Interference sound source signal processing method and device, computer device and storage medium

Abstract

The application relates to a method and device for processing an interference sound source signal, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a sound source signal, wherein the sound source signal comprises a drone interference signal; the drone interference signal comprises at least one of a wind noise signal or a microphone base signal; removing at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal according to a preset order to obtain a target signal. The method can accurately process the interference sound source signal.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electricity, in particular to a method and device for processing interference sound source signals, a computer device, a storage medium and a computer program product. BACKGROUND

[0002] At present, whether the power system is locally discharged is detected by manual method, but manual detection of local discharge has the problem of low efficiency, so the use of unmanned aerial vehicle equipment for inspection application is generated.

[0003] However, when using unmanned aerial vehicle equipment for inspection, there are a large number of interference sound sources, which will greatly affect the accuracy of detection. SUMMARY

[0004] Therefore, it is necessary to provide an interference sound source processing method, device, computer equipment, computer readable storage medium and computer program product capable of accurately processing interference sound source signals to solve the above technical problems.

[0005] In a first aspect, the present application provides an interference sound source processing method, which comprises:

[0006] Obtaining a sound source signal, wherein the sound source signal comprises an unmanned aerial vehicle interference signal; the unmanned aerial vehicle interference signal comprises at least one of a wind noise signal or a microphone base signal;

[0007] Removing at least one of the wind noise signal or the microphone base signal in the unmanned aerial vehicle interference signal from the sound source signal in a preset order to obtain a target signal.

[0008] In one embodiment, the above removing at least one of the wind noise signal or the microphone base signal in the unmanned aerial vehicle interference signal from the sound source signal in a preset order to obtain a target signal comprises:

[0009] Removing the wind noise signal in the unmanned aerial vehicle interference signal from the sound source signal to obtain a wind noise removal signal;

[0010] Filtering out the microphone base signal in the wind noise removal signal to obtain the target signal.

[0011] In one embodiment, after the above removing the wind noise signal in the unmanned aerial vehicle interference signal from the sound source signal to obtain a wind noise removal signal, the method further comprises:

[0012] Correcting the phase difference of the wind noise removal signal;

[0013] Filtering out the microphone base signal in the wind noise removal signal to obtain the target signal, comprising:

[0014] The vibration signal and the microphone base signal in the corrected wind noise removal signal are filtered out to obtain a target signal.

[0015] In one of the embodiments, the phase difference of the wind noise removal signal is corrected, including:

[0016] According to the microphone coordinate position on the voiceprint camera, the time difference of the wind noise removal signal is calculated;

[0017] According to the time difference of the wind noise removal signal, the phase difference of the wind noise removal signal is corrected.

[0018] In one of the embodiments, the wind noise signal in the drone interference signal is removed through a wind noise model; wherein the process of establishing the wind noise model includes:

[0019] The drone base signal is obtained;

[0020] The drone base signal is compared with an initial model to obtain a parameter value of the initial model, and a wind noise model is obtained based on the parameter value and the initial model, and the initial model is a model simulating the peak mode of the drone.

[0021] In one of the embodiments, before the wind noise signal or the microphone base signal in the drone interference signal is removed from the sound source signal in the preset order, it further includes:

[0022] The timestamp carried by the sound source signal is obtained;

[0023] The sound source signal is synchronized with the drone rotation period according to the timestamp and the drone rotation period;

[0024] The wind noise signal or the microphone base signal in the drone interference signal is removed from the sound source signal in the preset order to obtain a target signal, including:

[0025] The wind noise signal or the microphone base signal in the drone interference signal is removed from the synchronized sound source signal in the preset order to obtain a target signal.

[0026] In a second aspect, the application further provides an interference sound source signal processing device, which includes:

[0027] The signal acquisition module is configured to acquire a sound source signal, wherein the sound source signal includes a drone interference signal; the drone interference signal includes at least one of a wind noise signal or a microphone base signal;

[0028] The interference removal module is configured to remove at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal in a preset order to obtain a target signal.

[0029] In a third aspect, the present application provides a computer device, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the method in any one of the above embodiments when executing the computer program.

[0030] In a fourth aspect, the present application provides a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program implements the steps of the method in any one of the above embodiments when executed by a processor.

[0031] In a fifth aspect, the present application provides a computer program product. The computer program product comprises a computer program, and the computer program implements the steps of the method in any one of the above embodiments when executed by a processor.

[0032] The above interference sound source signal processing method, device, computer device, storage medium and computer program product first acquire a sound source signal, the sound source signal comprising a UAV interference signal, wherein the UAV interference signal comprises at least one of a wind noise signal or a microphone base signal, then remove at least one of the wind noise signal or the microphone base signal in the UAV interference signal according to a preset order to obtain a target signal, which can accurately process noise signals other than the target signal to obtain a pure target signal, and further enable the voiceprint camera to accurately locate the target signal. BRIEF DESCRIPTION OF DRAWINGS

[0033] Figure 1 An application environment diagram of the interference sound source signal processing method in one embodiment;

[0034] Figure 2 A flowchart of the interference sound source signal processing method in one embodiment;

[0035] Figure 3 A structural block diagram of the interference sound source signal processing device in one embodiment;

[0036] Figure 4 A flowchart of the interference sound source signal processing method in another embodiment;

[0037] Figure 5 An internal structure diagram of the computer device in one embodiment. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0039] The interference sound source signal processing method provided by the embodiments of the present application can be applied to, for example,Figure 1 The application environment shown. Among them, the voiceprint camera 102 communicates with the server 104 through the network. The data storage system can store the data required by the server 104 to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The voiceprint camera 102 acquires the sound source signal through the microphone array, and the sound source signal includes at least one of the unmanned aerial vehicle interference signal or the microphone base signal; the unmanned aerial vehicle interference signal includes at least one of the wind noise signal or the microphone base signal; the voiceprint camera removes at least one of the wind noise signal or the microphone base signal in the unmanned aerial vehicle interference signal according to a preset order to obtain a target signal, and the voiceprint camera 102 sends the target signal to the server 104 after acquiring the target signal. Among them, the voiceprint camera 102 is a device with sound source positioning carried on the unmanned aerial vehicle. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0040] In one embodiment, as Figure 2 shown, a branch recognition method is provided, and the method is applied to Figure 1 the server 104 in the figure for illustration, including the following steps:

[0041] S202, acquiring a sound source signal, the sound source signal including an unmanned aerial vehicle interference signal; the unmanned aerial vehicle interference signal including at least one of a wind noise signal or a microphone base signal.

[0042] Among them, the sound source signal refers to the data collected by the sound collection device on the unmanned aerial vehicle. For example, it can be the data collected by the microphone array on the voiceprint camera. The voiceprint camera is a device with sound source positioning, which can calculate the position of the sound source in the scene, and the voiceprint camera can also collect video signals in the form of heat map to the user interface, so that the user obtains the position of the sound source in the form of visualization in combination with the heat map and the sound source position on the interface.

[0043] Among them, the unmanned aerial vehicle interference signal refers to the noise generated by the unmanned aerial vehicle itself, for example, the rotation of the propeller during the flight of the unmanned aerial vehicle will form a downward wind channel, so that the sound source signal acquired by the voiceprint camera includes the wind noise signal caused by the rotation of the propeller of the unmanned aerial vehicle. In addition, the microphone array in the voiceprint camera carried on the unmanned aerial vehicle will also carry its own noise, that is, the microphone base signal, which is like the snowflake sound in the TV set. Because, when the motor rotates, the inductor generates a rotating torque, and in this process, abnormal discharge phenomenon is easy to occur, at which time the microphone will generate the microphone base signal.

[0044] Optionally, the drone interference signal in the sound source signal acquired by the voiceprint camera comprises at least one of a wind noise signal, a microphone base signal and a vibration signal. The vibration signal is generated by rotation of a rotor of the drone and is transmitted to the voiceprint camera through a gimbal on the drone, so that the vibration signal is also generated during flight of the drone.

[0045] In step 204, at least one of the wind noise signal or the microphone base signal in the drone interference signal is removed from the sound source signal according to a preset order to obtain a target signal.

[0046] Since the drone interference signal in the sound source signal greatly affects positioning of the target signal by the voiceprint camera, the accuracy of the voiceprint camera for the target signal is greatly affected, so it is necessary to remove the drone interference signal to enable the voiceprint camera to accurately position the target signal.

[0047] The target signal refers to a signal after the drone interference signal is removed, and the signal needs to be positioned by the voiceprint camera. In the power facility inspection scene, the target signal can be a partial discharge signal. In the use process of other scenes, the target signal can be any signal that needs to be positioned, which is not limited here.

[0048] The preset order refers to an order in which the wind noise signal or the microphone base signal in the drone interference signal is removed in advance, which can be set according to the size of the noise signal in the drone interference signal, so that smaller noise signals can be avoided from being submerged in larger noise signals, and the target signal can be obtained without other noise signals mixed therein.

[0049] Optionally, when the drone interference signal comprises only one signal, the signal is directly removed without considering the preset order.

[0050] In other embodiments, if the drone interference signal comprises other noise signals, they can all be processed according to the above method.

[0051] In the above embodiment, the sound source signal is first acquired, and the sound source signal comprises the drone interference signal, wherein the drone interference signal comprises at least one of the wind noise signal or the microphone base signal, and then at least one of the wind noise signal or the microphone base signal in the drone interference signal is removed according to the preset order to obtain the target signal, so that noise signals other than the target signal can be accurately processed to obtain a pure target signal, and the voiceprint camera can accurately position the target signal.

[0052] In one embodiment, the removing at least one of the wind noise signal or the microphone base signal in the drone interference signal in the preset order to obtain the target signal comprises: removing the wind noise signal in the drone interference signal to obtain a wind noise removed signal; and filtering the microphone base signal in the wind noise removed signal to obtain the target signal.

[0053] The wind noise signal in the drone interference signal is first removed to obtain a wind noise removed signal, where the wind noise removed signal refers to a signal obtained by removing the wind noise signal from the drone interference signal. Then, the microphone base signal is removed based on the wind noise removed signal, because the wind noise signal is larger than the microphone noise, so as to avoid the smaller noise being submerged in the larger noise, thereby causing the obtained target signal to be impure.

[0054] Optionally, when the drone interference signal includes the wind noise signal, the microphone base signal, and the vibration signal, the removing can be performed in the order of the wind noise signal, the vibration signal, and the microphone base signal.

[0055] Optionally, the wind noise signal can be achieved by using a pre-set wind noise model, where the wind noise model refers to a model capable of removing the wind noise signal in the drone interference signal.

[0056] In the above embodiment, at least one of the wind noise signal or the microphone base signal in the drone interference signal is removed in the preset order, so that a pure target signal can be obtained.

[0057] In one embodiment, after the wind noise signal in the drone interference signal is removed to obtain the wind noise removed signal, the method further comprises: correcting a phase difference of the wind noise removed signal.

[0058] Since the positioning of the target signal by the voiceprint camera depends on the phase difference of the same signal on different microphones, the phase difference of the wind noise removed signal needs to be corrected to avoid deviation when the target signal is positioned subsequently. Correspondingly, the filtering of the microphone base signal in the wind noise removed signal to obtain the target signal comprises: filtering the vibration signal and the microphone base signal in the corrected wind noise removed signal to obtain the target signal.

[0059] Optionally, the correcting of the phase difference of the wind noise removed signal comprises: calculating a time difference of the wind noise removed signal according to the coordinates of the microphones on the voiceprint camera; and correcting the phase difference of the wind noise removed signal according to the time difference of the wind noise removed signal.

[0060] First, the time difference of the same wind noise signal received by different microphone arrays is calculated according to the positions of the microphone arrays, and the time difference is taken as the time difference of the wind noise removed signal. Then, the phase difference of the wind noise removed signal is corrected according to the time difference.

[0061] Optionally, the time difference of the wind noise removal signals can be calculated based on the time of the wind noise signal received by the first microphone in the microphone array, and the time difference of the wind noise removal signals is used to correct the phase deviation of the wind noise removal signals.

[0062] Optionally, the time difference can be calculated based on the propagation speed of sound in air and the coordinate positions of the microphones.

[0063] Optionally, after the wind noise signal is corrected, the vibration signal and the microphone base signal in the wind noise removal signal are removed to obtain the target signal. Optionally, the vibration signal can be removed first, and then the microphone base signal is removed.

[0064] In the above embodiment, the wind noise removal signal is corrected to synchronize the signals received by the microphones.

[0065] In one embodiment, before removing at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal in the preset order, the method further comprises: obtaining a timestamp carried by the sound source signal; and synchronizing the sound source signal with the rotation period of the drone according to the timestamp and the rotation period of the drone.

[0066] Since the rotation of the drone has a fixed frequency, there is also a relatively fixed wind noise signal when hovering. Therefore, before removing at least one of the wind noise signal or the microphone base signal in the drone interference signal in the preset order, the timestamp mechanism is used to synchronize the sound source signal with the rotation period of the drone, so that the blade peak value can be more accurately captured.

[0067] The timestamp mechanism is used to synchronize the sound source signal with the rotation period of the drone, including: obtaining a timestamp carried by the sound source signal; and synchronizing the sound source signal with the rotation period of the drone according to the timestamp and the rotation period of the drone.

[0068] Each rotation of the drone blade will cause a signal fluctuation. When this fluctuation is detected, it can be considered that the drone blade has rotated once. Therefore, after recording the timestamp, the current rotation speed of the drone can be known, and the sound source signal is synchronized with the rotation period of the drone according to the timestamp. After the rotation period is synchronized, the noise of the blade rotation that can be monitored later can be roughly predicted, and the blade peak value can be more accurately captured.

[0069] In the above embodiment, the timestamp is used to synchronize the sound source signal with the rotation period of the drone, so that the blade peak value can be more accurately captured to remove the wind noise signal.

[0070] In one embodiment, the process of establishing the wind noise model comprises: obtaining a drone base signal; comparing the drone base signal with an initial model to obtain parameter values of the initial model to obtain the wind noise model, the initial model being a model simulating a peak mode of the drone.

[0071] The drone base signal refers to noise of the drone itself, including at least one of a wind noise signal caused by rotation of a blade of the drone, a vibration signal, and a microphone base signal.

[0072] Optionally, the drone base signal is obtained under a preset condition, wherein the preset condition refers to a condition that the drone base signal can be obtained without other interference signals. For example, the drone base signal is obtained by hovering the drone in the air in a weather with small wind or in an open field without a partial discharge sound source. The weather with small wind is selected to reduce the influence of external wind on the drone base signal, and the open field without a partial discharge sound source is also selected to reduce the influence of external signals on the drone base signal.

[0073] The drone base signal is compared with an initial model, wherein the initial model refers to a model that can simulate a peak mode of the drone. The rotation of the blade of the drone has periodicity and forms a relatively stable peak in a time domain graph, so the initial model can be selected according to this characteristic. For example, a Gaussian mixture model is selected to simulate the mode of the peak of the drone in a certain time interval. Then, the drone base signal is compared with the initial model to determine the parameter values in the initial model, and then the wind noise model is obtained.

[0074] Optionally, the Gaussian mixture model is selected as the initial model, and the expression of the Gaussian mixture model is as follows:

[0075] p(x|θ)=∑α k φ(x|θ k )

[0076] wherein α k is a coefficient, φ(x|θ k ) is a Gaussian distribution probability.

[0077] The drone base signal is compared with the Gaussian mixture model to obtain the parameter values in the Gaussian mixture model, and then the wind noise model is obtained.

[0078] Optionally, a plurality of drone base signals at the same time point and values corresponding to the Gaussian mixture model at the same time point can be selected to establish an equation group, so as to obtain the parameter values in the Gaussian mixture model, and then the wind noise model is obtained.

[0079] It should be noted that after the wind noise signal is established, the rotation period of the unmanned aerial vehicle also needs to be synchronized using the timestamp mechanism. The process of synchronizing the rotation period of the unmanned aerial vehicle using the timestamp mechanism can refer to the steps of the method in the above embodiments.

[0080] In the above embodiments, by comparing the unmanned aerial vehicle base signal with the initial model, the values of the parameters in the initial model can be obtained simply and quickly, and then the wind noise model can be obtained.

[0081] In one embodiment, the process of filtering out the microphone base signal in the wind noise removal signal to obtain the target signal is as follows:

[0082] Optionally, a large number of microphone base signals are obtained, the distribution of the microphone base signals is analyzed to obtain a microphone base signal distribution result, and a processing model is selected according to the distribution result.

[0083] The distribution result of the microphone base noise satisfies the Gaussian white noise distribution, so a high-order cumulant can be selected to filter out the microphone base signal. Optionally, a cumulant of three or more orders can be selected to eliminate the microphone base noise.

[0084] In one embodiment, the vibration signal removal method can obtain some fixed frequency interference in the frequency spectrum through Fourier transform, then reduce or average the intensity of the corresponding frequency, and finally reconstruct the wind noise removal signal after removing the vibration signal through inverse Fourier transform.

[0085] In one example embodiment, the interference sound source signal processing process is as follows:

[0086] S302, collect the sound source signal. The sound source signal is collected by the microphone array on the voiceprint camera, and the unmanned aerial vehicle interference signal is present in the sound source signal, wherein the unmanned aerial vehicle interference signal includes at least one of the wind noise signal, the vibration signal or the microphone base signal.

[0087] S304, synchronize the rotation period of the unmanned aerial vehicle using the timestamp mechanism. Optionally, the timestamp carried by the sound source signal is obtained; and the sound source signal is synchronized with the rotation period of the unmanned aerial vehicle according to the timestamp and the rotation period of the unmanned aerial vehicle.

[0088] S306, remove the wind noise signal. The wind noise signal caused by the rotation of the unmanned aerial vehicle blade in the sound source signal is removed by the wind noise model to obtain a wind noise removal signal. The wind noise model is established in advance, and the establishment process of the wind noise model can refer to the steps of the method in the above embodiments.

[0089] S308, phase correction is performed on the wind noise removal signal. Since the detection of partial discharge relies on the phase difference of the same signal on different microphones, the wind noise model of the unmanned aerial vehicle also needs to consider this phase difference, otherwise it will cause an overall shift in the positioning result of the partial discharge. According to the coordinate position of the microphone on the voiceprint camera, the time difference of the wind noise removal signal is calculated, and then the phase deviation of the wind noise removal signal is corrected according to the time difference of the wind noise removal signal.

[0090] S310, remove the vibration signal. After removing the wind noise signal, the unmanned aerial vehicle interference signal also includes the vibration signal and the microphone base signal, so further processing is required for the vibration signal. Optionally, some fixed frequency interference in the frequency spectrum can be obtained by Fourier transform, and then the intensity of the corresponding frequency is reduced or averaged, and finally the wind noise removal signal after removing the vibration signal is obtained by inverse Fourier transform reconstruction.

[0091] S312, remove the microphone base signal. Finally, the microphone base signal still exists in the unmanned aerial vehicle interference signal. Since the microphone base signal satisfies the Gaussian white noise distribution, the microphone base noise can be eliminated by the third-order or higher-order cumulant to obtain the partial discharge signal.

[0092] In the above embodiment, since the noise intensity of the unmanned aerial vehicle is high, the distribution range in the frequency domain is wide, and it belongs to a wide frequency strong interference sound source. Generally, the filtering method can find a signal with greater intensity, but it cannot work effectively under low signal-to-noise ratio, and by physically modeling the wind noise of the unmanned aerial vehicle, the signal-to-noise ratio of the partial discharge is greatly improved. In addition, during modeling, the inherent frequency of the motor rotating when the unmanned aerial vehicle hovers is considered, which can stably remove the interference brought by the unmanned aerial vehicle. Since the to-be-detected sound source of the partial discharge is generally strongly related to the power frequency period, resonance with the inherent frequency of the unmanned aerial vehicle will not occur, so the integrity of the partial discharge signal can be guaranteed, providing a strong guarantee for subsequent analysis.

[0093] It should be understood that although each step in the flowchart involved in each of the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise stated herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each of the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0094] Based on the same inventive concept, the embodiments of the present application also provide a device for implementing the interference sound source signal processing method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more interference sound source signal processing device embodiments provided below can refer to the limitations of the interference sound source signal processing method described above, which will not be repeated here.

[0095] In one embodiment, as shown in Figure 4 An interference sound source signal processing device is provided, comprising: a signal acquisition module 100, an interference removal module 200, wherein:

[0096] The signal acquisition module 100 is configured to acquire a sound source signal, wherein the sound source signal comprises a UAV interference signal; and the UAV interference signal comprises at least one of a wind noise signal or a microphone base signal.

[0097] The interference removal module 200 is configured to remove at least one of the wind noise signal or the microphone base signal in the UAV interference signal from the sound source signal in a preset order to obtain a target signal.

[0098] In one embodiment, the interference removal module 200 comprises:

[0099] The wind noise removal unit is configured to remove the wind noise signal in the UAV interference signal from the sound source signal to obtain a wind noise removed signal.

[0100] The base signal removal unit is configured to filter out the microphone base signal in the wind noise removed signal to obtain the target signal.

[0101] In one embodiment, the interference removal module 200 further comprises:

[0102] The correction unit is configured to correct a phase difference of the wind noise removed signal.

[0103] The vibration removal unit is configured to filter out the vibration signal and the microphone base signal in the corrected wind noise removed signal to obtain the target signal.

[0104] In one embodiment, the correction unit comprises:

[0105] The calculation sub-unit is configured to calculate a time difference of the wind noise removed signal according to a microphone coordinate position on the voiceprint camera.

[0106] The deviation correction sub-unit is configured to correct a phase deviation of the wind noise removed signal according to the time difference of the wind noise removed signal.

[0107] In one embodiment, the device further comprises:

[0108] The UAV signal obtaining module is configured to obtain a UAV base signal.

[0109] The model establishing module is configured to compare the UAV base signal with an initial model to obtain a parameter value of the initial model, and obtain a wind noise model based on the parameter value and the initial model, the initial model being a model simulating a peak mode of the UAV.

[0110] In one embodiment, the apparatus further includes:

[0111] The timestamp obtaining module is configured to obtain a timestamp carried by the sound source signal.

[0112] The cycle synchronizing module is configured to synchronize the sound source signal with a UAV rotation cycle according to the timestamp and the UAV rotation cycle.

[0113] In one embodiment, the interference removing module 200 includes:

[0114] The target signal obtaining unit is configured to remove at least one of a wind noise signal or a microphone base signal in the UAV interference signal from the synchronized sound source signal in a preset order to obtain a target signal.

[0115] The modules in the interference sound source signal processing apparatus can be realized by software, hardware, or a combination thereof. The modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform operations corresponding to the modules.

[0116] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 5 The computer device includes a processor, a memory, and a network interface connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store sound source signal data. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement an interference sound source signal processing method.

[0117] Those skilled in the art can understand that, Figure 5The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0118] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the following steps: obtaining a sound source signal, the sound source signal including a drone interference signal; the drone interference signal including at least one of a wind noise signal or a microphone base signal; removing at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal in a preset order to obtain a target signal.

[0119] In one embodiment, the processor executing the computer program to implement the step of removing at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal in a preset order to obtain a target signal comprises: removing the wind noise signal in the drone interference signal from the sound source signal to obtain a wind noise removed signal; filtering out the microphone base signal in the wind noise removed signal to obtain the target signal.

[0120] In one embodiment, after the processor executing the computer program to implement the step of removing the wind noise signal in the drone interference signal from the sound source signal to obtain a wind noise removed signal, the method further comprises: correcting the phase difference of the wind noise removed signal; filtering out the microphone base signal in the wind noise removed signal to obtain the target signal, which comprises: filtering out the vibration signal and the microphone base signal in the corrected wind noise removed signal to obtain the target signal.

[0121] In one embodiment, the processor executing the computer program to implement the step of correcting the phase difference of the wind noise removed signal comprises: calculating the time difference of the wind noise removed signal according to the microphone coordinate position on the voiceprint camera; correcting the phase difference of the wind noise removed signal according to the time difference of the wind noise removed signal.

[0122] In one embodiment, the processor executing the computer program to implement the step of removing the wind noise signal in the drone interference signal is implemented through a wind noise model; wherein the process of establishing the wind noise model comprises: obtaining a drone base signal; comparing the drone base signal with an initial model to obtain the parameter value of the initial model, and obtaining the wind noise model based on the parameter value and the initial model, the initial model being a model simulating the peak mode of the drone.

[0123] In one embodiment, the computer program, when executed by the processor, further comprises, before removing at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal in the preset order, obtaining a timestamp carried by the sound source signal; synchronizing the sound source signal with a drone rotation period according to the timestamp and the drone rotation period; and removing at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal in the preset order to obtain the target signal.

[0124] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program, when executed by a processor, implements the following steps: obtaining a sound source signal, the sound source signal including a drone interference signal; the drone interference signal including at least one of a wind noise signal or a microphone base signal; and removing at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal in a preset order to obtain a target signal.

[0125] In one embodiment, the computer program, when executed by the processor, further comprises, before removing at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal in the preset order, obtaining a timestamp carried by the sound source signal; synchronizing the sound source signal with a drone rotation period according to the timestamp and the drone rotation period; and removing at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal in the preset order to obtain the target signal.

[0126] In one embodiment, the computer program, when executed by the processor, further comprises, after removing the wind noise signal in the drone interference signal from the sound source signal to obtain the wind noise removal signal, correcting a phase difference of the wind noise removal signal; and filtering the microphone base signal in the wind noise removal signal to obtain the target signal, including filtering the vibration signal and the microphone base signal in the corrected wind noise removal signal to obtain the target signal.

[0127] In one embodiment, the computer program, when executed by the processor, further comprises, after removing the wind noise signal in the drone interference signal from the sound source signal to obtain the wind noise removal signal, correcting a phase difference of the wind noise removal signal; and filtering the microphone base signal in the wind noise removal signal to obtain the target signal, including filtering the vibration signal and the microphone base signal in the corrected wind noise removal signal to obtain the target signal.

[0128] In an embodiment, the computer program, when executed by the processor, implements the removal of the wind noise signal in the drone interference signal by a wind noise model; wherein the wind noise model is established by: obtaining a drone base signal; comparing the drone base signal with an initial model to obtain a parameter value of the initial model, and obtaining the wind noise model based on the parameter value and the initial model, the initial model being a model simulating a peak mode of the drone.

[0129] In an embodiment, before the computer program, when executed by the processor, implements the removal of at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal in the preset order, the computer program further implements: obtaining a timestamp carried by the sound source signal; synchronizing the sound source signal with a drone rotation period according to the timestamp and the drone rotation period; and removing at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal in the preset order to obtain a target signal, including: removing at least one of the wind noise signal or the microphone base signal in the drone interference signal from the synchronized sound source signal in the preset order to obtain the target signal.

[0130] In an embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the following steps: obtaining a sound source signal, the sound source signal including a drone interference signal; the drone interference signal including at least one of a wind noise signal or a microphone base signal; and removing at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal in a preset order to obtain a target signal.

[0131] In an embodiment, the computer program, when executed by the processor, implements the removal of at least one of the wind noise signal or the microphone base signal in the drone interference signal from the sound source signal in the preset order to obtain the target signal, including: removing the wind noise signal in the drone interference signal from the sound source signal to obtain a wind noise removed signal; and filtering out the microphone base signal in the wind noise removed signal to obtain the target signal.

[0132] In an embodiment, after the computer program, when executed by the processor, implements the removal of the wind noise signal in the drone interference signal from the sound source signal to obtain the wind noise removed signal, the computer program further implements: correcting a phase difference of the wind noise removed signal; and filtering out the microphone base signal in the wind noise removed signal to obtain the target signal, including: filtering out the vibration signal and the microphone base signal in the corrected wind noise removed signal to obtain the target signal.

[0133] In one embodiment, the processor executes the computer program to correct the phase difference of the wind noise removed signal, including: calculating the time difference of the wind noise removed signal according to the microphone coordinate position on the voiceprint camera; and correcting the phase difference of the wind noise removed signal according to the time difference of the wind noise removed signal.

[0134] In one embodiment, the processor executes the computer program to remove the wind noise signal in the unmanned aerial vehicle interference signal through a wind noise model; and the wind noise model is established by: obtaining an unmanned aerial vehicle base signal; comparing the unmanned aerial vehicle base signal with an initial model to obtain a parameter value of the initial model; and obtaining the wind noise model based on the parameter value and the initial model, the initial model being a model simulating a peak mode of the unmanned aerial vehicle.

[0135] In one embodiment, the processor executes the computer program to remove at least one of the wind noise signal in the unmanned aerial vehicle interference signal or the microphone base signal from the sound source signal in the preset order, further including: obtaining a timestamp carried by the sound source signal; synchronizing the sound source signal with a rotation period of the unmanned aerial vehicle according to the timestamp and the rotation period of the unmanned aerial vehicle; and removing at least one of the wind noise signal in the unmanned aerial vehicle interference signal or the microphone base signal from the sound source signal in the preset order to obtain a target signal, including: removing at least one of the wind noise signal in the unmanned aerial vehicle interference signal or the microphone base signal from the synchronized sound source signal in the preset order to obtain the target signal.

[0136] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0137] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0138] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for processing interference sound source signals, characterized in that, The method includes: Acquire sound source signals, including drone interference signals; the drone interference signals include at least one of wind noise signals or microphone base signals; the drone interference signals refer to noise generated by the drone itself; the microphone base signals are generated by abnormal discharge phenomena when the induction coil generates torque during the rotation of the motor in the drone; the wind noise signals are generated when the drone flies in a top-down wind tunnel formed by the rotation of the propeller blades. The target signal is obtained by removing at least one of the wind noise signal or microphone base signal from the drone interference signal in a preset order from the sound source signal; the preset order is based on the magnitude of the drone interference signal. The step of removing at least one of the wind noise signal or microphone base signal from the drone interference signal in a preset order to obtain the target signal includes: Remove the wind noise signal from the drone interference signal from the sound source signal to obtain the wind noise removed signal; The target signal is obtained by filtering out the microphone base signal from the wind noise removal signal; After removing the wind noise signal from the drone interference signal in the sound source signal to obtain the wind noise-removed signal, the method further includes: The phase difference of the wind noise removal signal is corrected; The process of filtering out the microphone base signal from the wind noise removal signal to obtain the target signal includes: The target signal is obtained by filtering out the vibration signal and the microphone base signal from the corrected wind noise removal signal; The correction of the phase difference of the wind noise removal signal includes: The time difference of the wind noise removal signal is calculated based on the microphone coordinates on the acoustic print camera; the time difference is calculated based on the time when the first microphone in the microphone array receives the wind noise signal, and the time difference when each microphone receives the same wind noise signal. The phase deviation of the wind noise removal signal is corrected based on the time difference of the wind noise removal signal.

2. The method according to claim 1, characterized in that, The removal of wind noise from the UAV interference signal is achieved through a wind noise model; wherein, the process of establishing the wind noise model includes: Acquire the base signal of the UAV; The base signal of the UAV is compared with the initial model to obtain the parameter values ​​of the initial model. Based on the parameter values ​​and the initial model, the wind noise model is obtained. The initial model is a model that simulates the peak mode of the UAV.

3. The method according to claim 1, characterized in that, Before removing at least one of the wind noise signal or microphone base signal from the drone interference signal according to a preset order from the sound source signal, the method further includes: Obtain the timestamp carried by the sound source signal; Based on the timestamp and the drone's rotation cycle, the sound source signal is synchronized with the drone's rotation cycle; The step of removing at least one of the wind noise signal or microphone base signal from the drone interference signal in a preset order to obtain the target signal includes: The target signal is obtained by removing at least one of the wind noise signal or microphone base signal from the synchronized sound source signal in a preset order.

4. A signal processing device for an interfering sound source, characterized in that, The device includes: The signal acquisition module is used to acquire sound source signals, including drone interference signals. The drone interference signals include at least one of wind noise signals or microphone base signals. The drone interference signals refer to noise generated by the drone itself. The microphone base signals are generated by abnormal discharge phenomena when the induction coil generates torque during the rotation of the motor in the drone. The wind noise signals are generated when the drone flies in a wind tunnel formed by the rotation of the propeller blades. An interference removal module is used to remove at least one of wind noise or microphone base signal from the drone interference signal from the sound source signal according to a preset order, to obtain a target signal; the preset order is based on the magnitude of the drone interference signal. The interference removal module includes: A wind noise removal unit is used to remove the wind noise signal from the drone interference signal from the sound source signal to obtain a wind noise removed signal; A base signal removal unit is used to filter out the microphone base signal from the wind noise removal signal to obtain the target signal; The interference removal module includes: A correction unit is used to correct the phase difference of the wind noise removal signal; A vibration removal unit is used to filter out the vibration signal and the microphone base signal in the corrected wind noise removal signal to obtain the target signal; The correction unit includes: The calculation subunit is used to calculate the time difference of the wind noise removal signal based on the microphone coordinate position on the acoustic print camera; the time difference is calculated based on the time when the first microphone in the microphone array receives the wind noise signal, and the time difference when each microphone receives the same wind noise signal. The deviation correction subunit is used to correct the phase deviation of the wind noise removal signal based on the time difference of the wind noise removal signal.

5. The apparatus according to claim 4, characterized in that, The device further includes: The UAV signal acquisition module is used to acquire the UAV's base signal; The model building module is used to compare the UAV base signal with the initial model to obtain the parameter values ​​of the initial model, and to obtain a wind noise model based on the parameter values ​​and the initial model. The initial model is a model that simulates the peak mode of the UAV.

6. The apparatus according to claim 4, characterized in that, The device further includes: The timestamp acquisition module is used to acquire the timestamp carried by the sound source signal; A period synchronization module is used to synchronize the sound source signal with the drone rotation cycle based on the timestamp and the drone rotation cycle. The target signal acquisition unit is used to remove at least one of the wind noise signal or microphone base signal from the synchronized sound source signal in a preset order to obtain the target signal.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

Images