculate the gradient: ∂ C ∂ y i = 4 ∑ j p ij − q ij y i − y j 1 + y i − y j 2 − 1 ▪ Move the two-dimensional representative vectors: y i t = y i t − 1 + h ∂ C ∂ y i + a y i t − 1 − y i t − 2 o End of optimization End of the process

[0080] With reference to the present method, representative vectors R1, R2, R3 are generated in the two-dimensional representation space 20 from the feature vectors M1, M2, M3 of the feature space 18 by the mapping rule described above.

[0081] A user of the hearing system 1 can now have the display space 20 displayed on their auxiliary device 5 (on the screen 21 of the smartphone 4) and, for example, define a contiguous area 22 as a first region 24, which corresponds to a specific first environmental situation 25 in their use of the hearing system 1. The user can now assign a specific setting 26 for signal processing of the audio signal 7 in the hearing device 3 to said first region 24, for example frequency band-wise amplification and / or compression values ​​and parameters, or control parameters for noise suppression or the like. With the assignment of the setting 26 of the signal processing to the first region 24 (and thus to the present first environmental situation 25, as characterized by the values ​​of the environmental data 15 in the individual feature vectors M1, M2, M3), the training phase 10 for a specific environmental situation can be considered complete.Preferably, several training phases 10 are carried out for different environmental situations.

[0082] In an application phase 30, the same environmental data 15 as in the training phase are collected from the audio signal 7 of the hearing device 3 and from the sensor signal 9 at an application time T4, and from this, in the same way, based on the values ​​determined at application time T4, a feature vector M4 is formed in the high-dimensional feature space 18. The values ​​can be formed, for example, from the mean value Mn, the variance Var, and the mean passage rate MCR of the acoustic and movement-related data 12, 14 collected over a short period of time (e.g., 60 seconds or similar) before application time T4.

[0083] The feature vector M4 for the application time T4 is now mapped to a representative vector R4 in the representation space 20.

[0084] Since the t-SNE method used in training phase 10 of the present example for mapping the feature vectors M1, M2, M3 of the feature space 18 to the representative vectors R1, R2, R3 in the representation space 20 is an optimization method that requires knowledge of all feature vectors used, a corresponding mapping is performed in application phase 30 using an approximate mapping (e.g., a so-called "out-of-sample extension," OOS kernel). This can be achieved via regression, by means of which a mapping is "learned" based on a large number of feature vectors of the feature space 18 (e.g., 80% of the feature vectors) to corresponding representative vectors of the representation space 20, and the remaining feature vectors (thus, for example, 20%) are used to "test" the quality of the resulting mapping.By mapping the "learning vectors," i.e., the feature vectors used to learn the mapping, to corresponding representative vectors, a kernel function can then be determined that preserves local distance relationships between the said feature and representative vectors in their respective spaces (feature and representation space, respectively). This allows a new, unknown feature vector to be mapped from feature space 18 to a corresponding representative vector in representation space 20 by preserving the local distance relationships between the known "learning vectors."

[0085] A detailed explanation can be found, for example, in "Out-of-Sample Kernel and Extensions for Nonparametric Dimensionality Reduction", Andrej Gisbrecht, Wouter Lueks, Bassam Mokbel and Barbara Hammer, ESANN 2012 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges (Belgium), April 25-27, 2012, as well as in "Parametric nonlinear dimensionality reduction using kernel t-SNE", Andrej Gisbrecht, Alexander Schulz and Barbara Hammer, Neurocomputing, Vol. 147, 71 - 82, January 2015.

[0086] If the representative vector R4 determined as described for the application time T4 lies in the first region 24, it is recognized that the first environmental situation 25 exists for the hearing system 1, and accordingly the hearing device 3 is operated with the settings 26 for the signal processing of the audio signal 26, and the previously defined amplification and / or compression values ​​and parameters, or control parameters of a noise suppression are applied to the audio signal 7.

[0087] Although the invention has been illustrated and described in detail by the preferred embodiment, the invention is not limited to this embodiment. Other variations may be devised by those skilled in the art without departing from the scope of the invention. List of reference symbols

[0088] 1 Hearing system 2 Hearing aid 3 Hearing device 4 Smartphone 5 Auxiliary device 6 Input transducer 7 Audio signal 8 Sensor 9 Sensor signal 10 Training phase 12 Acoustic environmental data 14 Movement-related environmental data 16 Buffering 18 Feature space 20 Display space 21 Screen 22 Area 24 First region 25 First environmental situation 26 Setting (of a signal processing) 30 Application phase M1, M2, M3 Feature vector (in the training phase) M4 Feature vector (in the application phase) MCR Mean passage rate Mn Mean R1, R2, R3 Representative vector (in the training phase) R4 Representative vector (in the application phase) T0 Start time T1, T2, T3 Elicitation time T4 Application time Var Variance

Claims

1. Method for environmentally dependent operation of a hearing system (1), wherein in a training phase (10) - values are determined for a first plurality of environmental data (15) of a first user of the hearing system (1) at a plurality of sampling times (T1, T2, T3), and on the basis of the values of the environmental data (15) for each of the sampling times (T1, T2, T3) a feature vector (M1, M2, M3) is formed in an at least four-dimensional, in particular at least six-dimensional, feature space (18), - each of the feature vectors (M1, M2, M3) is mapped in each case onto an associated representative vector (R1, R2, R3) in a maximally three-dimensional, in particular two-dimensional, representation space (20), and - by means of a spatial distribution of a subset of representative vectors (R1, R2, R3), a first region (24) in the representation space (20) is defined for a first environmental situation (25) of the hearing system (1), wherein for the first environmental situation (25) at least one value of a setting (26) for signal processing of the hearing system (1) is specified, and wherein in an application phase (30) - values for the first plurality of environmental data (15) of the first user or a second user of the hearing system (1) are determined at an application time (T4) and a corresponding feature vector (M4) for the application time (T4) is formed on the basis of the values of the environmental data (15), - on the basis of the first region (24) of the representation space (20) and on the basis of the feature vector (T4) for the application time (T4), a presence of the first environmental situation (25) is detected, and the at least one value of the signal processing of the hearing system (1) is set, in particular automatically, according to its specification for the first environmental situation (25), and - the hearing system (1) is operated with the at least one value set in this way, and wherein for the first plurality of environmental data (15) acoustic environmental data (12) is determined by means of a signal (7) of at least one electroacoustic input transducer, characterized in that for the first plurality of environmental data (15), in addition - motion-related environmental data (14) is determined based on at least one signal from an acceleration sensor (8) and / or a gyroscope, and / or - location-related environmental data is determined based on at least one signal from a GPS sensor and / or a WLAN connection, and / or - biometric environmental data is determined using an ECG sensor and / or an EEG sensor and / or a PPG sensor and / or an EMG sensor.

2. Method according to Claim 1, wherein in the training phase (10), information on a current usage situation of the hearing system (1) is stored by a user input, in particular depending on a demarcated situation of a daily routine of the first user of the hearing system (1), and wherein the respective information on the usage situation is linked to the feature vectors (T1, T2, T3) and / or the associated representative vectors (R1, R2, R3) which are formed on the basis of the values of the environmental data (15) collected during a particular user situation.

3. Method according to Claim 1 or Claim 2, wherein at least a sub-region of the representation space (20) is visualized, in particular by means of a display screen (21), and at least a subset of the representative vectors (R1, R2, R3) is displayed, and wherein the first region (24) in the representation space (20) is defined by means of a user input, in particular with regard to a grouping of visualized representative vectors (R1, R2, R3).

4. Method according to any of the preceding claims, wherein at least in the training phase (10) the mapping of the feature vectors (M1, M2, M3) onto the respectively corresponding representative vectors (R1, R2, R3) is carried out in such a way that distance relations of at least three feature vectors (M1, M2, M3) in the feature space (18) are at least approximately preserved in the representation space (20) for distance relations of the corresponding three representative vectors (R1, R2, R3) as a result of the mapping.

5. Method according to any of the preceding claims, wherein in the application phase (30), a presence of the first environmental situation is detected (25) by mapping the feature vector (M4) for the application time (T4) in the representation space (20), and evaluating a position of the representative vector (R4) thereby formed relative to the first region (24), and in particular by the representative vector (R4) being detected as lying within the first region (24).

6. Method according to any one of Claims 1 to 5, wherein in the application phase (30), a presence of the first environmental situation (25) is detected using the feature vector (M4) for the application time (T4) and using at least some of the feature vectors (M1, M2, M3) in the feature space (18) which are mapped onto the representative vectors (R1, R2, R3) of the first region (24) in the representation space (20).

7. Method according to any of the preceding claims, wherein in the application phase (30), values for the first plurality of environmental data (15) are determined at a plurality of successive application times (T4) and corresponding feature vectors (M4) for the successive application times (T4) are formed on the basis of the values of the environmental data (15), and wherein a presence of the first environmental situation (25) is detected using the first region (24) and using said feature vectors (M4) for the successive application times (T4), in particular using a polygonal chain consisting of said feature vectors (M4) or a polygonal chain consisting of the representative vectors (R4) which correspond to said feature vectors (M4) in the representation space (20).

8. Method according to any of the preceding claims, wherein for the acoustic environmental data (12) the signal (7) of the at least one electroacoustic input transducer is analyzed - with respect to speech activity of the first or second user of the hearing system (1) and / or - with respect to the occurrence of wind on the electroacoustic input transducer and / or - with respect to a spectral centre of gravity of a background noise and / or - with respect to a background noise in at least one frequency band and / or - with respect to the stationarity of a sound signal in the environment and / or - with respect to an autocorrelation function and / or - with respect to a modulation depth at a given modulation frequency, which is not more than 10 Hz, and / or - with respect to the onset of speech activity.

9. Method according to any of the preceding claims, wherein the values of the environmental data (15) determined for a sampling time (T1, T2, T3) and / or the application time (T4) are in each case a mean value (Mn) and / or a variance (Var) and / or a mean throughput rate (MCR) and / or a range of values and / or a median of the respective environmental data, in particular related to a period of time between the respective sampling time (T2, T3) and an immediately preceding sampling time (T1, T2), or to a period of time between the application time (T4) and an immediately preceding application time.

10. Method according to any of the preceding claims, wherein individual vector projections of the feature vectors (M1, M2, M3) of the sampling times (T1, T2, T3) are formed in an acoustic feature space based on the acoustic environmental data (12), wherein the vector projections of the acoustic feature space are each mapped onto acoustic representative vectors in a maximally three-dimensional, in particular two-dimensional, acoustic representation space, wherein a second region is defined in the acoustic representation space for the first environmental situation (25) of the hearing system (1), and wherein the presence of the first environmental situation (25) is detected additionally with reference to the second region of the acoustic representation space, in particular by a comparison with a mapping of the feature vector (M4) of the application time (T4) in the acoustic representation space.

11. Method according to any one of Claims 2 to 10, wherein the first environmental situation (25) is additionally defined on the basis of a first usage situation, and a first value of the setting (26) for the signal processing of the hearing system (1) is specified for the first environmental situation (25), wherein a second environmental situation is defined on the basis of a second usage situation, and a corresponding second value of the said setting (26) is specified, wherein a presence of the first or the second environmental situation is detected on the basis of a presence of the first or second usage situation, and the first or second value of the signal processing of the hearing system (1) is then set according to its specification for the first or second environmental situation respectively.

12. Method according to any of the preceding claims, wherein the definition of the first region (24) for the first environmental situation (25) is carried out in the training phase (10) by the first user of a hearing system (1) with a hearing device (3) and is stored in a cloud server, and wherein for the application phase (30) the said definition is downloaded from the cloud server to the hearing system (1) by the second user of a comparable hearing system for the application (1).

13. Hearing system (1), comprising a hearing device (3), in particular a hearing aid (2), hearing aid device or headphones, and an auxiliary device (5) with a computer unit, in particular a processor unit of a smartphone (4) or tablet, wherein the hearing system (1) is designed for carrying out the method according to any of the preceding claims.

Images