Audio processing method, device, electronic device and readable storage medium

Abstract

This application provides an audio processing method, apparatus, electronic device, and readable storage medium, relating to the field of audio processing technology. The method includes: acquiring first audio data output from a speaker via an audio motherboard module, and acquiring second audio data via an audio acquisition module; using an audio processing module to determine and filter out target audio components from the audio components of the second audio data to obtain target audio data, wherein the target audio components are at least partially identical to the audio components in the first audio data. In this solution, by utilizing the audio processing module to filter out the audio components in the acquired second audio data that are identical to those in the first audio data output from the speaker, echo in the acquired second audio data can be reduced through hardware noise reduction, thereby improving the quality of the target audio data.

Description

Technical Field

[0001] The present invention relates to the field of audio processing technology, and in particular to an audio processing method, device, electronic device and readable storage medium. Background Art

[0002] In the computer field, for scenarios that require voice interaction, the accuracy of voice analysis is an important part of voice interaction. If the device does not accurately analyze the voice, it will affect the voice interaction. Currently, during the voice analysis process, the user's voice is easily disturbed by the environment, which makes the collected audio data have a lot of noise, affecting the accuracy of voice analysis. Summary of the invention

[0003] The present application provides an audio processing method, device, electronic device and readable storage medium, which can improve the problem of high noise in collected audio data and help improve the accuracy of speech analysis.

[0004] In order to achieve the above purpose, the technical solutions provided in the embodiments of the present application are as follows:

[0005] In a first aspect, an embodiment of the present application provides an audio processing method, which is applied to an electronic device, wherein the electronic device includes an audio acquisition module, a speaker, an audio mainboard module, and an audio processing module, and the method includes:

[0006] Acquire first audio data input to the speaker through the audio mainboard module, and acquire second audio data through the audio acquisition module;

[0007] The audio processing module determines and filters out target audio components from the audio components of the second audio data to obtain target audio data, where the target audio components are the same as at least part of the audio components in the first audio data.

[0008] In the above implementation, by using the audio processing module to filter out the audio components in the collected second audio data that are the same as those in the first audio data output by the speaker, the echo in the collected second audio data can be reduced in a hardware noise reduction manner, thereby improving the quality of the target audio data. Since the echo is eliminated in the target audio data, it is beneficial to improve the accuracy of speech analysis.

[0009] In combination with the first aspect, in some optional implementations, obtaining first audio data input to the speaker through the audio mainboard module, and acquiring second audio data through the audio acquisition module include:

[0010] Within a preset time period of receiving an operation instruction for voice processing, the first audio data input to the speaker is acquired through the audio mainboard module, and the second audio data is acquired through the audio acquisition module.

[0011] In the above implementation, by acquiring corresponding audio data within a preset time period, there is no need to continuously acquire audio data for a long period of time, which is helpful to reduce energy consumption.

[0012] In combination with the first aspect, in some optional implementations, the audio acquisition module includes a directional microphone array, and the second audio data includes a speech signal corresponding to each microphone unit in the directional microphone array;

[0013] Determining and filtering out a target audio component from the audio components of the second audio data by the audio processing module to obtain target audio data includes:

[0014] Determine and filter out the target audio component from the audio components of each voice signal through the comparison circuit in the audio processing module to obtain a filtered voice signal;

[0015] The filtered voice signals of each channel are synthesized to obtain the target audio data.

[0016] In combination with the first aspect, in some optional implementations, the audio acquisition module includes a directional microphone array, and the second audio data includes a speech signal corresponding to each microphone unit in the directional microphone array;

[0017] Determining and filtering out a target audio component from the audio components of the second audio data by the audio processing module to obtain target audio data includes:

[0018] synthesizing each voice signal to obtain a synthesized voice signal;

[0019] The target audio component is determined and filtered out from the audio component of the synthesized speech signal by the comparison circuit in the audio processing module to obtain the target audio data.

[0020] In combination with the first aspect, in some optional implementations, determining and filtering a target audio component from audio components of the second audio data by the audio processing module to obtain target audio data includes:

[0021] Determine and filter out target audio components from audio components of the second audio data by a comparison circuit in the audio processing module to obtain filtered out second audio data;

[0022] The audio mainboard module performs noise reduction processing on the filtered second audio data based on a filter to obtain the target audio data.

[0023] In combination with the first aspect, in some optional implementations, the method further includes:

[0024] Analyze the target audio data through speech recognition algorithm;

[0025] When the target audio data represents a designated operation instruction, an operation corresponding to the designated operation instruction is performed by the electronic device.

[0026] In the above implementation, since the echo is eliminated in the target audio data, it is helpful to improve the accuracy of speech analysis when performing speech analysis.

[0027] In a second aspect, the present application also provides an audio processing device, which is applied to an electronic device, wherein the electronic device includes an audio acquisition module, a speaker, an audio mainboard module, and an audio processing module, and the device includes:

[0028] An audio acquisition unit, used for acquiring first audio data input to the speaker through the audio mainboard module, and acquiring second audio data through the audio acquisition module;

[0029] The noise reduction unit is used to determine and filter out a target audio component from the audio components of the second audio data through the audio processing module to obtain target audio data, where the target audio component is the same as at least part of the audio components in the first audio data.

[0030] In a third aspect, the present application also provides an electronic device, which includes an audio acquisition module, a speaker, an audio mainboard module, an audio processing module and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the audio mainboard module and the audio processing module, the electronic device executes the above method.

[0031] In combination with the third aspect, in some optional implementations, the electronic device includes an advertising machine.

[0032] In a fourth aspect, the present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is run on a computer, the computer executes the above method. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work.

[0034] Figure 1 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0035] Figure 2 A schematic diagram of the structure of an advertising machine provided in an embodiment of the present application.

[0036] Figure 3 A flowchart of an audio processing method provided in an embodiment of the present application.

[0037] Figure 4 A block diagram of an audio processing device provided in an embodiment of the present application.

[0038] Icons: 10-electronic device; 11-audio acquisition module; 12-speaker; 13-audio mainboard module; 14-audio processing module; 200-audio processing device; 210-audio acquisition unit; 220-noise reduction unit. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings in the embodiments of the present application. It should be noted that the terms "first", "second" and the like are only used to distinguish descriptions and cannot be understood as indicating or implying relative importance.

[0040] The embodiments of the present application are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0041] Please refer to Figure 1 The embodiment of the present application provides an electronic device 10, which can be used to perform noise reduction processing on input audio data to improve the quality of the collected audio data, thereby facilitating improving the accuracy of speech analysis of the audio data.

[0042] In this embodiment, the electronic device 10 may include an audio acquisition module 11, a speaker 12, an audio mainboard module 13, an audio processing module 14, and a memory. The memory stores a computer program, and when the computer program is executed by the audio mainboard module 13 and the audio processing module 14, the electronic device 10 can perform each step in the following audio processing method.

[0043] In this embodiment, the memory may be integrated into the audio processing module 14, or integrated into the audio mainboard module 13, or the memory is a device independent of the audio processing module 14 and the audio mainboard module 13. The memory may be used to store filters, speech recognition algorithms, and the like.

[0044] The audio acquisition module 11 may be one or more microphones, which may be used to collect the user's voice to obtain corresponding audio data. When the audio acquisition module 11 is a microphone array formed by multiple microphones, the audio acquisition module 11 may be a directional microphone array. The number of microphone units included in the directional microphone array may be determined according to actual conditions, for example, the number of microphone units may be 2, 4, 6, etc.

[0045] Understandably, when the sound propagation direction is the same as the collection direction of the directional microphone array, the directional microphone has a better sound collection effect. When the sound propagation direction is different from the collection direction of the directional microphone array, the directional microphone array has a better sound suppression effect. That is, the directional microphone array can retain the voice signal in the collection direction, collect the sound signal in a directionally, and effectively suppress the sound signal in the non-collection direction to achieve the required audio effect, thereby improving the quality of the collected audio data and reducing noise. Among them, the collection direction of the directional microphone array is the direction of the microphone unit in the directional microphone array.

[0046] The number of the speakers 12 in the electronic device 10 may be one or more. The number of the speakers 12 may be set according to actual conditions and is not specifically limited here. The speakers 12 may be used to emit sound according to the audio data so that the user can perform corresponding voice interaction according to the sound prompt.

[0047] The audio mainboard module 13 can output audio data to the speaker 12 to control the speaker 12 to make a sound. In addition, the audio mainboard module 13 can also obtain the audio data output to the speaker 12, so as to use the audio data output to the speaker 12 to perform echo noise reduction processing on the collected audio data. In addition, the audio mainboard module 13 can also perform noise reduction processing on the collected audio data through a filter to improve the quality of the audio data after noise reduction. Among them, the audio mainboard module 13 can be selected according to actual conditions. For example, the audio mainboard module 13 can be but not limited to the SWH5190 mainboard.

[0048] The audio processing module 14 has a comparison circuit, which can be used to compare audio components and eliminate the same audio components. The audio processing module 14 can be selected according to actual conditions, as long as it has a comparison circuit for comparing audio components and can filter out the same audio components. For example, the audio processing module 14 can be, but is not limited to, an AC108 voice processing board.

[0049] The electronic device 10 may be, but is not limited to, an advertising machine, a smart phone, etc., and may be a device that can be used for voice interaction.

[0050] Please refer to Figure 2 When the electronic device 10 is an advertising machine, the advertising machine may also include a display screen, a camera and other devices. Among them, the audio acquisition module 11 may be a directional microphone array. For a vertical advertising machine, the height of the advertising machine is usually more than 1 meter. At this time, the array microphone can be set within a specified height range. For example, the specified height range can be between 580 mm and 600 mm, and the acquisition direction of the unidirectional microphone array is an angle upward from the horizontal direction, and the angle can be within a specified range. For example, the acquisition direction of the array microphone is 20°±1° upward from the horizontal direction. At this time, the audio effect collected by the unidirectional microphone array is better.

[0051] Please refer to Figure 3 The present application also provides an audio processing method, which can be applied to the above-mentioned electronic device, and each step in the method is executed or implemented by the electronic device. The method may include the following steps:

[0052] Step S110, acquiring first audio data input to the speaker through the audio mainboard module, and acquiring second audio data through the audio acquisition module;

[0053] Step S120: determining and filtering out target audio components from the audio components of the second audio data through the audio processing module to obtain target audio data, wherein the target audio components are the same as at least part of the audio components in the first audio data.

[0054] In the above implementation, by using the audio processing module to filter out the audio components in the collected second audio data that are the same as those in the first audio data output by the speaker, the echo in the collected second audio data can be reduced in a hardware noise reduction manner, thereby improving the quality of the target audio data. Since the echo is eliminated in the target audio data, it is beneficial to improve the accuracy of speech analysis.

[0055] The following is a detailed description of each step in the method:

[0056] In step S110, the audio data input to the speaker is used to control the speaker to emit a corresponding sound. The audio data input to the speaker is usually provided by the audio mainboard module, so the audio mainboard module can obtain the audio data input to the speaker as the first audio data. The audio acquisition module can collect external sounds as the second audio data. The second audio data includes but is not limited to external noise components, the voice components of the target user, the sound emitted by the speaker, etc.

[0057] In step S120, the audio processing module can obtain the second audio data from the audio acquisition module, and can also obtain the first audio data from the audio mainboard module. The audio processing module can compare the audio components in the first audio data and the second audio data through a hardware circuit.

[0058] For example, the audio processing module can automatically detect the same audio components in the first audio data and the second audio data. In addition, the audio processing module can also filter out the same audio components in the second audio data as the first audio data. Among them, the same audio components can be understood as audio components with the same frequency, usually the echo formed by the sound emitted by the speaker. Based on this, by eliminating the same audio components, the echo can be eliminated from the second audio data to obtain the target audio data. Since the echo is eliminated in the obtained target audio data, it is beneficial to the subsequent audio analysis and to improve the accuracy of audio analysis.

[0059] As an optional implementation, step S110 may include:

[0060] Within a preset time period of receiving an operation instruction for voice processing, the first audio data input to the speaker is acquired through the audio mainboard module, and the second audio data is acquired through the audio acquisition module.

[0061] In this embodiment, the operation instruction is generally an instruction generated by the user through the operation of the electronic device. For example, the electronic device may include a touch screen, and when the user needs to interact with the electronic device by voice, the corresponding virtual button on the touch screen may be triggered, and then the electronic device generates an operation instruction based on the user's operation.

[0062] In addition, the preset duration can be determined according to actual conditions. For example, it can be a shorter duration such as 30 seconds or 60 seconds. By obtaining the corresponding audio data within the preset duration, there is no need to continuously obtain the audio data for a long time, which is conducive to reducing the energy consumption of the electronic device.

[0063] As an optional implementation, when the audio acquisition module is a directional microphone array, the second audio data includes a speech signal corresponding to each microphone unit in the directional microphone array. Step S120 may include:

[0064] Determine and filter out the target audio component from the audio components of each voice signal through the comparison circuit in the audio processing module to obtain a filtered voice signal;

[0065] The filtered voice signals of each channel are synthesized to obtain the target audio data.

[0066] In this embodiment, each microphone unit in the directional microphone array can have a synchronous analog-to-digital converter (ADC) with an independent programmable microphone bias voltage and a microphone boost amplifier to provide effective channel data, thereby eliminating channel crosstalk. An independent digital voice controller can be provided in the channel corresponding to each microphone unit to facilitate independent graded noise reduction processing of the voice signal collected by each microphone unit. Among them, the voice signal is the voice data obtained by a single microphone unit collecting the user's voice.

[0067] When performing echo cancellation processing, the comparison circuit in the audio processing module can identify and compare each voice signal with the first audio data, and eliminate the audio component in each audio data that is the same as the first audio data, so that the echo of each voice signal can be eliminated in a hardware manner. Among them, collecting voice through multiple microphone units can improve the quality of the collected voice data.

[0068] The voice signal after echo cancellation can be synthesized by a voice processing module or other modules to obtain target audio data. The method of synthesizing the target audio data is well known to those skilled in the art and will not be described in detail here.

[0069] As an optional implementation, when the audio acquisition module is a directional microphone array, the second audio data includes a speech signal corresponding to each microphone unit in the directional microphone array. Step S120 may include:

[0070] synthesizing each voice signal to obtain a synthesized voice signal;

[0071] The target audio component is determined and filtered out from the audio component of the synthesized speech signal by the comparison circuit in the audio processing module to obtain the target audio data.

[0072] In this embodiment, the electronic device can synthesize each voice signal through a voice processing module or other modules, and then perform echo cancellation on the synthesized voice signal. That is, the synthesized voice signal is analyzed and compared with the first audio data using a comparison circuit in the audio processing module, and the audio component in the synthesized voice signal that is the same as the first audio data is filtered out. Among them, collecting voice through multiple microphone units can improve the quality of the collected voice data.

[0073] As an optional implementation, the method may further include:

[0074] Determine and filter out target audio components from audio components of the second audio data by a comparison circuit in the audio processing module to obtain filtered out second audio data;

[0075] The audio mainboard module performs noise reduction processing on the filtered second audio data based on a filter to obtain the target audio data.

[0076] In this embodiment, after the echo cancellation is performed on the second audio data, the second audio data after the echo cancellation can also be subjected to noise reduction processing through the audio mainboard module to further improve the quality of the obtained second audio data. The filter in the audio mainboard module can be selected according to actual conditions, including but not limited to LMS (Least Mean Square) adaptive filter.

[0077] As an optional implementation, the method may further include:

[0078] Analyze the target audio data through speech recognition algorithm;

[0079] When the target audio data represents a designated operation instruction, an operation corresponding to the designated operation instruction is performed by the electronic device.

[0080] In this embodiment, the speech recognition algorithm can be used to determine whether the content corresponding to the target audio data matches the instructions in the voice instruction library. Among them, the voice instruction library can include a variety of voice instructions, which can be set according to actual conditions and used to control the electronic device to perform corresponding specified operations. Among them, the specified operation can be determined according to actual conditions. For example, the voice instruction library may include voice instructions for triggering navigation operations, voice instructions for controlling electronic devices to query the location that the user needs to find, etc. The voice instructions can be stored in the database in the form of text or voice.

[0081] The speech recognition algorithm can convert the target audio data into text content, and then determine whether there is text that is the same or similar to the text content in the voice instruction library. If there is the same or similar text, it is determined that there is a voice instruction matching the target audio data in the voice instruction library. Alternatively, the speech recognition algorithm can determine whether there is a voice instruction matching the target audio data in the voice instruction library by comparing the spectrum data corresponding to the target audio data and the spectrum data corresponding to the voice of the voice instruction, and by the similarity of the spectrum. If there is a voice instruction in the voice instruction library whose maximum similarity with the spectrum data of the target audio data exceeds a set value, it is determined that there is a voice instruction matching the target audio data in the voice instruction library, and the matched voice instruction is the voice instruction corresponding to the spectrum data with the maximum similarity.

[0082] The target audio data can be analyzed through the speech recognition algorithm. Since the echo is eliminated and the noise reduction process is performed in the target audio data, it is helpful to improve the accuracy of speech analysis when performing speech analysis.

[0083] It should be noted that the speech recognition algorithm is well known to those skilled in the art and will not be described in detail here.

[0084] Please refer to Figure 4 , the embodiment of the present application also provides an audio processing device 200, which can be applied to the above-mentioned electronic device to execute or implement each step in the method. The audio processing device 200 includes at least one software function module that can be stored in the storage module in the form of software or firmware (Firmware) or solidified in the operating system (OS) of the electronic device. The processing module is used to execute the executable module stored in the storage module, such as the software function module and computer program included in the audio processing device 200.

[0085] In this embodiment, the audio processing device 200 may include an audio acquisition unit and a noise reduction unit 220, and the operations performed may be as follows:

[0086] An audio acquisition unit 210, configured to acquire first audio data input to the speaker through the audio mainboard module, and acquire second audio data through the audio acquisition module;

[0087] The noise reduction unit 220 is used to determine and filter out a target audio component from the audio components of the second audio data through the audio processing module to obtain target audio data, where the target audio component is the same as at least part of the audio components in the first audio data.

[0088] Optionally, the audio acquisition unit 210 can also be used to acquire the first audio data input to the speaker through the audio mainboard module within a preset time period of receiving an operation instruction for voice processing, and to acquire the second audio data through the audio acquisition module.

[0089] Optionally, the audio acquisition module includes a directional microphone array, and the second audio data includes a speech signal corresponding to each microphone unit in the directional microphone array. The noise reduction unit 220 can also be used to: determine and filter out a target audio component from the audio component of each voice signal through a comparison circuit in the audio processing module to obtain a filtered voice signal; synthesize each of the filtered voice signals to obtain the target audio data.

[0090] Optionally, the noise reduction unit 220 can also be used to: synthesize each voice signal to obtain a synthesized voice signal; determine and filter out the target audio component from the audio component of the synthesized voice signal through the comparison circuit in the audio processing module to obtain the target audio data.

[0091] Optionally, the noise reduction unit 220 can also be used to: determine and filter out the target audio component from the audio component of the second audio data through the comparison circuit in the audio processing module to obtain the filtered second audio data; and perform noise reduction processing on the filtered second audio data based on the filter through the audio mainboard module to obtain the target audio data.

[0092] Optionally, the audio processing device 200 may further include an audio parsing unit and an execution unit. The audio parsing unit is used to parse the target audio data through a speech recognition algorithm; the execution unit is used to execute an operation corresponding to the specified operation instruction through the electronic device when the target audio data represents a specified operation instruction.

[0093] The processing module can be an integrated circuit chip with signal processing capabilities. The above-mentioned processing module can be a general-purpose processor. For example, the processor can be a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, which can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of this application.

[0094] The communication module is used to establish a communication connection between the electronic device and the order management server and the business processing server through the network, and to send and receive data through the network.

[0095] The storage module may be, but is not limited to, a random access memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, etc. In this embodiment, the storage module may be used to store audio data. Of course, the storage module may also be used to store a program, and the processing module executes the program after receiving the execution instruction.

[0096] Understandably, Figure 1 The structure shown is only a schematic diagram of the structure of the electronic device. The electronic device may also include Figure 1 More components are shown. Figure 1 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0097] It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working process of the electronic device and audio processing device 200 described above can refer to the corresponding process of each step in the aforementioned method, and will not be repeated here.

[0098] The embodiment of the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed on a computer, the computer executes the audio processing method described in the above embodiment.

[0099] Through the description of the above implementation methods, technical personnel in this field can clearly understand that the present application can be implemented by hardware, and can also be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0100] In summary, the present application provides an audio processing method, device, electronic device and readable storage medium. The method includes: obtaining the first audio data output by the speaker through the audio mainboard module, and obtaining the second audio data through the audio acquisition module; determining and filtering the target audio component from the audio component of the second audio data through the audio processing module to obtain the target audio data, and the target audio component is the same as at least part of the audio component in the first audio data. In this solution, by using the audio processing module to filter out the audio components in the collected second audio data that are the same as the first audio data output by the speaker, the echo in the collected second audio data can be reduced by hardware noise reduction, thereby improving the quality of the target audio data. Since the echo is eliminated in the target audio data, it is beneficial to improve the accuracy of speech analysis.

[0101] In the embodiments provided in the present application, it should be understood that the disclosed device, system and method can also be implemented in other ways. The above-described device, system and method embodiments are merely schematic, for example, the flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a part of a module, a program segment or a code, and a part of the module, program segment or code contains one or more executable instructions for implementing the specified logical function. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. In addition, each functional module in each embodiment of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0102] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An audio processing method, characterized in that: Applied to electronic equipment, the electronic equipment includes an audio acquisition module, a speaker, an audio mainboard module, and an audio processing module, and the method includes: Acquire first audio data input to the speaker through the audio mainboard module, and acquire second audio data through the audio acquisition module; Determine and filter out a target audio component from the audio components of the second audio data by the audio processing module to obtain target audio data, wherein the target audio component is the same as at least part of the audio components in the first audio data; Wherein, the audio collection module includes a directional microphone array, the directional microphone array is set within a height range of 580 mm-600 mm, and the collection direction of the directional microphone array is tilted upward at a preset angle of 20°±1° in the horizontal direction, and the collection direction is the direction of the microphone unit in the directional microphone array; the second audio data includes a voice signal corresponding to each microphone unit in the directional microphone array; when the propagation direction of the voice signal is the same as the collection direction of the directional microphone array, the directional microphone has a better sound collection effect; when the propagation direction of the voice signal is different from the collection direction of the directional microphone array, the directional microphone array has a better sound suppression effect; the directional microphone array retains the voice signal in the collection direction, directionally collects the voice signal, and suppresses the voice signal in the non-collection direction; The step of determining and filtering out a target audio component from the audio component of the second audio data by the audio processing module to obtain the target audio data comprises: determining and filtering out the target audio component identical to the first audio data from the audio component of each voice signal by a hardware comparison circuit in the audio processing module to obtain a filtered voice signal; synthesizing each of the filtered voice signals to obtain the target audio data; or The method of determining and filtering out a target audio component from the audio component of the second audio data through the audio processing module to obtain the target audio data includes: synthesizing each voice signal to obtain a synthesized voice signal; and determining and filtering out a target audio component identical to the first audio data from the audio component of the synthesized voice signal through a hardware comparison circuit in the audio processing module to obtain the target audio data.

2. The method according to claim 1, characterized in that Acquiring first audio data input to the speaker through the audio mainboard module, and acquiring second audio data through the audio acquisition module, including: Within a preset time period of receiving an operation instruction for voice processing, the first audio data input to the speaker is acquired through the audio mainboard module, and the second audio data is acquired through the audio acquisition module.

3. The method according to claim 1, characterized in that Determining and filtering out a target audio component from the audio components of the second audio data by the audio processing module to obtain target audio data includes: Determine and filter out target audio components from audio components of the second audio data by a comparison circuit in the audio processing module to obtain filtered out second audio data; The audio mainboard module performs noise reduction processing on the filtered second audio data based on a filter to obtain the target audio data.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Analyze the target audio data through speech recognition algorithm; When the target audio data represents a designated operation instruction, an operation corresponding to the designated operation instruction is performed by the electronic device.

5. An audio processing device, characterized in that: Applied to electronic equipment, the electronic equipment includes an audio acquisition module, a speaker, an audio mainboard module, and an audio processing module, and the device includes: An audio acquisition unit, used for acquiring first audio data input to the speaker through the audio mainboard module, and acquiring second audio data through the audio acquisition module; A noise reduction unit, configured to determine and filter out a target audio component from the audio component of the second audio data through the audio processing module to obtain target audio data, wherein the target audio component is the same as at least part of the audio component in the first audio data; wherein the audio acquisition module comprises a directional microphone array, the directional microphone array is arranged within a height range of 580 mm to 600 mm, and the acquisition direction of the directional microphone array is a preset angle of 20°±1° tilted upward in the horizontal direction, and the acquisition direction is the orientation of the microphone unit in the directional microphone array; the second audio data comprises a speech signal corresponding to each microphone unit in the directional microphone array; when the propagation direction of the speech signal is the same as the acquisition direction of the directional microphone array, the directional microphone has a better sound acquisition effect; when the propagation direction of the speech signal is different from the acquisition direction of the directional microphone array, the directional microphone array has a better sound suppression effect; the directional microphone array retains the speech signal in the acquisition direction, directionally acquires the speech signal, and suppresses the speech signal in the non-acquisition direction; The noise reduction unit is used to: determine and filter out the target audio component identical to the first audio data from the audio components of each voice signal through the hardware comparison circuit in the audio processing module to obtain the filtered voice signal; synthesize the filtered voice signals of each channel to obtain the target audio data; or, Each voice signal is synthesized to obtain a synthesized voice signal; and a target audio component identical to the first audio data is determined and filtered out from the audio components of the synthesized voice signal through a hardware comparison circuit in the audio processing module to obtain the target audio data.

6. An electronic device, characterized in that: The electronic device comprises an audio acquisition module, a speaker, an audio mainboard module, an audio processing module and a memory, wherein a computer program is stored in the memory. When the computer program is executed by the audio mainboard module and the audio processing module, the electronic device executes the method according to any one of claims 1 to 4.

7. The electronic device according to claim 6, characterized in that: The electronic device includes an advertising machine.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed on a computer, the computer is enabled to execute the method according to any one of claims 1 to 4.

Images