Audio processing method and electronic equipment

Abstract

The invention discloses an audio processing method and electronic equipment. The method comprises the following steps: acquiring audio data; at least two types of noise contained in the audio data are identified based on a target model, the at least two types of noise comprise a first type of noise and a second type of noise, and the type of the first type of noise is different from that of the second type of noise; outputting a first control corresponding to the first type of noise and a second control corresponding to the second type of noise, wherein the first control is used for configuring noise reduction for the first type of noise; the second control is used for configuring noise reduction for the second type of noise.

Description

Technical Field

[0001] The present application relates to the technical field of noise reduction, and more specifically, to an audio processing method and an electronic device. Background Art

[0002] When collecting video or audio, electronic devices can perform noise reduction on the obtained audio data, but the overall noise reduction effect is not ideal and there is still much room for improvement. Summary of the invention

[0003] In view of this, this application provides the following technical solutions:

[0004] The first aspect of the present application provides an audio processing method, the method comprising:

[0005] Get audio data;

[0006] Identify at least two types of noise contained in the audio data based on the target model, the at least two types of noise include a first type of noise and a second type of noise, and the first type of noise is different from the second type of noise;

[0007] A first control corresponding to the first type of noise and a second control corresponding to the second type of noise are output, wherein the first control is used to configure noise reduction for the first type of noise; and the second control is used to configure noise reduction for the second type of noise.

[0008] In one possible implementation,

[0009] The first control is used to configure noise reduction for the first type of noise, including:

[0010] the degree of noise reduction for the first type of noise;

[0011] The second control is used to configure the noise reduction for the second type of noise and includes:

[0012] The degree of noise reduction for the second type of noise.

[0013] In one possible implementation, the method further includes:

[0014] Obtaining a target configuration parameter, wherein the target configuration parameter is generated based on at least one control operation, and the at least one control includes any one of the following: the first control; or the second control;

[0015] In response to the target configuration parameter, the original data of the audio data is restored, the target configuration parameter is applied to the original data, and feedback audio data for feedback on the at least one control operation is output.

[0016] In a possible implementation, the audio data is obtained by processing a target noise reduction model, the target noise reduction model has an original noise reduction configuration, and the target noise reduction model matches a scene in which the audio data is collected;

[0017] The method further comprises:

[0018] A target noise reduction model corresponding to the audio data is determined based on the audio data.

[0019] In one possible implementation, the method further includes:

[0020] Obtaining a target configuration parameter, wherein the target configuration parameter is generated based on at least one control operation, and the at least one control includes any one of the following: the first control; or the second control;

[0021] Based on the target configuration parameter adjustment processing, the original noise reduction configuration of the target noise reduction model of the audio data is obtained to match the target configuration parameters, and the target noise reduction configuration used to characterize the user's expectations is obtained, so that the target noise reduction model responds based on the target noise reduction configuration when called.

[0022] A second aspect of the present application provides an audio processing method, the method comprising:

[0023] obtaining first audio data;

[0024] Determining a target noise reduction model based on a target object representing an audio scene when the first audio data is obtained, wherein the target noise reduction model has multiple groups of noise reduction configurations, and the multiple groups of noise reduction configurations include at least one group of noise reduction configurations obtained based on an interactive manner provided to a user;

[0025] Determining a target noise reduction configuration, the target noise reduction configuration belonging to a group of multiple noise reduction configurations;

[0026] The target noise reduction model performs noise reduction processing on the first audio data based on the target noise reduction configuration to generate second audio data.

[0027] In one possible implementation, obtaining the target object of the audio data scene based on the characterization includes:

[0028] Capturing a target image based on an image acquisition device, wherein the image acquisition device captures the target image in the process of obtaining the audio data, and the target object is the target image;

[0029] A target denoising model is determined based on the target image.

[0030] In a possible implementation, the configuration obtained based on the interaction mode provided to the user has the highest priority among the multiple groups of noise reduction configurations.

[0031] A third aspect of the present application provides an electronic device, including:

[0032] An audio acquisition module, used for acquiring audio data;

[0033] A noise recognition module, configured to recognize at least two types of noise contained in the audio data based on a target model, wherein the at least two types of noise include a first type of noise and a second type of noise, and the first type of noise is different from the second type of noise;

[0034] An interactive processing module is used to output a first control corresponding to the first type of noise and a second control corresponding to the second type of noise, wherein the first control is used to configure noise reduction for the first type of noise; and the second control is used to configure noise reduction for the second type of noise.

[0035] A fourth aspect of the present application provides an electronic device, including:

[0036] An audio acquisition module, used for acquiring first audio data;

[0037] a model determination module, configured to determine a target noise reduction model based on a target object representing an audio scene when the first audio data is obtained, wherein the target noise reduction model has multiple groups of noise reduction configurations, wherein the multiple groups of noise reduction configurations include at least one group of noise reduction configurations obtained based on an interactive manner provided to a user;

[0038] a configuration determination module, configured to determine a target noise reduction configuration, wherein the target noise reduction configuration belongs to a group of multiple noise reduction configurations;

[0039] The noise reduction processing module is used to control the target noise reduction model to perform noise reduction processing on the first audio data based on the target noise reduction configuration to generate second audio data. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0041] Figure 1 A flowchart of an audio processing method disclosed in an embodiment of the present application;

[0042] Figure 2 This is an example diagram of the interface display of the control disclosed in the embodiment of the present application;

[0043] Figure 3This is an example diagram of a display interface of another control disclosed in an embodiment of the present application;

[0044] Figure 4 A flowchart of another audio processing method disclosed in an embodiment of the present application;

[0045] Figure 5 A flowchart of another audio processing method disclosed in an embodiment of the present application;

[0046] Figure 6 A schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application;

[0047] Figure 7 A schematic diagram of the structure of another electronic device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] The embodiments of the present application can be applied to electronic devices. The present application does not limit the product form of the electronic device, which can include but is not limited to smart phones, tablet computers, wearable devices, personal computers (PCs), netbooks, etc., and can be selected according to application requirements.

[0050] Figure 1 This is a flow chart of an audio processing method disclosed in an embodiment of the present application. Figure 1 As shown, the audio processing method may include:

[0051] Step 101: Obtain audio data.

[0052] The audio data may be audio data in the video content or audio data that exists independently. In the present application, the audio data refers to audio data that already exists or has been stored in the electronic device, and the audio data may have been subjected to noise reduction processing by the corresponding noise reduction model during the acquisition process. The noise reduction model here refers to a universal noise reduction model, and will not perform targeted and differentiated processing on the audio data collected in different audio acquisition scenarios.

[0053] The audio data includes processed audio data processed by the aforementioned universal noise reduction model, or includes both the processed audio data and the original audio data that was originally collected and not processed in any way, or the audio data includes processed audio data and corresponding processing parameters. This application does not impose any fixed restrictions on this.

[0054] Step 102: Identify at least two types of noise contained in the audio data based on the target model, where the at least two types of noise include a first type of noise and a second type of noise, and the first type of noise is different from the second type of noise.

[0055] Among them, the target model can be a pre-trained model that can identify various types of noise present in audio data. A noise type may correspond to only one sound source, or to multiple sound sources at the same time. For example, in a natural environment scene, the sound of wind, as a separate sound source, is identified as a type of noise - wind noise; in an outdoor scene, the sounds of multiple sound sources such as car horns, conversations of pedestrians on the street, and hawking of vendors are uniformly defined as a type of noise - background noise. In addition, other types of noise, such as harmful noise, include harsh sounds such as chainsaws and building knocks; concert noise, including applause and conversations in the audience.

[0056] There is no fixed limit on the number of noise types contained in the audio data, which can be any type of sound other than the main sound contained in the audio data recognized by the target model. In theory, the noise types contained in the audio data recognized by the target model can be any number, including one category, but in the embodiment of the present application, the noise types recognized by the target model are limited to at least two categories in order to reflect that noise reduction can be configured separately for different types of noise.

[0057] Since the aforementioned processed audio data is audio data processed by a universal noise reduction model, some of the noise therein may have been suppressed to the point where it is difficult to accurately identify. Therefore, in this application, the audio data identified by the target model may be the original audio data, ensuring that all types of noise contained in the audio data can be identified.

[0058] Step 103: output a first control corresponding to the first type of noise and a second control corresponding to the second type of noise, wherein the first control is used to configure noise reduction for the first type of noise; and the second control is used to configure noise reduction for the second type of noise.

[0059] After identifying at least two types of noise, a control may be outputted for each type of noise, and each control is used to implement a separate noise reduction configuration for a certain type of noise. The configuration here includes but is not limited to the configuration of whether to enable noise reduction for the current type of noise. Figure 2This is an example of the interface display of the control disclosed in the embodiment of the present application, in which wind noise and background noise are enabled by default. Figure 2 Understand the relevant content.

[0060] It should be noted that the control in this application is not limited to a virtual object that can be triggered and controlled by the user directly or through an input device in the human-computer interaction interface, but can generally refer to a control that can provide an interactive basis for the user, so that the user can implement the noise reduction configuration of the corresponding type of noise. For example, the first control corresponding to the first type of noise and the second control corresponding to the second type of noise can only be a list of various types of noise output on the display screen. These lists are not operational and are only used to show what types of noise the audio data includes. The user can input which type of noise he wants to reduce through voice commands.

[0061] The method described in this embodiment can be a post-editing process for audio files generated by video or audio recording. Through this solution, an interactive method is provided for users, so that users can independently configure noise reduction for different types of noise in audio data based on their own needs or preferences, so as to finally obtain audio that meets the user's expectations.

[0062] The audio processing method described in this embodiment first identifies at least two types of noise contained in the audio data, and then can output a corresponding control for each type of noise, so that the user can use the control to independently configure noise reduction for each type of noise, thereby meeting the user's needs for personalized noise reduction processing of audio data.

[0063] In the above embodiment, the first control is used to configure the noise reduction for the first type of noise, which may include: the processing degree of noise reduction for the first type of noise; the second control is used to configure the noise reduction for the second type of noise, which may include: the processing degree of noise reduction for the second type of noise.

[0064] That is, for the noise reduction configuration of various types of noise, not only can you configure whether to enable noise reduction for a certain type of noise, but you can also further configure the noise reduction degree or noise reduction parameters for the type of noise that enables noise reduction. For example, the user can configure the first type of noise to be reduced by 50% through the first control, and the second type of noise to be reduced by 30% through the second control. This implementation allows users to configure noise reduction for various types of noise more freely. Figure 3 This is another example of a display interface of a control disclosed in an embodiment of the present application, in which a wind noise reduction ratio of 90% and a background noise reduction ratio of 50% are used as an example. Figure 3 Understand the relevant content.

[0065] Figure 4This is a flow chart of another audio processing method disclosed in an embodiment of the present application. Figure 4 As shown, based on the foregoing content, the audio processing method may include:

[0066] Step 401: Obtain audio data.

[0067] Step 402: Identify at least two types of noise contained in the audio data based on the target model, where the at least two types of noise include a first type of noise and a second type of noise, and the first type of noise is different from the second type of noise.

[0068] Step 403: output a first control corresponding to the first type of noise and a second control corresponding to the second type of noise, wherein the first control is used to configure noise reduction for the first type of noise; and the second control is used to configure noise reduction for the second type of noise.

[0069] Step 404: Obtain target configuration parameters, wherein the target configuration parameters are generated based on at least one control operation, and the at least one control includes one of the following: the first control; or the second control.

[0070] In the implementation, for the first control and the second control, the user can operate the first control alone to input the noise reduction configuration for the first type of noise corresponding to the first control and then apply it, or can operate the second control alone to input the noise reduction configuration for the second type of noise corresponding to the second control and then apply it, or can operate the two controls successively to input the noise reduction configuration for the first type of noise and the second type of noise and then apply them.

[0071] Step 405: In response to the target configuration parameters, the original data of the audio data is restored, the target configuration parameters are applied to the original data, and feedback audio data for feedback on the at least one control operation is output.

[0072] Here, restoring the original data of the audio data may be directly obtaining the original audio data, or restoring the original audio data based on the processed audio data and the corresponding processing parameters. Then, the target configuration parameters may be directly applied to the original data to obtain and output feedback audio data corresponding to the target configuration parameters, so that the user can perceive the audio effect of the feedback audio data obtained based on the configured target configuration parameters and determine whether it meets the user's expected processing effect.

[0073] This embodiment introduces the processing process of obtaining feedback audio data by implementing personalized noise reduction configuration based on user interaction, which is convenient for technicians in the field to better understand and implement the technical solution of this application.

[0074] In one implementation, the audio data is obtained by processing a target noise reduction model, the target noise reduction model has an original noise reduction configuration, and the target noise reduction model matches the scene in which the audio data is collected. Under this premise, the audio processing method may also include: determining a target noise reduction model corresponding to the audio data based on the audio data.

[0075] That is, multiple noise reduction models are pre-arranged in the electronic device, and different noise reduction models are used to match different audio acquisition scenarios. After obtaining the audio data, the noise reduction model that best matches the scene of the audio data can be matched from the preset multiple noise reduction models as the target noise reduction model through recognition processing of the audio data. The conditions for matching the target noise reduction model can be, but are not limited to, the audio data itself, and can also be other auxiliary content, such as a reference scene input by the user, other environmental data in the recording scene, etc.

[0076] The target noise reduction model is a noise reduction model that is determined to best match the scene in which the audio data is collected, but does not indicate that its default original noise reduction configuration is the optimal noise reduction configuration for processing the audio data. Therefore, after determining the target noise reduction model, the user can still input target configuration parameters for different types of noise in the audio data based on the first control and / or the second control.

[0077] Thus, the audio processing method may further include: obtaining a target configuration parameter, wherein the target configuration parameter is generated based on at least one control operation, and the at least one control includes any one of the following: the first control; or the second control. Based on the target configuration parameter, the original noise reduction configuration of the target noise reduction model of the audio data is adjusted and processed to obtain an item that matches the target configuration parameter, and the target noise reduction configuration used to characterize the user's expectation is obtained, so that the target noise reduction model responds based on the target noise reduction configuration when it is called.

[0078] The target noise reduction model includes multiple noise reduction configuration items, and the target configuration parameters may only include configuration parameters of some configuration items. After obtaining the target configuration parameters, the original noise reduction configuration of the target noise reduction model and the items that match the target configuration parameters can be adjusted according to the target configuration parameters; for the configuration items not involved in the target configuration parameters, the original configuration of the target noise reduction model is retained. For example, the target noise reduction model includes 5 noise reduction configuration items A, B, C, D, and E. The target configuration parameters input by the user based on the control include A', B', and C', involving the three configuration items A, B, and C. Then, A', B', and C' replace A, B, and C, and retain D and E. The final target noise reduction configuration is A', B', C', D, and E.

[0079] After obtaining the target noise reduction configuration, the corresponding noise reduction configuration can be saved in the target noise reduction model. In this way, if other audio data with the same collection scenario as the audio data appears later, the target noise reduction configuration can be directly called or switched to output the other audio data. The user does not need to repeat the noise reduction configuration for the audio data under the same audio collection scenario.

[0080] The audio processing scheme described in the embodiment of the present application can first determine the target noise reduction model that best matches the audio data acquisition scenario when multiple noise reduction models are pre-installed in the electronic device, and then adjust the original noise reduction configuration of the target noise reduction model based on the target configuration parameters input by the user through the control, so that the feedback audio data obtained by calling and processing the adjusted target noise reduction model is closer to the user's expectations.

[0081] Figure 5 This is a flowchart of another audio processing method disclosed in an embodiment of the present application. Figure 5 As shown, the audio processing method may include:

[0082] Step 501: Obtain first audio data.

[0083] Similarly, the first audio data may be audio data in the video content or independent audio data. The audio data may be audio data that already exists or has been stored in the electronic device, and the audio data may have been subjected to noise reduction processing by a corresponding noise reduction model during the collection process.

[0084] Step 502: Determine a target noise reduction model based on a target object that represents the audio scene when the first audio data is obtained, wherein the target noise reduction model has multiple groups of noise reduction configurations, and the multiple groups of noise reduction configurations include at least one group of noise reduction configurations obtained based on an interactive method provided to the user.

[0085] The target object may be the audio data itself, or may include data other than audio data, such as images, air pressure, ambient light, geographic location, etc. Such data other than audio data may be identified and obtained from the video file corresponding to the audio data, such as identifying the recording scene from the image, or the electronic device may automatically obtain the data through the corresponding function when collecting audio data / image data. For example, during the recording process, the electronic device may automatically detect the address location, air pressure and other data through the positioning device, or may detect the ambient light through the photosensitive element.

[0086] Based on the target object and the pre-trained recognition model, the target noise reduction model that best fits the audio acquisition scenario can be determined from the noise reduction models preset in the electronic device. In this embodiment, the target noise reduction model has been configured by the user at least once, and the relevant noise reduction configuration is saved, so the target noise reduction model includes multiple groups of noise reduction configurations, at least one of which is obtained based on the interaction method provided to the user. The interaction method here includes the controls described in the previous embodiment.

[0087] Step 503: Determine a target noise reduction configuration, where the target noise reduction configuration belongs to a group of multiple noise reduction configurations.

[0088] There are different implementations for determining the target noise reduction configuration from the target noise reduction model. For example, the target noise reduction configuration can be determined based on the priority of each group of noise reduction configurations, or based on the user's selection. For example, in the implementation of determining the target noise reduction configuration based on priority, if the configuration obtained based on the interactive method provided to the user has the highest priority among the multiple groups of noise reduction configurations, the noise reduction configuration input by the user will be directly determined as the target noise reduction configuration. In the implementation of determining the target noise reduction configuration based on the user's selection, the target noise reduction model will first output all noise reduction configurations, and the user will trigger the selection of the desired noise reduction configuration as the target noise reduction configuration.

[0089] The target noise reduction configuration may be an original noise reduction configuration of the target noise reduction model, or may be a noise reduction configuration previously input and saved by the user in an interactive manner. In this embodiment, multiple groups of noise reduction configurations in the target noise reduction model may be switched to meet different noise reduction requirements of the user.

[0090] Step 504: The target noise reduction model performs noise reduction processing on the first audio data based on the target noise reduction configuration to generate second audio data.

[0091] After the target noise reduction configuration is determined, the target noise reduction model performs noise reduction processing on the first audio data according to the determined target noise reduction configuration to obtain second audio data.

[0092] The audio processing method described in this embodiment can switch between different noise reduction configurations based on the set logic when the target noise reduction model has been configured, and determine the target noise reduction configuration from multiple groups of noise reduction configurations according to the set logic to perform noise reduction processing on the first audio data. This implementation provides users with more noise reduction options and can meet different noise reduction needs of users in different audio collection scenarios.

[0093] In one implementation, obtaining the target object of the audio data scene based on the characterization may include: capturing a target image based on an image acquisition device, wherein the image acquisition device captures the target image during the process of obtaining the audio data, and the target object is the target image; and determining a target noise reduction model based on the target image.

[0094] During the video recording process, the electronic device will collect audio data and image data at the same time, where the image data includes the target image, and based on the recognition and processing of the target image, the audio data scene of the first audio data can be determined. For example, by identifying and analyzing that the target image includes a stage, and the stage includes people (performers) and various musical instruments, it can be determined that the audio data scene of the first audio data is a concert scene, and the noise reduction model corresponding to the concert scene can be determined as the target noise reduction model.

[0095] The above content introduces the implementation of determining the target noise reduction model based on the processing of the target image synchronized with the audio data, which is convenient for technicians in the field to better understand and implement the technical solution of the present application.

[0096] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0097] The method is described in detail in the embodiments disclosed in the above-mentioned application. The method of the application can be implemented by various forms of devices. Therefore, the application also discloses a device, and a specific embodiment is given below for detailed description.

[0098] Figure 6 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application. Figure 6 As shown, the electronic device 60 may include:

[0099] The audio acquisition module 601 is used to obtain audio data.

[0100] The noise recognition module 602 is used to recognize at least two types of noise contained in the audio data based on the target model, where the at least two types of noise include a first type of noise and a second type of noise, and the first type of noise is different from the second type of noise.

[0101] The interactive processing module 603 is used to output a first control corresponding to the first type of noise and a second control corresponding to the second type of noise, wherein the first control is used to configure noise reduction for the first type of noise; and the second control is used to configure noise reduction for the second type of noise.

[0102] When the electronic device described in this embodiment performs noise reduction processing on the audio data existing in the device, it first identifies at least two types of noise contained in the audio data, and then can output a corresponding control for each type of noise, so that the user can use the control to independently configure noise reduction for each type of noise, thereby meeting the user's needs for personalized noise reduction processing of audio data.

[0103] In one implementation, the first control is used to configure noise reduction for the first type of noise, including: the processing degree of noise reduction for the first type of noise; the second control is used to configure noise reduction for the second type of noise, including: the processing degree of noise reduction for the second type of noise.

[0104] In one implementation, the device also includes: a parameter acquisition module, used to obtain target configuration parameters, wherein the target configuration parameters are generated based on at least one control operation, and the at least one control includes any one of the following: the first control; or, the second control; a noise reduction control module, used to respond to the target configuration parameters, restore the original data of the audio data, apply the target configuration parameters to the original data, and output feedback audio data for feedback on the at least one control operation.

[0105] In one implementation, the audio data is obtained by processing a target noise reduction model, the target noise reduction model has an original noise reduction configuration, and the target noise reduction model matches the scene in which the audio data is collected; the device may also include: a model determination module, used to determine the target noise reduction model corresponding to the audio data based on the audio data.

[0106] In one implementation, the device may also include: a parameter acquisition module, used to obtain target configuration parameters, wherein the target configuration parameters are generated based on at least one control operation, and the at least one control includes any one of the following: the first control; or, the second control; a noise reduction control module, used to adjust the original noise reduction configuration of the target noise reduction model of the audio data based on the target configuration parameters and obtain an item that matches the target configuration parameters, and obtain a target noise reduction configuration used to characterize the user's expectations, so that the target noise reduction model responds based on the target noise reduction configuration when called.

[0107] Figure 7 This is a schematic diagram of the structure of another electronic device disclosed in an embodiment of the present application. Figure 7 As shown, the electronic device 70 may include:

[0108] The audio acquisition module 701 is used to obtain first audio data.

[0109] The model determination module 702 is used to determine a target noise reduction model based on a target object that represents the audio scene when the first audio data is obtained, and the target noise reduction model has multiple groups of noise reduction configurations, and the multiple groups of noise reduction configurations include at least one group of noise reduction configurations obtained based on an interactive method provided to the user.

[0110] The configuration determination module 703 is used to determine a target noise reduction configuration, where the target noise reduction configuration belongs to a group of multiple noise reduction configurations.

[0111] The noise reduction processing module 704 is used to control the target noise reduction model to perform noise reduction processing on the first audio data based on the target noise reduction configuration to generate second audio data.

[0112] In the case where the target noise reduction model has been configured, the electronic device described in this embodiment can switch between different noise reduction configurations based on the set logic, and determine the target noise reduction configuration from multiple groups of noise reduction configurations according to the set logic to perform noise reduction processing on the first audio data. This implementation provides users with more noise reduction options and can meet different noise reduction needs of users in different audio collection scenarios.

[0113] In one implementation, the model determination module can be specifically used to: capture a target image based on an image acquisition device, wherein the image acquisition device captures the target image during the process of obtaining audio data, and the target object is the target image; and determine a target noise reduction model based on the target image.

[0114] In one implementation, the configuration obtained based on the interaction mode provided to the user has the highest priority among the multiple groups of noise reduction configurations.

[0115] The specific implementation of the above electronic device and the modules it contains, as well as other possible implementations can be found in the corresponding parts of the method embodiment, which will not be repeated again.

[0116] Any of the electronic devices described in the above embodiments includes a processor and a memory. The audio acquisition module, noise recognition module, interaction processing module, model determination module, configuration determination module, noise reduction processing module, etc. in the above embodiments are all stored in the memory as program modules, and the processor executes the above program modules stored in the memory to implement corresponding functions.

[0117] The processor includes a kernel, which retrieves the corresponding program module from the memory. One or more kernels can be set, and the processing of the access data can be realized by adjusting the kernel parameters.

[0118] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0119] In an exemplary embodiment, a computer-readable storage medium is also provided, which can be directly loaded into the internal memory of a computer and contains software code. After being loaded and executed by a computer, the computer program can implement the steps shown in any embodiment of the above audio processing method.

[0120] In an exemplary embodiment, a computer program product is also provided, which can be directly loaded into the internal memory of a computer and contains software codes. After being loaded and executed by a computer, the computer program can implement the steps shown in any embodiment of the audio processing method described above.

[0121] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0122] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0123] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0124] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An audio processing method, the method comprising: Get audio data; Identify at least two types of noise contained in the audio data based on the target model, the at least two types of noise include a first type of noise and a second type of noise, and the first type of noise is different from the second type of noise; A first control corresponding to the first type of noise and a second control corresponding to the second type of noise are output, wherein the first control is used to configure noise reduction for the first type of noise; and the second control is used to configure noise reduction for the second type of noise.

2. The audio processing method according to claim 1, The first control is used to configure noise reduction for the first type of noise, including: the degree of noise reduction for the first type of noise; The second control is used to configure the noise reduction for the second type of noise and includes: The degree of noise reduction for the second type of noise.

3. The audio processing method according to claim 2, further comprising: Obtaining a target configuration parameter, wherein the target configuration parameter is generated based on at least one control operation, and the at least one control includes any one of the following: the first control; or the second control; In response to the target configuration parameter, the original data of the audio data is restored, the target configuration parameter is applied to the original data, and feedback audio data for feedback on the at least one control operation is output.

4. The audio processing method according to claim 1, wherein the audio data is obtained by processing a target noise reduction model, the target noise reduction model has an original noise reduction configuration, and the target noise reduction model matches a scene in which the audio data is collected; The method further comprises: A target noise reduction model corresponding to the audio data is determined based on the audio data.

5. The audio processing method according to claim 2 or 4, further comprising: Obtaining a target configuration parameter, wherein the target configuration parameter is generated based on at least one control operation, and the at least one control includes any one of the following: the first control; or the second control; Based on the target configuration parameter adjustment processing, the original noise reduction configuration of the target noise reduction model of the audio data is obtained to match the target configuration parameters, and the target noise reduction configuration used to characterize the user's expectations is obtained, so that the target noise reduction model responds based on the target noise reduction configuration when called.

6. An audio processing method, the method comprising: obtaining first audio data; Determining a target noise reduction model based on a target object representing an audio scene when the first audio data is obtained, wherein the target noise reduction model has multiple groups of noise reduction configurations, and the multiple groups of noise reduction configurations include at least one group of noise reduction configurations obtained based on an interactive manner provided to a user; Determining a target noise reduction configuration, the target noise reduction configuration belonging to a group of multiple noise reduction configurations; The target noise reduction model performs noise reduction processing on the first audio data based on the target noise reduction configuration to generate second audio data.

7. The audio processing method according to claim 6, wherein the target object of the audio data scene is obtained based on the characterization, comprising: Capturing a target image based on an image acquisition device, wherein the image acquisition device captures the target image in the process of obtaining the audio data, and the target object is the target image; A target denoising model is determined based on the target image.

8. The audio processing method according to claim 6, wherein: The configuration obtained based on the interaction mode provided to the user has the highest priority among the multiple groups of noise reduction configurations.

9. An electronic device, comprising: An audio acquisition module, used for acquiring audio data; A noise recognition module, configured to recognize at least two types of noise contained in the audio data based on a target model, wherein the at least two types of noise include a first type of noise and a second type of noise, and the first type of noise is different from the second type of noise; An interactive processing module is used to output a first control corresponding to the first type of noise and a second control corresponding to the second type of noise, wherein the first control is used to configure noise reduction for the first type of noise; and the second control is used to configure noise reduction for the second type of noise.

10. An electronic device comprising: An audio acquisition module, used for acquiring first audio data; a model determination module, configured to determine a target noise reduction model based on a target object representing an audio scene when the first audio data is obtained, wherein the target noise reduction model has multiple groups of noise reduction configurations, wherein the multiple groups of noise reduction configurations include at least one group of noise reduction configurations obtained based on an interactive manner provided to a user; a configuration determination module, configured to determine a target noise reduction configuration, wherein the target noise reduction configuration belongs to a group of multiple noise reduction configurations; The noise reduction processing module is used to control the target noise reduction model to perform noise reduction processing on the first audio data based on the target noise reduction configuration to generate second audio data.

Images