A method, device, storage medium and electronic device for detecting environmental noise

Abstract

Some embodiments of the present application provide a method, apparatus, storage medium, and electronic device for detecting environmental noise. The method includes: processing the original audio in a target service environment to obtain processed audio; obtaining the signal-to-noise ratio of the processed audio and the original audio; comparing the signal-to-noise ratio with a signal-to-noise ratio threshold to obtain a noise detection result for the target service environment. Some embodiments of the present application can achieve rapid detection of environmental noise with high efficiency, thereby enabling users to carry out their business normally without being disturbed by environmental noise.

Description

Technical Field

[0001] This application relates to the technical field of noise detection. Specifically, it relates to a method, device, storage medium, and electronic device for detecting environmental noise. Background Art

[0002] With the development of Internet technology, the applications of artificial intelligence and big data have been popularized.

[0003] Currently, in a company, interviews are generally conducted with employees to understand their situations. With the popularization of interview robots or online applications, online communication has become the mainstream. To ensure the efficiency and effectiveness of online communication, it is necessary to detect the noise in the meeting environment before communication to reduce the impact of ambient noise on online communication. In the prior art, noise is generally detected by training a model. However, training a model requires a high time cost and difficult data collection. Effective data resources cannot be obtained when a project starts, which will reduce the detection efficiency and accuracy of environmental noise.

[0004] Therefore, how to provide a technical solution for an efficient method of detecting environmental noise has become an urgent technical problem to be solved. Summary of the Invention

[0005] Some embodiments of this application aim to provide a method, device, storage medium, and electronic device for detecting environmental noise. Through the technical solutions of the embodiments of this application, rapid detection of environmental noise can be achieved, confirmation of whether the meeting environment (i.e., the target business environment) meets the requirements can be made, with high efficiency and high accuracy, improving the user experience.

[0006] In a first aspect, some embodiments of this application provide a method for detecting environmental noise, including: processing the original audio in a target business environment to obtain processed audio; obtaining the signal-to-noise ratio of the processed audio and the original audio; comparing the signal-to-noise ratio with a signal-to-noise ratio threshold to obtain the noise detection result of the target business environment.

[0007] Some embodiments of this application process the original audio in a target business environment, then calculate the signal-to-noise ratio before and after processing, and further confirm the noise detection result through the signal-to-noise ratio. The embodiments of this application can achieve rapid detection of environmental noise, confirm whether the meeting environment (i.e., the target business environment) meets the requirements, with high efficiency and high accuracy, improving the user experience.

[0008] In some embodiments, processing the original audio in the target business environment to obtain the processed audio includes: in response to an operation instruction of a customer, turning on a microphone; receiving the original audio in the target business environment sent by the microphone; and performing noise reduction processing on the original audio through spectral subtraction to obtain the processed audio.

[0009] In some embodiments of the present application, by turning on the microphone to collect the original audio and then using spectral subtraction for processing, the time cost can be reduced, the cost of using the server can be reduced, and the efficiency is relatively high.

[0010] In some embodiments, receiving the original audio in the target business environment sent by the microphone includes: receiving the original audio collected by the microphone within a preset time period.

[0011] In some embodiments of the present application, by collecting the original audio within a preset time period, the detection of the environment can be realized before the meeting, which can ensure the effective progress of the meeting on time.

[0012] In some embodiments, comparing the signal-to-noise ratio with a signal-to-noise ratio threshold to obtain the noise detection result of the target business environment includes: if the signal-to-noise ratio is greater than the signal-to-noise ratio threshold, confirming that the noise detection result is passed; if the signal-to-noise ratio is not greater than the signal-to-noise ratio threshold, confirming that the noise detection result is not passed.

[0013] In some embodiments of the present application, through the relationship between the signal-to-noise ratio and the signal-to-noise ratio threshold, it can be confirmed whether the noise in the target business environment meets the requirements, and the accuracy is relatively high and the efficiency is relatively high.

[0014] In some embodiments, before comparing the signal-to-noise ratio with the signal-to-noise ratio threshold, the method further includes: obtaining multiple scene audio data in multiple business scenario environments; performing noise reduction processing on the multiple scene audio data through spectral subtraction to obtain multiple noise-reduced audio data; calculating the signal-to-noise ratio of the multiple noise-reduced audio data and the multiple scene audio data to obtain multiple audio signal-to-noise ratios; inputting the multiple noise-reduced audio data into a speech recognition model to obtain multiple audio recognition rates; selecting the maximum audio recognition rate from the multiple audio recognition rates, and searching for the audio signal-to-noise ratio corresponding to the maximum audio recognition rate from the multiple audio signal-to-noise ratios; and using the audio signal-to-noise ratio corresponding to the maximum audio recognition rate as the signal-to-noise ratio threshold.

[0015] In some embodiments of the present application, by processing and recognizing multiple scene audio data in multiple business scenario environments, multiple audio recognition rates are obtained. Then, based on the multiple audio recognition rates, the maximum value is selected, and further the signal-to-noise ratio threshold is obtained. The embodiments of the present application can select a signal-to-noise ratio threshold with relatively high accuracy, providing effective data support for detecting environmental noise.

[0016] In some embodiments, obtaining multiple scenario audio data in multiple service scenario environments includes: collecting original scenario audio in the multiple service scenario environments; and processing the original scenario audio in the multiple service scenario environments to obtain the multiple scenario audio data.

[0017] In some embodiments of the present application, by processing the collected original scenario audio to obtain multiple scenario audio data, audio data with better effects can be obtained at a lower cost.

[0018] In some embodiments, processing the original scenario audio in the multiple service scenario environments to obtain the multiple scenario audio data includes: removing the original scenario audio in the multiple service scenario environments whose audio duration does not reach a preset duration threshold to obtain the multiple scenario audio data.

[0019] In some embodiments of the present application, by performing a removal process on the original scenario audio, invalid data can be removed to ensure the validity and accuracy of the audio data.

[0020] In a second aspect, some embodiments of the present application provide a device for detecting environmental noise, including: an audio processing module for processing original audio in a target service environment to obtain processed audio; a data acquisition module for acquiring the signal-to-noise ratio of the processed audio and the original audio; and a result acquisition module for comparing the signal-to-noise ratio with a signal-to-noise ratio threshold to obtain a noise detection result of the target service environment.

[0021] In a third aspect, some embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method described in any embodiment of the first aspect can be implemented.

[0022] In a fourth aspect, some embodiments of the present application provide an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the method described in any embodiment of the first aspect can be implemented.

[0023] In a fifth aspect, some embodiments of the present application provide a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, the method described in any embodiment of the first aspect can be implemented. Description of the Drawings

[0024] To more clearly illustrate the technical solutions of some embodiments of the present application, the following will briefly introduce the drawings required for use in some embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0025] Figure 1 A system diagram for detecting environmental noise provided for some embodiments of the present application;

[0026] Figure 2 A flowchart of a method for obtaining a signal-to-noise ratio threshold provided for some embodiments of the present application;

[0027] Figure 3 A flowchart of one of the methods for detecting environmental noise provided for some embodiments of the present application;

[0028] Figure 4 A flowchart of another method for detecting environmental noise provided for some embodiments of the present application;

[0029] Figure 5 A block diagram of the device for detecting environmental noise provided for some embodiments of the present application;

[0030] Figure 6 A schematic diagram of an electronic device provided for some embodiments of the present application. Detailed implementation manners

[0031] The following will describe the technical solutions in some embodiments of the present application in conjunction with the drawings in some embodiments of the present application.

[0032] It should be noted that: Similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0033] In the related art, with the development of the Internet, the applications of artificial intelligence and big data have been popularized. For example, in the field of insurance business, an insurance company generally includes multiple subsidiaries. To comprehensively understand the situation of each company, the insurance company conducts online interviews with the employees of its subsidiaries, and thus interview robots have emerged. During the interview process, the interview robot needs to record the interview content in real time. However, considering that the ambient noise of meetings in different subsidiaries varies, it has a great impact on the speech recognition rate. Therefore, it is necessary to detect the ambient noise through the sound transmitted by the microphone before the meeting. Currently, most of the noise detection methods are based on deep learning methods, such as RNNoise, Sepformer, SDD-Net and other methods. Although these methods have good effects, the models are relatively complex and require high resource deployment for implementation; moreover, training the model takes a long time, and it is difficult to collect the data sets for corresponding scenarios. The small amount of data in the data set results in a low accuracy of the trained model. In practical applications, when a project is initially established, there are not many resources, and it is impossible to deploy a noise detection module on a GPU (Graphics Processing Unit) server. Customers need to wait for a long time when using it, which greatly reduces the user experience. Moreover, collecting the data related to training the model takes a lot of time and has a great impact on the progress of the project.

[0034] As can be seen from the above related art, the cost of detecting ambient noise in the prior art is relatively high, and the detection efficiency and accuracy cannot be guaranteed.

[0035] In view of this, some embodiments of the present application provide a method for detecting ambient noise. This method processes the original audio in the target business environment to obtain the processed audio, and then calculates the signal-to-noise ratio of the processed audio and the original audio, and obtains the noise detection result based on the signal-to-noise ratio and the signal-to-noise ratio threshold. Some embodiments of the present application can obtain the noise detection result by processing the original audio and calculating the signal-to-noise ratio, which greatly reduces the time cost and has a high detection accuracy. It can provide strong support for the meeting noise detection project when there is no large amount of training data or when the data is scarce, and reduces a large amount of cost.

[0036] The following Figure 1 exemplarily elaborates on the overall composition structure of a system for detecting ambient noise provided by some embodiments of the present application.

[0037] As Figure 1As shown, some embodiments of the present application provide a system for detecting environmental noise. The system for detecting environmental noise includes: a microphone 100 and a terminal 200. For example, before a meeting, a customer can operate on the terminal 200 to turn on the microphone 100. The microphone 100 can collect the original audio in the current target business environment and send it to the terminal 200. After receiving the original audio, the terminal 200 processes it to obtain the processed audio. Then, the terminal 200 solves the signal-to-noise ratio of the processed audio and the original audio and compares it with the signal-to-noise ratio threshold to obtain the noise detection result.

[0038] In some embodiments of the present application, the microphone 100 can be connected to the terminal 200 by wire or wirelessly. In some other embodiments of the present application, the microphone 100 can also be on the terminal 200. It should be understood that the embodiments of the present application are not limited thereto.

[0039] It can be understood that when detecting the noise of the target business environment before a meeting, it is first necessary to determine the signal-to-noise ratio threshold. The following will be combined with the attached Figure 2 Exemplarily illustrate the implementation process of obtaining the signal-to-noise ratio threshold executed by the terminal 200 provided by some embodiments of the present application.

[0040] Please refer to the attached Figure 2 , Figure 2 is a flowchart of the method for obtaining the signal-to-noise ratio threshold provided by some embodiments of the present application. The method for obtaining the signal-to-noise ratio threshold includes:

[0041] S210, obtain multiple scene audio data in multiple business scenario environments.

[0042] For example, in some embodiments of the present application, in order to adapt to the business environment scenarios in different meetings, it is necessary to obtain the audio data in multiple business environment scenarios.

[0043] In some embodiments of the present application, S210 may include: collecting the original scene audio in the multiple business scenario environments; processing the original scene audio in the multiple business scenario environments to obtain the multiple scene audio data.

[0044] For example, in some embodiments of the present application, the recording data of meetings in different scenarios are manually collected as the original scene data (as a specific example of the original scene audio), and each original scene data in the original scene data is numbered to obtain the original scene data ID (Identity document, unique code). Then, the original scene data is processed to obtain multiple scene audio data.

[0045] In some embodiments of the present application, S210 may include: removing the original scenario audio in the multiple business scenario environments where the audio duration does not reach the preset duration threshold to obtain the multiple scenario audio data.

[0046] For example, in some embodiments of the present application, the python scripting language is used to process the original scenario data, and the useless data with too short duration or poor speech fluency is filtered out.

[0047] S220, perform noise reduction processing on the multiple scenario audio data through spectral subtraction to obtain multiple noise-reduced audio data.

[0048] For example, in some embodiments of the present application, noise reduction processing is performed on the multiple collected scenario audio data through spectral subtraction, and the original scenario data ID is associated with the noise-reduced audio (as a specific example of the multiple noise-reduced audio data) one by one.

[0049] S230, calculate the signal-to-noise ratio of the multiple noise-reduced audio data and the multiple scenario audio data to obtain multiple audio signal-to-noise ratios.

[0050] For example, in some embodiments of the present application, the signal-to-noise ratio of the original scenario data and the noise-reduced audio is calculated through the signal-to-noise ratio calculation formula to obtain multiple audio signal-to-noise ratios. Among them, each audio signal-to-noise ratio is stored in a bound manner with the original scenario data ID.

[0051] S240, input the multiple noise-reduced audio data into a speech recognition model to obtain multiple audio recognition rates.

[0052] For example, in some embodiments of the present application, the audio noise-reduced through spectral subtraction is sent into an ASR model (as a specific example of the speech recognition model), and multiple ASR recognition rates (as a specific example of the multiple audio recognition rates) of all the noise-reduced audio are recorded. The audio with better effect is obtained through the ASR recognition rate.

[0053] S250, select the maximum audio recognition rate from the multiple audio recognition rates, and find the audio signal-to-noise ratio corresponding to the maximum audio recognition rate from the multiple audio signal-to-noise ratios.

[0054] For example, in some embodiments of the present application, the maximum value (as a specific example of the maximum audio recognition rate) is selected from the multiple ASR recognition rates. Then, based on the maximum value, the corresponding noise-reduced audio is first obtained, and finally the audio signal-to-noise ratio of the corresponding noise-reduced audio is found.

[0055] S260, use the audio signal-to-noise ratio corresponding to the maximum audio recognition rate as the signal-to-noise ratio threshold.

[0056] For example, in some embodiments of the present application, the audio signal-to-noise ratio of the denoised audio corresponding to the maximum value is used as the signal-to-noise ratio threshold and stored in the terminal 200.

[0057] The following combines the attached Figure 3 Exemplarily illustrate the specific process of detecting environmental noise executed by the terminal 200 provided by some embodiments of the present application.

[0058] Please refer to the attached Figure 3 , Figure 3 FIG. is a flowchart of a method for detecting environmental noise provided by some embodiments of the present application. The method for detecting environmental noise includes:

[0059] S310, process the original audio in the target service environment to obtain the processed audio.

[0060] For example, in some embodiments of the present application, before a meeting is held in a meeting room (a specific example of the target service environment), it is first necessary to confirm whether the noise in the target service environment meets the meeting requirements. Therefore, it is necessary to process the original audio.

[0061] In some embodiments of the present application, S310 may include: in response to an operation instruction of a customer, turn on the microphone; receive the original audio in the target service environment sent by the microphone; perform noise reduction processing on the original audio through spectral subtraction to obtain the processed audio.

[0062] For example, in some embodiments of the present application, the customer can operate on the terminal 200 to turn on the microphone 100 of the meeting. After the microphone 100 is turned on, it can collect the original audio in the current meeting room and send it to the terminal 200. After receiving the original audio, the terminal 200 performs noise reduction processing on it through spectral subtraction to obtain the processed audio.

[0063] In order to ensure the meeting effect, in some embodiments of the present application, S310 may include: receiving the original audio collected within a preset time period sent by the microphone.

[0064] For example, in some embodiments of the present application, 10 minutes before the start of the meeting (a specific example of the preset time period), the customer can first turn on the microphone 100.

[0065] S320, obtain the signal-to-noise ratio of the processed audio and the original audio.

[0066] For example, in some embodiments of the present application, the signal-to-noise ratio calculation formula is used to calculate the processed audio and the original audio to obtain the current signal-to-noise ratio.

[0067] S330, compare the signal-to-noise ratio with a signal-to-noise ratio threshold to obtain a noise detection result for the target service environment.

[0068] For example, in some embodiments of the present application, compare the current signal-to-noise ratio with the signal-to-noise ratio threshold stored in the terminal 200 to obtain a noise detection result for the meeting room.

[0069] In some embodiments of the present application, S330 may include: if the signal-to-noise ratio is greater than the signal-to-noise ratio threshold, confirm that the noise detection result is passed; if the signal-to-noise ratio is not greater than the signal-to-noise ratio threshold, confirm that the noise detection result is not passed.

[0070] For example, in some embodiments of the present application, if the signal-to-noise ratio is greater than the signal-to-noise ratio threshold, the noise detection result is passed. At this time, a voice prompt can be sent to the customer indicating that the meeting can continue. If the signal-to-noise ratio is not greater than the signal-to-noise ratio threshold, the noise detection result is not passed. At this time, the customer needs to be prompted that the noise in the current meeting room is too high and the meeting may not be suitable.

[0071] In some other embodiments of the present application, the customer can, according to the meeting requirements, continue to collect audio within a preset time period when the noise detection result is not passed, and detect the noise in the meeting room again to confirm the noise detection result.

[0072] Next, taking the interview robot as the terminal 200 as an example, the specific process of detecting environmental noise provided by some embodiments of the present application is described by way of example in combination with the attached Figure 4 Exemplarily elaborate on the specific process of detecting environmental noise provided by some embodiments of the present application.

[0073] Please refer to the attached Figure 4 , Figure 4 , which is a flowchart of a method for detecting environmental noise provided by some embodiments of the present application. It should be noted that the interview robot internally stores a signal-to-noise ratio threshold calculated through the method embodiments in Figure 2 .

[0074] Next, the specific process of detecting environmental noise is described by way of example.

[0075] S410, in response to an operation instruction from the customer, turn on the microphone.

[0076] For example, as a specific example of the present application, when an insurance company conducts an online interview with an employee of a subsidiary, the employee can enter the interview meeting room where the interview robot is located (as a specific example of the target service environment) 10 minutes in advance. Then the employee can perform a click operation on the interview robot to turn on the microphone carried by the interview robot itself.

[0077] S420, receive the original audio in the target service environment sent by the microphone.

[0078] For example, as a specific example of the present application, a microphone of an interview robot collects audio in an interview conference room (as a specific example of the original audio) and sends it to a processing module of the interview robot.

[0079] S430, perform noise reduction processing on the original audio through spectral subtraction to obtain processed audio.

[0080] For example, as a specific example of the present application, a processing module of an interview robot performs noise reduction processing on the audio through spectral subtraction to obtain noise-reduced audio (as a specific example of the processed audio).

[0081] S440, obtain the signal-to-noise ratio of the processed audio and the original audio.

[0082] For example, as a specific example of the present application, a processing module of an interview robot obtains the signal-to-noise ratio of the noise-reduced audio and the audio as 80 dB through a signal-to-noise ratio calculation formula.

[0083] S450, determine that the signal-to-noise ratio is greater than the signal-to-noise ratio threshold. If so, execute S460; otherwise, execute S470.

[0084] For example, as a specific example of the present application, the signal-to-noise ratio threshold is 70 dB. It can be seen from this that when the signal-to-noise ratio is 80 dB, it is greater than the signal-to-noise ratio threshold, and the noise detection result is passed at this time.

[0085] S460, play a first prompt voice.

[0086] For example, as a specific example of the present application, after an interview robot confirms that the noise detection result is passed, it sends a prompt voice to an employee to inform that the online interview will start soon.

[0087] S470, play a second prompt voice.

[0088] For example, as another specific example of the present application, after an interview robot confirms that the noise detection result is not passed, it sends a prompt voice to an employee to inform that the noise in the interview conference room is too large and not suitable for an online interview. The employee can schedule the interview at another time or wait for the noise in the interview conference room to be re-detected.

[0089] It can be seen from the above-mentioned embodiments of the present application that the present application applies spectral subtraction to the detection of noise in the conference room environment, performs noise reduction processing on the audio of multiple environmental scenes transmitted from the microphone, and then calculates the signal-to-noise ratio and then obtains the audio with better effect through the ASR recognition rate, and finally obtains the signal-to-noise ratio threshold of the signal-to-noise ratio in the conference room environment. If the signal-to-noise ratio threshold is lower than this, the background noise of the meeting is too loud. Moreover, when many projects are established, there is not much resource support. The present application can develop new businesses without sufficient data and GPU server deployment. Compared with the use of deep learning models, the present application has a faster response time and saves hardware and data resources, and has a better detection effect.

[0090] Please refer to Figure 5 , Figure 5 The block diagram of the device for detecting environmental noise provided by some embodiments of the present application is shown. It should be understood that the device for detecting environmental noise corresponds to the above method embodiment and can perform each step involved in the above method embodiment. The specific functions of the device for detecting environmental noise can be found in the description above. To avoid repetition, the detailed description is appropriately omitted here.

[0091] Figure 5 The device for detecting environmental noise includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the device for detecting environmental noise. The device for detecting environmental noise includes: an audio processing module 510, which is used to process the original audio in the target business environment and obtain the processed audio; a data acquisition module 520, which is used to obtain the signal-to-noise ratio of the processed audio to the original audio; and a result acquisition module 530, which is used to compare the signal-to-noise ratio with a signal-to-noise ratio threshold to obtain the noise detection result of the target business environment.

[0092] In some embodiments of the present application, the audio processing module 510 is used to turn on the microphone in response to a customer's operation instruction; receive the original audio in the target business environment sent by the microphone; and perform noise reduction processing on the original audio through spectral subtraction to obtain the processed audio.

[0093] In some embodiments of the present application, the audio processing module 510 is used to receive the original audio collected within a preset time period and sent by the microphone.

[0094] In some embodiments of the present application, the result acquisition module 530 is used to confirm that the noise detection result is passed if the signal-to-noise ratio is greater than the signal-to-noise ratio threshold; if the signal-to-noise ratio is not greater than the signal-to-noise ratio threshold, confirm that the noise detection result is failed.

[0095] In some embodiments of the present application, before the result acquisition module 530, the device for detecting environmental noise further includes: a threshold acquisition module (not shown in the figure), configured to acquire multiple scene audio data in multiple service scenario environments; perform noise reduction processing on the multiple scene audio data through spectral subtraction to obtain multiple denoised audio data; calculate the signal-to-noise ratios of the multiple denoised audio data and the multiple scene audio data to obtain multiple audio signal-to-noise ratios; input the multiple denoised audio data into a speech recognition model to obtain multiple audio recognition rates; select the maximum audio recognition rate from the multiple audio recognition rates, and find the audio signal-to-noise ratio corresponding to the maximum audio recognition rate from the multiple audio signal-to-noise ratios; use the audio signal-to-noise ratio corresponding to the maximum audio recognition rate as the signal-to-noise ratio threshold.

[0096] In some embodiments of the present application, the threshold acquisition module (not shown in the figure) is configured to collect the original scene audio in the multiple service scenario environments; process the original scene audio in the multiple service scenario environments to obtain the multiple scene audio data.

[0097] In some embodiments of the present application, the threshold acquisition module (not shown in the figure) is configured to remove the original scene audio in the multiple service scenario environments whose audio duration does not reach a preset duration threshold to obtain the multiple scene audio data.

[0098] Some embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the operations corresponding to any of the methods provided in the above embodiments can be implemented.

[0099] Some embodiments of the present application further provide a computer program product, the computer program product includes a computer program, wherein when the computer program is executed by a processor, the operations corresponding to any of the methods provided in the above embodiments can be implemented.

[0100] As Figure 6 As shown, some embodiments of the present application provide an electronic device 600, and the electronic device 600 includes: a memory 610, a processor 620, and a computer program stored on the memory 610 and executable on the processor 620. When the processor 620 reads the program from the memory 610 through a bus 630 and executes the program, the methods of any of the above embodiments can be implemented.

[0101] The processor 620 can process digital signals and can include various computing architectures. For example, a complex instruction set computer architecture, a reduced instruction set computer architecture, or an architecture that implements a combination of multiple instruction sets. In some examples, the processor 620 can be a microprocessor.

[0102] The memory 610 can be used to store instructions executed by the processor 620 or data related to the instruction execution process. These instructions and / or data can include code for implementing some or all of the functions of one or more modules described in the embodiments of the present application. The processor 620 in the embodiments of the present disclosure can be used to execute the instructions in the memory 610 to implement the method shown above. The memory 610 includes a dynamic random access memory, a static random access memory, a flash memory, an optical memory, or other memories well known to those skilled in the art.

[0103] The above are only the embodiments of the present application and are not used to limit the protection scope of the present application. For those skilled in the art, the present application can have various changes and modifications. 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. It should be noted that similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0104] As mentioned above, this is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0105] It should be noted that in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

Claims

1. A method for detecting environmental noise, characterized in that, Including: Performing noise reduction processing on the original audio in the target business environment to obtain the processed audio; Obtaining the signal-to-noise ratio of the processed audio and the original audio; Comparing the signal-to-noise ratio with a signal-to-noise ratio threshold to obtain the noise detection result of the target business environment; Before comparing the signal-to-noise ratio with the signal-to-noise ratio threshold, the method further includes: Obtaining multiple scene audio data in multiple business scenario environments; performing noise reduction processing on the multiple scene audio data through spectral subtraction to obtain multiple denoised audio data; calculating the signal-to-noise ratios of the multiple denoised audio data and the multiple scene audio data to obtain multiple audio signal-to-noise ratios; inputting the multiple denoised audio data into a speech recognition model to obtain multiple audio recognition rates; selecting the maximum audio recognition rate from the multiple audio recognition rates, and searching for the audio signal-to-noise ratio corresponding to the maximum audio recognition rate from the multiple audio signal-to-noise ratios; using the audio signal-to-noise ratio corresponding to the maximum audio recognition rate as the signal-to-noise ratio threshold; The comparing the signal-to-noise ratio with the signal-to-noise ratio threshold to obtain the noise detection result of the target business environment includes: if the signal-to-noise ratio is greater than the signal-to-noise ratio threshold, confirming that the noise detection result is passed; if the signal-to-noise ratio is not greater than the signal-to-noise ratio threshold, confirming that the noise detection result is not passed.

2. The method according to claim 1, characterized in that, The performing noise reduction processing on the original audio in the target business environment to obtain the processed audio includes: Responding to the operation instruction of the customer to turn on the microphone; Receiving the original audio in the target business environment sent by the microphone; Performing noise reduction processing on the original audio through spectral subtraction to obtain the processed audio.

3. The method according to claim 2, characterized in that, The receiving the original audio in the target business environment sent by the microphone includes: Receiving the original audio collected by the microphone within a preset time period.

4. The method according to claim 1, characterized in that, The obtaining multiple scene audio data in multiple business scenario environments includes: Collecting the original scene audio in the multiple business scenario environments; Processing the original scene audio in the multiple business scenario environments to obtain the multiple scene audio data.

5. The method according to claim 4, characterized in that, The processing the original scene audio in the multiple business scenario environments to obtain the multiple scene audio data includes: Removing the original scene audio in the multiple business scenario environments whose audio duration does not reach the preset duration threshold to obtain the multiple scene audio data.

6. A device for detecting environmental noise, characterized in that, The device is used to execute the method as described in claim 1, including: An audio processing module, configured to perform noise reduction processing on the original audio in the target business environment to obtain the processed audio; A data acquisition module, configured to obtain the signal-to-noise ratio of the processed audio and the original audio; A result acquisition module, configured to compare the signal-to-noise ratio with a signal-to-noise ratio threshold to obtain the noise detection result of the target business environment.

7. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, wherein the computer program, when run by a processor, executes the method as described in any one of claims 1-5.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and running on the processor. Wherein, when the computer program is run by the processor, it executes the method according to any one of claims 1-5.

Images