Vehicle noise reduction method, device, equipment, system and storage medium

Abstract

The application provides a vehicle noise reduction method, device, equipment, system and storage medium, and relates to the technical field of vehicles.The method comprises the following steps: acquiring noise signals of a vehicle engine collected by each microphone in a vector microphone array, wherein the vector microphone array comprises at least two microphones, and the microphones are arranged on the side of the vehicle engine; performing beamforming on the noise signals collected by each microphone respectively to obtain beamformed signals; performing noise reduction processing on the beamformed signals to obtain noise reduction signals, and outputting the noise reduction signals in the vehicle; and wherein the noise reduction signals are opposite in phase to noise signals propagating to the vehicle. The technical scheme provided by the application can reduce the engine noise in the vehicle.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a vehicle noise reduction method, apparatus, device, system, and storage medium. Background Technology

[0002] Vehicles are a primary means of transportation and occupy an important place in people's lives. As living standards improve, while enjoying the convenience brought by vehicles, people also have higher and higher requirements for vehicle driving comfort. For example, the quieter the interior environment, the higher the driving comfort.

[0003] Vehicles inevitably generate noise during operation, with engine noise being one of the most common sources. Engine noise is typically caused by a combination of factors, including cylinder detonation, exhaust noise, and transmission system noise. This noise not only affects driving comfort but can also negatively impact health. Therefore, reducing engine noise inside the vehicle is crucial for providing a quieter and more comfortable driving environment. Summary of the Invention

[0004] This invention provides a vehicle noise reduction method, apparatus, device, system, and storage medium to reduce engine noise inside a vehicle.

[0005] This invention provides a vehicle noise reduction method, comprising:

[0006] Acquire noise signals from the vehicle engine collected by each microphone in a vector microphone array; the vector microphone array includes at least two microphones, which are deployed to the side of the vehicle engine;

[0007] Beamforming is performed on the noise signal collected by each of the microphones to obtain a beamformed signal;

[0008] The beamforming signal is subjected to noise reduction processing to obtain a noise-reduced signal, and the noise-reduced signal is output inside the vehicle; the noise-reduced signal is out of phase with the noise signal propagating into the vehicle.

[0009] According to a vehicle noise reduction method provided by the present invention, the step of beamforming the noise signal collected by each of the microphones to obtain a beamformed signal includes:

[0010] Extract the first feature data of the noise signal collected by each of the microphones;

[0011] Based on the layout of the microphones in the vector microphone array and the first feature data corresponding to each microphone, the target weight of each microphone is determined;

[0012] Based on the target weight of each microphone, the noise signals collected by each microphone are synthesized to obtain the beamforming signal.

[0013] A vehicle noise reduction method according to the present invention further includes:

[0014] The noise detection signal of the vehicle engine collected by the noise detection device is acquired, and the spectral characteristics of the noise detection signal are extracted.

[0015] Determine the propagation path of the noise detection signal on the vehicle;

[0016] The layout information of the microphone is determined based on the spectral characteristics and the propagation path;

[0017] Output the layout information.

[0018] A vehicle noise reduction method according to the present invention further includes:

[0019] Determine the signal-to-noise ratio of the noise-reduced signal to the noise signal;

[0020] The target parameters of the vector microphone array and / or the parameters of the beamforming algorithm are adjusted based on the signal-to-noise ratio; the target parameters include the microphone gain and / or target weights.

[0021] A vehicle noise reduction method according to the present invention further includes:

[0022] Obtain the operating status data of the vehicle engine;

[0023] If the operating status data changes, the parameters of the beamforming algorithm and / or the parameters of the noise reduction algorithm are adjusted based on the operating status data.

[0024] A vehicle noise reduction method according to the present invention further includes:

[0025] Acquire the noise detection signal of the vehicle engine collected by the noise detection device, and extract the second feature data of the noise detection signal;

[0026] Obtain the operating status data of the vehicle engine;

[0027] The noise reduction algorithm used in the noise reduction process is determined based on the second feature data and the running status data.

[0028] The present invention also provides a vehicle noise reduction device, comprising:

[0029] A signal acquisition module is used to acquire noise signals from the vehicle engine collected by each microphone in the vector microphone array; the vector microphone array includes at least two microphones, which are deployed to the side of the engine;

[0030] A beamforming module is used to beamform the noise signal collected by each of the microphones to obtain a beamformed signal.

[0031] The noise reduction module is used to perform noise reduction processing on the beamforming signal to obtain a noise-reduced signal;

[0032] A signal output module is used to output the noise reduction signal inside the vehicle; the noise reduction signal is out of phase with the noise signal propagating into the vehicle.

[0033] The present invention also provides a vehicle noise reduction system, including a vector microphone array, a sound output device, and the vehicle noise reduction device as described above;

[0034] The vector microphone array includes at least two microphones, which are deployed on the side of the vehicle engine and connected to the vehicle noise reduction device. The at least two microphones are used to collect noise signals from the vehicle engine.

[0035] The sound output device is located inside the vehicle and connected to the vehicle noise reduction device. The sound output device is used to output the noise reduction signal obtained by the vehicle noise reduction device.

[0036] The present invention also provides a vehicle noise reduction device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the vehicle noise reduction method as described above.

[0037] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle noise reduction method as described above.

[0038] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the vehicle noise reduction method as described above.

[0039] The vehicle noise reduction method, apparatus, device, system, and storage medium provided by this invention utilize a vector microphone array containing at least two microphones deployed on the side of the vehicle engine. Noise signals from the vehicle engine are collected through the microphones in the vector microphone array. Beamforming is applied to the noise signals collected by each microphone to obtain beamformed signals. These beamformed signals are then subjected to noise reduction processing to obtain a noise-reduced signal, which is output inside the vehicle. The noise-reduced signal is out of phase with the noise signal propagating into the vehicle interior. This allows the noise-reduced signal to cancel out the noise signals from the vehicle engine propagating into the vehicle interior, reducing the energy of the noise signals inside the vehicle and thus achieving the goal of reducing engine noise inside the vehicle. Furthermore, using a vector microphone array can more accurately locate and capture noise signals of various frequencies from the vehicle engine. Then, by using beamforming to synthesize and phase-flip the noise signals collected by each microphone, the noise signals can be amplified in a specific direction, resulting in a beamformed signal that accurately reflects the engine noise. Noise reduction processing can further improve the signal-to-noise ratio of the beamformed signal, resulting in a noise-reduced signal with a better signal-to-noise ratio. In this way, using the noise-reduced signal to cancel the noise signals of the vehicle engine propagating into the vehicle can improve the noise reduction effect of the engine noise. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0041] Figure 1 This is a schematic flowchart of the vehicle noise reduction method provided in an embodiment of the present invention;

[0042] Figure 2 This is a schematic diagram of the vehicle noise reduction device provided in an embodiment of the present invention;

[0043] Figure 3 This is a schematic diagram of the structure of the vehicle noise reduction device provided in an embodiment of the present invention;

[0044] Figure 4 This is a schematic diagram of the vehicle noise reduction system provided in an embodiment of the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0046] It should be noted that the serial numbers assigned to the objects described in this invention, such as "first" and "second", are only used to distinguish the objects being described and do not have any sequential or technical meaning.

[0047] Among the technologies related to reducing engine noise, one approach is to add sound insulation materials to the vehicle, but this can easily lead to environmental problems. Alternatively, noise can be reduced by modifying the exhaust system design, but this method comes at the cost of altering the exhaust system design, resulting in higher costs and limited applicability.

[0048] Active noise control technology reduces engine noise by minimizing low-frequency noise. It uses microphones and audio systems to detect engine noise and then emits sound waves to cancel out the noise by placing speakers or vibrators near the noise source, thus reducing noise propagation. This method is more environmentally friendly and eliminates the need for sound-absorbing materials or other polluting substances.

[0049] However, active noise control technology has the following drawbacks: First, while it achieves noise reduction by decreasing low-frequency noise, its effectiveness is not ideal for high-frequency noise, especially complex noise. Second, in addition to using sensors to detect noise signals, it requires placing speakers or vibrators near the noise source to emit sound waves to cancel out the noise. This results in a complex structure, requiring high-precision sensors and control systems, demanding advanced technology and incurring high costs. This makes it difficult to widely apply active noise control technology to different types and levels of vehicles. Third, it requires outputting the sound waves used to cancel out noise to the audio system, increasing the engine load and energy consumption. These drawbacks limit the application of active noise control technology in various types of vehicles, resulting in limited applicability and varying noise reduction effects across different vehicle types and operating environments.

[0050] Based on this, this invention provides a vehicle noise reduction method. A vector microphone array containing at least two microphones is deployed on the side of the vehicle engine, i.e., around the engine. The microphones in the vector microphone array locate and capture noise signals of various frequencies from the vehicle engine. Beamforming is performed on the noise signal collected by each microphone to obtain a beamformed signal. Then, the beamformed signal is subjected to noise reduction processing to obtain a noise-reduced signal, which is output inside the vehicle. The noise-reduced signal is out of phase with the noise signal propagating into the vehicle, thus canceling out the noise signal from the vehicle engine propagating into the vehicle, reducing the energy of the noise signal inside the vehicle, and thereby achieving the goal of reducing engine noise inside the vehicle.

[0051] Compared with active noise control technology in related technologies, beamforming and noise reduction processing can process and synthesize noise signals collected by microphone arrays, and use phase difference and amplitude adjustment to cancel and reduce noise. It is more suitable for noise sources in fixed locations, and does not require additional speakers or vibrators to be placed near the noise source. Only a vector microphone array needs to be deployed around the vehicle engine. It is simple to implement and has a wider range of applications.

[0052] The following is combined Figure 1 The vehicle noise reduction method of the present invention will be described.

[0053] Figure 1 An exemplary flowchart of a vehicle noise reduction method provided in an embodiment of the present invention is shown below. Figure 1 As shown, the vehicle noise reduction method may include the following steps 110 to 140.

[0054] Step 110: Acquire the noise signal of the vehicle engine collected by each microphone in the vector microphone array.

[0055] The vector microphone array includes at least two microphones deployed to the side of the vehicle engine. In this embodiment, "side of the vehicle engine" refers to a location on the vehicle close to the engine, i.e., around the engine, and may include the engine itself. For example, it could be deployed on the inner wall of the engine compartment or on the engine hood.

[0056] A vector microphone array is a microphone array comprising at least two microphones that are directional and position-aware. When an engine is running, it generates noise signals of various frequencies that propagate through the air. Each microphone in a vector microphone array can capture these noise signals and convert them into electrical signals for processing by electronic devices such as processors.

[0057] Step 120: Beamforming is performed on the noise signal collected by each microphone to obtain the beamformed signal.

[0058] After acquiring the vehicle engine noise signals collected by each microphone in the vector microphone array, beamforming can be applied to these noise signals. Beamforming then combines these noise signals into a single composite signal, known as the beamformed signal. Beamforming optimizes the direction and response of the noise signals based on the microphone positions and characteristics of the acquired noise signals, thus improving the localization of the vehicle engine noise. The beamformed signal obtained through beamforming has a higher signal-to-noise ratio and can accurately reflect the noise signals generated by the engine.

[0059] During beamforming, the weights and phases of each microphone in the vector microphone array can be adjusted to enhance the synthesized signal in a specific direction while canceling each other out in other directions. At the same time, phase flipping makes the phase of the synthesized signal opposite to the phase of the noise signal generated by the vehicle engine.

[0060] For example, each microphone in the vector microphone array can be pre-configured with its own target weight. During beamforming, the noise signals collected by each microphone are weighted and summed based on their target weights to obtain the beamforming signal. The target weights can be configured according to the microphone layout; for example, microphones closer to the vehicle engine can have a larger target weight.

[0061] For example, during beamforming, the target weight of each microphone can be determined in real time based on the characteristic data of the noise signals collected by each microphone. The characteristic data may include at least one of the following, but is not limited to: spectral characteristics, temporal characteristics, and signal strength. For instance, the target weight can be determined based on the relative magnitude of the signal strength of the noise signals collected by each microphone, so that microphones with higher signal strength have higher target weights.

[0062] For example, the noise signals collected by each microphone can be beamformed in both the time and frequency domains to form a beam with a specified directional response, thereby enhancing the noise signal in the specified direction and suppressing noise and interference signals in other directions.

[0063] For example, beamforming algorithms may include the Minimum Variance Distortionless Response (MVDR) algorithm or the Minimum Mean Square Error (MMSE) algorithm, etc., and this invention does not specifically limit them.

[0064] Step 130: Perform noise reduction processing on the beamforming signal to obtain a noise-reduced signal.

[0065] After obtaining the beamforming signal, a noise reduction processing algorithm can be used to process the beamforming signal to obtain a noise-reduced signal.

[0066] For example, the noise reduction algorithm used in the noise reduction process can be a pre-set noise reduction algorithm, or it can be determined and dynamically updated based on the operating status and noise characteristics of the vehicle engine. For instance, a correspondence between the operating status of the vehicle engine, noise characteristics, and noise reduction algorithms can be established in advance. During noise reduction, the required noise reduction algorithm can be matched from the established correspondence based on the current operating status data and noise characteristics of the vehicle engine.

[0067] For example, noise reduction algorithms may include digital filtering algorithms, adaptive filtering algorithms, wavelet transform algorithms, or noise reduction algorithms based on signal amplitude.

[0068] Digital filtering algorithms can reduce noise by inputting the vehicle engine noise signal into a digital filter and filtering out unwanted frequency components. These digital filters can include low-pass, high-pass, or band-pass filters, which can filter out unwanted frequency components based on the characteristics of the vehicle engine noise signal. Adaptive filtering algorithms can continuously update their filter coefficients based on the error between the input and output signals, thereby suppressing noise. They can continuously adjust the filter parameters through feedback control based on the characteristics of the vehicle engine noise signal to achieve noise reduction. Wavelet transform algorithms can decompose the signal into different frequency components to process noise of different frequencies; wavelet transform algorithms can include continuous wavelet transform or discrete wavelet transform. Signal amplitude-based noise reduction algorithms can determine whether a signal is a noise component based on its amplitude and filter it out. Signal amplitude-based noise reduction algorithms can include short-time amplitude-based noise reduction algorithms and long-time amplitude-based noise reduction algorithms.

[0069] Step 140: Output noise reduction signal inside the vehicle.

[0070] In this process, the noise reduction signal is out of phase with the noise signal propagating into the vehicle.

[0071] After obtaining the noise reduction signal, it can be output to the driver and passengers in the vehicle through the vehicle's audio system or headphones. This noise reduction signal can cancel out the noise signal of the vehicle engine that is transmitted into the vehicle, effectively reducing the noise of the vehicle engine and improving driving comfort and riding experience.

[0072] For example, to ensure the listening experience for the driver and passengers inside the vehicle, gain control can be introduced into the noise reduction signal to make the volume of the output noise reduction signal suitable for the human ear's hearing sensitivity. Then, the gain-controlled noise reduction signal is output to the driver and passengers through the vehicle's audio system or headphones. Specifically, the noise reduction signal can be determined by the following formula (1):

[0073] y(n)=sum_{k=0}^{N-1}h(k)x(nk) (1)

[0074] Where n and k represent discrete time points, y(n) represents the output noise-reduced signal, x(n) represents the input beamforming signal, h(k) represents the impulse response of the filter, and N represents the length of the filter.

[0075] In gain control, the gain of the output noise-reduced signal can be calculated using the following formula (2):

[0076] g(n)=10^{-\frac{d(n)}{20}} (2)

[0077] Where g(n) represents the gain of the output noise-reduced signal, and d(n) represents the difference between the target loudness of the gain controller and the actual loudness of the output noise-reduced signal, in decibels.

[0078] The vehicle noise reduction method provided in this invention deploys a vector microphone array containing at least two microphones on the side of the vehicle engine. The microphones in the vector microphone array can collect noise signals from the vehicle engine. The noise signals collected by each microphone are beamformed to obtain beamformed signals. These beamformed signals are then subjected to noise reduction processing to obtain a noise-reduced signal, which is output inside the vehicle. The noise-reduced signal is out of phase with the noise signal propagating into the vehicle, thus canceling out the noise signal from the vehicle engine propagating into the vehicle, reducing the energy of the noise signal inside the vehicle, and thereby achieving the goal of reducing engine noise inside the vehicle. Furthermore, using a vector microphone array can more accurately locate and capture noise signals of various frequencies from the vehicle engine. Then, by using beamforming to synthesize and phase-flip the noise signals collected by each microphone, the noise signals can be amplified in a specific direction, resulting in a beamformed signal that accurately reflects the engine noise. Noise reduction processing can further improve the signal-to-noise ratio of the beamformed signal, resulting in a noise-reduced signal with a better signal-to-noise ratio. In this way, using the noise-reduced signal to cancel the noise signals of the vehicle engine propagating into the vehicle can improve the noise reduction effect of the engine noise.

[0079] based on Figure 1In one example embodiment, the vehicle noise reduction method of the corresponding embodiment performs beamforming on the noise signal collected by each microphone to obtain a beamforming signal. This may include: extracting first feature data of the noise signal collected by each microphone; determining the target weight of each microphone based on the layout of the microphones in the vector microphone array and the first feature data corresponding to each microphone; and synthesizing the noise signal collected by each microphone based on the target weight of each microphone to obtain a beamforming signal.

[0080] The first feature data may include at least one of the following, but is not limited to: spectral features, time-domain features, and signal strength.

[0081] The layout of microphones in a vector microphone array characterizes the relative positions of the microphones and determines the directionality of the acquired noise signal. Different layouts result in different beamforming characteristics. Microphone layouts in a vector microphone array can include linear, matrix, or circular layouts, but are not limited to these. Once the microphone layout is determined, the number of microphones and the spatial position of each microphone are also determined.

[0082] For example, after obtaining the first feature data of the noise signal collected by each microphone, the initial weight of each microphone can be determined based on the first feature data. For example, according to the relative magnitude of the signal strength of the noise signal collected by each microphone, the microphone with the larger signal strength is assigned a larger weight, thereby determining the initial weight of each microphone. Then, beamforming is performed on the noise signal collected by each microphone based on the initial weight and the layout of the microphones to obtain an initial synthesized signal. Then, the initial synthesized signal is compared with a preset target signal to determine the error between the two. The initial weight of each microphone is adjusted with the goal of minimizing the error, and the weight of each microphone when the error is minimized is determined as the target weight of each microphone.

[0083] For example, the noise signals collected by each microphone can be weighted and synthesized based on the target weight of each microphone to obtain a beamforming signal. The target weight determines the relative contribution of the noise signals collected by each microphone to the synthesized beamforming signal.

[0084] For example, suppose a vector microphone array includes 5 microphones arranged in a linear array, numbered M1, M2, M3, M4, and M5 in sequence. The target weights for each microphone can be calculated using beamforming algorithms such as MVDR or MMSE, assuming they are w1, w2, w3, w4, and w5 respectively. Multiplying the noise signal of each microphone by its corresponding target weight and summing them yields the synthesized beamforming signal, which can be expressed as: w1*M1 + w2*M2 + w3*M3 + w4*M4 + w5*M5.

[0085] based on Figure 1 In one example embodiment of the vehicle noise reduction method corresponding to the embodiments, the layout of microphones in the vector microphone array can be determined in advance through noise detection. Specifically, the vehicle noise reduction method may further include: acquiring a noise detection signal of the vehicle engine collected by a noise detection device and extracting the spectral characteristics of the noise detection signal; determining the propagation path of the noise detection signal on the vehicle; determining the microphone layout information based on the spectral characteristics and the propagation path; and outputting the layout information.

[0086] The noise detection equipment may include microphone arrays, vibration sensors, vector microphone arrays, or other noise sensors. Multiple noise detection devices may be used and positioned on vehicle body components, inside the vehicle, etc., to detect the sound emitted by the vehicle engine during operation from different locations, obtaining noise detection signals. Layout information may include the number of microphones, their arrangement, and the distance between each microphone.

[0087] The spectral characteristics of a noise detection signal can reflect the frequency distribution range and characteristics of the noise detection signal. Based on these spectral characteristics, the propagation path of the noise detection signal on the vehicle can be determined. For example, the path detected by the noise detection device corresponding to a noise detection signal with a frequency amplitude greater than a preset amplitude threshold can be determined as a propagation path of the noise detection signal of the vehicle engine on the vehicle.

[0088] For example, acoustic propagation inside a vehicle can also be simulated. By simulating the location of different noise sources, the acoustic properties of the materials inside the vehicle, the vibration transmission of the vehicle structure, and other factors, the acoustic properties, reflection, scattering, and absorption of the vehicle structure can be analyzed to predict the propagation path and sound pressure level distribution of noise inside the vehicle.

[0089] For example, after obtaining the spectral characteristics and propagation path of the noise detection signal, the number of microphones can be determined based on these characteristics and propagation path. The microphones can then be positioned near the main noise source and along the propagation path to maximize noise signal capture, thus obtaining microphone layout information. For instance, if the spectral characteristics of the noise detection signal indicate that the noise signal from the vehicle engine is mainly concentrated in the low-frequency range of 20Hz-200Hz, and the main propagation path is through the vehicle's body structure 1 and body structure 2, then body structure 1 and body structure 2 can be used as the location information for microphone deployment, the preset number of microphones for each structure can be used as the number of microphones deployed, and the preset microphone arrangement for each structure can be used as an optional arrangement, thus obtaining microphone layout information.

[0090] For example, the layout information that matches the spectral characteristics and propagation path of the noise detection signal can be found in a preset layout information table by looking up a table, and this information can be used as the microphone's layout information. The preset layout information table can store the correspondence between spectral characteristics, propagation paths, and microphone layout information.

[0091] For example, after obtaining the microphone layout information, microphones can be arranged on the vehicle according to this information, with the appropriate number of microphones installed at the corresponding locations. Then, the sound signals collected by these microphones are acquired and beamformed to obtain a synthesized signal. This synthesized signal is used to evaluate the effectiveness of the layout and the noise reduction performance, thereby adjusting the microphone layout information to achieve a better noise reduction effect.

[0092] based on Figure 1 In one example embodiment of the vehicle noise reduction method corresponding to the embodiments, the noise reduction effect of the vehicle can also be monitored in real time, and the parameters of the vector microphone array can be adjusted and optimized based on the noise reduction effect to improve the noise reduction effect. Specifically, the vehicle noise reduction method may further include: determining the signal-to-noise ratio of the noise-reduced signal to the noise signal; adjusting the target parameters of the vector microphone array and / or the parameters of the beamforming algorithm based on the signal-to-noise ratio; wherein the target parameters include the microphone gain and / or target weights.

[0093] For example, when the signal-to-noise ratio (SNR) of the noise signal to the noise signal is less than the SNR threshold, at least one of the following parameters can be adjusted: microphone gain, microphone target weight, and beamforming algorithm parameters, with the goal of achieving an SNR greater than the SNR threshold.

[0094] based on Figure 1 In one example embodiment of the vehicle noise reduction method corresponding to the embodiments, the parameters of the beamforming algorithm and / or the noise reduction processing algorithm can be adjusted in real time according to the operating status of the vehicle engine to adapt to different operating conditions of the vehicle engine. Specifically, the vehicle noise reduction method may further include: acquiring operating status data of the vehicle engine; and adjusting the parameters of the beamforming algorithm and / or the noise reduction processing algorithm based on the operating status data when the operating status data changes.

[0095] For example, a first data table can be pre-established to store the correspondence between operating status data, beamforming algorithm parameters, and noise reduction algorithm parameters. During the operation of the vehicle engine, the operating status data of the vehicle engine can be monitored in real time, and the beamforming algorithm parameters and noise reduction algorithm parameters corresponding to the operating status data can be matched in the first data table.

[0096] For example, the target weights of each noise signal in the beamforming algorithm can be adjusted based on changes in vehicle engine load. For instance, when the load increases, the target weights of each noise signal can be adjusted to reduce the load. Alternatively, the time-varying nature of each noise signal can be adjusted based on changes in vehicle engine temperature.

[0097] based on Figure 1 In one example embodiment of the vehicle noise reduction method corresponding to the embodiments, the noise reduction processing algorithm can be selected based on the noise characteristics and operating status of the vehicle engine, and the noise reduction processing algorithm can be adaptively adjusted according to the real-time noise characteristics and operating status. Specifically, the vehicle noise reduction method may further include: acquiring the noise detection signal of the vehicle engine collected by the noise detection device, and extracting the second feature data of the noise detection signal; acquiring the operating status data of the vehicle engine; and determining the noise reduction processing algorithm to be used for noise reduction processing based on the second feature data and the operating status data.

[0098] The second feature data includes at least one of the following: spectral features, time-domain features, and signal strength, but is not limited to these.

[0099] For example, determining the noise reduction algorithm used for noise reduction based on the second feature data and the operating status data may include: matching the noise reduction algorithm corresponding to the second feature data and the operating status data from a second data table to obtain the noise reduction algorithm used for noise reduction. The second data table stores the correspondence between the feature data, the operating status data, and the noise reduction algorithm.

[0100] For example, during vehicle engine operation, noise signals and operating status data of the vehicle engine can be monitored in real time, and the characteristic data of the noise signals can be extracted. Then, the noise reduction processing algorithm can be adjusted in real time based on the noise signals and operating status data. In this way, the noise reduction processing algorithm can be optimized according to the operating conditions of the vehicle engine to adapt to different operating conditions.

[0101] For example, the parameters of the filters in the noise reduction algorithm can be adjusted based on the vehicle engine's operating status data to adapt to noise components within different frequency ranges. For instance, the filter's cutoff frequency can be adjusted according to changes in the vehicle engine's speed, or the filter's order can be adjusted according to changes in the vehicle engine's load.

[0102] For example, the adaptive step size or regularization parameters of the adaptive filter can be adjusted according to the operating status of the vehicle engine to improve the convergence speed and performance of the adaptive filter.

[0103] The vehicle noise reduction device provided by the present invention is described below. The vehicle noise reduction device described below can be referred to in correspondence with the vehicle noise reduction method described above.

[0104] Figure 2 An exemplary schematic diagram of the vehicle noise reduction device provided in an embodiment of the present invention is shown, with reference to... Figure 2 As shown, the vehicle noise reduction device 200 may include: a signal acquisition module 210 for acquiring the noise signal of the vehicle engine collected by each microphone in the vector microphone array, wherein the vector microphone array includes at least two microphones deployed on the side of the engine; a beamforming module 220 for beamforming the noise signal collected by each microphone to obtain a beamformed signal; a noise reduction module 230 for performing noise reduction processing on the beamformed signal to obtain a noise-reduced signal; and a signal output module 240 for outputting the noise-reduced signal inside the vehicle; wherein the noise-reduced signal is out of phase with the noise signal propagating into the vehicle.

[0105] In one example embodiment, the beamforming module 220 may include: a feature extraction unit for extracting first feature data of the noise signal collected by each microphone; a weight determination unit for determining the target weight of each microphone based on the layout of the microphones in the vector microphone array and the first feature data corresponding to each microphone; and a synthesis unit for synthesizing the noise signal collected by each microphone based on the target weight of each microphone to obtain a beamforming signal.

[0106] In one example embodiment, the vehicle noise reduction device 200 further includes a layout determination module, which is used to: acquire the noise detection signal of the vehicle engine collected by the noise detection device and extract the spectral characteristics of the noise detection signal; determine the propagation path of the noise detection signal on the vehicle; determine the layout information of the microphone based on the spectral characteristics and the propagation path; and output the layout information.

[0107] In one example embodiment, the vehicle noise reduction device 200 further includes a first adjustment module, which is configured to: determine the signal-to-noise ratio of the noise reduction signal to the noise signal; and adjust the target parameters of the vector microphone array and / or the parameters of the beamforming algorithm based on the signal-to-noise ratio; wherein the target parameters include the microphone gain and / or target weights.

[0108] In one example embodiment, the vehicle noise reduction device 200 further includes a second adjustment module, which is used to: acquire the operating status data of the vehicle engine; and adjust the parameters of the beamforming algorithm and / or the parameters of the noise reduction processing algorithm based on the operating status data when the operating status data changes.

[0109] In one example embodiment, the vehicle noise reduction device 200 further includes a noise reduction algorithm determination module, which is used to: acquire the noise detection signal of the vehicle engine collected by the noise detection device and extract the second feature data of the noise detection signal; acquire the operating status data of the vehicle engine; and determine the noise reduction processing algorithm to be used when performing noise reduction processing based on the second feature data and the operating status data.

[0110] Figure 3 An example is a schematic diagram of a vehicle noise reduction device, such as... Figure 3 As shown, the vehicle noise reduction device may include a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 can communicate with each other through the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute the vehicle noise reduction method provided in any of the above method embodiments. The method may include, for example, acquiring the noise signal of the vehicle engine collected by each microphone in a vector microphone array, wherein the vector microphone array includes at least two microphones, and the microphones are deployed on the side of the vehicle engine; performing beamforming on the noise signal collected by each microphone to obtain a beamforming signal; performing noise reduction processing on the beamforming signal to obtain a noise-reduced signal, and outputting the noise-reduced signal inside the vehicle; wherein the noise-reduced signal is out of phase with the noise signal propagating into the vehicle.

[0111] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0112] This invention also provides a vehicle noise reduction system. Figure 4 An exemplary schematic diagram of the vehicle noise reduction system is shown, with reference to... Figure 4As shown, the vehicle noise reduction system may include a vector microphone array 41, a sound output device 42, and a vehicle noise reduction device 43.

[0113] The vector microphone array 41 may include at least two microphones, which are deployed on the side of the vehicle engine, i.e., near the vehicle engine, or on the vehicle engine itself. These at least two microphones are connected to the vehicle noise reduction device 43 and are used to collect noise signals from the vehicle engine. For example, the microphones in the vector microphone array 41 may be arranged in a linear, matrix, or circular pattern.

[0114] A sound output device 42 is disposed inside the vehicle and connected to a vehicle noise reduction device 43. The sound output device 42 is used to output the noise reduction signal obtained by the vehicle noise reduction device 43. For example, the sound output device 42 may include at least one of a vehicle audio system and headphones that are connected to the vehicle for communication.

[0115] For example, the vehicle noise reduction device 43 may be a device integrated into the vector microphone array 41, or it may be a separate electronic device that is communicatively connected to the microphone of the vector microphone array 41.

[0116] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the vehicle noise reduction method provided in the above-described method embodiments. This method may include, for example, acquiring noise signals of the vehicle engine collected by each microphone in a vector microphone array, wherein the vector microphone array includes at least two microphones deployed to the side of the vehicle engine; performing beamforming on the noise signals collected by each microphone to obtain beamforming signals; performing noise reduction processing on the beamforming signals to obtain noise-reduced signals, and outputting the noise-reduced signals inside the vehicle; wherein the noise-reduced signals are out of phase with the noise signals propagating into the vehicle.

[0117] In another aspect, the present invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, is implemented to perform the vehicle noise reduction method provided in the above-described method embodiments. This method may include, for example, acquiring noise signals from the vehicle engine collected by each microphone in a vector microphone array, wherein the vector microphone array includes at least two microphones deployed to the side of the vehicle engine; performing beamforming on the noise signals collected by each microphone to obtain beamformed signals; performing noise reduction processing on the beamformed signals to obtain noise-reduced signals, and outputting the noise-reduced signals inside the vehicle; wherein the noise-reduced signals are out of phase with the noise signals propagating into the vehicle.

[0118] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0119] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle noise reduction method, characterized in that, include: Acquire the noise signal of the vehicle engine collected by each microphone in the vector microphone array; The vector microphone array includes at least two microphones, which are deployed to the side of the vehicle engine; Beamforming is performed on the noise signal collected by each of the microphones to obtain a beamformed signal; The beamforming signal is subjected to noise reduction processing to obtain a noise-reduced signal, and the noise-reduced signal is output inside the vehicle. The noise reduction signal is out of phase with the noise signal propagating into the vehicle. Also includes: Determine the signal-to-noise ratio of the noise-reduced signal to the noise signal; The target parameters of the vector microphone array and / or the parameters of the beamforming algorithm are adjusted based on the signal-to-noise ratio; the target parameters include the microphone gain and / or target weights.

2. The vehicle noise reduction method according to claim 1, characterized in that, The step of beamforming the noise signal collected by each of the microphones to obtain a beamformed signal includes: Extract the first feature data of the noise signal collected by each of the microphones; Based on the layout of the microphones in the vector microphone array and the first feature data corresponding to each microphone, the target weight of each microphone is determined; Based on the target weight of each microphone, the noise signals collected by each microphone are synthesized to obtain the beamforming signal.

3. The vehicle noise reduction method according to claim 1 or 2, characterized in that, Also includes: The noise detection signal of the vehicle engine collected by the noise detection device is acquired, and the spectral characteristics of the noise detection signal are extracted. Determine the propagation path of the noise detection signal on the vehicle; The layout information of the microphone is determined based on the spectral characteristics and the propagation path; Output the layout information.

4. The vehicle noise reduction method according to claim 1 or 2, characterized in that, Also includes: Obtain the operating status data of the vehicle engine; If the operating status data changes, the parameters of the beamforming algorithm and / or the parameters of the noise reduction algorithm are adjusted based on the operating status data.

5. The vehicle noise reduction method according to claim 1 or 2, characterized in that, Also includes: Acquire the noise detection signal of the vehicle engine collected by the noise detection device, and extract the second feature data of the noise detection signal; Obtain the operating status data of the vehicle engine; The noise reduction algorithm used in the noise reduction process is determined based on the second feature data and the running status data.

6. A vehicle noise reduction device, characterized in that, include: The signal acquisition module is used to acquire the noise signal of the vehicle engine collected by each microphone in the vector microphone array; The vector microphone array includes at least two microphones, which are deployed to the side of the engine; A beamforming module is used to beamform the noise signal collected by each of the microphones to obtain a beamformed signal. The noise reduction module is used to perform noise reduction processing on the beamforming signal to obtain a noise-reduced signal; A signal output module is used to output the noise reduction signal inside the vehicle; the noise reduction signal is out of phase with the noise signal propagating into the vehicle. It also includes a first adjustment module, which is used for: Determine the signal-to-noise ratio (SNR) between the noise-reduced signal and the noise signal; adjust the target parameters of the vector microphone array and / or the parameters of the beamforming algorithm based on the SNR; wherein the target parameters include the microphone gain and / or target weights.

7. A vehicle noise reduction device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the vehicle noise reduction method as described in any one of claims 1 to 5.

8. A vehicle noise reduction system, characterized in that, Includes a vector microphone array, a sound output device, and a vehicle noise reduction device as described in claim 7; The vector microphone array includes at least two microphones, which are deployed on the side of the vehicle engine and connected to the vehicle noise reduction device. The at least two microphones are used to collect noise signals from the vehicle engine. The sound output device is located inside the vehicle and connected to the vehicle noise reduction device. The sound output device is used to output the noise reduction signal obtained by the vehicle noise reduction device.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the vehicle noise reduction method as described in any one of claims 1 to 5.

Images