Wind noise suppression method and device, equipment and storage medium

Abstract

The invention discloses a wind noise suppression method and device, equipment and a storage medium, and relates to the technical field of intelligent equipment, and the method comprises the steps: carrying out the time domain waveform mutation degree detection of the pickup data of each pickup assembly integrated on the intelligent equipment; determining a peak factor of each frame of time domain waveform of each channel according to a detection result; screening target channels of which the peak value factors are greater than a preset peak value factor threshold value, and erasing abrupt change waveforms of the target channels; and performing wind noise suppression according to the erased target channel and a target beam forming algorithm. Through the above mode, due to the influence of wind noise, all the pickup assemblies integrated on the intelligent device have differences and waveform abrupt changes appear on different channels, at the moment, the abrupt change waveform of the target channel is erased from the time domain dimension, and then wind noise suppression is carried out in combination with the target beam forming algorithm. Compared with the prior art that wind noise suppression is carried out through a pure beam forming algorithm, the accuracy of wind noise suppression can be effectively improved, and the voice fidelity is ensured.

Description

Technical Field

[0001] The present application relates to the field of smart device technology, and in particular to a wind noise suppression method, apparatus, device, and storage medium. Background Art

[0002] As the functions of smart devices continue to improve, they are becoming more and more popular among people, such as true wireless Bluetooth headsets, smart speakers, smart glasses, etc. However, when users wear these smart devices, they are inevitably affected by the surrounding environment, such as noisy human voices and the "whoosh" wind noise generated by running. Currently, the common method for wind noise suppression is based on pure beamforming algorithms. However, under the influence of wind noise, even after using pure beamforming algorithms to suppress wind noise, there will still be residual wind noise. Therefore, the accuracy of wind noise suppression using the above method is relatively low.

[0003] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a wind noise suppression method, device, equipment and storage medium, aiming to solve the technical problem of low accuracy of wind noise suppression in the existing technology.

[0005] To achieve the above objectives, the present application proposes a method for suppressing wind noise, the method comprising: Acquiring sound pickup data of each sound pickup component integrated on the smart device, and performing time domain waveform mutation degree detection on the sound pickup data of each sound pickup component; Determine the peak factor of each frame of the time domain waveform of each channel according to the detection results; Screening the target channel whose peak factor is greater than a preset peak factor threshold, and erasing the sudden change waveform of the target channel; Wind noise suppression is performed based on the erased target channel and target beamforming algorithm.

[0006] In one embodiment, the step of determining the peak factor of each frame of the time domain waveform of each channel according to the detection result includes: Determine the time domain waveform data of each sampling point within the frame of each channel according to the detection results; Get the number of sampling points for each frame; Calculating a channel frame root mean square value based on the time domain waveform data and the number of sampling points based on a target channel frame algorithm; The peak factor of each frame of the time domain waveform of each channel is calculated according to the channel frame root mean square value and the target channel frame peak value.

[0007] In one embodiment, before the step of screening the target channel whose peak factor is greater than a preset peak factor threshold, the method further includes: Acquire peak factor distribution data in a wind noise scenario, and determine a current peak factor according to the peak factor distribution data in the wind noise scenario; Acquire peak factor distribution data in a scene without wind noise, and determine a target peak factor based on the peak factor distribution data in the scene without wind noise; A threshold setting interval is determined according to the current peak factor and the target peak factor, and a preset peak factor threshold is set according to the threshold setting interval.

[0008] In one embodiment, the step of erasing the sudden change waveform of the target channel includes: Determine the time domain waveform mutation position of the target channel according to the detection result; The sudden change waveform of the target channel is erased according to the sudden change position of the time domain waveform.

[0009] In one embodiment, after the step of erasing the sudden waveform of the target channel according to the sudden change position of the time domain waveform, the method further includes: Obtaining a sampling point set of the target channel; Selecting a target number of initial benchmark sampling points from the sampling point set; Generate a target time-domain normal waveform according to the initial reference sampling points through a target spline interpolation algorithm; The waveform of the erased target channel is completed according to the target time domain normal waveform and the time domain waveform mutation position.

[0010] In one embodiment, the step of performing wind noise suppression based on the erased target channel and the target beamforming algorithm includes: Obtaining the time domain waveform data of the erased target channel and the time domain waveform data of other normal channels; generating a sound pickup component array according to position information of each sound pickup component integrated on the smart device; cascade target beamforming algorithm according to the pickup assembly array; Wind noise suppression is performed based on the erased time domain waveform data of the target channel, the time domain waveform data of other normal channels, and the target beamforming algorithm.

[0011] In one embodiment, after the step of performing wind noise suppression according to the erased target channel and the target beamforming algorithm, the method further includes: Obtain voice information after wind noise suppression; performing wind noise detection on the voice information; When the detection result shows that there is no residual wind noise, performing a fidelity detection on the voice information to obtain a current fidelity feature value; When the current fidelity characteristic value is greater than a preset value, the voice information is played through a playback component integrated on the smart device.

[0012] In addition, to achieve the above objectives, the present application also proposes a wind noise suppression device, which includes: An acquisition module is used to acquire sound data collected by each sound collection component integrated on the smart device, and perform time domain waveform mutation detection on the sound data collected by each sound collection component; A determination module, used to determine the peak factor of each frame of the time domain waveform of each channel according to the detection result; an erasing module, configured to screen target channels whose peak factors are greater than a preset peak factor threshold, and to erase the sudden change waveforms of the target channels; The suppression module is used to suppress wind noise according to the erased target channel and the target beamforming algorithm.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a wind noise suppression device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the wind noise suppression method as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium and stores a computer program. When the computer program is executed by a processor, the steps of the wind noise suppression method described above are implemented.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: obtaining the sound pickup data of each sound pickup component integrated on the smart device, and detecting the degree of time domain waveform mutation of the sound pickup data of each sound pickup component; determining the peak factor of the time domain waveform of each frame of each channel based on the detection result; screening the target channel whose peak factor is greater than a preset peak factor threshold, and erasing the mutation waveform of the target channel; performing wind noise suppression based on the erased target channel and the target beamforming algorithm. Through the above method, due to the influence of wind noise, each sound pickup component integrated on the smart device has differences and waveform mutations appear on different channels. At this time, the mutation waveform of the target channel whose peak factor is greater than the preset peak factor threshold is erased from the time domain dimension, and then the target beamforming algorithm is combined to perform wind noise suppression. Compared with the existing technology of wind noise suppression through pure beamforming algorithm, it can effectively improve the accuracy of wind noise suppression and ensure voice fidelity. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 A flow chart of the first embodiment of the wind noise suppression method of the present application is provided; Figure 2 A flow chart of the second embodiment of the wind noise suppression method of the present application is provided; Figure 3 This is a schematic diagram of the module structure of the wind noise suppression device according to an embodiment of the present application; Figure 4 Schematic diagram of the device structure of the hardware operating environment involved in the wind noise suppression method in the embodiment of the present application.

[0019] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of implementing the above functions, such as a wind noise suppression device. The following uses a wind noise suppression device as an example to illustrate this embodiment and the following embodiments.

[0021] Based on this, the embodiment of the present application provides a method for suppressing wind noise, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the wind noise suppression method of the present application.

[0022] In this embodiment, the wind noise suppression method includes steps S10 to S40: Step S10: Acquire the sound pickup data of each sound pickup component integrated in the smart device, and perform a time domain waveform mutation degree detection on the sound pickup data of each sound pickup component.

[0023] It should be noted that the smart device may be a true wireless Bluetooth headset, smart speaker, smart glasses, etc. with an embedded real-time platform. The above-mentioned wind noise suppression method can be quickly deployed to the embedded real-time platform. The sound pickup component may be a microphone. There may be multiple sound pickup components integrated in the smart device, for example, MIC1, MIC2, MIC3, ..., MICN. After each sound pickup component integrated in the smart device is started, it will pick up sound in real time, and the sound pickup data of each sound pickup component will be detected for the degree of time domain waveform mutation.

[0024] Step S20: determining the peak factor of each frame of the time domain waveform of each channel according to the detection result.

[0025] It can be understood that the peak factor refers to a key indicator for measuring the degree of mutation of the time domain waveform. After the degree of mutation of the time domain waveform of the sound pickup data of each sound pickup component is detected, the peak factor of the time domain waveform of each frame of each channel can be determined based on the detection results.

[0026] Furthermore, step S20 includes: determining the time domain waveform data of each sampling point in the frame of each channel according to the detection results; obtaining the number of sampling points in each frame; calculating the channel frame root mean square value according to the time domain waveform data and the number of sampling points based on the target channel frame algorithm; and calculating the peak factor of each frame of the time domain waveform of each channel according to the channel frame root mean square value and the target channel frame peak value.

[0027] It should be understood that the target channel frame algorithm refers to an algorithm for calculating the root mean square value of the channel frame, and the target channel frame algorithm can be expressed as: .

[0028] in, Indicates the channel frame RMS value, Indicates the number of sampling points, Represents the time domain waveform data of each sampling point within the frame of each channel.

[0029] It should be noted that the above channel frame root mean square value can also be called the RMS value of the channel frame, which is a quantitative indicator for measuring the average energy of the time domain waveform. The target channel frame peak value refers to the maximum absolute value of all sampling points in a frame of the channel's time domain waveform. The peak factor of each frame of the time domain waveform of each channel is then calculated based on the channel frame root mean square value and the target channel frame peak value. Specifically, .

[0030] in, Indicates the peak factor of each frame of the time domain waveform of each channel, Indicates the target channel frame peak value, Indicates the channel frame RMS value.

[0031] Step S30 , screening target channels whose peak factors are greater than a preset peak factor threshold, and erasing the sudden change waveforms of the target channels.

[0032] It should be understood that after obtaining the peak factor of each frame of the time domain waveform of each channel, the peak factor of each frame of the time domain waveform of each channel is compared with the preset peak factor threshold in turn to screen out the target channel whose peak factor is greater than the preset peak factor threshold, which can be specifically expressed as: .

[0033] in, Indicates the preset crest factor threshold, Indicates the peak factor of each frame of the time domain waveform of each channel, Indicates target channels whose crest factors are greater than the preset crest factor threshold.

[0034] It should be noted that the target channel represents a channel with a high degree of mutation. In the spectrum, the target channel's mutation waveform is displayed as vertical bars, which can be called vertical bar noise. These vertical bar noises do not appear simultaneously in the channels of all sound pickup components. To effectively improve the accuracy of wind noise suppression, it is necessary to eliminate these vertical bar noises. In this embodiment, a target spline interpolation algorithm can be used to eliminate the mutation waveform of the target channel.

[0035] Furthermore, before the step of screening the target channel whose peak factor is greater than the preset peak factor threshold, it also includes: obtaining peak factor distribution data in a wind noise scene, and determining the current peak factor based on the peak factor distribution data in the wind noise scene; obtaining peak factor distribution data in a no-wind noise scene, and determining the target peak factor based on the peak factor distribution data in the no-wind noise scene; determining a threshold setting interval based on the current peak factor and the target peak factor, and setting a preset peak factor threshold based on the threshold setting interval.

[0036] It can be understood that in this embodiment, a preset peak factor threshold can be set based on the difference in peak factor distribution data in a wind noise scene and a non-wind noise scene. Specifically, the current peak factor is determined based on the peak factor distribution data in the wind noise scene, and the target peak factor is determined based on the peak factor distribution data in the non-wind noise scene. Here, the current peak factor can be the minimum peak factor in the peak factor distribution data in the wind noise scene, and similarly, the target peak factor can be the maximum peak factor in the peak factor distribution data in the non-wind noise scene.

[0037] It should be understood that in order to ensure that the sudden waveform is accurately identified, this embodiment determines the threshold setting interval based on the current peak factor and the target peak factor, and sets the preset peak factor threshold according to the threshold setting interval. For example, if the current peak factor is 14dB and the target peak factor is 10dB, the threshold setting interval is [10,14], and the preset peak factor threshold set at this time can be 12db.

[0038] Furthermore, the step of erasing the sudden change waveform of the target channel includes: determining a sudden change position of the time domain waveform of the target channel according to a detection result; and erasing the sudden change waveform of the target channel according to the sudden change position of the time domain waveform.

[0039] It should be understood that the time domain waveform mutation position refers to the position where the time domain waveform of the target channel has a larger degree of mutation. The cause of the mutation may be that wind noise causes the diaphragm of the pickup component to vibrate violently, generating high-amplitude instantaneous noise. At this time, the mutation waveform of the target channel is erased according to the time domain waveform mutation position.

[0040] Furthermore, after the step of erasing the sudden waveform of the target channel according to the sudden change position of the time domain waveform, the method further includes: obtaining a sampling point set of the target channel; selecting a target number of initial reference sampling points from the sampling point set; generating a target time domain normal waveform according to the initial reference sampling points through a target spline interpolation algorithm; and completing the waveform of the erased target channel according to the target time domain normal waveform and the sudden change position of the time domain waveform.

[0041] It can be understood that the target spline interpolation algorithm is a piecewise polynomial interpolation algorithm. The target spline interpolation algorithm can be a cubic spline interpolation algorithm. After obtaining the sampling point set of the target channel, a target number of initial reference sampling points are selected therefrom. Taking a target channel as an example, the target number of the selected initial reference sampling points can be init_N (init_N<=8), so as to achieve the effect of reducing the amount of calculation. At this time, the target time domain normal waveform can be generated by the target spline interpolation algorithm, which can be specifically expressed as: .

[0042] in, Indicates the normal waveform of the target time domain, represents the initial reference sampling point, Represents the target spline interpolation algorithm.

[0043] Step S40 , performing wind noise suppression according to the erased target channel and the target beamforming algorithm.

[0044] It can be understood that after erasing the sudden waveform of the target channel and completing the target time-domain normal waveform, the cascade target beamforming algorithm is used to suppress wind noise, wherein the target beamforming algorithm can be a common beamforming algorithm, such as the Minimum Variance Distortionless Response (MVDR) algorithm, the Generalized Sidelobe Canceller (GSC) algorithm, etc., to achieve the purpose of suppressing sudden wind noise and directional wind noise, and significantly improve the clarity of speech.

[0045] Furthermore, step S40 includes: obtaining the time domain waveform data of the erased target channel and the time domain waveform data of other normal channels; generating a sound pickup component array according to the position information of each sound pickup component integrated on the smart device; cascading a target beamforming algorithm according to the sound pickup component array; and performing wind noise suppression according to the time domain waveform data of the erased target channel, the time domain waveform data of other normal channels, and the target beamforming algorithm.

[0046] It should be understood that the sound pickup component array refers to an array composed of various sound pickup components integrated on the smart device. For sound pickup components in different positions, the generated sound pickup component array is different. After generating the sound pickup component array and obtaining the time domain waveform data of the erased target channel and the time domain waveform data of other normal channels, the cascade target beamforming algorithm further suppresses low-frequency wind noise.

[0047] This embodiment obtains the sound pickup data of each sound pickup component integrated on the smart device, and performs a time domain waveform mutation degree detection on the sound pickup data of each sound pickup component; determines the peak factor of the time domain waveform of each frame of each channel based on the detection result; selects the target channel whose peak factor is greater than a preset peak factor threshold, and erases the mutation waveform of the target channel; and performs wind noise suppression based on the erased target channel and the target beamforming algorithm. Through the above method, due to the influence of wind noise, each sound pickup component integrated on the smart device has differences and waveform mutations appear on different channels. At this time, the mutation waveform of the target channel whose peak factor is greater than the preset peak factor threshold is erased from the time domain dimension, and then the target beamforming algorithm is combined to perform wind noise suppression. Compared with the existing technology of suppressing wind noise through a pure beamforming algorithm, it can effectively improve the accuracy of wind noise suppression and ensure voice fidelity.

[0048] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 After step S40, the process further includes steps S501 to S504: Step S501: Acquire voice information after wind noise suppression.

[0049] Step S502: Perform wind noise detection on the voice information.

[0050] It is understandable that in order to verify the above-mentioned wind noise suppression effect, after obtaining the voice information after wind noise suppression, it is necessary to perform wind noise detection on the voice information to determine whether there is any residual wind noise.

[0051] Step S503: When the detection result shows that there is no residual wind noise, a fidelity detection is performed on the voice information to obtain a current fidelity feature value.

[0052] It should be understood that when the detection result is determined to be that there is no residual wind noise, it indicates that the wind noise suppression method of this embodiment can avoid the occurrence of wind noise residual phenomenon. The current fidelity characteristic value refers to the characteristic value used to measure the fidelity of speech. The larger the current fidelity characteristic value, the higher the fidelity of the speech information after wind noise suppression.

[0053] Step S504: When the current fidelity characteristic value is greater than a preset value, the voice information is played through a playback component integrated on the smart device.

[0054] It can be understood that when it is determined that the current fidelity characteristic value is greater than the preset value, it indicates that the voice information after wind noise suppression does not have voice distortion, and thus will not affect the listening experience after wind noise suppression. At this time, the voice information can be played through the playback component integrated on the smart device, and the playback component can be a speaker.

[0055] This embodiment obtains voice information after wind noise suppression; performs wind noise detection on the voice information; when the detection result shows that there is no residual wind noise, performs fidelity detection on the voice information to obtain a current fidelity characteristic value; when the current fidelity characteristic value is greater than a preset value, plays the voice information through a playback component integrated on the smart device. Through the above method, after obtaining the voice information after wind noise suppression, wind noise detection and fidelity detection are performed on the voice information respectively. When the detection results meet the requirements, the voice information is played through the playback component, thereby ensuring voice fidelity while avoiding the phenomenon of residual wind noise, thereby improving the listening experience after wind noise suppression.

[0056] This application also provides a wind noise suppression device, please refer to Figure 3 , the wind noise suppression device comprises: The acquisition module 10 is used to acquire the sound pickup data of each sound pickup component integrated in the smart device, and perform a time domain waveform mutation degree detection on the sound pickup data of each sound pickup component.

[0057] The determination module 20 is used to determine the peak factor of each frame of the time domain waveform of each channel according to the detection result.

[0058] The erasing module 30 is configured to screen target channels whose peak factors are greater than a preset peak factor threshold, and to erase the sudden change waveforms of the target channels.

[0059] The suppression module 40 is configured to suppress wind noise according to the erased target channel and the target beamforming algorithm.

[0060] This embodiment obtains the sound pickup data of each sound pickup component integrated on the smart device, and performs a time domain waveform mutation degree detection on the sound pickup data of each sound pickup component; determines the peak factor of the time domain waveform of each frame of each channel based on the detection result; selects the target channel whose peak factor is greater than a preset peak factor threshold, and erases the mutation waveform of the target channel; and performs wind noise suppression based on the erased target channel and the target beamforming algorithm. Through the above method, due to the influence of wind noise, each sound pickup component integrated on the smart device has differences and waveform mutations appear on different channels. At this time, the mutation waveform of the target channel whose peak factor is greater than the preset peak factor threshold is erased from the time domain dimension, and then the target beamforming algorithm is combined to perform wind noise suppression. Compared with the existing technology of suppressing wind noise through a pure beamforming algorithm, it can effectively improve the accuracy of wind noise suppression and ensure voice fidelity.

[0061] The wind noise suppression device provided in this application utilizes the wind noise suppression method described in the aforementioned embodiment, thereby resolving the technical issue of low wind noise suppression accuracy in the prior art. Compared to the prior art, the wind noise suppression device provided in this application achieves the same beneficial effects as the wind noise suppression method described in the aforementioned embodiment. Other technical features of the wind noise suppression device are the same as those disclosed in the aforementioned embodiment and are not further elaborated upon here.

[0062] In one embodiment, the determination module 20 is further used to determine the time domain waveform data of each sampling point in the frame of each channel based on the detection results; obtain the number of sampling points in each frame; calculate the channel frame root mean square value based on the time domain waveform data and the number of sampling points based on the target channel frame algorithm; calculate the peak factor of each frame of the time domain waveform of each channel based on the channel frame root mean square value and the target channel frame peak value.

[0063] In one embodiment, the erasing module 30 is further used to obtain peak factor distribution data in a wind noise scenario, and determine a current peak factor based on the peak factor distribution data in the wind noise scenario; obtain peak factor distribution data in a no-wind noise scenario, and determine a target peak factor based on the peak factor distribution data in the no-wind noise scenario; determine a threshold setting interval based on the current peak factor and the target peak factor, and set a preset peak factor threshold based on the threshold setting interval.

[0064] In one embodiment, the erasing module 30 is further configured to determine a sudden change position of the time domain waveform of the target channel according to the detection result; and erase the sudden change waveform of the target channel according to the sudden change position of the time domain waveform.

[0065] In one embodiment, the erasing module 30 is further used to obtain a set of sampling points of the target channel; select a target number of initial reference sampling points from the sampling point set; generate a target time domain normal waveform based on the initial reference sampling points through a target spline interpolation algorithm; and complete the waveform of the erased target channel based on the target time domain normal waveform and the time domain waveform mutation position.

[0066] In one embodiment, the suppression module 40 is further used to obtain the time domain waveform data of the target channel after erasure and the time domain waveform data of other normal channels; generate a sound pickup component array according to the position information of each sound pickup component integrated on the smart device; cascade the target beamforming algorithm according to the sound pickup component array; and perform wind noise suppression based on the time domain waveform data of the target channel after erasure, the time domain waveform data of other normal channels, and the target beamforming algorithm.

[0067] In one embodiment, the suppression module 40 is further used to obtain voice information after wind noise suppression; perform wind noise detection on the voice information; when the detection result is that there is no residual wind noise, perform fidelity detection on the voice information to obtain a current fidelity characteristic value; when the current fidelity characteristic value is greater than a preset value, play the voice information through a playback component integrated on the smart device.

[0068] The present application provides a wind noise suppression device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the wind noise suppression method in the above-mentioned embodiment 1.

[0069] Reference below Figure 4, which shows a schematic structural diagram of a wind noise suppression device suitable for implementing embodiments of the present application. The wind noise suppression device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The wind noise suppression device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0070] like Figure 4 As shown, the wind noise suppression device may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in ROM (Read Only Memory) 1002 or programs loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the wind noise suppression device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007, such as a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003, such as a magnetic tape or hard disk; and communication device 1009. Communication device 1009 can allow the wind noise suppression device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a wind noise suppression device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems can be implemented or have alternatively.

[0071] In particular, according to the embodiments disclosed herein, the processes described above with reference to the flowcharts can be implemented as computer software programs. The computer programs contain program code for executing the methods shown in the flowcharts. In such embodiments, the computer programs can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer programs are executed by processing device 1001, the above-described functions defined in the methods of the embodiments disclosed herein are performed.

[0072] The wind noise suppression device provided in this application utilizes the wind noise suppression method described in the aforementioned embodiment, resolving the technical issue of low wind noise suppression accuracy in the prior art. Compared to the prior art, the beneficial effects of the wind noise suppression device provided in this application are the same as those of the wind noise suppression method described in the aforementioned embodiment. Other technical features of the wind noise suppression device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0073] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0074] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0075] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, wherein the computer-readable program instructions are used to execute the wind noise suppression method in the above-mentioned embodiment.

[0076] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0077] The computer-readable storage medium may be included in the wind noise suppression device, or may exist independently without being assembled into the wind noise suppression device.

[0078] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0079] The flow charts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems and methods according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0080] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0081] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned wind noise suppression method. This computer-readable storage medium can address the low accuracy of wind noise suppression in existing technologies. Compared to existing technologies, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the wind noise suppression method provided in the aforementioned embodiments, and are not further elaborated here.

[0082] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for suppressing wind noise, characterized in that: The method comprises: Acquiring sound pickup data of each sound pickup component integrated on the smart device, and performing time domain waveform mutation degree detection on the sound pickup data of each sound pickup component; Determine the peak factor of each frame of the time domain waveform of each channel according to the detection results; Screening the target channel whose peak factor is greater than a preset peak factor threshold, and erasing the sudden change waveform of the target channel; Wind noise suppression is performed based on the erased target channel and target beamforming algorithm.

2. The method according to claim 1, wherein The step of determining the peak factor of each frame of the time domain waveform of each channel according to the detection result includes: Determine the time domain waveform data of each sampling point within the frame of each channel according to the detection results; Get the number of sampling points for each frame; Calculating a channel frame root mean square value based on the time domain waveform data and the number of sampling points based on a target channel frame algorithm; The peak factor of each frame of the time domain waveform of each channel is calculated according to the channel frame root mean square value and the target channel frame peak value.

3. The method according to claim 1, wherein Before the step of screening the target channel whose peak factor is greater than the preset peak factor threshold, the method further includes: Acquire peak factor distribution data in a wind noise scenario, and determine a current peak factor according to the peak factor distribution data in the wind noise scenario; Acquire peak factor distribution data in a scene without wind noise, and determine a target peak factor based on the peak factor distribution data in the scene without wind noise; A threshold setting interval is determined according to the current peak factor and the target peak factor, and a preset peak factor threshold is set according to the threshold setting interval.

4. The method according to claim 1, wherein The step of erasing the sudden change waveform of the target channel includes: Determine the time domain waveform mutation position of the target channel according to the detection result; The sudden change waveform of the target channel is erased according to the sudden change position of the time domain waveform.

5. The method according to claim 4, wherein After the step of erasing the sudden change waveform of the target channel according to the sudden change position of the time domain waveform, the method further includes: Obtaining a sampling point set of the target channel; Selecting a target number of initial benchmark sampling points from the sampling point set; Generate a target time-domain normal waveform according to the initial reference sampling points through a target spline interpolation algorithm; The waveform of the erased target channel is completed according to the target time domain normal waveform and the time domain waveform mutation position.

6. The method according to claim 1, wherein The step of performing wind noise suppression according to the erased target channel and the target beamforming algorithm includes: Obtaining the time domain waveform data of the erased target channel and the time domain waveform data of other normal channels; generating a sound pickup component array according to position information of each sound pickup component integrated on the smart device; cascade target beamforming algorithm according to the pickup assembly array; Wind noise suppression is performed based on the erased time domain waveform data of the target channel, the time domain waveform data of other normal channels, and the target beamforming algorithm.

7. The method according to any one of claims 1 to 6, characterized in that After the step of performing wind noise suppression according to the erased target channel and the target beamforming algorithm, the method further includes: Obtain voice information after wind noise suppression; performing wind noise detection on the voice information; When the detection result shows that there is no residual wind noise, performing a fidelity detection on the voice information to obtain a current fidelity feature value; When the current fidelity characteristic value is greater than a preset value, the voice information is played through a playback component integrated on the smart device.

8. A wind noise suppression device, characterized in that: The device comprises: An acquisition module is used to acquire sound data collected by each sound collection component integrated on the smart device, and perform time domain waveform mutation detection on the sound data collected by each sound collection component; A determination module, used to determine the peak factor of each frame of the time domain waveform of each channel according to the detection result; an erasing module, configured to screen target channels whose peak factors are greater than a preset peak factor threshold, and to erase the sudden change waveforms of the target channels; The suppression module is used to suppress wind noise according to the erased target channel and the target beamforming algorithm.

9. A wind noise suppression device, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the wind noise suppression method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the wind noise suppression method according to any one of claims 1 to 7 are implemented.

Images