WO2022243257A2 - Vorrichtung und verfahren zum bestimmen von audio-verarbeitungsparametern - Google Patents
Vorrichtung und verfahren zum bestimmen von audio-verarbeitungsparametern Download PDFInfo
- Publication number
- WO2022243257A2 WO2022243257A2 PCT/EP2022/063211 EP2022063211W WO2022243257A2 WO 2022243257 A2 WO2022243257 A2 WO 2022243257A2 EP 2022063211 W EP2022063211 W EP 2022063211W WO 2022243257 A2 WO2022243257 A2 WO 2022243257A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- audio
- user
- parameters
- processing
- input signal
- Prior art date
Links
- 238000012545 processing Methods 0.000 title claims abstract description 291
- 238000000034 method Methods 0.000 title claims abstract description 74
- 230000005236 sound signal Effects 0.000 claims description 88
- 230000002787 reinforcement Effects 0.000 claims description 70
- 238000004458 analytical method Methods 0.000 claims description 65
- 238000013528 artificial neural network Methods 0.000 claims description 64
- 230000006870 function Effects 0.000 claims description 30
- 230000013707 sensory perception of sound Effects 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 230000006835 compression Effects 0.000 claims description 7
- 238000007906 compression Methods 0.000 claims description 7
- 230000001419 dependent effect Effects 0.000 claims description 6
- 238000000926 separation method Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000033458 reproduction Effects 0.000 description 19
- 238000010586 diagram Methods 0.000 description 12
- 238000013473 artificial intelligence Methods 0.000 description 10
- 230000003595 spectral effect Effects 0.000 description 7
- 230000003321 amplification Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 238000003199 nucleic acid amplification method Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 230000003203 everyday effect Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 230000008447 perception Effects 0.000 description 4
- 230000006978 adaptation Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000033228 biological regulation Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000010183 spectrum analysis Methods 0.000 description 2
- 238000009732 tufting Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000005188 flotation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R25/00—Deaf-aid sets, i.e. electro-acoustic or electro-mechanical hearing aids; Electric tinnitus maskers providing an auditory perception
- H04R25/50—Customised settings for obtaining desired overall acoustical characteristics
- H04R25/505—Customised settings for obtaining desired overall acoustical characteristics using digital signal processing
- H04R25/507—Customised settings for obtaining desired overall acoustical characteristics using digital signal processing implemented by neural network or fuzzy logic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2225/00—Details of deaf aids covered by H04R25/00, not provided for in any of its subgroups
- H04R2225/41—Detection or adaptation of hearing aid parameters or programs to listening situation, e.g. pub, forest
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2225/00—Details of deaf aids covered by H04R25/00, not provided for in any of its subgroups
- H04R2225/43—Signal processing in hearing aids to enhance the speech intelligibility
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2430/00—Signal processing covered by H04R, not provided for in its groups
- H04R2430/01—Aspects of volume control, not necessarily automatic, in sound systems
Definitions
- Embodiments according to the present invention relate to an apparatus and a method for determining audio processing parameters depending on at least one audio input signal.
- Embodiments according to the invention relate to a device and a method with artificial intelligence, for example in a sound reproduction device, which can analyze audio signals and assign or combine them with user-specific settings during user operation.
- Embodiments further relate to concepts for determining audio processing parameters based on audio signals obtained during user operation.
- the sound perception differs from person to person. For example, a conversation with a person in a room with many people is more difficult for one than for the other. Likewise, the same setting of a sound reproduction is perceived differently depending on the needs. Ambient parameters, such as the auditory environment, also have a significant influence on the control values for adjusting the sound of a sound reproduction device.
- Current sound reproduction devices offer specific sound adjustments that are not applied automatically. In the case of sound reproduction devices, such as, for example, portable devices for assisting hearing, such as headphones, headsets or hearing aids, only volume control and equalizer are often available for adjusting the sound.
- the Klanganpas solution such as increasing the volume or adjusting the higher or lower tones is performed once by the user. It has been recognized that in order to achieve consistently good audio quality, these settings must be repeated for each additional sound reproduction.
- the algorithm creates the relevance of a specific frequency spectrum that is decisive for the decision of the user (user) and automatically selects the associated parameters as the basis for a prediction model.
- the prediction model is applied to the previously recorded frequency spectrum analysis. It was recognized that the complexity of the frequency spectrum cannot be mapped using this learning application for sound reproduction, so that further user adjustments are always necessary.
- a core idea of the exemplary embodiments of the present invention consists in knowing how to make sound adjustments intuitively carried out by the users at runtime and to integrate them in the learning system in real time.
- An embodiment according to the present invention comprises a device for determining audio processing parameters, for example parameters for audio processing, depending on at least one audio input signal, for example coming from an audio input, the device being designed to at least to determine a coefficient of a processing parameter determination rule user-specifically based on audio signals obtained during user operation, and wherein the device is designed to obtain the audio processing parameters using the processing parameter determination rule based on the audio input signal.
- Coefficients of a processing parameter determination rule be, for example, coefficients of a neural network, which receives the audio input signal, or input signal parameters extracted therefrom, as an input variable, and which provides the audio processing parameters as an output variable.
- the coefficients of the processing parameter determination rule can, for example, be determined user-specifically based on input audio signals obtained during user operation, for example during user operation.
- the device can be designed to obtain the audio processing parameters, for example using the processing parameter determination rule defined by the at least one coefficient based on the audio input signal.
- This embodiment is based on the core idea that a user-specific setting of one or more coefficients of the processing parameter determination rule based on audio signals obtained during user operation makes it possible to adapt the processing parameter determination rule to the individual habits and wishes of the user.
- audio signals obtained during user operation for the user-specific setting of the coefficients of the processing parameter determination rule, it can be achieved that the coefficients are well adapted to those (specific) listening situations in which the user is usually actually located.
- it is no longer necessary to pre-classify an acoustic environment e.g.
- the coefficients can be adapted to the actual listening environments in which the user listens to, for example, music or Listens to speech, and can also be adapted to the individual needs of the user.
- a direct and user-specific determination of audio processing parameters can take place, with the processing parameter determination rule adapted by coefficients, for example, allowing a direct determination of the audio processing parameters without categorizing the acoustic environment into one of requires several statically specified categories.
- coefficients of the processing parameter determination rule can be adjusted based on the audio signals obtained during user operation, so that the listening environments relevant to the user, in which the user desires different audio processing parameters, are "hard” or “soft” (e.g. with a smooth transition) who can distinguish.
- the inventive concept makes it possible, for example, that in the presence of speech in different acoustic environments in which the user is located (for example, noisy open-plan office , single office, street crossing with many trucks, street crossing with tram traffic, etc.) completely different audio processing parameters can be provided.
- the parameters provided are then typically based on the settings desired by the user in the respective situations.
- the inventive concept provides audio processing parameters that are adapted to the reality of life of an individual user and their specific preferences with justifiable effort.
- the device is designed to determine a database as a function of user parameters set by the user, so that entries in the database describe the user parameters set by the user.
- the database can be created in real time during user operation and a prediction model can be determined.
- the database can be used to determine the coefficients of the processing parameter determination rule by the database containing the information of the user parameters.
- the database can also contain personal control settings that can be linked to the user parameters.
- the user parameters set by the user can, for example, take the place of the audio processing parameters as an initial variable, or change the audio processing parameters so that the entries in the database represent, for example, the user parameters set by the user.
- the database is correspondingly at least partially integrated into reinforcement learning, which uses the user parameters set by the user, for example.
- the coefficients of the processing parameter determination rule can be successively improved or optimized, for example.
- the user parameters set by the user typically in different acoustic environments
- this database can be used to determine the coefficients of the processing parameter determination rule.
- Determination regulation By determining a database that grows, for example, with increasing duration of use by the user, it can be achieved, for example, that over time an ever larger database for (automatic) determination (or improvement) of the coefficients of the processing parameters Determination regulation is present, which allows an increasing refinement or improvement of the said coefficients (e.g. based on an ever-increasing base of un ferent listening environments in which the user has stayed).
- the user experience can be continuously improved by creating and continuously expanding the database.
- the device is designed to determine a database as a function of the at least one audio input signal, so that entries in the database represent the audio input signal.
- the database can be used to determine the coefficients of the processing parameter determination rule.
- personal control settings for example the user parameters set by the user, were initially stored, which are expanded with sound information from the auditory environment as an external framework.
- a data basis can be created which, for example, provides coefficients for the processing parameter determination rule using reinforcement learning.
- the device is designed to determine the database in such a way that the database describes an association between different audio input signals and the respective user parameters set by the user.
- the device can, for example, assign the external framework conditions based on the audio input signal and the personal control settings, for example the user parameters set by the user, to one another.
- the assignment can, for example, serve as a basis for the prediction model, which can be changed by further sound adjustments by the user, for example ad hoc, for example by integrating the respective user parameters set by the user with the database (and then, for example the coefficients of the processing parameter determination rule are redetermined or improved).
- the auditory scene is continuously recorded by means of microphones, and/or analyzed and/or evaluated, so that, for example, an analysis of the auditory scene is generated via the dynamics and/or frequency and/or spectral property.
- the analysis result of the auditory scene can, for example, be integrated into the database as an environment parameter and assigned to the user parameter in order to obtain a link between the user parameter and the audio input signal in the auditory environment for this corresponding point in time.
- the device is designed to determine a database, for example for determining the coefficients of the processing parameter determination rule, as a function of an audio output signal, so that entries in the database describe or represent the audio output signal.
- the processing parameter determination rule for example reinforcement learning, can use the database to determine coefficients of the processing parameter determination rule, for example for a neural network to be able to
- the coefficients of the processing parameter processing specification can be obtained, for example, by jointly processing an audio input signal and an associated output signal or by comparing the audio output signal with the audio input signal.
- the device is designed to determine the database in such a way that the database describes an association between different audio output signals and the respective user parameters set by the user.
- the database describes an association between different audio input signals, between different audio output signals and respective user parameters set by the user in order to be able to determine coefficients of the processing parameter determination rule.
- sound processing can be integrated into the training of a self-reinforcing learning algorithm, for example by analyzing the incoming and outgoing audio signal.
- the incoming audio signal or the audio input signal can contain the sound environment, for example the auditory environment.
- the coefficients of the processing parameter determination rule can be selected so that the desired relationship between audio input signal and audio output signal results at least approximately by the processing parameter determination rule.
- the device is designed to adapt the at least one coefficient of the processing parameter determination rule based on the database acquired by the device in order to customize the processing parameter determination rule in order to obtain user-specific audio processing parameters.
- the reinforcement learning is adapted to a user model based on an artificial intelligence in order to obtain user-specific audio processing parameters or a user-specific audio signal.
- customized audio processing parameters may enable processing of the input audio signal using the audio processing parameters to obtain customized audio signals during user operation.
- a user-specific parameter set for sound processing can be obtained or developed from the database, which on the one hand automatically applies the same control parameters under the same external conditions, but also allows further user adjustments to the situation itself, which are integrated into the device as a learning system .
- the learning system and the application can adapt to the tonal user preferences in a continuous learning process.
- the device is designed to provide and/or adapt the processing parameter determination rule based on the database.
- the device can use the database, for example using reinforcement learning, to provide the processing parameter determination rule in order to obtain user-customized audio signals, for example during user operation, using the audio processing parameters.
- the device is designed to calculate the at least one coefficient of the processing parameter determination rule based on to determine and/or adapt at least one audio processing parameter that has been corrected and/or changed by a user.
- the device can be designed to take into account or set user adjustments to the user parameters during user operation and, for example, to allow further user adjustments to the user parameters at a later point in time and corresponding to the same place or corresponding to the same sound environment, so that the previous ones the user parameters can be set and/or overwritten with newly set user parameters.
- coefficients of the processing parameter determination rule can be corrected by a user and/or changed audio processing parameters can be determined, for example depending on the sound environment at the time in which the user is located.
- the device is designed to carry out audio processing, for example a parameterized audio processing specification, based on the audio input signal and based on the audio processing parameters in order to convert the user-customized audio signals, for example taking into account User modifications of the audio processing parameters.
- the device can provide a user-customized audio signal for the audio output by means of an optional audio processing of the audio input signal and the audio processing parameters.
- the audio processing can be integrated into the device, as a result of which an efficient system is obtained. Audio processing can optionally also be included in the determination of the audio processing parameters.
- the device is designed to calculate the coefficients of the processing parameter determination rule using a comparison of the audio input signal and an audio input signal supplied using the audio processing parameters, for example taking into account user modifications of the audio processing parameters , to determine.
- the determination of the coefficients of the processing parameter determination rule can be based on a comparison between the audio input signal and the direct audio output signal or the audio output signal provided by the audio processing.
- an audio analysis of the audio input signal or an audio analysis of the audio output signal can optionally be carried out before or after using the comparison. nals done to determine the coefficients of the comparison parameter determination rule based on an audio analysis result of the audio signals.
- Determining the coefficients of the parameter determination rule using such a comparison provides particularly reliable or robust results since the audio signal actually output to the user can be used as a criterion for determining the coefficients of the parameter determination rule.
- the criterion that the audio output signal should correspond to what the user wants is more meaningful and robust than simply optimizing the audio processing parameters per se.
- the device is designed to provide the user parameters set by the user as an output variable instead of the audio processing parameters, the user parameters set by the user comprising volume parameters and/or sound parameters and/or equalizer parameters.
- user parameters can include, for example, filter parameters for tone shaping and/or for equalization of tone frequencies.
- the device is designed to combine the user parameters with the audio processing parameters, for example by addition, in order thereby to obtain combined parameters of the audio processing and to provide them as an output variable.
- Combined parameters may include, for example, user parameters and audio processing parameters that are combined provided to the audio processing or combined using the audio processing and provided as an output to, for example, reinforcement learning. Accordingly, quick user intervention is possible, and the audio processing can thus be adapted to the user's wishes.
- the device is designed to carry out an audio analysis of the audio input signal in order to use an audio input signal analysis result to determine the at least one coefficient of a processing phase.
- rameter determination rule for example using the processing parameter determination rule to provide.
- the processing parameter determination rule can define a derivation rule for deriving the audio processing parameters from the audio input signal analysis result.
- the audio analysis of the audio input signal can provide audio input signal analysis results, for example in the form of information about spectral properties and/or dynamics and/or frequency of the audio input signal, or also information about intensity values per band.
- the audio input signal analysis results can be provided, for example, as input variables for determining one or the coefficients of the processing parameter determination rule, for example using reinforcement learning.
- Exemplary embodiments also provide that the audio analysis analyzes and evaluates the audio input signal coming from the audio input in advance in order to make it available to the processing parameter determination specification, although this is not absolutely necessary. It is thus possible, for example, to obtain additional information about spectral properties of the audio input signal as an audio input signal analysis result.
- the processing parameter determination rule can be made simpler than if, for example, the complete audio input signal were used to determine audio processing parameters.
- parameters or values of the audio input signal analysis result can describe the essential characteristics of the audio input signal in an efficient manner, so that the processing parameter determination rule includes a comparatively small number of input variables (namely, for example, the) parameters or values of the audio Has input signal analysis result and is therefore comparatively easy to implement. Good results can thus be achieved with little effort.
- the device is designed to carry out an audio analysis of the audio output signal in order to obtain an audio output signal analysis result, for example in the form of information about spectral properties of the audio input signal, for determining the at least one coefficient of processing processing parameter determination rule, for example using the processing parameter determination rule.
- the device is designed to carry out an audio analysis before the processing parameter determination rule or after the processing parameter determination rule in order to obtain either an audio input signal analysis result or an audio output signal analysis. to provide the result of the test or both for a determination of the coefficient of the processing parameter determination rule.
- the audio output signal analysis result it is particularly easy to compare the audio input signal and the audio output signal, with, for example, values or parameters of the audio output signal analysis result identifying the characteristic properties of the audio output signal particularly efficiently (or in particular compact form) can describe.
- a determination or optimization of the coefficients of the processing parameter determination rule is possible particularly efficiently, whereby the processing desired by the user can be achieved in an efficient manner, for example by evaluating the audio output signal analysis result or with a comparison being made between the audio input signal analysis result and Audio output signal analysis result can allow conclusions to be drawn about coefficients of the processing parameter determination rule.
- the audio processing parameter or the audio processing parameters comprise at least one multiband compression parameter R and/or at least one hearing threshold adjustment parameter T and/or at least one band-dependent gain parameter G and/or at least one noise reduction parameter and/or at least a blind source separation parameter.
- the audio processing parameters can include at least one sound direction parameter, and/or binaural parameters, and/or parameters relating to the number of different speakers, and/or parameters of adaptive filters in general, for example reverberation suppression, feedback, echo cancellation, active noise -Cancellation (ANC), include.
- the directivity of the sound source can be selected or set using a sound direction parameter, so that the sound is only processed from the desired direction, for example the conversation partner in a conversation, for the combination of the audio processing parameters.
- audio processing parameters of this type can affect audio signal processing in an efficient manner, with audio signal processing being able to be influenced over a wide adjustment range even with a small number of parameters, which can be determined without major difficulties by a processing parameter determination rule is.
- the device can include a neural network, which implements the processing parameter determination rule, for example, so that the at least one coefficient is defined, or preferably a plurality are defined by coefficients designed to obtain the audio processing parameters using the processing parameter determination rule.
- the neural network can be designed to receive the audio processing parameters based on the audio input signal directly from the audio input or by means of the intermediate audio analysis as an analyzed audio input signal. It was recognized that a neural network is well suited for determining the audio processing parameters and can be easily adapted to the personal perception of the individual user by means of the coefficients.
- the neural network whose edge weights can be defined, for example, by the coefficients of the processing parameter determination rule, can be adapted to the needs of the user through the choice of the coefficients (which can be done, for example, by a training rule). For example, the coefficients can be successively improved if further user settings are available. In this way, results can be achieved that offer a very good user experience.
- the device is designed to determine the processing parameters based on a method of reinforcement learning, and/or based on a method of reinforcement learning, and/or based on a method of unsupervised learning, and/or based on a method of multivariate prediction, and/or based on a multidimensional parameter fixed with multivariable regression to provide and/or adjust to determine the audio processing parameter.
- the processing parameter determination rule can, for example, provide coefficients for the neural network, which are based, for example, on the reinforcement learning method.
- the multivariate prediction method can include, for example, a prediction of frequency bands and/or a prediction of input/output characteristics or input/output characteristics according to the user parameters.
- the multivariable regression method can, for example, analyze all frequency bands present in order to define a multidimensional parameter space.
- a multidimensional parameter space can be understood, for example, as a two-dimensional parameter setting that has a graphical interface in which the user parameters can be set and can be continually adjusted.
- the device can determine the audio processing parameter so that For example, a learning algorithm sets user-specific audio processing parameters, or so that the audio processing parameters supplied by applying the processing parameter determination rule approach the audio processing parameters corrected by the user as learning progresses, or so that the Adapts processing parameter determination rule in a continuous learning process, for example depending on user adjustments of the audio processing parameters.
- access of the methods to the database or the data memory is unrestricted (so that, for example, as the size of the database increases, better and better coefficients can be determined using the learning methods mentioned).
- the device is designed to transmit the user parameters set by the user, for example via or by means of an interface, for example a user interface, an intuitive and/or ergonomic user control, such as a 2D space on a smartphone display. to obtain.
- the device can comprise an interface (for example an electrical interface or also a human-machine interface part) in order to be able to set the user parameters.
- a visual user control can preferably include a volume setting, for example by means of a slider for louder and quieter and/or a treble and bass control. In this way, the setting of the parameter can be made very easy for humans, it being recognized that this simple sound setting already results in a good hearing impression in many cases.
- the audio input signal includes a multi-channel audio signal, for example with at least four channels or at least two audio channels.
- the audio input signal can be provided by the audio input, for example by, via or by means of a microphone.
- the audio input signal can contain information such as the number of channels and/or the number of frequency bands.
- the use of multi-channel signals allows, for example, localization of desired and/or interfering sound sources and consideration of directions of the desired or interfering sound sources when determining the audio processing parameters or the coefficients of the processing parameter determination rule.
- the device is designed to carry out audio processing separately for at least four frequency bands of the audio input signal.
- the device is designed to determine the at least one coefficient of the processing parameter determination rule on a user-specific basis, for example continuously, continuously, during user operation, for example in real time, in order to determine the audio processing parameters in real time, for example in runtime during user operation, and/or to determine and/or adjust the changed audio processing parameters in real time.
- the device is designed, for example, to determine and/or adapt the audio processing parameters in real time, so that the device, as a learning system, carries out this learning process in real time, for example during user operation.
- the sound processing is controlled on the basis of external conditions measured in real time.
- the present invention comprises a fluting device, the fluting device having audio processing and the fluting device having a device for determining audio processing parameters, the audio processing being designed to depend on an audio input signal of the audio processing parameters to process.
- the flotation device can implement or integrate the device in order to improve the user's individual perception of sound or tones in the form of audio signals. It has been shown that the device described herein is particularly well suited for use in a tufting device, and that the tufting impression can be significantly improved through the use of the inventive concept.
- An embodiment according to the present invention comprises a method for determining audio processing parameters as a function of at least one audio input signal, the method including a user-specific determination of at least one coefficient of a processing parameter determination protocol, based on audio signals obtained during user operation, and obtaining audio processing parameters using the processing parameter determination rule based on the audio input signal.
- the method is based on the same considerations as the device described above and can optionally be supplemented by all the features, functionalities and details that are also described here with regard to the device according to the invention. The method can be supplemented by the features, functionalities and details mentioned both individually and in combination.
- a further exemplary embodiment according to the present invention comprises a computer program with a program code for carrying out the method when the program runs on the computer.
- FIG. 1 shows a schematic block diagram of a device according to an exemplary embodiment, which determines audio processing parameters as a function of at least one audio input signal
- FIG. 2 shows a schematic block diagram of a device according to an embodiment, which determines audio processing parameters as a function of at least one audio input signal and by means of reinforcement learning, based on an audio input signal and an audio output signal;
- FIG. 3 shows a schematic block diagram of a device according to an exemplary embodiment, which determines audio processing parameters as a function of at least one audio input signal and by means of reinforcement learning, based on an audio analysis of the audio input signal and an audio analysis of the audio output signal;
- FIG. 4 shows a schematic block diagram of a device according to an exemplary embodiment, which determines audio processing parameters as a function of at least one audio input signal and by means of reinforcement learning, based on an audio analysis of the audio input signal and on user parameters set by the user ;
- FIG. 5 shows a schematic block diagram of a device according to an exemplary embodiment, which determines audio processing parameters as a function of at least one audio input signal and by means of reinforcement learning, based on an audio input signal and on user parameters set by the user;
- FIG. 6 shows a schematic flow chart of a method according to an embodiment for determining audio processing parameters.
- FIG. 1 shows a schematic block diagram of a device 100 for determining audio processing parameters 120, which are shown on the output side of device 100, as a function of at least one audio input signal 110, which is shown on the input side of device 100.
- the exemplary schematic representation of the device 100 includes, for example, a determination of coefficients, which is represented by the block coefficient determination 130, so that coefficients 132 of the coefficient determination 130 of the processing parameter determination rule 140 can be provided.
- the audio input signal 110 can, for example, be used directly by the processing parameter determination rule 140 in order to obtain the coefficients 142 of the processing parameter determination rule 140, and/or be used as an audio signal 112 obtained during user operation by the coefficient determination 130, to provide the coefficients 132 to the coefficient determination 130 .
- the coefficient determination 130 can be user-specific during user operation, so that the coefficients 132 of the coefficient determination 130 are provided to the processing parameter determination rule 140 in order to use the audio processing parameters 120 using the processing determination rule 140 based on the audio input signal 110.
- the coefficients of the processing parameter determination rule can be set, for example, so that the processing parameter determination rule provides based on the audio input signal and using the coefficients as an output audio processing parameters that when used in an audio processing to a Lead audio output signal that corresponds to the user's expectations.
- FIG. 2 shows a schematic block diagram of a device 200 according to an exemplary embodiment.
- the device 200 shown for determining audio processing parameters includes, for example, an audio input 210, audio processing 220, user control 230, an audio output 240, a processing determination rule (or processing parameter determination device) in the form of reinforcement learning 250 and a neural network 260.
- the audio input 210 can include, for example, a microphone or other audio capture device and contain, for example, information about the number of channels, for example “C” and/or information about the number of frequency bands, for example “B”.
- audio signal 212 may be provided to neural network 260, audio signal 214 to reinforcement learning 250, and audio signal 216 to audio processing 220 (where audio signals 212,214,216 may be the same, or differ, for example, in detail (e.g., in Fig sampling rate, the frequency resolution, the bandwidth, etc.)
- the audio signal 212 can be the same as the audio signal 214 and/or the audio signal 216 (or at least describe the same audio content) and the same information about the number of Having frequency channels and frequency bands, so that the audio input signal from the audio input 210 is divided directly, for example without further audio analysis, and can be made available, for example via a number of outputs or data paths of the audio input 210.
- the audio processing 220 can have, for example, one and/or more parameterized audio processing specifications that process/process one or more audio signals 216, for example, in such a way that, based on the incoming audio signal 216 (or the incoming audio signals), using the parameterized audio processing rule, which is parameterized, for example, by the combined parameters 272, a user-customized audio signal 217 is provided (or several user-customized audio signals are provided).
- the audio processing 220 enables the audio input signal 216, which is based on the audio input 210, to be processed using the combined parameters 272, for example using the parameterized audio processing rule, in order to customize the audio signal 217 to the user receive.
- Optional details and exemplary embodiments for the combined parameters 272 are explained in more detail later in the present patent application. Before that, further details and exemplary embodiments of the components of the device 200 follow.
- the audio output 240 can, for example, receive the audio signal 217 that has been changed, reassigned, and customized by the audio processing unit 220 and can be used as a changed or processed audio signal 218 for a determination of parameters or coefficients of the processing parameter determination rule (e.g. of the neural network 260) a coefficient determiner 250 (the two for example realized using reinforcement learning).
- the audio output can provide, for example, the audio signal 217 that has been modified, reassigned, and customized by the audio processing unit 220 as a modified or processed audio signal 219 for an interface, for example for headphones or loudspeakers, with the it is not mandatory.
- exemplary embodiments allow additional information of the audio signal 218 to be provided via the audio output 240 to the reinforcement learning 250 (or another device for determining coefficients or parameters of the processing parameter determination rule), for example a data memory 252 (the content of which may be part of a database) with information about audio signals.
- the audio output signal 218 can, for example like the audio input signal 214, be provided to the reinforcement learning 250 for determining coefficients or parameters of the processing parameter determination rule 260, so that for example the information of the audio input signal 214 and the audio output signals 218 can be stored in a data memory 252 as a corresponding database of the device 200.
- the reinforcement learning 250 can determine coefficients or parameters of the processing parameter determination rule 260 by means of the audio signals 218 and 214, for example. Furthermore, the reinforcement learning 250 can, for example, based on the audio signals 214, 218 enlarge the database and/or record the audio signals 214, 218 in the data memory 252. Alternatively or additionally, the reinforcement learning can determine at least one user-adapted coefficient 254 or store it in the database.
- the database or the data memory 252 can include a variety of information, for example information about the audio input 210 (or about a Audio input signal) and/or coming from the audio input 210 via one or more of the audio signals 212 and 214, and/or information about the audio output 240 and/or about the audio signal 218 coming from the audio output 240 , and/or information about and for the audio processing 220 and, for example, at least one user-adapted coefficient 254.
- User-adapted coefficients 254 can be understood to mean coefficients which, for example, are intended for use by the processing parameter determination rule 250 based on the database 252 and/or determined based on a set user parameter 232. However, user-adapted coefficients can also be understood as audio processing parameters set by the user.
- the coefficients of the processing parameter determination rule for example edge weights of the neural network, can be based, among other things, on a method of reinforcement learning, which is identified in FIG. 2 with the reference number 250 as “reinforcement learning”.
- the reinforcement learning 250 (for example as a sub-function) can determine the database or the content of the data memory 252 in such a way that the data memory 252 can assign different audio input signals 212, 214 and the respective user parameters 232 set by the user, for example a user-adapted one coefficients 254.
- the reinforcement learning 250 determining the database or the content of the data memory 252 in such a way that the data memory 252 (for example additionally) describes an association between the audio output signal 218 and the respective user parameters set by the user, for example a user-adapted coefficient 254
- Neural network coefficients 256 are advantageously provided by reinforcement learning 250 .
- the processing parameter determination rule may be designed as a neural network 260, or may be integrated into a neural network to obtain audio processing parameters 262 using the coefficient 256 determined by reinforcement learning 250, for example.
- it can, for example, use the neural network 260 based on the audio signal 212 and the through The coefficients 256 obtained from the reinforcement learning 250 determine the audio processing parameters 262, so that as a result, for example, a learning algorithm sets user-specific audio processing parameters 262.
- the at least one audio processing parameter 262 provided by the neural network 260 may be a single parameter or may include multiple parameters.
- the neural network 260 can supply one or more of the following parameters as the audio processing parameter 262, for example: a parameter of the user profile N, and/or a multiband compression parameter R, and/or a hearing threshold adjustment parameter T, and/or smoothing (or one or more smoothing parameters) and/or compression settings (or one or more compression parameters).
- one or more parameters can be used (or supplied by the neural network as audio processing parameters 262), such as a band-dependent gain G, noise reduction (or one or more noise reduction parameters) and/or a blind source separation (or one or more parameters of a blind source separation).
- the number of input parameters can result in dependence on a number C of channels of a multi-channel audio signal, and also in dependence on a number B of processing bands, or in Dependence on a number P of user parameters.
- the number of user parameters P can result from the product of the number of frequency bands B and the number of audio signals or audio channels C.
- the number of output parameters (e.g. the output parameters of the neural network 260 or the input parameters of the audio processing) in a learned user profile M can result from the number of audio channels (e.g. C), the hearing threshold adjustment T, the multiband compression with rate R , the band-dependent gain G and two other time constants, with the number of values of G, R, T corresponding to the number of bands B, for example.
- the value of the learned user profile M (or the values of the learned user profile M) form the user-adapted coefficient (or parameter) 254 (or a set of user-adapted coefficients or parameters).
- the user control 230 provides at least one user parameter 232, which can include, for example, volume parameters and/or tone control parameters.
- the user control can include, for example, an interface for visualizing the one or more user parameters.
- a volume control or a volume regulation which can be performed by the user controller 230, can provide parameters, for example, which cause an amplification or attenuation of the audio signal.
- the user can use the user control 230 to set parameters of the tone control, for example, which can be used, for example, as part of the user parameters 232 with the audio processing parameters 262 (supplied by the neural network 260).
- a combination 270 can be merged.
- the user parameters 232 provided by the user control 230 may be combined with the audio processing parameter 262, such as by addition, multiplication, division, or subtraction.
- the combination 270 of the user parameters 232 with the audio processing parameters 262 can, for example, provide combined parameters 272 to the audio processing 220 .
- the user parameters 232 can also replace the parameters 262 , for example if the user desires a significantly different setting than that specified by the parameters 262 .
- the device 200 processes an audio input signal, which is received via the audio input 210, in the audio processing 220 in order to adapt sound properties to the wishes or needs of a user.
- a processing characteristic of the audio processing 220 is set by the parameters 272, the parameters 272 being influenced on the one hand by the neural network 260 and on the other hand being modified by the user via the user control 230.
- reinforcement learning 250 performs the function of adjusting one or more coefficients (e.g., edge weights) of the neural network such that the parameters provided by the neural network essentially match the user's meet expectations, that is, within acceptable tolerances, the parameter values that the user sets via the user control 230 in the respective different acoustic environments.
- the device after sufficient training in many different acoustic environments, achieves an automatic adjustment of the audio processing that is comfortable for the user.
- FIG. 3 shows a schematic illustration or a schematic block diagram of a device 300 for determining audio processing parameters as a function of at least one audio input signal, which is based on the device 200 from FIG. 2 .
- function blocks which are also shown in FIG. 2 can, for example, have a similar or the same functionality as corresponding function blocks in the device 200 (but do not necessarily have to have). It should also be noted that the device 300 can optionally be supplemented with all of the features, functionality and details described herein, both individually and in combination.
- Device 300 like device 200, has audio input 310 (which may correspond to audio input 200), audio processing 320 (which may correspond to audio processing 220), user control 330 (which can correspond to the user control 230), an audio output 340 (which can correspond to the audio output 240), a reinforcement learning 350 (which can correspond to the reinforcement learning 250 in its basic function, for example), a neural network 360 (the for example, its basic function can correspond to the neural network 260) and the combination 370 of the user parameters 332 set individually by the user and the audio processing parameters 362 (which, for example, can correspond to the combination 270).
- audio input 310 which may correspond to audio input 200
- audio processing 320 which may correspond to audio processing 220
- user control 330 which can correspond to the user control 230
- an audio output 340 which can correspond to the audio output 240
- a reinforcement learning 350 which can correspond to the reinforcement learning 250 in its basic function, for example
- a neural network 360 the for example, its basic function can correspond to the neural network 260
- the device 300 from FIG audio output 340 and reinforcement learning 350 Based on the device 200 from FIG. 2, the device 300 from FIG audio output 340 and reinforcement learning 350.
- this arrangement enables the audio analysis 380-1 to receive and analyze the audio input signal 311 emanating from the audio input 310, for example, in order to obtain an audio input signal analysis result, for example information about spectral properties and/or dynamics and/or Frequency of the audio input signal 311 in the form of the audio analysis signal 312 and/or 314 to provide.
- the information of the audio analysis result of the audio analysis 380-1 can be provided to the neural network 360 and the reinforcement learning 350 (for example at the same time) via the analyzed audio signals 312, 314, for example.
- the processing parameter determination rule which can include, for example, a part of the neural network 360 (or a part of the reinforcement learning 350), or which is implemented by the neural network 360, can, for example, be a derivation rule for deriving the audio processing parameters 362 from the audio input analysis result.
- Audio analysis 380-1 can be used to obtain additional (or compact) information about spectral properties, for example an intensity value per frequency band and channel, in order to provide frequency selectivity for audio signals (for example multi-channel audio signals). The frequency selectivity is required to be able to analyze and represent the perceptible sonic aspects of the signal.
- an input data amount of the neural network can be significantly reduced by the audio analysis 380-1, for example compared to a concept in which time-domain samples are input to the neural network.
- the analyzed audio signals 312, 314 containing parameters that describe the properties of the audio input signal in compact form where a number of parameters per time segment is, for example, at least a factor of 10 or at least a factor of 20 or at least a factor of 50 less as a number of samples per time unit
- the complexity of the neural network 360 can be kept comparatively low.
- the number of coefficients of the neural network can be kept comparatively small, which facilitates a learning process (for example through reinforcement learning 350). This applies all the more, the better the parameters of the analyzed audio signals are suitable for differentiating between different acoustic environments.
- an audio analysis 380-2 of the audio output signal 342 can be performed in order to provide an audio output signal analysis result for a determination of the at least one coefficient of the processing parameter specification, for example at least one coefficient of reinforcement learning 350.
- a “common” audio analysis of the audio input signal 311 and the audio output signal 342 is also possible (i.e., for example, an audio analysis of both the audio input signal and the audio output signal), with separate audio signal analysis results being provided can become.
- separately means that the audio input signal analysis result can be made available to other components, for example, compared to the audio output signal analysis result.
- the information of the audio analysis 380 - 1 , 380 - 2 of the input or output signal can be different from one another or correspondingly the same.
- Exemplary embodiments also provide that the audio output 340 provides a modified or processed audio signal 319 for an interface, for example for headphones or loudspeakers, although this is not absolutely necessary. Furthermore, exemplary embodiments make it possible for the audio analysis 380-2 to provide the audio signal 313 for the interface or for another interface. In this way, the device 300 can provide the audio signal 319 and 313 to external components, for example via at least one interface, although this is not absolutely necessary.
- the device 300 it is not the input audio signal or the output audio signal itself that is supplied to the neural network 360 or the reinforcement learning 350, but rather one or more corresponding audio analysis results.
- a complexity of the neural network and thus also a complexity of the reinforcement learning can be kept low by suitable prior analysis of the input audio signal and/or the output audio signal, which significantly reduces the implementation effort.
- FIG. 4 shows a schematic block diagram of a device 400 for determining audio processing parameters as a function of at least one input signal, which is partly based on the device 200 from FIG.
- Device 400 includes an audio input 410 (which may correspond, for example, to audio input 210), audio processing 420 (which may correspond, for example, to audio processing 220), a user control 430 (which, for example, may correspond to the user controller 230), an audio output 440 (which, for example, can correspond to the audio output 240), a reinforcement learning 450 (which, for example, can correspond to the reinforcement learning 250 in terms of its basic function), a neural network 460 (which can, for example, correspond to the neural network 260 in terms of its basic function), a combination 470) which can, for example, correspond to the combination 270) and an audio analysis 480 (which can, for example, correspond to the audio analysis 380-1) between the audio input 410 and the neural network 460 and reinforcement learning 450.
- an audio input 410 which may correspond, for example, to audio input 210
- audio processing 420 which may correspond, for example, to audio processing 220
- a user control 430 which, for example, may correspond to the user controller 230
- device 400 does not include audio analysis of audio output 440 and compared to device 200, no audio output signal coming from audio output 440 is provided to reinforcement learning 450.
- the reinforcement learning 450 receives no information about the audio output signal.
- the reinforcement learning 450 is based on the combined parameters 472, 473 or on information 433 that describes changes or adjustments to the audio processing parameters 462 supplied by the neural network 460 by the user. Further, the reinforcement learning uses the audio input signal analysis result 414.
- the reinforcement learning 450 can determine a database 452 depending on user parameters set by the user or the combined parameters 472, 473, so that entries in the database 452 represent the user parameters 472, 473 set by the user.
- the database 452 can be provided or used to determine the coefficients 456 of the processing parameter determination rule or the neural network 460 . This allows a prediction model to be determined that is directly based on user parameters (or the audio signal processing parameters 472 customized by the user) that are mapped directly into the reinforcement learning 450 .
- the one or more combined parameters 472, 473 or user parameters can also enter the neural network 460 directly during operation by means of the combined parameter 474, so that the compressor settings and/or other parameters for the audio processing parameters 462, for example, are provided as an output can become.
- the particular user parameters 432 set by the user may be provided directly to the reinforcement learning 450 (as shown at reference numeral 433), although this is not mandatory.
- the reinforcement learning 450 may be provided directly to the reinforcement learning 450 (as shown at reference numeral 433), although this is not mandatory.
- information about how much the user changes the parameters 462 supplied by the neural network 460 can be used for the reinforcement learning. If the user does not change the parameters 462 supplied by the neural network 460 at all or only slightly, it can be assumed that the user is completely or at least to a very high degree satisfied with the current functionality of the neural network, so that coefficients of the neural network do not have to be changed at all or only slightly.
- the reinforcement learning can be assumed through the reinforcement learning that a significant change in the coefficients of the neural network is necessary in order to ensure that the parameters 462 supplied by the neural network correspond to the user expectations.
- the information 433 describing a user intervention can be used by the reinforcement learning to trigger learning and/or to determine an extent of the changes in the coefficients of the neural network.
- the exemplary embodiment according to FIG. 4 makes it possible to learn and/or (e.g. continuously) improve the coefficients 456 of the neural network 460 in an efficient manner.
- Fig. 5 shows a device 500, which has similar properties as the devices 200, 300 and 400. It should be noted that in the device 500 according to FIG. 5 function blocks, which are also shown in FIGS. 2, 3 4 and 4 may, for example, have similar or identical functionality to corresponding functional blocks in device 200, device 300, and device 400 (but not necessarily have to have). It should also be noted that the device 500 can optionally be supplemented with all of the features, functionality and details described herein, both individually and in combination.
- the schematic block diagram of Fig. 5 shows the device 500, comprising an audio input 510 (which can correspond, for example, to the audio input 210), audio processing 520 (which can correspond, for example to the audio processing 220), a user control 530 (which may correspond, for example, to user control 230), an audio output 540 (which may correspond, for example, to audio output 240), reinforcement learning 550 (which, for example, may correspond to reinforcement learning 250 in terms of its basic function), a neural network 560 (which, for example, can correspond to the neural network 260 in terms of its basic function) and a combination 570 (which, for example, can correspond to the combination 270).
- an audio input 510 which can correspond, for example, to the audio input 210
- audio processing 520 which can correspond, for example to the audio processing 220
- a user control 530 which may correspond, for example, to user control 230
- an audio output 540 which may correspond, for example, to audio output 240
- reinforcement learning 550 which, for example, may correspond to
- device 500 includes no audio analysis of the audio input signal and no audio analysis of the audio output signal, so audio signals 512 and 514 are routed directly from audio input 510 to reinforcement learning 550 and neural network 560, respectively can become.
- the device 500 can also carry out an audio analysis of the audio input signal.
- an audio input signal 512 for the neural network 560 and an audio input signal 514 for the reinforcement learning NEN 550 can be provided.
- reinforcement learning 550 of device 500 may be based on audio input signal 514 and audio processing parameter(s) 572 provided to audio processing 520 (or actually used by audio processing 520).
- the user parameter or the combined parameter 572 can be provided to the neural network 560, so that the user parameter 572 and the coefficient(s) supplied by the reinforcement learning 550 are received or provided as input variables of the neural network 560.
- the device 500 allows a particularly efficient adjustment of the coefficients of the neural network, since the reinforcement learning 550 through the audio signal processing 520 parameters actually used are taken into account and the coefficients of the neural network can therefore be determined and optimized very precisely.
- FIG. 6 shows a schematic flow diagram of a method 600 for operating a device, such as device 100, 200, 300, 400 or 500, or more generally for obtaining audio processing parameters.
- a first step 610 includes a user-specific determination of at least one coefficient of a processing parameter determination rule based on audio signals obtained during user operation.
- a second step 620 includes obtaining audio processing parameters using the processing parameter determination rule based on the audio input signal.
- the method 600 is carried out, for example, in such a way that audio processing parameters are determined as a function of at least one audio input signal.
- the method 600 can be carried out in such a way that sound processing or audio processing based on directly recorded ambient noises (whereby, for example, an audio input signal leads to an adjustment of audio processing parameters) leads to an improvement in the individual perception of sound.
- the coefficients of the processing parameter determination rule are based on audio input signals obtained during user operation and are determined individually for the user (e.g. in real time), so that audio processing parameters using a neural network whose coefficients are determined by reinforcement learning can be determined or even continuously adjusted based on the audio input signal obtained.
- the method 600 can optionally be supplemented with all features, functionality and details described herein, even if they have been described in terms of devices. These features, functionalities and details can be added to the process both individually and in combination.
- Situation-dependent control parameters that can be set by the user, or user parameters set by the user, can be integrated into the sound processing in the training of a self-reinforcing learning algorithm, for example by analyzing the incoming and outgoing audio signal, as shown in FIG.
- the incoming audio signal may contain the sound environment. This allows changes in the sound environment and user settings to be inherently learned over time, for example.
- the self-reinforcing learning algorithm can use this data, for example, to develop a user-specific parameter set for sound processing, which on the one hand automatically applies the same control parameters under the same external conditions, but also allows further user adjustments to the situation itself, which are integrated into the learning system (e.g. based on a principle of reinforcement learning).
- the machine learning system and the application can adapt to the tonal user preferences in a continuous learning process.
- Algorithms such as those used in hearing aids, can be integrated and controlled to adjust the sound. This can include, for example, multiband compression with rate R and hearing threshold adjustment T and band-dependent gain G, background noise reduction or blind source separation.
- the incoming audio signal, the sound processing parameters and/or the audio signal processed with the sound processing parameters can be stored in a cloud (e.g. a central data store) for training the user profile, for example.
- the sound processing parameters selected by the user, or user parameters can be applied to the incoming audio signal.
- a possible implementation of the method or the device in the area of sound control is, for example, that a user wears a sound reproduction device (e.g. a hearable or an earphone with an additional function), which is equipped with a system with integrated sound amplification and an audio analysis, for example as shown in FIG. 3 or FIG. 4.
- the user can control the parameters of the sound amplification, for example, with an app (or with application software), for example using the user control described above.
- the audio analysis can, for example, constantly record and analyze the auditory scene by means of microphony and evaluate it, for example, in terms of dynamics and/or frequency and/or the spectral properties (for example in the audio analysis).
- a given auditory scene e.g. B.
- AI artificial intelligence
- the prediction model is applied and the sound amplification parameters (e.g. parameter 262) are automated by the system (e.g. provided by the neural network 260 defined by coefficients 256. If the user (user) adjusts the sound again if necessary (for example via the interface 230), these can be integrated ad hoc into the self-learning system, for example.
- the prediction model is based on real-time multidimensional optimization that analyzes all frequency bands present.
- the adjustment can take place continuously during runtime, for example the processing parameter determination rule and/or the audio processing parameters.
- Embodiments according to the invention relate, for example, primarily to an intuitive and ergonomic user control of sounds in everyday acoustic environments and therefore prefer generalized setting options, for the following reasons:
- the user can perform complex sound adjustments (e.g., in device 230) with a simple and intuitive interface such as a 2D touch surface of a smartphone.
- Tonal properties of individual sounds could sound different in combination than in preference, e.g. B. Sounds like music as a foreground or background noise. Therefore, in the case of the present invention, for example, the complexity of the auditory scene is adapted to a perception of all existing sounds that is optimized for the user. • Settings for individual signals do not dynamically adapt to changing environmental conditions. For example, when speech is spoken softly or music is only played softly, even a slight increase in the volume of the background noise can make speech incomprehensible or music no longer audible.
- a processor controls the sound processing of the hearing device on the basis of "user preferences and interests” (user preferences and interests) and “historical activity patterns” (earlier activity patterns).
- the sound processing of the hearing device is controlled, for example, on the basis of external framework conditions measured in real time, for example as shown in FIG.
- the criteria or requirements mentioned above are integrated into a learning method or a device that learns in real time from user settings and automatically applies them to the individual perception of sound or tones in the form of audio signals for the user.
- a signal reproduction or audio reproduction optimized to the user preferences can be realized by means of the present invention.
- embodiments according to the invention may take into account that sound perception differs from person to person. For example, a conversation with a person in a room with many people with a loud soundscape is more difficult for one than for the other. Likewise, depending on the need, the same setting of a sound reproduction is perceived differently.
- exemplary embodiments according to the invention can take into account that environmental parameters, such as the auditory environment, also significantly influence the control values for a sound adjustment of a sound reproduction device.
- exemplary embodiments according to the present invention provide an apparatus and a method which perform sound processing on the basis of ambient noise which is recorded or measured directly. Based on these recordings and the user parameters set by the user, a learning algorithm, for example, generates a prediction model that allows further adjustments in the situation itself, which are integrated into the learning system to improve the individual perception of sound or tones in the form of audio signals to improve for the user.
- embodiments of the invention may be implemented in hardware or in software. Implementation can be performed using a digital storage medium such as a floppy disk, DVD, Blu-ray Disc, CD, ROM, PROM, EPROM, EEPROM or FLASH memory, hard disk or other magnetic or optical memory, on which electronically readable control signals are stored, which interact with a programmable computer system in such a way ken or cooperation that the respective method is carried out. Therefore, the digital storage medium can be computer-readable.
- Some exemplary embodiments according to the invention thus include a data carrier which has electronically readable control signals which are capable of interacting with a programmable computer system in such a way that one of the methods described herein is carried out.
- exemplary embodiments of the present invention can be implemented as a computer program product with a program code, the program code being effective to carry out one of the methods when the computer program product runs on a computer.
- the program code can also be stored on a machine-readable carrier, for example.
- exemplary embodiments include the computer program for performing one of the methods described herein, the computer program being stored on a machine-readable medium.
- an exemplary embodiment of the method according to the invention is therefore a computer program that has a program code for performing one of the methods described herein when the computer program runs on a computer.
- a further exemplary embodiment of the method according to the invention is therefore a data carrier (or a digital storage medium or a computer-readable medium) on which the computer program for carrying out one of the methods described herein is recorded.
- a further exemplary embodiment of the method according to the invention is therefore a data stream or a sequence of signals which represents the computer program for carrying out one of the methods described herein.
- the data stream or sequence of signals may be configured to be transmitted over a data communications link, such as the Internet.
- Another embodiment includes a processing device, such as a computer or programmable logic device, configured or adapted to perform any of the methods described herein.
- a processing device such as a computer or programmable logic device, configured or adapted to perform any of the methods described herein.
- Another embodiment includes a computer on which the computer program for performing one of the methods described herein is installed.
- a programmable logic device eg, a field programmable gate array, an FPGA
- a field programmable gate array may cooperate with a microprocessor to perform any of the methods described herein.
- the methods are performed by any flardware device. This can be hardware that can be used universally, such as a computer processor (CPU), or hardware that is specific to the method, such as an ASIC, for example.
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Automation & Control Theory (AREA)
- Neurosurgery (AREA)
- Otolaryngology (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Circuit For Audible Band Transducer (AREA)
- Stereophonic System (AREA)
- Input Circuits Of Receivers And Coupling Of Receivers And Audio Equipment (AREA)
- Signal Processing Not Specific To The Method Of Recording And Reproducing (AREA)
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202280050454.2A CN117652160A (zh) | 2021-05-17 | 2022-05-16 | 用于确定音频处理参数的装置和方法 |
EP22729553.2A EP4342189A2 (de) | 2021-05-17 | 2022-05-16 | Vorrichtung und verfahren zum bestimmen von audio-verarbeitungsparametern |
US18/513,012 US20240089672A1 (en) | 2021-05-17 | 2023-11-17 | Apparatus and Method for Determining Audio Processing Parameters |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102021204974.5A DE102021204974A1 (de) | 2021-05-17 | 2021-05-17 | Vorrichtung und Verfahren zum Bestimmen von Audio-Verarbeitungsparametern |
DE102021204974.5 | 2021-05-17 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US18/513,012 Continuation US20240089672A1 (en) | 2021-05-17 | 2023-11-17 | Apparatus and Method for Determining Audio Processing Parameters |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2022243257A2 true WO2022243257A2 (de) | 2022-11-24 |
WO2022243257A3 WO2022243257A3 (de) | 2023-03-16 |
Family
ID=82019473
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2022/063211 WO2022243257A2 (de) | 2021-05-17 | 2022-05-16 | Vorrichtung und verfahren zum bestimmen von audio-verarbeitungsparametern |
Country Status (5)
Country | Link |
---|---|
US (1) | US20240089672A1 (de) |
EP (1) | EP4342189A2 (de) |
CN (1) | CN117652160A (de) |
DE (1) | DE102021204974A1 (de) |
WO (1) | WO2022243257A2 (de) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150195641A1 (en) | 2014-01-06 | 2015-07-09 | Harman International Industries, Inc. | System and method for user controllable auditory environment customization |
US20200066264A1 (en) | 2018-08-21 | 2020-02-27 | International Business Machines Corporation | Intelligent hearing aid |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08249303A (ja) * | 1995-03-13 | 1996-09-27 | Ricoh Co Ltd | 信号処理装置 |
EP0814636A1 (de) * | 1996-06-21 | 1997-12-29 | Siemens Audiologische Technik GmbH | Hörgerät |
DE10347211A1 (de) | 2003-10-10 | 2005-05-25 | Siemens Audiologische Technik Gmbh | Verfahren zum Nachtrainieren und Betreiben eines Hörgeräts und entsprechendes Hörgerät |
DK1708543T3 (en) * | 2005-03-29 | 2015-11-09 | Oticon As | Hearing aid for recording data and learning from it |
US10129664B2 (en) * | 2015-04-15 | 2018-11-13 | Starkey Laboratories, Inc. | User adjustment interface using remote computing resource |
EP3692634A1 (de) * | 2017-10-04 | 2020-08-12 | Google LLC | Verfahren und systeme zur automatischen entzerrung von audioausgängen basierend auf raumeigenschaften |
DE102019200956A1 (de) | 2019-01-25 | 2020-07-30 | Sonova Ag | Signalverarbeitungseinrichtung, System und Verfahren zur Verarbeitung von Audiosignalen |
DE102019203786A1 (de) | 2019-03-20 | 2020-02-13 | Sivantos Pte. Ltd. | Hörgerätesystem |
DE102019216100A1 (de) | 2019-10-18 | 2021-04-22 | Sivantos Pte. Ltd. | Verfahren zum Betrieb eines Hörgeräts sowie Hörgerät |
-
2021
- 2021-05-17 DE DE102021204974.5A patent/DE102021204974A1/de active Pending
-
2022
- 2022-05-16 WO PCT/EP2022/063211 patent/WO2022243257A2/de active Application Filing
- 2022-05-16 CN CN202280050454.2A patent/CN117652160A/zh active Pending
- 2022-05-16 EP EP22729553.2A patent/EP4342189A2/de active Pending
-
2023
- 2023-11-17 US US18/513,012 patent/US20240089672A1/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150195641A1 (en) | 2014-01-06 | 2015-07-09 | Harman International Industries, Inc. | System and method for user controllable auditory environment customization |
US20200066264A1 (en) | 2018-08-21 | 2020-02-27 | International Business Machines Corporation | Intelligent hearing aid |
Also Published As
Publication number | Publication date |
---|---|
DE102021204974A1 (de) | 2022-11-17 |
WO2022243257A3 (de) | 2023-03-16 |
CN117652160A (zh) | 2024-03-05 |
EP4342189A2 (de) | 2024-03-27 |
US20240089672A1 (en) | 2024-03-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE60222813T2 (de) | Hörgerät und methode für das erhöhen von redeverständlichkeit | |
EP1912474B1 (de) | Verfahren zum Betreiben einer Hörhilfe, sowie Hörhilfe | |
DE60120949T2 (de) | Eine hörprothese mit automatischer hörumgebungsklassifizierung | |
DE602004008455T2 (de) | Verfahren, vorrichtung und computerprogramm zur berechung und einstellung der wahrgenommenen lautstärke eines audiosignals | |
DE10228632B3 (de) | Richtungshören bei binauraler Hörgeräteversorgung | |
WO2001020965A2 (de) | Verfahren zur bestimmung einer momentanen akustischen umgebungssituation, anwendung des verfharens und ein hörgerät | |
DE102018216667B3 (de) | Verfahren zur Verarbeitung von Mikrofonsignalen in einem Hörsystem sowie Hörsystem | |
EP1489885A2 (de) | Verfahren zum Betrieb eines Hörhilfegerätes sowie Hörhilfegerät mit einem Mikrofonsystem, bei dem unterschiedliche Richtcharakteristiken einstellbar sind | |
DE102010041740A1 (de) | Verfahren zur Signalverarbeitung in einem Hörhilfegerät sowie Hörhilfegerät | |
EP1247425B1 (de) | Verfahren zum betrieb eines hörgerätes und ein hörgerät | |
EP3167627A1 (de) | Hörsystem mit anwenderspezifischer programmierung | |
EP2172062A1 (de) | Verfahren zum anpassen eines hörgeräts mit hilfe eines perzeptiven modells | |
EP1489882A2 (de) | Verfahren zum Betrieb eines Hörhilfegerätes, sowie Hörhilfegerät mit einem Mikrofonsystem, bei dem unterschiedliche Richtcharakteristiken einstellbar sind | |
EP1471770B1 (de) | Verfahren zur Erzeugung einer angenäherten Teilübertragungsfunktion | |
EP1432282B1 (de) | Verfahren zum Anpassen eines Hörgerätes an eine momentane akustische Umgebungssituation und Hörgerätesystem | |
DE102006015497B4 (de) | Audiosystem und Verfahren sowie Computerprogramm und Datenträger der das Computerprogramm enthält zur Anpassung der Übertragungsfunktion eines Audiosystems mittels Sprachsteuerung | |
DE102012203349B4 (de) | Verfahren zum Anpassen einer Hörvorrichtung anhand des Sensory Memory und Anpassvorrichtung | |
WO2022243257A2 (de) | Vorrichtung und verfahren zum bestimmen von audio-verarbeitungsparametern | |
EP2120484B1 (de) | Verfahren zum Betreiben eines Hörgeräts und Hörgerät | |
DE102009004185B3 (de) | Verfahren zur Signalverarbeitung einer Hörvorrichtung und entsprechende Hörvorrichtung | |
DE102011085036A1 (de) | Verfahren zum Ermitteln einer Kompressionskennlinie | |
DE102015212609A1 (de) | Verfahren zum Betrieb eines Hörgerätesystems und Hörgerätesystem | |
EP3698474B1 (de) | Verfahren zur einstellung von parametern zur individuellen anpassung eines audiosignals | |
DE3027953A1 (de) | Elektro-akustisches hoergeraet mit adaptiver filterschaltung | |
DE102020216439A1 (de) | Verfahren zum Betrieb eines Hörsystems mit einem Hörinstrument |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22729553 Country of ref document: EP Kind code of ref document: A2 |
|
DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2023571527 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022729553 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2022729553 Country of ref document: EP Effective date: 20231218 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202280050454.2 Country of ref document: CN |