Vehicle noise reduction method, device, equipment, medium, product and vehicle

Abstract

The invention relates to a vehicle noise reduction method, device and equipment, a medium, a product and a vehicle. Noise information collected by at least two sensors on the vehicle is obtained; and performing noise reduction processing according to the noise information. The invention aims to improve the noise reduction effect of the vehicle.

Description

Technical Field

[0001] The present application relates to the field of vehicle noise reduction, and in particular to a vehicle noise reduction method, device, equipment, medium, product and vehicle. Background Art

[0002] With the development of the economy, consumers are paying more and more attention to the comfort of riding in cars while paying attention to the parameters, appearance and safety of cars. More and more car manufacturers are increasing their investment in the acoustic experience of car cabins in vehicle research and development. At present, acceleration sensors are usually used to collect noise reference signals for noise reduction, but they only have a certain inhibitory effect on structure-borne road noise, and have a poor inhibitory effect on air-borne road noise, resulting in poor noise reduction effect on the overall vehicle. Summary of the invention

[0003] The embodiments of the present application provide a vehicle noise reduction method, device, equipment, medium, product and vehicle, which improve the vehicle noise reduction effect and at least partially solve the above-mentioned technical problems.

[0004] In order to achieve the above object, according to a first aspect of the present application, a vehicle noise reduction method is provided, the vehicle noise reduction method comprising:

[0005] Acquire noise information collected by at least two sensors on the vehicle;

[0006] Noise reduction processing is performed according to the noise information.

[0007] According to a second aspect of the present application, there is provided an electronic device, including:

[0008] A transceiver module, used to obtain noise information collected by at least two sensors on the vehicle;

[0009] The noise reduction module is used to perform noise reduction processing according to the noise information.

[0010] According to a third aspect of the present application, an electronic device is also provided, including a processor, wherein the processor is connected to a memory, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to execute any of the above-mentioned vehicle noise reduction methods.

[0011] According to a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any of the above-mentioned vehicle noise reduction methods is implemented.

[0012] According to a fifth aspect of the present application, a computer program product is provided, which includes a computer program, and the computer program is executed by a processor to implement any of the above-mentioned vehicle noise reduction methods.

[0013] According to a sixth aspect of the present application, a vehicle is provided, comprising the electronic device or electronic equipment as described above.

[0014] The vehicle noise reduction method provided in the embodiment of the present application obtains noise information collected by at least two sensors on the vehicle; and performs noise reduction processing according to the noise information. In this way, multiple sensors are used to collect vehicle noise, and the corresponding noise information collected by at least two sensors is used for noise reduction processing. In this way, the propagation characteristics of vehicle noise are more fully considered, and multiple road noises can be reduced, which can improve the vehicle noise reduction effect.

[0015] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without creative work.

[0017] In order to more completely understand the present application and its beneficial effects, the following description will be given in conjunction with the accompanying drawings, wherein the same figure numbers represent the same parts in the following description.

[0018] Figure 1 is a flow chart of an embodiment of a vehicle noise reduction method provided in an embodiment of the present invention;

[0019] Figure 2 is a schematic diagram of the noise reduction process corresponding to the vehicle noise reduction method provided in an embodiment of the present invention;

[0020] Figure 3 is a schematic diagram of a training process corresponding to the vehicle noise reduction method provided in an embodiment of the present invention;

[0021] Figure 4 Schematic diagram of the noise reduction effect of the vehicle noise reduction method provided in an embodiment of the present invention;

[0022] Figure 5 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention;

[0023] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0025] With the development of the economy, consumers are paying more and more attention to the comfort of riding in cars while paying attention to the parameters, appearance and safety of cars. More and more car manufacturers are increasing their investment in the acoustic experience of car cabins in vehicle research and development. At present, acceleration sensors are usually used to collect noise reference signals for noise reduction, but they only have a certain inhibitory effect on structure-borne road noise, and have a poor inhibitory effect on air-borne road noise, resulting in poor noise reduction effect on the overall vehicle.

[0026] The inventors found that road noise can be divided into structure-borne noise and air-borne road noise according to different propagation modes, among which structure-borne road noise is mainly distributed in the frequency band below 500Hz; while air-borne road noise is distributed in the frequency band above 500Hz. The current vehicle noise reduction scheme usually uses an acceleration sensor to collect noise information as a reference for noise reduction, but it contains less information about air-borne road noise. As a result, the current vehicle noise reduction system can only obtain noise information with a high correlation with road noise as a reference in the frequency band below 500Hz, and achieve a certain noise reduction effect. In the frequency band above 500Hz, since the noise information has a low correlation with the road noise above 500Hz, the noise reduction effect is poor or even no noise reduction can be achieved.

[0027] In order to solve the above problems, the embodiments of the present application propose a vehicle noise reduction method, device, equipment, medium, product and vehicle. The embodiments of the present application perform noise reduction processing based on at least two types of noise information collected by at least two sensors on the vehicle, which can improve the noise reduction effect.

[0028] Specifically, the vehicle noise reduction method in the present application can be applied to an electronic device, the executor of the vehicle noise reduction method can be an electronic device, and the electronic device can be a vehicle, such as a car, an electric car, a hybrid car, etc.

[0029] In the following, each embodiment is described in detail by taking the case where the execution subject of the vehicle noise reduction method is an electronic device as an example.

[0030] Correspondingly, if Figure 1 As shown, the vehicle noise reduction method may include the following steps:

[0031] S10, obtaining noise information collected by at least two sensors on the vehicle;

[0032] In this embodiment, the vehicle noise reduction method can be applied to vehicles. According to the propagation of road noise, at least two sensors for collecting vehicle road noise can be set on the vehicle, such as an acceleration sensor, a sound collection device, a vibration sensor, etc. After the sensor is set on the vehicle, it can be used to collect road noise at the set position. Different types of sensors make the sensors collect different types of noise. The different types of sensors can include differences in installation positions, sensor models, sensor structures, etc. Through different types of sensors, noise information corresponding to different types of road noise can be collected. The noise information can represent the noise signal, noise intensity, noise frequency and other information of the road noise.

[0033] Optionally, for each sensor, there may be at least two sensors of the same type, which are respectively arranged at different positions on the vehicle to obtain more noise information.

[0034] S20: Perform noise reduction processing according to the noise information.

[0035] In this embodiment, noise information corresponding to at least two different types of road noise can be obtained through at least two sensors, that is, at least two types of noise information can be obtained. By using the at least two types of noise information as reference information, the road noise of the vehicle can be comprehensively reduced, and the suppression of at least two types of road noise can be achieved, thereby improving the noise reduction effect of the vehicle.

[0036] Furthermore, different noise information corresponds to different noise frequency bands.

[0037] In this embodiment, different noise information corresponds to different noise frequency bands. This noise frequency band is the frequency band of the noise information corresponding to the road noise, which is determined by the type of the sensor that collects the noise information.

[0038] Specifically, in this embodiment, at least one type of noise information corresponds to a noise frequency band below 500 Hz, so that the road noise below 500 Hz can be better suppressed, and at least one type of noise information corresponds to a noise frequency band above 500 Hz, so that the road noise above and below 500 Hz can be well suppressed.

[0039] By combining the noise frequency bands corresponding to at least two types of noise information, a target noise frequency band can be obtained. In this way, the noise reduction processing performed according to at least two types of noise information can at least reduce the road noise within the target noise frequency band, thereby achieving noise reduction over a wider frequency band and further improving the noise reduction effect of the vehicle.

[0040] Further, at least one of the noise information includes structural noise information, and at least one of the noise information includes air noise information.

[0041] In this embodiment, there are at least two noise information, among which at least one noise information is structural noise information, and at least one noise information is air noise information. The structural noise information mainly includes the relevant information of the road noise transmitted through the vehicle structure, and the air noise information mainly includes the relevant information of the road noise transmitted through the vehicle structure. Among them, the structurally transmitted road noise is mainly distributed in the noise frequency band below 500Hz, so that the noise frequency band corresponding to the structural noise information is below 500Hz; the air-transmitted road noise is distributed in the frequency band above 500Hz, so that the noise frequency band corresponding to the air noise information is above 500Hz. Through the structural noise information corresponding to the noise frequency band below 500Hz, the road noise below 500Hz can have an excellent noise reduction effect, and through the air noise information corresponding to the noise frequency band above 500Hz, the road noise above 500Hz can have an excellent noise reduction effect. In this way, through the structural noise information and the air noise information, the road noise above and below 500Hz can have a noise reduction effect, so that the vehicle can reduce noise in a wider frequency band, thereby improving the noise reduction effect of the vehicle.

[0042] Furthermore, the structural noise information is collected by an acceleration sensor of the vehicle, and the air noise information is collected by a sound collection device of the vehicle.

[0043] In this embodiment, at least two sensors are installed on the vehicle, at least one of which is an acceleration sensor and at least one is a sound collection device, and the sound collection device may be a microphone. The acceleration sensor may be arranged on the suspension of the vehicle, and / or the sound collection device may be arranged in the vehicle compartment. Through the acceleration sensor on the suspension, the road noise transmitted through the vehicle chassis may be mainly collected, and through the sound collection device in the vehicle compartment, the road noise transmitted through the air may be mainly collected.

[0044] In this way, the vehicle's acceleration sensor and sound collection device can be used to obtain noise information in two different noise frequency bands, thereby widening the noise reduction frequency band and further improving the vehicle's noise reduction effect.

[0045] Further, the performing noise reduction processing according to the noise information includes:

[0046] Obtaining a frequency domain weight vector corresponding to the sensor, wherein different sensors have different frequency domain weight vectors.

[0047] Processing the noise information collected by the sensor according to the frequency domain weight vector corresponding to the sensor to obtain reconstructed noise information;

[0048] Noise reduction processing is performed according to the reconstructed noise information corresponding to each sensor.

[0049] In this embodiment, due to the differences in sensor types and spectral characteristics corresponding to noise information, that is, different noise frequency bands, different frequency domain weight vectors are set for different sensors to remove the frequency bands containing fewer signals in the noise information collected by the corresponding sensor, thereby reducing the interference caused by irrelevant information. For example, for the structural noise information collected by the acceleration sensor, the corresponding acceleration frequency domain weight vector F G and the microphone frequency domain weight vector F M There are differences in the frequency bands they focus on. A typical setting is: the frequency domain weight vector of one sensor is set to 30-500Hz, and the frequency domain weight vector of another sensor is set to 400-1000Hz. However, for the same type of sensor, the frequency domain weight vector corresponding to the noise information collected is the same.

[0050] For each type of noise information, the noise information is processed according to the frequency domain weight vector corresponding to the sensor that collects the noise information, so as to obtain reconstructed noise information.

[0051] In this way, the noise information is reconstructed through the frequency domain weight vector, so that the reconstructed noise information mainly includes the road noise in the frequency band that the sensor that collects the noise information wants to collect, removes irrelevant noise, and improves the correlation between the reconstructed noise information and the sensor. Current research shows that this correlation determines the upper limit of the noise reduction system, so the noise reduction effect of the vehicle can be further improved.

[0052] Furthermore, after the noise information collected by the sensor is processed according to the frequency domain weight vector corresponding to the sensor to obtain the reconstructed noise information, the method further includes:

[0053] The reconstructed noise information corresponding to the sensor is filtered based on the filter corresponding to the sensor.

[0054] In this embodiment, at least two sensors of the same type may be provided on the vehicle, that is, the vehicle may have at least two sensors of the same type, and two noise information of the same type may be obtained through each sensor, thereby obtaining richer information. For example, at least two acceleration sensors may be provided on the vehicle, and two structural noise information may be obtained through at least two acceleration sensors.

[0055] For sensors of the same type, the noise information is reconstructed through the corresponding frequency domain weight vector to obtain the reconstructed noise information. For each sensor of this type, a filter is set accordingly. The reconstructed noise signal corresponding to each sensor is filtered, which can increase the amount of information corresponding to the road noise contained in the current reconstructed noise information, thereby further improving the noise reduction effect of the vehicle.

[0056] For example, the structure-borne noise information and the airborne noise information are collected by an acceleration sensor and a microphone, respectively. Figure 2 As shown, the noise reduction process corresponding to the noise reduction method in this embodiment is mainly divided into a reconstruction module and an active noise reduction module. Among them, the reconstruction module is mainly used to realize the reconstruction of structural noise information and air noise information, including an acceleration sensor group and a microphone sensor group. The acceleration sensor group includes n acceleration sensors and the structural noise information G1,...,G n , the acceleration frequency domain weight vector F G , and n acceleration filters The microphone sensor group includes k microphone sensors and the structure noise information M1,...,M k , microphone frequency domain weight vector F M , and n microphone filters According to the spectral characteristics of structure-borne noise and air-borne noise, the corresponding acceleration frequency domain weight vector F is set respectively. G and the microphone frequency domain weight vector F M Set up to remove the frequency bands with less signals in the current sensor group to reduce the interference caused by irrelevant information. Then pass n acceleration filters The reconstructed structural noise information G1,...,G corresponding to n acceleration sensors is respectively n Filtering is performed to increase the amount of information of the current acceleration sensor. Through k microphone filters The reconstructed air noise signals M1,...,M corresponding to k microphones are k Perform filtering to increase the amount of information from the current microphone.

[0057] Furthermore, different sensors are arranged at different positions on the vehicle, and the noise reduction process is performed according to the reconstructed noise information corresponding to each sensor, including:

[0058] For each of the sensors, according to the weight information corresponding to the sensor, weighted processing is performed on the reconstructed noise information corresponding to the sensor;

[0059] Based on the reconstructed noise information after each weighting process, noise reduction processing is performed.

[0060] In this embodiment, after reconstructing and filtering the noise information collected by each sensor, the weighted information corresponding to the sensor can also be obtained. The weighted information includes a weighting coefficient, and the weighted information represents the importance of collecting the sensor and the information collected by the sensor. Since each sensor is set at a different location and contains different amounts of information, it is necessary to adjust the importance of the information collected by the sensor in the noise reduction process through weighted processing. The reconstructed noise information corresponding to the sensor is weighted according to the weight information corresponding to the sensor to adjust the importance of the reconstructed noise information corresponding to the sensor in the noise reduction process, and then the noise reduction process is performed according to the reconstructed noise information after each weighted process, which can further improve the noise reduction effect of the vehicle.

[0061] For example, reference Figure 2 The reconstruction module also includes a weighting module, which includes n+k weighting coefficients w1,...,w n ,w n+1 ,...w n+k , corresponding to each microphone and each acceleration sensor respectively. After the acceleration sensor group and the microphone sensor group are processed, that is, the noise information is reconstructed and filtered, its output is passed through n+k weighting coefficients w1,...,w n ,w n+1 ,...w h+k Perform weighted processing to obtain weighted reconstructed noise information for subsequent noise reduction processing.

[0062] Furthermore, the noise reduction process is performed based on the reconstructed noise information after each weighted process, including:

[0063] The weighted reconstructed noise information is fused to obtain the target reconstructed noise;

[0064] The target reconstructed noise is input into the active noise reduction module for noise reduction processing.

[0065] In some embodiments, each weighted reconstructed noise information may be input into an active noise reduction module for noise reduction processing.

[0066] In this embodiment, the reconstructed noise information after each weighted processing can be fused, and the fusion method can be addition, splicing, etc., to obtain the final reconstructed target reconstructed noise, and then the target reconstructed noise is used as a reference signal to characterize the current road noise and input into the active noise reduction module for noise reduction processing. The active noise reduction module can adaptively generate noise reduction parameters according to the target reconstructed noise and perform corresponding noise reduction processing. The noise reduction effect of the vehicle can be further improved by performing noise reduction processing on the target reconstructed noise through the active noise reduction module, and multi-channel noise information can be compressed into one channel of noise, so that data fusion is realized before data analysis, and the number of required operations is reduced.

[0067] Further, the active noise reduction module includes a secondary speaker;

[0068] The active noise reduction module performs filtering processing on the target reconstructed noise through a weight vector to obtain a noise suppression signal, and controls the secondary speaker to emit sound based on the noise suppression signal to perform noise reduction processing.

[0069] In this embodiment, reference Figure 2 The active noise reduction module mainly includes a secondary speaker, which is used to emit a noise suppression signal. The active noise reduction module filters the target reconstructed noise through the weight vector w(z). The weight vector w(z) is an inverted vector, so that the target reconstructed noise after filtering is the noise suppression signal of the target reconstructed noise signal. The target reconstructed noise represents the road noise generated in the current vehicle, and its noise suppression signal represents the sound opposite to the road noise. Then, based on the noise suppression signal, the secondary speaker is controlled to emit a sound opposite to the road noise, so as to suppress the road noise generated in the vehicle and achieve a noise reduction process with a better noise reduction effect. In this embodiment, the noise suppression signal is played through the secondary speaker to produce a wide-band noise reduction effect in the target noise reduction area, such as Figure 4 As shown, it can be seen that the noise reduction method provided by this embodiment has a better noise reduction effect in a wide frequency band.

[0070] Furthermore, the active noise reduction module also includes a howling suppressor, which is arranged in the propagation path before the secondary speaker, and is used to detect whether there is acoustic feedback and perform howling suppression. Since the sound collection device is easily affected by acoustic feedback and produces howling when collecting noise information. Specifically, the filtered target reconstructed noise is detected by the howling suppressor to determine whether it has a howling frequency. If there is a howling frequency, the howling frequency is suppressed using the notch filter in the howling suppressor, and then the filtered and howling-suppressed target reconstructed noise is sent to the secondary speaker for sounding. If the howling frequency is not found, the filtered target reconstructed noise can be directly sent to the secondary speaker for sounding. In this way, the howling noise that may be caused by the setting of the sound collection device can be reduced by the howling suppressor, thereby further improving the vehicle noise reduction effect.

[0071] Further, the active noise reduction module includes an error sound collection device and a reconstructed secondary path, wherein the reconstructed secondary path is used to simulate the transmission from the secondary speaker to the error sound collection device;

[0072] Inputting the target reconstruction noise into the reconstructed secondary path to obtain secondary reconstruction noise;

[0073] The weight vector is updated according to the secondary reconstruction noise and the error noise collected by the error sound collection device.

[0074] In this embodiment, the active noise reduction module includes an error sound collection device and a reconstructed secondary path, and the reconstructed secondary path is used to simulate the transmission of the noise suppression signal from the secondary speaker to the error sound collection device. Figure 2 The active noise reduction module includes a secondary path S(z), which represents the transmission of the noise suppression signal from the secondary speaker to the error microphone. The secondary path S(z) is estimated in advance by modeling to obtain the reconstructed secondary path And added to the active noise reduction module, so that the active noise reduction module also includes reconstruction of the secondary path The error sound collection device may be a microphone. The error sound collection device is set in the target noise reduction area in the vehicle. The target noise reduction area is the area in the vehicle where noise reduction is required. In this embodiment, the target noise reduction area includes the area where the vehicle's seat headrest is located, that is, near the ears of the vehicle driver and passengers. The error noise in the target noise reduction area can be collected by the error sound collection device. The error noise can represent the relevant information of the noise that is not eliminated after the noise reduction process.

[0075] On the one hand, the active noise reduction module needs to input the target reconstructed noise into the reconstructed secondary path. The target reconstructed noise can be filtered by reconstructing the secondary path, and then the secondary path can be reconstructed to simulate the secondary path, and the secondary reconstructed noise can also be output. The error noise e(n) collected by the secondary reconstructed noise and the error sound collection device after the secondary speaker performs noise reduction processing is input into the adaptive algorithm of the active noise reduction module to update the weight vector w(z), which can offset the influence of the attenuation and delay of the secondary path on the noise reduction, so that the updated w(z) can more accurately filter the new target reconstructed noise, thereby generating a more accurate noise suppression signal and realizing adaptive noise elimination. When the weight vector w(z) reaches the optimal value, the sound emitted by the secondary speaker is exactly the same as the sum of the noise d1(n) transmitted through the structure and the noise d2(n) transmitted through the air, and the phase is opposite, so that the road noise in the car can be better eliminated and the noise reduction effect can be further improved.

[0076] Furthermore, the weight information and / or filter corresponding to each sensor is obtained through pre-training.

[0077] In this embodiment, in order to maximize the information collection, the weight information and filter corresponding to each sensor are obtained through pre-training, which can maximize the information collected by the corresponding sensor. In the training stage, an objective function can be introduced.

[0078] Furthermore, the pre-training comprises the following steps:

[0079] Acquire at least two types of training noise collected by the sensors and training error noise in a target noise reduction area;

[0080] Reconstructing according to the training noise to obtain training reconstructed noise;

[0081] For each sensor, the weight information and / or the filter corresponding to the sensor are obtained through training according to the frequency domain weight vector corresponding to the sensor, the training reconstruction noise, and the training error noise.

[0082] In this embodiment, the sensor setting position of the vehicle remains unchanged during the training stage and the noise reduction stage. During the training stage, the vehicle is driven on different roads and at different speeds to collect multiple sets of training data, each set of training data including training noise information collected by at least two sensors on the vehicle and training error noise collected by the error sound collection device in the target noise reduction area. It can be understood that since noise reduction is not performed during the training stage, the training error noise collected by the error sound collection device in the target noise reduction area is the actual noise formed after different road noises are propagated to the target noise reduction area.

[0083] First, the above-mentioned reconstruction and filtering process is performed based on the training noise information collected by at least two sensors on the vehicle to obtain the training reconstructed noise. For each sensor, according to the frequency domain weight vector corresponding to the sensor, as well as the training reconstructed noise and the training error noise, the weight information and / or filter corresponding to each sensor under the sensor is obtained by training with the goal of minimizing the difference between the training reconstructed noise and the training error noise, thus completing the pre-training of the weight information and / or filter corresponding to each sensor.

[0084] Further, according to the frequency domain weight vector corresponding to the sensor, the training reconstruction noise and the training error noise, training to obtain the weight information corresponding to the sensor and / or the filter includes:

[0085] Determining a global reconstruction error according to the training error noise information and the training reconstruction noise information;

[0086] Constructing an objective function corresponding to the sensor according to the global reconstruction error and a frequency domain weight vector corresponding to the sensor;

[0087] The initial weight information of the sensor and / or the initial filter is updated iteratively through the objective function to obtain the weight information and / or the filter.

[0088] In this embodiment, first, the corresponding initial weight information and / or initial filter are set for each sensor. Based on each sensor, according to the frequency domain weight vector, initial weight information and / or initial filter corresponding to the sensor, the processing consistent with the above-mentioned reconstruction, filtering and other processes is implemented to obtain the training reconstruction noise. According to the training error noise and the training reconstruction noise, the global reconstruction error is determined. Since the frequency domain weight vectors of sensors of the same type are the same, for each sensor, according to the global reconstruction error and its corresponding frequency domain weight vector, the objective function corresponding to this type of sensor can be constructed. Within the frequency domain weight vector interval corresponding to this type of sensor, the weight information and / or filter of each sensor of this type is trained, the initial weight information and / or initial filter are updated, and finally the weight information and / or initial filter that can be used in the noise reduction stage are obtained, thereby further improving the vehicle noise reduction effect.

[0089] For example, reference Figure 3 In the training phase, the acceleration filters corresponding to the n acceleration sensors need to be pre-trained. Microphone filters corresponding to k microphones And n+k weighted information w1,...,w n ,w n+1 ,...w h+k Only by training and obtaining the optimal configuration can the noise information be accurately and effectively reconstructed. The objective function J can be introduced G With J M , which are used to evaluate the difference between the structural noise information collected by the acceleration sensor and the error noise collected by the error microphone, and the difference between the air noise information collected by the evaluation microphone and the error noise collected by the error microphone. An optional objective function is:

[0090] J G =E(||X(n)-d(n)|| 2 F G )

[0091] J M =E(||X(n)-d(n)|| 2 F M )

[0092] According to the objective function J G With J M The current value of the n acceleration filters is dynamically adjusted k microphone filters and m+k weighting coefficients w1,...,w n ,w n+1 ,...w h+k , to minimize the objective function JG With J M , obtain the acceleration filter, microphone filter and weighting coefficient that meet the training requirements, and complete the training.

[0093] This embodiment also provides an electronic device, which can be integrated into a vehicle, for example Figure 5 As shown, the electronic device may include:

[0094] The transceiver module 1001 is used to obtain noise information collected by at least two sensors on the vehicle;

[0095] The noise reduction module 1002 is used to perform noise reduction processing according to the noise information.

[0096] Optionally, different noise information corresponds to different noise frequency bands.

[0097] Optionally, at least one of the noise information includes structural noise information, and at least one of the noise information includes air noise information.

[0098] Optionally, the structural noise information is collected by an acceleration sensor of the vehicle, and the air noise information is collected by a sound collection device of the vehicle.

[0099] Optionally, the acceleration sensor is arranged on a suspension of the vehicle, and / or the sound collecting device is arranged in a compartment of the vehicle.

[0100] Optionally, the noise reduction module 1002 is further configured to:

[0101] Obtaining a frequency domain weight vector corresponding to the sensor, wherein different sensors have different frequency domain weight vectors.

[0102] Processing the noise information collected by the sensor according to the frequency domain weight vector corresponding to the sensor to obtain reconstructed noise information;

[0103] Noise reduction processing is performed according to the reconstructed noise information corresponding to each sensor.

[0104] Optionally, the noise reduction module 1002 is further configured to:

[0105] The reconstructed noise information corresponding to the sensor is filtered based on the filter corresponding to the sensor.

[0106] Optionally, the noise reduction module 1002 is further configured to:

[0107] For each of the sensors, according to the weight information corresponding to the sensor, weighted processing is performed on the reconstructed noise information corresponding to the sensor;

[0108] Based on the reconstructed noise information after each weighting process, noise reduction processing is performed.

[0109] Optionally, the noise reduction module 1002 is further configured to:

[0110] The weighted reconstructed noise information is fused to obtain the target reconstructed noise;

[0111] The target reconstructed noise is input into the active noise reduction module for noise reduction processing.

[0112] Optionally, the active noise reduction module includes a secondary speaker; the active noise reduction module filters the target reconstructed noise through a weight vector, and controls the secondary speaker to emit sound based on the filtered target reconstructed noise to perform noise reduction processing.

[0113] Optionally, the active noise reduction module includes a howling suppressor;

[0114] The howling suppressor performs howling suppression processing on the filtered target reconstructed noise.

[0115] Optionally, the active noise reduction module includes an error sound collection device and a reconstructed secondary path, and the error sound collection device is arranged in a target noise reduction area in the vehicle;

[0116] The active noise reduction module inputs the target reconstructed noise into the reconstructed secondary path, obtains secondary reconstructed noise through the reconstructed secondary path, and updates the weight vector according to the secondary reconstructed noise and the error noise collected by the error sound collection device.

[0117] Optionally, the weight information and / or filter corresponding to each sensor is obtained through pre-training.

[0118] Optionally, the pre-training comprises the following steps:

[0119] Acquire training noise information collected by at least two sensors, and training error noise in a target noise reduction area;

[0120] Obtaining training reconstruction noise according to the training noise information;

[0121] For each sensor, the weight information and / or the filter corresponding to the sensor are obtained through training according to the frequency domain weight vector corresponding to the sensor, the training reconstruction noise, and the training error noise.

[0122] Optionally, determining a global reconstruction error according to the training error noise and the training reconstruction noise;

[0123] Constructing an objective function corresponding to the sensor according to the global reconstruction error and a frequency domain weight vector corresponding to the sensor;

[0124] The initial weight information of the sensor and / or the initial filter is updated by the objective function to obtain the weight information and / or the filter.

[0125] The vehicle noise reduction method provided in this embodiment obtains noise information collected by at least two sensors on the vehicle; and performs noise reduction processing according to the noise information. In this way, multiple sensors are used to collect vehicle noise, and the corresponding noise information collected by at least two sensors is used for noise reduction processing. In this way, the propagation characteristics of vehicle noise are more fully considered, multiple road noises can be reduced, and the vehicle noise reduction effect can be improved.

[0126] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0127] Accordingly, an embodiment of the present application further provides an electronic device, such as Figure 6 As shown, Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 1100 also includes a processor 1101 having one or more processing cores, a memory 1102 having one or more computer-readable storage media, and a computer program stored in the memory 1102 and executable on the processor. The processor 1101 is electrically connected to the memory 1102. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0128] The processor 1101 is the control center of the electronic device 1100, and uses various interfaces and lines to connect various parts of the entire electronic device 1100. By running or loading software programs and / or units stored in the memory 1102, and calling data stored in the memory 1102, the processor 1101 executes various functions of the electronic device 1100 and processes data, thereby monitoring the electronic device 1100 as a whole. The processor 1101 can be a processor CPU, a graphics processor GPU, a network processor (Network Processor, NP), etc., and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application.

[0129] In the embodiment of the present application, the processor 1101 in the electronic device 1100 will load instructions corresponding to the processes of one or more application programs into the memory 1102 according to the following steps, and the processor 1101 will run the application programs stored in the memory 1102 to implement various functions, such as:

[0130] Acquire noise information collected by at least two sensors on the vehicle;

[0131] Noise reduction processing is performed according to the noise information.

[0132] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0133] Optional, such as Figure 6 As shown, the electronic device 1100 further includes: a touch screen 1103, a radio frequency circuit 1104, an audio circuit 1105, an input unit 1106, and a power supply 1107. The processor 1101 is electrically connected to the touch screen 1103, the radio frequency circuit 1104, the audio circuit 1105, the input unit 1106, and the power supply 1107, respectively. Those skilled in the art can understand that Figure 6 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or have different component arrangements.

[0134] The touch display screen 1103 can be used to display a graphical user interface and receive operation instructions generated by the user acting on the graphical user interface. The touch display screen 1103 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user and various graphical user interfaces of the electronic device, and these graphical user interfaces can be composed of graphics, text, icons, videos and any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD, Liquid Crystal Display), an organic light-emitting diode (OLED, Organic Light-EmittingDiode) and the like. The touch panel can be used to collect the touch operation of the user on or near it (such as the operation of the user using any suitable object or attachment such as a finger, a stylus, etc. on the touch panel or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute corresponding programs. Optionally, the touch panel may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 1101, and can receive the command sent by the processor 1101 and execute it. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 1101 to determine the type of touch event, and then the processor 1101 provides corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present invention, the touch panel and the display panel can be integrated into the touch display screen 1103 to realize the input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize the input and output functions. That is, the touch display screen 1103 can also be used as a part of the input unit 1106 to realize the input function.

[0135] The radio frequency circuit 1104 may be used to send and receive radio frequency signals, so as to establish wireless communication with a network medical device or other electronic devices through wireless communication, and to send and receive signals between the network medical device or other electronic devices.

[0136] The audio circuit 1105 can be used to provide an audio interface between the user and the electronic device through a speaker and a microphone. The audio circuit 1105 can transmit the electrical signal converted from the received audio data to the speaker, which is converted into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 1105 and converted into audio data, and then the audio data is output to the processor 1101 for processing, and then sent to another electronic device through the radio frequency circuit 1104, or the audio data is output to the memory 1102 for further processing. The audio circuit 1105 may also include an earplug jack to provide communication between an external headset and an electronic device.

[0137] The input unit 1106 may be used to receive input numbers, character information or user feature information (such as fingerprint, iris, facial information, etc.), and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0138] The power supply 1107 is used to supply power to various components of the electronic device 1100. Optionally, the power supply 1107 can be logically connected to the processor 1101 through a power management device, so that the power management device can manage charging, discharging, power consumption and other functions. The power supply 1107 can also include one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0139] although Figure 6 Not shown, the electronic device 1100 may also include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be described in detail here.

[0140] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0141] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0142] To this end, an embodiment of the present application provides a computer-readable storage medium, in which a plurality of computer programs are stored. The computer program can be loaded by a processor to execute any vehicle noise reduction method provided in the embodiment of the present application. The computer program can execute the following steps of the vehicle noise reduction method:

[0143] Acquire noise information collected by at least two sensors on the vehicle;

[0144] Noise reduction processing is performed according to the noise information.

[0145] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0146] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0147] Since the computer readable storage medium can implement the computer program that can be beneficially stored in any of the vehicle noise reduction methods provided in the embodiments of the present application, any of the vehicle noise reduction methods provided in the embodiments of the present application can be executed, the effects are detailed in the previous embodiments and will not be repeated here.

[0148] In the above-mentioned vehicle noise reduction method, electronic device, electronic device, vehicle, computer-readable storage medium, computer program product, etc., the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and beneficial effects of the above-mentioned electronic device, electronic device, vehicle, computer-readable storage medium, computer program product and its corresponding units can refer to the description of the vehicle noise reduction method in the above embodiment, and will not be repeated here.

[0149] The above is a detailed introduction to a vehicle noise reduction method, device, vehicle, computer-readable storage medium and computer program product provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A vehicle noise reduction method, characterized in that: The vehicle noise reduction method comprises: Acquire noise information collected by at least two sensors on the vehicle; Noise reduction processing is performed according to the noise information.

2. The vehicle noise reduction method according to claim 1, characterized in that: The noise frequency bands corresponding to different noise information are different.

3. The vehicle noise reduction method according to claim 2, characterized in that: At least one of the noise information includes structure-borne noise information, and at least one of the noise information includes airborne noise information.

4. The vehicle noise reduction method according to claim 3, characterized in that: The structural noise information is collected by an acceleration sensor of the vehicle, and the air noise information is collected by a sound collection device of the vehicle.

5. The vehicle noise reduction method according to claim 4, characterized in that: The acceleration sensor is arranged on a suspension of the vehicle, and / or the sound collecting device is arranged in a compartment of the vehicle.

6. The vehicle noise reduction method according to claim 1, characterized in that: The performing noise reduction processing according to the noise information includes: Obtaining a frequency domain weight vector corresponding to the sensor, wherein different sensors have different frequency domain weight vectors. Processing the noise information collected by the sensor according to the frequency domain weight vector corresponding to the sensor to obtain reconstructed noise information; Noise reduction processing is performed according to the reconstructed noise information corresponding to each sensor.

7. The vehicle noise reduction method according to claim 6, characterized in that: After the noise information collected by the sensor is processed according to the frequency domain weight vector corresponding to the sensor to obtain the reconstructed noise information, the method further includes: The reconstructed noise information corresponding to the sensor is filtered based on the filter corresponding to the sensor.

8. The vehicle noise reduction method according to claim 7, characterized in that: The noise reduction process is performed according to the reconstructed noise information corresponding to each sensor, including: For each of the sensors, according to the weight information corresponding to the sensor, weighted processing is performed on the reconstructed noise information corresponding to the sensor; Based on the reconstructed noise information after each weighting process, noise reduction processing is performed.

9. The vehicle noise reduction method according to claim 8, characterized in that: The noise reduction process is performed based on the reconstructed noise information after each weighted process, including: The reconstructed noise information after each weighted process is fused to obtain the target reconstructed noise; The target reconstructed noise is input into the active noise reduction module for noise reduction processing.

10. The vehicle noise reduction method according to claim 9, characterized in that: The active noise reduction module includes a secondary speaker; The active noise reduction module performs filtering processing on the target reconstructed noise through a weight vector to obtain a noise suppression signal, and controls the secondary speaker to emit sound based on the noise suppression signal to perform noise reduction processing.

11. The vehicle noise reduction method according to claim 9, characterized in that: The active noise reduction module includes a howling suppressor; The howling suppressor performs a howling suppression process on the noise suppression signal.

12. The vehicle noise reduction method according to claim 10, characterized in that: The active noise reduction module includes an error sound collection device and a reconstructed secondary path, wherein the reconstructed secondary path is used to simulate the transmission from the secondary speaker to the error sound collection device; Inputting the target reconstruction noise into the reconstructed secondary path to obtain secondary reconstruction noise; The weight vector is updated according to the secondary reconstruction noise and the error noise collected by the error sound collection device.

13. The vehicle noise reduction method according to claim 8, characterized in that: The weight information and / or filter corresponding to each sensor is obtained through pre-training.

14. The vehicle noise reduction method according to claim 13, characterized in that: The pre-training comprises the following steps: Acquire training noise information collected by at least two sensors, and training error noise in a target noise reduction area; Obtaining training reconstruction noise according to the training noise information; For each sensor, the weight information and / or the filter corresponding to the sensor are obtained through training according to the frequency domain weight vector corresponding to the sensor, the training reconstruction noise, and the training error noise.

15. The vehicle noise reduction method according to claim 14, characterized in that: The step of training to obtain weight information corresponding to the sensor and / or the filter according to the frequency domain weight vector corresponding to the sensor, the training reconstruction noise, and the training error noise includes: Determining a global reconstruction error based on the training error noise and the training reconstruction noise; Constructing an objective function corresponding to the sensor according to the global reconstruction error and a frequency domain weight vector corresponding to the sensor; The initial weight information and / or the initial filter of the sensor is updated by the objective function to obtain the weight information and / or the filter.

16. An electronic device, characterized in that: include: A transceiver module, used to obtain noise information collected by at least two sensors on the vehicle; The noise reduction module is used to perform noise reduction processing according to the noise information.

17. An electronic device, characterized in that: The invention comprises a processor, wherein the processor is connected to a memory, wherein the memory stores a computer program, and wherein the processor is used to run the computer program in the memory to execute the vehicle noise reduction method according to any one of claims 1 to 15.

18. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle noise reduction method according to any one of claims 1 to 15 is implemented.

19. A computer program product, characterized in that The method comprises a computer program, wherein the computer program is executed by a processor to implement the vehicle noise reduction method according to any one of claims 1 to 15.

20. A vehicle, characterized in that: Comprising the electronic device as claimed in claim 16 or the electronic equipment as claimed in claim 17.

Images