Active noise reduction method, device, controller and system of vehicle, medium and vehicle

Abstract

The invention relates to the technical field of automobile intelligent cabins, in particular to an active noise reduction method, device, controller and system for a vehicle, a medium and the vehicle. According to the method, the environment sound scene where the vehicle is located is recognized according to the collected environment sound signal of the noise in the environment where the vehicle is located, the noise reduction algorithm parameter matched with the environment sound scene is determined from the preset noise reduction algorithm parameter library, and the signal capable of being counteracted with the environment sound signal is calculated according to the corresponding noise reduction algorithm parameter. According to the method, the sound waves corresponding to the signals are output, intelligent active noise reduction of different environment sound scenes is achieved, different environment sound scenes are matched with different noise reduction algorithm parameters, the deep noise reduction effect can be achieved, and the problem that the noise reduction effect is poor due to the fact that a set of fixed noise reduction algorithm parameters are used for active noise reduction of different environment sound scenes is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of automotive intelligent cockpits, and in particular, to an active noise reduction method, device, controller, system, medium and vehicle for a vehicle. Background Art

[0002] As vehicles become more and more intelligent, users' demands for intelligent cockpits are gradually increasing. Among them, the "hearing" sense, as an important part of the five human senses, directly affects the user's driving and riding experience. Among them, the interior quietness is particularly important. When external environmental noise enters the vehicle, it is very likely to cause discomfort to the people inside the vehicle. In the field of vehicle NVH control technology, the control of external environmental noise in the past was mainly through sound insulation materials for passive noise reduction. With the popularization of intelligent cockpits, active noise reduction technology has also been gradually applied to the field of vehicle noise control. By emitting a reverse sound wave signal with the opposite phase and equal amplitude to the noise through in-vehicle speakers, based on the principle of sound wave cancellation, the noise signal is cancelled, creating a quiet zone to achieve active noise reduction of the vehicle.

[0003] Currently, in the process of realizing in-vehicle active noise reduction, generally a set of fixed noise reduction algorithm parameters are run, which easily leads to poor actual noise reduction effect in different environmental sound scenarios. Therefore, in the process of in-vehicle active noise reduction, how to improve the noise reduction effect has become an urgent problem to be solved. Summary of the Invention

[0004] In view of this, the embodiments of the present invention provide an active noise reduction method, device, controller, system, medium and vehicle for a vehicle to solve the problem of poor noise reduction effect in the process of in-vehicle active noise reduction.

[0005] In a first aspect, an embodiment of the present invention provides an active noise reduction method for a vehicle, including: Collecting an environmental sound signal of the environment where the vehicle is located and an error noise signal inside the vehicle; Identifying a target environmental sound scenario where the vehicle is located according to the environmental sound signal; Determining, according to the target environmental sound scenario, noise reduction algorithm parameters matching the target environmental sound scenario from a preset noise reduction algorithm parameter library to obtain target noise reduction algorithm parameters, where the noise reduction algorithm parameters include a convergence step size and a filter weight coefficient; Controlling to output a sound signal that cancels the environmental sound signal according to the environmental sound signal, the error noise signal, and the convergence step size and the filter weight coefficient in the target noise reduction algorithm parameters to obtain a target cancellation noise signal, and outputting a corresponding sound wave according to the target cancellation noise signal to cancel the noise in the target environmental sound scenario where the vehicle is located.

[0006] In a second aspect, an embodiment of the present invention provides an active noise reduction device for a vehicle, including: A collection module for collecting the environmental sound signal of the vehicle's environment and the error noise signal inside the vehicle; An identification module for identifying the target environmental sound scene where the vehicle is located according to the environmental sound signal; A determination module for determining, according to the target environmental sound scene, the noise reduction algorithm parameters matching the target environmental sound scene from a preset noise reduction algorithm parameter library to obtain target noise reduction algorithm parameters, where the noise reduction algorithm parameters include a convergence step size and a filter weight coefficient; An output module for controlling the output of a sound signal that cancels out the environmental sound signal according to the convergence step size and the filter weight coefficient in the environmental sound signal, the error noise signal, and the target noise reduction algorithm parameters to obtain a target cancellation noise signal, and outputting a corresponding sound wave according to the target cancellation noise signal to cancel out the noise in the target environmental sound scene where the vehicle is located.

[0007] In a third aspect, an embodiment of the present invention provides a controller, where the controller includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the active noise reduction method described above is implemented.

[0008] In a fourth aspect, an embodiment of the present invention provides an active noise reduction system for a vehicle, where the active noise reduction system includes a controller and a microphone, and the controller is communicatively connected to the microphone; The microphone is used for collecting the environmental sound signal of the vehicle's environment; The controller is used for identifying the target environmental sound scene where the vehicle is located according to the environmental sound signal; Determining, according to the target environmental sound scene, the noise reduction algorithm parameters matching the target environmental sound scene from a preset noise reduction algorithm parameter library to obtain target noise reduction algorithm parameters, where the noise reduction algorithm parameters include a convergence step size and a filter weight coefficient; Controlling the output of a sound signal that cancels out the environmental sound signal according to the convergence step size and the filter weight coefficient in the environmental sound signal, the error noise signal, and the target noise reduction algorithm parameters to obtain a target cancellation noise signal, and outputting a corresponding sound wave according to the target cancellation noise signal to cancel out the noise in the target environmental sound scene where the vehicle is located.

[0009] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the active noise reduction method described above is implemented.

[0010] In a sixth aspect, an embodiment of the present invention provides a vehicle, where the vehicle includes the above-mentioned active noise reduction system.

[0011] The beneficial effects of the present invention compared with the prior art are as follows: In the present invention, according to the ambient sound signal of the noise in the environment where the vehicle is located collected, the ambient sound scene where the vehicle is located is identified, the noise reduction algorithm parameters matching the ambient sound scene are determined from the preset noise reduction algorithm parameter library, and according to the corresponding noise reduction algorithm parameters, the signal that can cancel the ambient sound signal is calculated, and the sound wave of the corresponding signal is output, realizing intelligent active noise reduction for different ambient sound scenes. Moreover, different ambient sound scenes match different noise reduction algorithm parameters, which can achieve the effect of deep noise reduction, and improve the problem of poor noise reduction effect caused by applying a set of fixed noise reduction algorithm parameters to different ambient sound scenes for active noise reduction. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0013] Figure 1 is a schematic flowchart of an active noise reduction method for a vehicle provided in Embodiment 1 of the present invention; Figure 2 is a structural block diagram of an active noise reduction device for a vehicle provided in Embodiment 2 of the present invention; Figure 3 is a schematic structural diagram of a controller provided in Embodiment 3 of the present invention; Figure 4 is a schematic structural diagram of an active noise reduction system for a vehicle provided in Embodiment 4 of the present invention; Figure 5 is a schematic structural diagram of an active noise reduction system for a vehicle provided in Embodiment 5 of the present invention; Figure 6 is a schematic structural diagram of a vehicle provided in Embodiment 6 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the protection scope of the present invention.

[0015] In the following description, specific details such as specific system architectures, technologies, etc. are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, systems, circuits, and methods are omitted to avoid unnecessary details from obstructing the description of the present invention.

[0016] It should be understood that when used in the specification and the appended claims of the present invention, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0017] It should also be understood that the term "and / or" as used in the specification and the appended claims of the present invention refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0018] As used in the specification and the appended claims of the present invention, the term "if" can be interpreted as "when" or "once" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]" depending on the context.

[0019] In addition, in the description of the specification and the appended claims of the present invention, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0020] The reference to "one embodiment" or "some embodiments" etc. described in the specification of the present invention means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the present invention. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0021] It should be understood that the sequence numbers of the steps in the following embodiments do not imply the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0022] To illustrate the technical solution of the present invention, the following specific embodiments are used for illustration.

[0023] See Figure 1 , which is a schematic flowchart of an active noise reduction method for a vehicle provided in the first embodiment of the present invention. As Figure 1 shown, the active noise reduction method for the vehicle may include the following steps.

[0024] S101: Collect the environmental sound signal of the environment where the vehicle is located and the error noise signal inside the vehicle.

[0025] In step S101, a reference microphone is used to collect the environmental sound signal, and an error microphone is used to collect the error noise signal inside the vehicle. Among them, the environmental sound signal is the sound signal in the environment where the vehicle is located. The error noise signal is the sound signal collected only at the human ear.

[0026] In this embodiment, a reference microphone is arranged outside the vehicle to collect the external noise signal in the environment where the vehicle is located, that is, the environmental sound signal. An error microphone is arranged at the human ear inside the vehicle to collect the noise signal at the human ear inside the vehicle, that is, the error noise signal. Among them, the reference microphone can be arranged at any position outside the vehicle.

[0027] In this embodiment, the environmental sound signal of the environment where the vehicle is located and the error noise signal inside the vehicle are collected, so as to control the output of a sound signal that cancels out the environmental sound signal according to the environmental sound signal and the error noise signal.

[0028] S102: Identify the target environmental sound scene where the vehicle is located according to the environmental sound signal.

[0029] In step S102, the target environmental sound scene is the scene where the noise signal in the environment where the vehicle is located contains the corresponding environmental sound signal.

[0030] In this embodiment, according to the environmental sound signal, the target environmental sound scene where the vehicle is located is identified. When identifying the target environmental sound scene where the vehicle is located, it can be identified through a pre-acquired and trained scene recognition model. The environmental sound signal is used as the input, and the environmental sound scene is used as the output. Among them, the scene recognition model can be a neural network model. The environmental sound scene can be a scene formed under different noises. For example, the environmental sound scene can be a scene where a large vehicle (such as a large truck, a train, a high-speed train, etc.) roars past beside the vehicle, and the noise in this scene is the sound generated during the driving process of the large truck, the train, the high-speed train, etc. The environmental sound scene can also be a scene of mechanical construction sounds and piling sounds at a construction site, and the noise in this scene is the sound generated during the mechanical construction at the construction site. The environmental sound scene can also be a scene of noisy human voices at the school gate, in the market, on the street, etc., and the noise in this scene is the sound generated by the people at the school gate, in the market, on the street, etc. The environmental sound scene can also be a scene where there are emergency braking sounds, exhaust sounds, and roaring sounds around the vehicle, and the noise in this scene is the sound generated by other vehicles around the vehicle due to emergency braking. The environmental sound scene can also be a scene under the steam whistle of a port ship and the noise of an airport aircraft, and the noise in this scene is the sound generated by the port ship, the airport aircraft, etc. The environmental sound scene can also be a scene of the idle noise of a large vehicle around a stationary vehicle, and the noise in this scene is the sound generated by the large vehicle around the stationary vehicle due to idling.

[0031] It should be noted that the training process of the trained scene recognition model includes: obtaining training samples and an initial scene recognition model. The training samples include environmental sound signals collected under different environmental sound scenes and the environmental sound scenes corresponding to the environmental sound signals. Among them, the environmental sound scene is the label corresponding to the environmental sound signal. The initial scene recognition model is supervised and trained using the training samples to obtain the trained scene recognition model.

[0032] In this embodiment, according to the environmental sound signal, the target environmental sound scene where the vehicle is located is identified, so as to determine the corresponding noise reduction algorithm parameters based on different target environmental sound scenes.

[0033] Optionally, identifying the target environmental sound scene where the vehicle is located further includes: Collecting environmental visual information of the environment where the vehicle is located; According to the environmental visual information and the environmental sound signal, identifying the target environmental sound scene where the vehicle is located.

[0034] In this embodiment, in order to improve the recognition accuracy of the environmental sound scene, auxiliary recognition can also be performed through the environmental visual information of the vehicle's environment. The environmental visual information of the vehicle's environment is collected, where the environmental visual information is an image, that is, an image of the vehicle's surrounding environment collected by an in-vehicle camera. According to the environmental visual information and the environmental sound signal, the target environmental sound scene where the vehicle is located is recognized. When recognizing the target environmental sound scene where the vehicle is located, it can be recognized through a pre-obtained trained recognition model. The environmental sound signal and the environmental visual information are used as inputs, and the environmental sound scene is used as the output. Among them, the recognition model can be a neural network model.

[0035] It should be noted that the training process of the trained recognition model includes: obtaining training samples and an initial recognition model. The training samples include environmental sound signals and environmental visual information collected under different environmental sound scenes, and the environmental sound scenes corresponding to the environmental sound signals and environmental visual information. Among them, the environmental sound scene is the label corresponding to the environmental sound signal and the environmental visual information. The initial recognition model is supervised and trained using the training samples to obtain the trained recognition model.

[0036] In this embodiment, according to the environmental visual information and the environmental sound signal, the target environmental sound scene where the vehicle is located is recognized. By recognizing the environmental sound scene through multi-modal information, the recognition accuracy of the environmental sound scene is improved.

[0037] S103: According to the target environmental sound scene, determine the noise reduction algorithm parameters matching the target environmental sound scene from a preset noise reduction algorithm parameter library to obtain the target noise reduction algorithm parameters. The noise reduction algorithm parameters include a convergence step size and a filter weight coefficient.

[0038] In step S103, according to the target environmental sound scene, determine the noise reduction algorithm parameters matching the target environmental sound scene from a preset noise reduction algorithm parameter library. Among them, the preset noise reduction algorithm parameter library stores noise reduction algorithm parameters under different environmental sound scenes. The noise reduction algorithm parameters are used to generate a sound signal that cancels out the environmental sound signal. The noise reduction algorithm parameters include a convergence step size and a filter weight coefficient.

[0039] In this implementation, since the acoustic characteristics of the noise signals corresponding to different environmental sound scenes are different. For example, the sound characteristics of a large truck roaring past are broadband, smooth spectral characteristics, and acoustic characteristics with a relatively high proportion of low-frequency components; while the acoustic characteristics of noisy human voices are relatively high-frequency, and there will be multiple spikes in the sound spectrum. Different acoustic characteristics require different noise reduction mode parameters to achieve better effects. Therefore, it is necessary to match the noise reduction algorithm parameters that can cancel the corresponding sound in the environmental sound scene according to different environmental sound scenes to improve the response speed and noise reduction amount of noise reduction.

[0040] The optimal noise reduction algorithm parameters for different environmental sound scenarios are stored in the noise reduction algorithm parameter library. The target environmental sound scenario is matched with the noise reduction algorithm parameters stored in the preset noise reduction algorithm parameter library to obtain the noise reduction algorithm parameters that match the target environmental sound scenario, that is, the target noise reduction algorithm parameters.

[0041] It should be noted that the noise reduction algorithm parameters include a convergence step size and a filter weight coefficient. Among them, the convergence step size and the filter weight coefficient are used to control the sound signal that cancels out the environmental sound signal.

[0042] In this embodiment, according to the target environmental sound scenario, the noise reduction algorithm parameters that match the target environmental sound scenario are determined from the preset noise reduction algorithm parameter library to obtain the target noise reduction algorithm parameters, so that each different environmental sound scenario corresponds to a set of noise reduction algorithm parameters, avoiding using the same set of noise reduction algorithm parameters for different environmental sound scenarios, facilitating the calling of the corresponding noise reduction algorithm parameters for different environmental sound scenarios, and improving the noise reduction response speed and noise reduction amount.

[0043] Optionally, before determining the noise reduction algorithm parameters that match the target environmental sound scenario from the preset noise reduction algorithm parameter library according to the target environmental sound scenario to obtain the target noise reduction algorithm parameters, it further includes: Obtaining N reference environmental sound scenarios, the reference environmental sound signals in each reference environmental sound scenario, the error noise signals in each reference environmental sound scenario, and the initial values of each noise reduction algorithm parameter, where N is an integer greater than zero; For any reference environmental sound scenario, according to the reference environmental sound signal, the error noise signal, and the initial value of the noise reduction algorithm parameter in the reference environmental sound scenario, aiming at the best noise reduction effect, the noise reduction algorithm parameters are debugged to obtain the best noise reduction algorithm parameters corresponding to the reference environmental sound scenario; According to each reference environmental sound scenario and the best noise reduction algorithm parameters in the corresponding environmental sound scenario, a preset noise reduction algorithm parameter library is constructed, and the environmental sound scenarios and the noise reduction algorithm parameters in the noise reduction algorithm parameter library are in one-to-one correspondence.

[0044] In this embodiment, before determining the noise reduction algorithm parameters that match the target environmental sound scenario from the preset noise reduction algorithm parameter library according to the target environmental sound scenario to obtain the target noise reduction algorithm parameters, it is necessary to construct a database containing the noise reduction algorithm parameters for different environmental sound scenarios, that is, the preset noise reduction algorithm parameter library. When constructing a database containing the noise reduction algorithm parameters for different environmental sound scenarios, it is necessary to determine the corresponding noise reduction algorithm parameters for different environmental sound scenarios.

[0045] When determining the noise reduction algorithm parameters corresponding to different ambient sound scenarios, first obtain N reference ambient sound scenarios, the reference ambient sound signals in each reference ambient sound scenario, the error noise signals in each reference ambient sound scenario, and the initial values of each noise reduction algorithm parameter, where N is an integer greater than zero. Among them, the N reference ambient sound scenarios are the ambient sound scenarios in which the vehicle may be located. The reference ambient sound signals in each reference ambient sound scenario are the sound signals collected by the reference microphone outside the vehicle in the corresponding sound field. The error noise signal is the sound signal inside the vehicle in this ambient sound scenario collected by the error microphone. The initial values of each noise reduction algorithm parameter are the values before debugging each noise reduction algorithm parameter. Among them, the initial values can be set according to experience or by other methods, which are not limited in this embodiment.

[0046] It should be noted that the error noise signal is the sound signal inside the vehicle in this ambient sound scenario collected by the error microphone, where the error microphone can be set at the human ear inside the vehicle.

[0047] For any reference ambient sound scenario, according to the reference ambient sound signal in the reference ambient sound scenario, the error noise signal in the reference ambient sound scenario, and the initial value of the noise reduction algorithm parameter, with the best noise reduction effect as the goal, debug the noise reduction algorithm parameter to obtain the best noise reduction algorithm parameter corresponding to the reference ambient sound scenario. Among them, debugging the noise reduction algorithm parameter means debugging the convergence step size and the magnitude of the filter weight coefficient. With the best noise reduction effect as the goal, debug the noise reduction algorithm parameter. Among them, the best noise reduction effect means the best response speed and noise reduction amount during corresponding noise reduction. Among them, the faster the response speed, the better the corresponding noise reduction effect, and the larger the noise reduction amount, the better the corresponding noise reduction effect.

[0048] When debugging, a corresponding debugging step size can be set, that is, each time of debugging, the value of the noise reduction algorithm parameter increases or decreases by the corresponding debugging step size. For example, if the initial value of the convergence step size is 0.001 and the corresponding debugging step size is 0.0005, then when debugging the convergence step size, first adjust the value of the convergence step size to 0.0015. If the noise reduction effect corresponding to 0.0015 of the convergence step size is not the best, then continue to debug the convergence step size and adjust the value of the convergence step size to 0.002 until the noise reduction effect is the best.

[0049] Traverse each reference ambient sound scenario to obtain the best noise reduction algorithm parameter corresponding to each reference ambient sound scenario, and correspond the ambient sound scenario with the best noise reduction algorithm parameter in the corresponding ambient sound scenario one by one to construct a noise reduction algorithm parameter library. The best noise reduction algorithm parameters in different ambient sound scenarios can be equal or not equal.

[0050] It should be noted that after the noise reduction algorithm parameter library is constructed, when there is no noise reduction algorithm parameter in the noise reduction algorithm parameter library that matches the target environmental sound scene, the noise reduction algorithm parameter corresponding to the target environmental sound scene can be added to the noise reduction algorithm parameter library to improve the noise reduction algorithm parameter library, so that when the target environmental sound scene appears subsequently, the noise reduction algorithm parameter that matches the target environmental sound scene can be determined from the preset noise reduction algorithm parameter library.

[0051] In this embodiment, N reference environmental sound scenes are obtained to make the noise reduction algorithm parameter library contain as many environmental sound scenes as possible where the vehicle may be located. For any reference environmental sound scene, aiming at the best noise reduction effect, the noise reduction algorithm parameters are debugged to obtain the best noise reduction algorithm parameters corresponding to the reference environmental sound scene. A preset noise reduction algorithm parameter library is constructed so that the noise reduction algorithm parameter corresponding to the target environmental sound scene can be determined from the noise reduction algorithm parameter library, and then the corresponding sound wave is output according to the corresponding noise reduction algorithm parameter.

[0052] S104: According to the convergence step size and filter weight coefficient in the environmental sound signal, error noise signal, and target noise reduction algorithm parameter, control the output of the sound signal that cancels the environmental sound signal to obtain the target cancellation noise signal. According to the target cancellation noise signal, output the corresponding sound wave to cancel the noise in the target environmental sound scene where the vehicle is located.

[0053] In step S104, the target cancellation noise signal is used to cancel the environmental sound signal, and the corresponding sound wave is the sound output through the vehicle-mounted speaker.

[0054] In this embodiment, the FxLMS (Filtered-x Least Mean Square) algorithm is used to control the output of the sound signal that cancels the environmental sound signal. According to the convergence step size and filter weight coefficient in the environmental sound signal, error noise signal, and target noise reduction algorithm parameter, the output sound signal is iterated until the output sound signal can cancel the environmental sound signal. The iteration formula of FxLMS is as follows: Where, is the error noise signal collected by using the error microphone, is the target noise signal, is the sound signal of the control output after the nth iteration, that is, the estimated noise signal, is the environmental sound signal collected by the reference microphone, that is, the reference signal, is the filter weight coefficient, is the convergence step size. When is zero, the noise reduction effect is the best.

[0055] When the preset iteration stop condition is met, stop the iteration, control the output of the corresponding sound signal, obtain the target cancellation noise signal, and according to the target cancellation noise signal, the in-vehicle speaker outputs the corresponding sound wave to cancel the noise in the target environmental sound scene where the vehicle is located. The preset iteration stop condition may be that the number of iterations is greater than the preset number, that is, when the number of iterations is greater than the preset number, stop the iteration and obtain the target cancellation noise signal. The preset iteration stop condition may also be other conditions, which are not limited in this embodiment.

[0056] In this embodiment, according to the ambient sound signal, the error noise signal, the convergence step size and the filter weight coefficient in the target noise reduction algorithm parameters, with the minimum error noise signal as the target, control the output of the sound signal that cancels the ambient sound signal to obtain the target cancellation noise signal. By updating the weight coefficient of the filter in real time and optimizing the control signal, it is possible to dynamically track noise changes (such as low-frequency noise, time-varying noise), and significantly improve the noise reduction accuracy. By adjusting the weight update through the error feedback mechanism, the system divergence caused by the secondary path modeling error can be avoided.

[0057] Optionally, according to the ambient sound signal, the error noise signal, the convergence step size and the filter weight coefficient in the target noise reduction algorithm parameters, control the output of the sound signal that cancels the ambient sound signal to obtain the target cancellation noise signal, including: According to the ambient sound signal, the error noise signal, the convergence step size and the filter weight coefficient in the target noise reduction algorithm parameters, with the minimum error noise signal as the target, control the output of the sound signal that cancels the ambient sound signal to obtain the target cancellation noise signal.

[0058] In this embodiment, according to the ambient sound signal, the error noise signal, the convergence step size and the filter weight coefficient in the target noise reduction algorithm parameters, with the minimum error noise signal as the target, that is, with the minimum difference between the sound signal output by the control after the nth iteration and the ambient sound signal as the target. Control the output of the sound signal that cancels the ambient sound signal.

[0059] In this embodiment, with the minimum error noise signal as the target, control the output of the sound signal that cancels the ambient sound signal, that is, in the case of the best noise reduction effect, to improve the accuracy of the corresponding sound signal.

[0060] In the present invention, according to the environmental sound signal of the noise in the environment where the vehicle is located, the environmental sound scene where the vehicle is located is identified, the noise reduction algorithm parameters matching the environmental sound scene are determined from a preset noise reduction algorithm parameter library, and according to the corresponding noise reduction algorithm parameters, a signal that can cancel the environmental sound signal is calculated, and the sound wave of the corresponding signal is output, so as to realize intelligent active noise reduction for different environmental sound scenes. Moreover, different environmental sound scenes match different noise reduction algorithm parameters, which can achieve the effect of deep noise reduction, and improve the problem of poor noise reduction effect caused by applying a set of fixed noise reduction algorithm parameters to different environmental sound scenes for active noise reduction.

[0061] See Figure 2 , Figure 2 FIG. is a structural block diagram of an active noise reduction device for a vehicle provided in Embodiment 2 of the present invention. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown. See Figure 2 , the active noise reduction device 20 includes a collection module 21, an identification module 22, a determination module 23, and an output module 24.

[0062] The collection module 21 is used to collect the environmental sound signal of the environment where the vehicle is located and the error noise signal in the vehicle.

[0063] The identification module 22 is used to identify the target environmental sound scene where the vehicle is located according to the environmental sound signal.

[0064] The determination module 23 is used to determine the noise reduction algorithm parameters matching the target environmental sound scene from a preset noise reduction algorithm parameter library according to the target environmental sound scene, and obtain the target noise reduction algorithm parameters. The noise reduction algorithm parameters include the convergence step size and the filter weight coefficient.

[0065] The output module 24 is used to control the output of a sound signal that cancels the environmental sound signal according to the convergence step size and the filter weight coefficient in the environmental sound signal, the error noise signal, and the target noise reduction algorithm parameters, obtain the target cancellation noise signal, and output the corresponding sound wave according to the target cancellation noise signal to cancel the noise in the target environmental sound scene where the vehicle is located.

[0066] Optionally, the above-mentioned active noise reduction device 20 further includes: An acquisition module, which is used to acquire N reference environmental sound scenes, the reference environmental sound signals in each reference environmental sound scene, the error noise signals in each reference environmental sound scene, and the initial values of each noise reduction algorithm parameter, where N is an integer greater than zero.

[0067] A debugging module, which is used to debug the noise reduction algorithm parameters for any reference environmental sound scene with the best noise reduction effect as the goal according to the reference environmental sound signal in the reference environmental sound scene, the error noise signal in the reference environmental sound scene, and the initial value of the noise reduction algorithm parameter, and obtain the best noise reduction algorithm parameters corresponding to the reference environmental sound scene.

[0068] A building block for constructing a preset noise reduction algorithm parameter library according to each reference environmental sound scene and the optimal noise reduction algorithm parameters in the corresponding environmental sound scene, where the environmental sound scenes in the noise reduction algorithm parameter library correspond one by one to the noise reduction algorithm parameters.

[0069] Optionally, the above recognition module 22 includes: An acquisition unit for acquiring environmental visual information of the environment where the vehicle is located.

[0070] A recognition unit for recognizing the target environmental sound scene where the vehicle is located according to the environmental visual information and the environmental sound signal.

[0071] Optionally, the above output module 24 includes: An output unit for controlling the output of a sound signal that cancels out the environmental sound signal with the goal of minimizing the error noise signal according to the environmental sound signal, the error noise signal, the convergence step size and the filter weight coefficient in the target noise reduction algorithm parameters, and obtaining the target cancellation noise signal.

[0072] It should be noted that for the information interaction, execution process, etc. between the above modules, since they are based on the same concept as the method embodiment of the present application, for their specific functions and the technical effects brought, reference can be specifically made to the method embodiment part, and details are not elaborated here.

[0073] Figure 3 This is a schematic structural diagram of a controller provided in Embodiment III of the present invention. As Figure 3 shown, the controller of this embodiment includes: at least one processor ( Figure 3 only one is shown in the figure), a memory, and a computer program stored in the memory and executable on at least one processor. When the processor executes the computer program, the steps in any of the above method embodiments of the active noise reduction method for vehicles are implemented.

[0074] The controller may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that Figure 3 this is only an example of the controller and does not constitute a limitation on the controller. The controller may include more or fewer components than those shown in the figure, or combine certain components, or different components. For example, it may also include a network interface, a display screen, and an input device, etc.

[0075] The so-called processor may be a CPU, and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0076] The memory includes a readable storage medium, an internal memory, etc. Among them, the internal memory may be the memory of the controller, and the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be the hard disk of the controller, and in some other embodiments, it may also be an external storage device of the controller. For example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the controller. Further, the memory may also include both the internal storage unit of the controller and the external storage device. The memory is used to store the operating system, application programs, a boot loader, data, and other programs, such as the program code of a computer program. The memory may also be used to temporarily store the data that has been output or will be output.

[0077] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of the functional units and modules are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the foregoing method embodiment and will not be elaborated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned method embodiment of this application, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0078] All or part of the processes in the above-mentioned method embodiment of this application can also be completed by a computer program product. When the computer program product runs on the controller, the controller can be made to execute the steps in the above-mentioned method embodiment.

[0079] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0080] Those of ordinary skill in the art will realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0081] In the embodiments provided in this application, it should be understood that the disclosed device / controller and method can be implemented in other ways. For example, the device / controller embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be electrical, mechanical or other forms.

[0082] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] See Figure 4 , Figure 4 FIG. 13 is a schematic structural diagram of an active noise reduction system of a vehicle provided in the fourth embodiment of the present invention. The active noise reduction system 40 includes a controller and a microphone, and the controller is communicatively connected to the microphone; The microphone is used to collect the environmental sound signal of the vehicle's surrounding environment and the error noise signal inside the vehicle; The controller is used to identify the target environmental sound scene where the vehicle is located according to the environmental sound signal; According to the target environmental sound scene, determine the noise reduction algorithm parameters matching the target environmental sound scene from the preset noise reduction algorithm parameter library to obtain the target noise reduction algorithm parameters. The noise reduction algorithm parameters include a convergence step size and a filter weight coefficient; According to the convergence step size and the filter weight coefficient in the environmental sound signal, the error noise signal, and the target noise reduction algorithm parameters, control the output of a sound signal that cancels the environmental sound signal to obtain the target cancellation noise signal. According to the target cancellation noise signal, output the corresponding sound wave to cancel the noise in the target environmental sound scene where the vehicle is located.

[0084] In this embodiment, the microphone includes a reference microphone and an error microphone. The reference microphone is used to collect the ambient sound signal of the environment where the vehicle is located, and the error microphone is used to collect the error noise signal inside the vehicle.

[0085] See Figure 5 , Figure 5 which is a schematic structural diagram of an active noise reduction system for a vehicle provided in Embodiment 5 of the present invention. The active noise reduction system 50 further includes a vision sensor. The controller is communicatively connected to the microphone and the vision sensor. The microphone is used to collect the ambient sound signal of the environment where the vehicle is located and the error noise signal inside the vehicle; the vision sensor is used to collect the ambient vision information of the environment where the vehicle is located. The controller is used to identify the target ambient sound scene where the vehicle is located according to the ambient sound signal; according to the target ambient sound scene, determine the noise reduction algorithm parameters matching the target ambient sound scene from a preset noise reduction algorithm parameter library to obtain the target noise reduction algorithm parameters. The noise reduction algorithm parameters include a convergence step size and a filter weight coefficient; according to the ambient sound signal, the error noise signal, and the convergence step size and the filter weight coefficient in the target noise reduction algorithm parameters, control the output of a sound signal that cancels out the ambient sound signal to obtain the target cancellation noise signal, and according to the target cancellation noise signal, output the corresponding sound wave to cancel out the noise in the target ambient sound scene where the vehicle is located.

[0086] See Figure 6 , Figure 6 which is a schematic structural diagram of a vehicle 60 provided in Embodiment 6 of the present invention. The vehicle 60 includes the above-mentioned active noise reduction system.

[0087] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An active noise reduction method for a vehicle, characterized in that, Including: Collecting an environmental sound signal of the environment where the vehicle is located and an error noise signal inside the vehicle; Identifying a target environmental sound scene where the vehicle is located according to the environmental sound signal; According to the target environmental sound scene, determining noise reduction algorithm parameters matching the target environmental sound scene from a preset noise reduction algorithm parameter library to obtain target noise reduction algorithm parameters, where the noise reduction algorithm parameters include a convergence step size and a filter weight coefficient; According to the environmental sound signal, the error noise signal, the convergence step size and the filter weight coefficient in the target noise reduction algorithm parameters, controlling the output of a sound signal that cancels out the environmental sound signal to obtain a target cancellation noise signal, and according to the target cancellation noise signal, outputting a corresponding sound wave to cancel out the noise in the target environmental sound scene where the vehicle is located.

2. The active noise reduction method according to claim 1, characterized in that The identifying the target environmental sound scene where the vehicle is located further includes: Collecting environmental visual information of the environment where the vehicle is located; Identifying the target environmental sound scene where the vehicle is located according to the environmental visual information and the environmental sound signal.

3. The active noise reduction method according to claim 1, characterized in that Before determining the noise reduction algorithm parameters matching the target environmental sound scene from a preset noise reduction algorithm parameter library according to the target environmental sound scene to obtain the target noise reduction algorithm parameters, it further includes: Obtaining N reference environmental sound scenes, reference environmental sound signals in each of the reference environmental sound scenes, error noise signals in each of the reference environmental sound scenes, and initial values of each noise reduction algorithm parameter, where N is an integer greater than zero; For any one of the reference environmental sound scenes, debugging the noise reduction algorithm parameters with the best noise reduction effect as the goal according to the reference environmental sound signal, the error noise signal, and the initial value of the noise reduction algorithm parameter in the reference environmental sound scene to obtain the best noise reduction algorithm parameters corresponding to the reference environmental sound scene; Constructing a preset noise reduction algorithm parameter library according to each reference environmental sound scene and the best noise reduction algorithm parameters in the corresponding environmental sound scene, where the environmental sound scenes and the noise reduction algorithm parameters in the noise reduction algorithm parameter library correspond one by one.

4. The active noise reduction method according to claim 1, wherein The controlling the output of a sound signal that cancels out the environmental sound signal according to the environmental sound signal, the error noise signal, the convergence step size and the filter weight coefficient in the target noise reduction algorithm parameters to obtain a target cancellation noise signal includes: Controlling the output of a sound signal that cancels out the environmental sound signal with the minimum error noise signal as the goal according to the environmental sound signal, the error noise signal, the convergence step size and the filter weight coefficient in the target noise reduction algorithm parameters to obtain a target cancellation noise signal.

5. An active noise reduction device for a vehicle, characterized in that, Including: A collection module for collecting an environmental sound signal of the environment where the vehicle is located and an error noise signal inside the vehicle; An identification module for identifying a target environmental sound scene where the vehicle is located according to the environmental sound signal; A determination module for determining noise reduction algorithm parameters matching the target environmental sound scene from a preset noise reduction algorithm parameter library according to the target environmental sound scene to obtain target noise reduction algorithm parameters, where the noise reduction algorithm parameters include a convergence step size and a filter weight coefficient; An output module, configured to control the output of a sound signal that cancels out the environmental sound signal according to the environmental sound signal, the error noise signal, the convergence step size and the filter weight coefficient in the target noise reduction algorithm parameters, so as to obtain a target cancellation noise signal, and output a corresponding sound wave according to the target cancellation noise signal to cancel out the noise in the target environmental sound scene where the vehicle is located.

6. The active noise reduction device according to claim 5, characterized in that, Further comprising: An acquisition module, configured to acquire N reference environmental sound scenes, the reference environmental sound signals in each of the reference environmental sound scenes, the error noise signals in each of the reference environmental sound scenes, and the initial values of each noise reduction algorithm parameter, where N is an integer greater than zero; A debugging module, configured to, for any one of the reference environmental sound scenes, debug the noise reduction algorithm parameters with the best noise reduction effect as the goal according to the reference environmental sound signal in the reference environmental sound scene, the error noise signal in the reference environmental sound scene, and the initial values of the noise reduction algorithm parameters, so as to obtain the best noise reduction algorithm parameters corresponding to the reference environmental sound scene; A construction module, configured to construct a preset noise reduction algorithm parameter library according to each reference environmental sound scene and the best noise reduction algorithm parameters in the corresponding environmental sound scene, where the environmental sound scenes and the noise reduction algorithm parameters in the noise reduction algorithm parameter library are in one-to-one correspondence.

7. A controller, characterized in that, The controller includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the active noise reduction method according to any one of claims 1 to 4 is implemented.

8. An active noise reduction system for a vehicle, characterized in that, The active noise reduction system includes the controller of claim 7 and a microphone, and the controller is communicatively connected to the microphone; The microphone is configured to collect the environmental sound signal of the environment where the vehicle is located and the error noise signal inside the vehicle; The controller is configured to identify the target environmental sound scene where the vehicle is located according to the environmental sound signal; According to the target environmental sound scene, determine the noise reduction algorithm parameters that match the target environmental sound scene from the preset noise reduction algorithm parameter library to obtain target noise reduction algorithm parameters, where the noise reduction algorithm parameters include a convergence step size and a filter weight coefficient; According to the environmental sound signal, the error noise signal, the convergence step size and the filter weight coefficient in the target noise reduction algorithm parameters, control the output of a sound signal that cancels out the environmental sound signal to obtain a target cancellation noise signal, and output a corresponding sound wave according to the target cancellation noise signal to cancel out the noise in the target environmental sound scene where the vehicle is located.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the active noise reduction method according to any one of claims 1 to 4 is implemented.

10. A vehicle, characterized in that, The vehicle includes the active noise reduction system of claim 8.

Images