Audio noise suppression evaluation method, device, storage medium, and system

Abstract

The application discloses an audio noise suppression evaluation method and device, a storage medium and a system. The method comprises the following steps: generating a third audio by using a first audio and a second audio, wherein the first audio is an original audio, the second audio is a characteristic audio with a preset frequency and amplitude, and the third audio is a target audio to be evaluated; recording the third audio by using a scheduling system to obtain a fourth audio, wherein the scheduling system is used for automatically controlling the audio recording process in the network live broadcast; and performing noise suppression evaluation based on the third audio and the fourth audio to obtain an evaluation result. The application solves the technical problem that the operation process of audio noise suppression evaluation is complex in the related art, resulting in low evaluation efficiency and high evaluation cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular, to an audio noise suppression evaluation method, device, storage medium and system. BACKGROUND

[0002] With the wide rise of live streaming, more and more users watch live streaming, and audio and video quality plays a crucial role in retaining users. Audio quality evaluation generally includes delay, lag, noise, echo, clarity, objective quality, and gain size. In some objective environments, anchors will live stream in noisy scenes, such as outdoor scenes, but the noise in the scene often makes it difficult for users to hear the anchor's voice. Noise suppression needs to eliminate the objective environmental sound during the streaming process and try to clearly retain the anchor's voice to improve the effect of noise elimination.

[0003] In related technologies, there are two main methods for audio noise evaluation: one is based on professional audio equipment, such as a digital speech level analyzer (DSLA), which connects the anchor streaming end and the playback end to the two sides of the DSLA, then simulates the live streaming scene, and obtains the noise suppression result. However, such audio equipment is often expensive and complex to operate. Another method is to use algorithms to evaluate the effect of automatic noise suppression (ANS) before and after noise reduction at the streaming end. However, this method is highly invasive and cannot be quickly used on other applications, and the cost is high.

[0004] At present, there is no effective solution to the above problems. SUMMARY

[0005] The embodiments of the present application provide an audio noise suppression evaluation method, device, storage medium and system to at least solve the technical problems of low evaluation efficiency and high evaluation cost in related technologies due to the complex operation process of audio noise suppression evaluation.

[0006] According to an aspect of the embodiments of the present application, an audio noise suppression evaluation method is provided, including: generating a third audio by using a first audio and a second audio, wherein the first audio is an original audio, the second audio is a characteristic audio with a preset frequency and amplitude, and the third audio is a target audio to be evaluated; recording the third audio by using a scheduling system to obtain a fourth audio, wherein the scheduling system is used for automatically controlling the audio recording process in network live streaming; and performing noise suppression evaluation based on the third audio and the fourth audio to obtain an evaluation result.

[0007] According to another aspect of the embodiments of the present application, there is also provided an audio noise suppression evaluation device, comprising: a generating module configured to generate a third audio by using a first audio and a second audio, wherein the first audio is an original audio, the second audio is a characteristic audio with preset frequency and amplitude, and the third audio is a target audio to be evaluated; a recording module configured to record the third audio by using a scheduling system to obtain a fourth audio, wherein the scheduling system is configured to automatically control an audio recording process in a network live broadcast; and an evaluation module configured to perform noise suppression evaluation based on the third audio and the fourth audio to obtain an evaluation result.

[0008] According to another aspect of the embodiments of the present application, there is also provided a storage medium comprising a stored program, wherein the program, when executed, controls a device in which the storage medium is located to perform any one of the audio noise suppression evaluation methods described above.

[0009] According to another aspect of the embodiments of the present application, there is also provided an audio noise suppression evaluation system, comprising: a processor; and a memory connected to the processor and configured to provide the processor with instructions to process the following processing steps: generating a third audio by using a first audio and a second audio, wherein the first audio is an original audio, the second audio is a characteristic audio with preset frequency and amplitude, and the third audio is a target audio to be evaluated; recording the third audio by using a scheduling system to obtain a fourth audio, wherein the scheduling system is configured to automatically control an audio recording process in a network live broadcast; and performing noise suppression evaluation based on the third audio and the fourth audio to obtain an evaluation result.

[0010] In the embodiments of the present application, the third audio is generated by using the first audio and the second audio, the first audio is an original audio, the second audio is a characteristic audio with preset frequency and amplitude, and the third audio is a target audio to be evaluated, and then the third audio is recorded by using a scheduling system to obtain a fourth audio, the scheduling system is configured to automatically control an audio recording process in a network live broadcast, and finally noise suppression evaluation is performed based on the third audio and the fourth audio to obtain an evaluation result.

[0011] It is easy to note that, according to the embodiments of the present application, the target audio to be evaluated can be generated by using the original audio and the characteristic audio with preset frequency and amplitude, and then the target audio is recorded by using the scheduling system, and noise suppression evaluation is performed on the audio obtained after recording to obtain an evaluation result.

[0012] Therefore, the embodiment of the present application achieves the purpose of quickly evaluating the noise suppression of the audio, thereby simplifying the operation process of the noise suppression evaluation of the audio, improving the evaluation efficiency, and reducing the evaluation cost, thereby solving the technical problems of low evaluation efficiency and high evaluation cost caused by the complex operation process of the noise suppression evaluation of the audio in the related art. BRIEF DESCRIPTION OF DRAWINGS

[0013] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and together with the description serve to explain the present application. In the drawings:

[0014] Figure 1 A hardware structure block diagram of a computer terminal (or a mobile device) for implementing the audio noise suppression evaluation method is shown;

[0015] Figure 2 A flowchart of an audio noise suppression evaluation method according to an embodiment of the present application is shown;

[0016] Figure 3 A schematic diagram of an interframe processing according to an embodiment of the present application is shown;

[0017] Figure 4 A frequency spectrum diagram of a third audio according to an embodiment of the present application is shown;

[0018] Figure 5 A process schematic diagram of pushing a stream to a cloud server according to an embodiment of the present application is shown;

[0019] Figure 6 A schematic diagram of an audio noise suppression evaluation method according to an embodiment of the present application is shown;

[0020] Figure 7 A structural schematic diagram of an audio noise suppression evaluation device according to an embodiment of the present application is shown;

[0021] Figure 8 A structural block diagram of another computer terminal according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor should fall within the protection scope of the present application.

[0023] It should be noted that the terms "first", "second", and the like in the description and claims of the application and the above drawings are used to distinguish similar objects and are not necessarily used to describe a particular sequential or chronological order. It should be understood that the data thus used can be interchanged, where appropriate, so that the embodiments of the application described herein can be carried out in other than the order shown or described herein. Furthermore, the terms "comprise" and "have", and any variations thereof, are intended to cover non-exclusive inclusion, for example, processes, methods, systems, products, or devices that include a list of steps or units not necessarily limited to those clearly listed, but can include other steps or units not clearly listed or inherent to such processes, methods, products, or devices.

[0024] First, some of the nouns or terms that appear in the description of the embodiments of the application are applicable to the following explanations:

[0025] Audio noise suppression: refers to the separation of human voice and non-human voice in audio, and related processing is performed to eliminate background noise as much as possible, and the remaining human voice is left.

[0026] Robotic process automation (RPA): Robotic process automation is a new type of technical concept that allows software robots to simulate and execute predetermined business processes based on certain rules of interaction. RPA robots can operate various applications such as browsers, Office software, programs written in Java / .net languages, enterprise resource planning (ERP) software (SAP / Oracle), etc. like humans.

[0027] Embodiment 1

[0028] According to the embodiments of the application, an audio noise suppression evaluation method embodiment is also provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0029] The method embodiment provided by the embodiment of the application can be executed in a mobile terminal, a computer terminal, or a similar computing device. Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing an audio noise suppression evaluation method is shown. As Figure 1As shown, the computer terminal 10 (or mobile device 10) can include one or more processors 102 (the processor 102 can include, but not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it can also include a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which can be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. Those skilled in the art can understand that Figure 1 The structure shown is only schematic, which does not limit the structure of the above-mentioned electronic device. For example, the computer terminal 10 can include more or fewer components than those shown in Figure 1 or have a different configuration than that shown in Figure 1 .

[0030] It should be noted that the one or more processors 102 and / or other data processing circuits described above can be generally referred to herein as "data processing circuits". The data processing circuits can be embodied in whole or in part as software, hardware, firmware or any other combination. In addition, the data processing circuits can be a single independent processing module, or any one of the other elements incorporated into the computer terminal 10 (or mobile device) in whole or in part. As referred to in the embodiments of the present application, the data processing circuit is a processor control (for example, selection of a variable resistance terminal path connected to an interface).

[0031] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage means corresponding to the audio noise suppression evaluation method in the embodiments of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implements the above-mentioned audio noise suppression evaluation method. The memory 104 can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 can further include a memory remotely disposed with respect to the processor 102, which can be connected to the computer terminal 10 through a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0032] The transmission device 106 is configured to receive or send data via a network. The network can include, for example, a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network interface controller (NIC) that can connect to other network devices through a base station to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module that is configured to communicate with the Internet wirelessly.

[0033] The display can be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0034] It is noted that, in some alternative embodiments, the above-mentioned Figure 1 The computer device (or mobile device) can include hardware elements (including circuitry), software elements (including computer code stored on a computer readable medium), or a combination of both hardware and software elements. It should be noted that Figure 1 is merely one example of a particular implementation and is intended to illustrate the types of components that can be present in the above-mentioned computer device (or mobile device).

[0035] In the above-mentioned operating environment, the present application provides an audio noise suppression evaluation method as shown in the accompanying drawings. Figure 2 The audio noise suppression evaluation method includes the following steps. Figure 2 is a flowchart of an audio noise suppression evaluation method according to an embodiment of the present application, the audio noise suppression evaluation method includes the following steps. Figure 2

[0036] In step S21, a third audio is generated using a first audio and a second audio, wherein the first audio is an original audio, the second audio is a characteristic audio with a preset frequency and amplitude, and the third audio is a target audio to be evaluated.

[0037] The first audio is a playable audio that meets the ITU P.863 standard, the length of the second audio is 0.5s, and the frequency and amplitude of the second audio are preset values.

[0038] Optionally, the third audio is generated by performing frame interpolation processing on the first audio and the second audio.

[0039] Specifically, the implementation process of generating the third audio using the first audio and the second audio can refer to the further introduction of the embodiments of the present application, and will not be described here.

[0040] ​In step S22, a third audio is recorded by using a scheduling system to obtain a fourth audio, wherein the scheduling system is used for automatically controlling an audio recording process in the network live broadcast.

[0041] In step S23, noise suppression evaluation is performed based on the third audio and the fourth audio to obtain an evaluation result.

[0042] Specifically, the implementation process of performing noise suppression evaluation based on the third audio and the fourth audio to obtain an evaluation result can refer to the further introduction of the embodiments of the present application, and will not be described here.

[0043] In the embodiments of the present application, the third audio is generated by using the first audio and the second audio, the first audio is the original audio, the second audio is the characteristic audio with a preset frequency and amplitude, and the third audio is the target audio to be evaluated. Then, the third audio is recorded by using the scheduling system to obtain the fourth audio, the scheduling system is used for automatically controlling the audio recording process in the network live broadcast, and finally, noise suppression evaluation is performed based on the third audio and the fourth audio to obtain an evaluation result.

[0044] It is easy to note that, by the embodiments of the present application, the target audio to be evaluated can be generated by using the original audio and the characteristic audio with a preset frequency and amplitude, and then the target audio is recorded by using the scheduling system, and noise suppression evaluation is performed on the recorded audio to obtain an evaluation result.

[0045] Therefore, the embodiments of the present application achieve the purpose of quickly performing noise suppression evaluation on the audio, thereby simplifying the operation process of audio noise suppression evaluation, improving the evaluation efficiency and reducing the evaluation cost, and further solving the technical problems of low evaluation efficiency and high evaluation cost caused by the complex operation process of audio noise suppression evaluation in the related art.

[0046] The audio noise suppression evaluation method provided by the embodiments of the present application can be applied to the statistics of the audio noise suppression effect of various live products, and can simply and quickly obtain accurate audio noise suppression evaluation effect.

[0047] In an optional embodiment, in step S21, generating the third audio by using the first audio and the second audio includes:

[0048] In step S211, the first audio is obtained, wherein the first audio includes at least one type of pure noise audio and at least one type of fitting audio, and the at least one type of fitting audio is obtained by fitting a preset type of audio and at least one type of pure noise audio according to different signal-to-noise ratios.

[0049] The aforementioned at least one type of pure noise audio includes white noise, pink noise, and real-world scene noise. White noise refers to noise with a constant power spectral density across the entire frequency domain; pink noise has equal intensity at each octave. At least one type of pure noise audio is used to evaluate the effectiveness of noise cancellation.

[0050] The aforementioned preset audio types are speech audio with different signal-to-noise ratios (SNR). At least one type of fitted audio is obtained by fitting the speech audio with at least one type of pure noise audio at different SNRs. For example, if the preset audio type is SNR0 or SNR6, the first fitted audio is obtained by fitting the speech audio with white noise; the second fitted audio is obtained by fitting the speech audio with white noise; the third fitted audio is obtained by fitting the speech audio with pink noise; the fourth fitted audio is obtained by fitting the speech audio with pink noise; the fifth fitted audio is obtained by fitting the speech audio with real-world scene noise; and the sixth fitted audio is obtained by fitting the speech audio with real-world scene noise.

[0051] Step S212: Insert the second audio at a preset position in the first audio to generate the third audio.

[0052] Specifically, the second audio is inserted at the beginning of the first audio to generate the third audio.

[0053] Figure 3 This is a schematic diagram of a frame interpolation process according to an embodiment of the present invention. Figure 4 This is a spectrum diagram of a third audio signal according to an embodiment of the present invention, such as... Figure 3 As shown, a second audio segment is inserted between each audio segment in the first audio, generating an audio like this. Figure 4 The third audio is shown. The second audio is 0.5s long and has a frequency of 1Hz, which is a preset value.

[0054] Based on the above steps S211 to S212, by acquiring the first audio and then inserting the second audio at a preset position in the first audio, the target audio to be evaluated is quickly generated to obtain feature material for audio noise suppression evaluation.

[0055] In one optional embodiment, the audio noise suppression evaluation method further includes:

[0056] Step S213: The scheduling system is used to schedule the first terminal to play the third audio, which is input to the sound card through the audio cable and then input to the second terminal through the sound card;

[0057] Specifically, the first terminal is a personal computer (PC) device, and the second terminal can be a mobile terminal device such as a mobile phone or a tablet computer. The second terminal is a push streaming terminal device.

[0058] For example, the RPA is used to trigger the PC device to automatically play the third audio by using the scheduling system. The third audio is input to the sound card through the 3.5 mm audio cable, and is output to the socket of the second terminal through the Lightning adapter, and is input to the push streaming terminal as the input of the second terminal.

[0059] In step S214, the scheduling system is used to schedule the second terminal to push the third audio to the cloud server.

[0060] Specifically, Figure 5 is a process diagram for pushing to the cloud server according to an embodiment of the present application, as Figure 5 shown, the scheduling system is used to start the automatic script of the second terminal to push the third audio to the cloud server.

[0061] Based on the above steps S213 to S214, the scheduling system is used to schedule the first terminal to play the third audio, which is input to the sound card through the audio cable, and is input to the second terminal through the sound card. Then, the scheduling system is used to schedule the second terminal to push the third audio to the cloud server, which can automatically realize the pushing of the third audio, thereby simplifying the operation process of the audio pushing and further improving the pushing efficiency.

[0062] In an optional embodiment, in step S22, the scheduling system is used to record the third audio to obtain a fourth audio, including: the scheduling system is used to schedule the third terminal to pull the third audio from the cloud server, and the third audio is recorded by using a preset recording parameter to obtain the fourth audio.

[0063] The third terminal can be a mobile terminal device such as a mobile phone or a tablet computer. The third terminal is a playback terminal device, and the audio recording application software is installed in the third terminal. For example, when the playback terminal device is an IOS operating system, the audio recording application software developed based on the replaykit framework can be installed. When the playback terminal device is an Android operating system, the system built-in audio recording application software can be used.

[0064] The preset recording parameter includes a recording sampling rate, a sound channel, a bit depth, etc.

[0065] Specifically, the scheduling system is used to schedule the third terminal to pull the third audio from the cloud server, and the audio recording application software is used to record the third audio at a recording sampling rate of 48000 Hz, a sound channel of single sound channel, and a bit depth of 16 to obtain the fourth audio.

[0066] The noise suppression evaluation can be triggered by one key. Taking the audio noise suppression evaluation process of the live product as an example, the dispatching system triggers the PC automation to play the third audio, starts the push streaming end client automation script to push stream, after the push streaming succeeds, the dispatching playback end automation script enters the push streaming live room, and finally the audio internal recording software is started to record the third audio to obtain the fourth audio.

[0067] In an optional embodiment, the recording duration of the fourth audio is determined by the preset duration of the third audio.

[0068] For example, the recording duration of the fourth audio is twice the preset duration of the third audio, so that complete recording of the third audio can be ensured.

[0069] In an optional embodiment, in step S23, the noise suppression evaluation is performed based on the third audio and the fourth audio, and the evaluation result includes:

[0070] In step S231, at least one type of pure noise audio and at least one type of fitting audio are parsed from the fourth audio.

[0071] Specifically, the implementation process of parsing at least one type of pure noise audio and at least one type of fitting audio from the fourth audio can be further introduced in the following embodiments, and will not be described here.

[0072] In step S232, a target difference curve is obtained by using at least one type of pure noise audio and the third audio, and a comparison analysis result is obtained by using at least one type of fitting audio and the third audio, wherein the target difference curve is used to find a noise reduction convergence point, and the comparison analysis result is used to determine the damage degree of at least one type of fitting audio.

[0073] Specifically, the implementation process of obtaining the target difference curve by using at least one type of pure noise audio and the third audio can be further introduced in the following embodiments, and will not be described here.

[0074] In step S233, noise suppression evaluation is performed on at least one type of pure noise audio based on the target difference curve, and noise suppression evaluation is performed on at least one type of fitting audio based on the comparison analysis result, to obtain the evaluation result.

[0075] Specifically, a first time point at which a target difference curve continuously decreases to a preset threshold amplitude is found on the target difference curve, and is recorded as a noise reduction convergence point. When the noise reduction convergence point exists, it is determined that the noise suppression algorithm can continuously reduce at least one type of pure noise audio to a specific level, and the noise reduction effect is better. When the noise reduction convergence point does not exist, it is determined that the processing result of the noise suppression algorithm on the at least one type of pure noise audio does not converge, and the noise reduction effect is poorer. When it is determined that the noise reduction convergence point exists on the target difference curve, the convergence time and the average noise reduction amplitude are obtained.

[0076] Specifically, the perceptual evaluation of speech quality (PESQ) and the short-time objective intelligibility (STOI) are used to compare and analyze the at least one type of fitted audio and the third audio, and a comparison result is obtained to determine the damage degree of the at least one type of fitted audio.

[0077] PESQ and STOI are two different active objective evaluation algorithms of audio, which can obtain a comparison result according to the at least one type of fitted audio and the third audio. If the score of the comparison result is higher, it is determined that the at least one type of fitted audio in the third audio is closer to the at least one type of fitted audio in the fourth audio, the damage degree of the noise suppression algorithm on the at least one type of fitted audio is smaller, and the speech information in the at least one type of fitted audio can be preserved as much as possible; if the score of the comparison result is lower, it is determined that the at least one type of fitted audio in the third audio is more different from the at least one type of fitted audio in the fourth audio, the damage degree of the noise suppression algorithm on the at least one type of fitted audio is greater, and the speech information in the at least one type of fitted audio is more likely to be lost.

[0078] Based on steps S231 to S233, by analyzing the at least one type of pure noise audio and the at least one type of fitted audio from the fourth audio, then obtaining the target difference curve by using the at least one type of pure noise audio and the third audio, and obtaining the comparison result by using the at least one type of fitted audio and the third audio, finally evaluating the noise suppression of the at least one type of pure noise audio based on the target difference curve, and evaluating the noise suppression of the at least one type of fitted audio based on the comparison result, the noise suppression evaluation result can be quickly and conveniently obtained.

[0079] In an optional embodiment, in step S231, analyzing the at least one type of pure noise audio and the at least one type of fitted audio from the fourth audio includes:

[0080] Step S2311, frame and frequency calculation are performed on the fourth audio to determine the insertion position of the second audio.

[0081] Specifically, frame and frequency calculation are performed on the fourth audio to find the starting position of the second audio in the fourth audio, and then the insertion position of the second audio is determined.

[0082] Step S2312, the recorded audio segment corresponding to the first audio is parsed from the fourth audio by using the insertion position of the second audio.

[0083] Step S2313, at least one type of pure noise audio and at least one type of fitting audio are obtained from the recorded audio segment.

[0084] Based on the above steps S2311 to S2313, by performing frame and frequency calculation on the fourth audio to determine the insertion position of the second audio, and then parsing the recorded audio segment corresponding to the first audio from the fourth audio by using the insertion position of the second audio, and finally obtaining at least one type of pure noise audio and at least one type of fitting audio from the recorded audio segment, at least one type of pure noise audio and at least one type of fitting audio can be quickly parsed from the fourth audio.

[0085] In an optional embodiment, in step S232, obtaining the target difference curve by using at least one type of pure noise audio and the third audio includes:

[0086] Step S2321, a first curve and a second curve are obtained, wherein the first curve is a smooth amplitude reduction curve corresponding to at least one type of pure noise audio, and the second curve is a smooth amplitude reduction curve corresponding to the third audio.

[0087] Specifically, the first curve includes smooth root mean square (RMS) data corresponding to at least one type of pure noise audio in the fourth audio, and the second curve includes smooth RMS data corresponding to at least one type of pure noise audio in the third audio.

[0088] Step S2322, a difference between the first curve and the second curve is calculated to obtain the target difference curve.

[0089] Based on the above steps S2321 to S2322, by obtaining the first curve and the second curve, and then calculating the difference between the first curve and the second curve, the target difference curve can be obtained, which can be used to quickly evaluate the convergence of noise processing.

[0090] Figure 6 is a schematic diagram of an audio noise suppression evaluation method according to an embodiment of the present application, as shown in Figure 6As shown, the audio noise suppression evaluation method is mainly realized through three parts: feature material production, audio topology building, and audio noise suppression effect calculation.

[0091] In the feature material production, a third audio is generated using a first audio and a second audio, the first audio is the original audio, the second audio is a feature audio with a preset frequency and amplitude, and the third audio is the target audio to be evaluated.

[0092] In the audio topology building, a PC device, a sound card, a Lightning adapter, and several 3.5mm audio cables are included, and an internal recording software is installed on the playback device. The scheduling system can perform PC automation task scheduling, client automation task scheduling, and result feedback and display. The scheduling system is used to schedule the PC device to play the third audio, which is input to the sound card through the audio cable, and then input to the streaming end through the sound card. The scheduling system is used to schedule the second terminal to push the third audio to the cloud server. The scheduling system is used to schedule the third terminal to pull the third audio from the cloud server, and record the third audio using preset recording parameters to obtain the fourth audio.

[0093] In the audio noise suppression effect calculation, at least one type of pure noise audio and at least one type of fitting audio are obtained from the fourth audio; a target difference curve is obtained using the at least one type of pure noise audio and the third audio, and a comparative analysis result is obtained using the at least one type of fitting audio and the third audio, wherein the target difference curve is used to find the noise reduction convergence point, and the comparative analysis result is used to determine the damage degree of the at least one type of fitting audio; the at least one type of pure noise audio is evaluated based on the target difference curve, and the at least one type of fitting audio is evaluated based on the comparative analysis result, to obtain the evaluation result. By combining the PC automation framework, the client automation framework, and the self-developed audio internal recording software and overall scheduling system, the evaluation result of audio noise suppression can be obtained after one-key start and running under the condition of fully covering different noise scenes.

[0094] The flat audio noise suppression evaluation method provided in the embodiments of the present application can support the statistics of audio noise of any application program in a live scene, and is non-intrusive and simple to operate. Although the statistics based on the professional hardware device in the related art is accurate, the device is usually expensive and has a high cost. The embodiments of the present application use a sound card, combine the current automatic tool, the self-developed internal recording tool and the simple scheduling framework, and can perform one-key audio noise suppression effect evaluation. Therefore, the audio noise suppression evaluation method provided in the embodiments of the present application achieves the purpose of quickly evaluating the noise suppression of audio, thereby achieving the technical effects of simplifying the operation process of audio noise suppression evaluation, improving the evaluation efficiency and reducing the evaluation cost, and further solving the technical problems of low evaluation efficiency and high evaluation cost caused by the complex operation process of audio noise suppression evaluation in the related art.

[0095] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the action sequence described, because according to the present application, certain steps can be performed in other sequences or at the same time. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0096] From the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software and the necessary general hardware platform, and of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, or optical disc), and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device) to execute the method described in each embodiment of the present application.

[0097] Embodiment 2

[0098] According to the embodiments of the present application, a device embodiment for implementing the above-mentioned audio noise suppression evaluation method is also provided, Figure 7 is a structural schematic diagram of an audio noise suppression evaluation device according to the embodiments of the present application, as Figure 7 shown, the device comprises:

[0099] The generating module 701 is configured to generate a third audio by using a first audio and a second audio, wherein the first audio is an original audio, the second audio is a characteristic audio with a preset frequency and amplitude, and the third audio is a target audio to be evaluated;

[0100] The recording module 702 is configured to record the third audio by using a scheduling system to obtain fourth audio, where the scheduling system is configured to automatically control an audio recording process in a network live broadcast.

[0101] The evaluation module 703 is configured to evaluate noise suppression based on the third audio and the fourth audio to obtain an evaluation result.

[0102] Optionally, the generation module 701 is further configured to: obtain the first audio, where the first audio includes at least one type of pure noise audio and at least one type of fitted audio, the at least one type of fitted audio being obtained by fitting a preset type of audio and the at least one type of pure noise audio according to different signal-to-noise ratios; and insert the second audio at a preset position in the first audio to generate the third audio.

[0103] Optionally, the audio noise suppression evaluation device further includes: a scheduling module 704 configured to schedule the first terminal to play the third audio by using a scheduling system, input the third audio to a sound card through an audio line, and input the third audio to the second terminal through the sound card; and a push streaming module 705 configured to schedule the second terminal to push the third audio to a cloud server by using the scheduling system.

[0104] Optionally, the recording module 702 is further configured to: schedule the third terminal to pull the third audio from the cloud server by using the scheduling system, and record the third audio by using preset recording parameters to obtain the fourth audio.

[0105] Optionally, the evaluation module 703 is further configured to: parse at least one type of pure noise audio and at least one type of fitted audio from the fourth audio; obtain a target difference curve by using the at least one type of pure noise audio and the third audio, and obtain a comparative analysis result by using the at least one type of fitted audio and the third audio, where the target difference curve is used to find a noise reduction convergence point, and the comparative analysis result is used to determine a damage degree of the at least one type of fitted audio; evaluate noise suppression of the at least one type of pure noise audio based on the target difference curve, and evaluate noise suppression of the at least one type of fitted audio based on the comparative analysis result to obtain the evaluation result.

[0106] Optionally, the evaluation module 703 is further configured to: perform frame division and frequency calculation on the fourth audio to determine an insertion position of the second audio; parse a recording audio segment corresponding to the first audio from the fourth audio by using the insertion position of the second audio; and obtain the at least one type of pure noise audio and the at least one type of fitted audio from the recording audio segment.

[0107] Optionally, the evaluation module 703 is further configured to: obtain a first curve and a second curve, where the first curve is a smooth amplitude reduction curve corresponding to the at least one type of pure noise audio, and the second curve is a smooth amplitude reduction curve corresponding to the third audio; and calculate a difference between the first curve and the second curve to obtain a target difference curve.

[0108] Optionally, the recording duration of the fourth audio is determined by the preset duration of the third audio.

[0109] It should be noted that the above generation module 701, recording module 702 and evaluation module 703 correspond to steps S21 to S23 in Embodiment 1, and the three modules have the same instances and application scenarios as the corresponding steps, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules as part of the device can run in the computer terminal 10 provided in Embodiment 1.

[0110] In the embodiment of the application, the third audio is generated by using the first audio and the second audio, the first audio is the original audio, the second audio is the characteristic audio with the preset frequency and amplitude, the third audio is the target audio to be evaluated, and then the third audio is recorded by using the scheduling system to obtain the fourth audio. The scheduling system is used for automatically controlling the audio recording process in the network live broadcast, and finally the noise suppression evaluation is performed based on the third audio and the fourth audio to obtain the evaluation result.

[0111] It is easy to note that, by the embodiment of the application, the original audio and the characteristic audio with the preset frequency and amplitude can be used to generate the target audio to be evaluated, and then the target audio is recorded by using the scheduling system, and the noise suppression evaluation is performed on the audio obtained after recording, so as to obtain the evaluation result.

[0112] Therefore, the embodiment of the application achieves the purpose of quickly performing noise suppression evaluation on the audio, thereby simplifying the operation process of the audio noise suppression evaluation, improving the evaluation efficiency and reducing the evaluation cost, thereby solving the technical problems that the operation process of the audio noise suppression evaluation is complex in the related art, resulting in low evaluation efficiency and high evaluation cost. It should be noted that the preferred embodiments of the present embodiment can refer to the related description in Embodiment 1, which will not be repeated here.

[0113] Embodiment 3

[0114] According to the embodiment of the application, an embodiment of an electronic device is also provided, which can be any one of the computing devices in the computing device group. The electronic device comprises a processor and a memory, wherein:

[0115] The memory is connected with the processor and is configured to provide the processor with instructions for processing the following processing steps: generating a third audio by using a first audio and a second audio, wherein the first audio is an original audio, the second audio is a characteristic audio with a preset frequency and amplitude, and the third audio is a target audio to be evaluated; recording the third audio by using a scheduling system to obtain a fourth audio, wherein the scheduling system is configured to automatically control an audio recording process in a network live broadcast; and performing noise suppression evaluation based on the third audio and the fourth audio to obtain an evaluation result.

[0116] In the embodiment of the present application, the third audio is generated by using the first audio and the second audio, the first audio is the original audio, the second audio is the characteristic audio with the preset frequency and amplitude, and the third audio is the target audio to be evaluated. Then, the third audio is recorded by using the scheduling system to obtain the fourth audio. The scheduling system is configured to automatically control the audio recording process in the network live broadcast. Finally, the noise suppression evaluation is performed based on the third audio and the fourth audio to obtain the evaluation result.

[0117] It is easy to note that, by the embodiment of the present application, the target audio to be evaluated can be generated by using the original audio and the characteristic audio with the preset frequency and amplitude. Then, the target audio is recorded by using the scheduling system. The noise suppression evaluation is performed on the audio obtained after recording, so as to obtain the evaluation result.

[0118] Therefore, the embodiment of the present application achieves the purpose of quickly performing the noise suppression evaluation on the audio. Thus, the technical effects of simplifying the operation process of the audio noise suppression evaluation, improving the evaluation efficiency, and reducing the evaluation cost are achieved. Furthermore, the technical problem that the operation process of the audio noise suppression evaluation is complicated in the related art, resulting in low evaluation efficiency and high evaluation cost is solved.

[0119] It should be noted that the preferred embodiments of the present embodiment can refer to the related description in Embodiment 1, which will not be repeated here.

[0120] Embodiment 4

[0121] The embodiment of the present application can provide a computer terminal, which can be any computer terminal device in a computer terminal group. Alternatively, in the present embodiment, the computer terminal can be replaced by a mobile terminal or other terminal device.

[0122] Alternatively, in the present embodiment, the computer terminal can be located in at least one network device of a plurality of network devices of a computer network.

[0123] In the embodiment, the computer terminal can execute program codes of the following steps in the audio noise suppression evaluation method: generating a third audio by using a first audio and a second audio, wherein the first audio is an original audio, the second audio is a characteristic audio with a preset frequency and amplitude, and the third audio is a target audio to be evaluated; recording the third audio by using a scheduling system to obtain a fourth audio, wherein the scheduling system is used for automatically controlling an audio recording process in a network live broadcast; and performing noise suppression evaluation based on the third audio and the fourth audio to obtain an evaluation result.

[0124] Optionally, Figure 8 is a structural block diagram of another computer terminal according to an embodiment of the present application, as shown in the figure, the computer terminal can include one or more (only one is shown in the figure) processors 82, a memory 84, and a peripheral interface 86. Figure 8

[0125] The memory can be used to store software programs and modules, such as program instructions / modules corresponding to the audio noise suppression evaluation method and device in the embodiment of the present application. The processor performs various functional applications and data processing by running the software programs and modules stored in the memory, that is, implements the above-mentioned audio noise suppression evaluation method. The memory can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, a flash memory, or other non-volatile solid-state memories. In some examples, the memory can further include a memory remotely arranged with respect to the processor, and these remote memories can be connected to the computer terminal through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0126] The processor can call information and application programs stored in the memory through the transmission device to execute the following steps: generating a third audio by using a first audio and a second audio, wherein the first audio is an original audio, the second audio is a characteristic audio with a preset frequency and amplitude, and the third audio is a target audio to be evaluated; recording the third audio by using a scheduling system to obtain a fourth audio, wherein the scheduling system is used for automatically controlling an audio recording process in a network live broadcast; and performing noise suppression evaluation based on the third audio and the fourth audio to obtain an evaluation result.

[0127] Optionally, the processor can further execute program codes of the following steps: obtaining the first audio, wherein the first audio includes at least one type of pure noise audio and at least one type of fitting audio, and the at least one type of fitting audio is obtained by fitting a preset type of audio with at least one type of pure noise audio according to different signal-to-noise ratios; and inserting the second audio at a preset position in the first audio to generate the third audio.

[0128] ​Optionally, the processor can further execute program codes of the following steps: scheduling the first terminal to play the third audio by using the scheduling system, inputting the third audio into the sound card through the audio line, and inputting the third audio into the second terminal through the sound card; and scheduling the second terminal to push the third audio to the cloud server by using the scheduling system.

[0129] Optionally, the processor can further execute program codes of the following steps: scheduling the third terminal to pull the third audio from the cloud server by using the scheduling system, and recording the third audio by using preset recording parameters to obtain the fourth audio.

[0130] Optionally, the processor can further execute program codes of the following steps: parsing at least one type of pure noise audio and at least one type of fitting audio from the fourth audio; obtaining a target difference curve by using the at least one type of pure noise audio and the third audio, and obtaining a comparative analysis result by using the at least one type of fitting audio and the third audio, wherein the target difference curve is used to find a noise reduction convergence point, and the comparative analysis result is used to determine the damage degree of the at least one type of fitting audio; and performing noise suppression evaluation on the at least one type of pure noise audio based on the target difference curve, and performing noise suppression evaluation on the at least one type of fitting audio based on the comparative analysis result, to obtain an evaluation result.

[0131] Optionally, the processor can further execute program codes of the following steps: performing frame division and frequency calculation on the fourth audio to determine an insertion position of the second audio; parsing a recording audio segment corresponding to the first audio from the fourth audio by using the insertion position of the second audio; and obtaining the at least one type of pure noise audio and the at least one type of fitting audio from the recording audio segment.

[0132] Optionally, the processor can further execute program codes of the following steps: obtaining a first curve and a second curve, wherein the first curve is a smooth amplitude reduction curve corresponding to the at least one type of pure noise audio, and the second curve is a smooth amplitude reduction curve corresponding to the third audio; calculating a difference between the first curve and the second curve to obtain a target difference curve.

[0133] Optionally, the processor can further execute program codes of the following steps: determining a recording time length of the fourth audio according to a preset time length of the third audio.

[0134] In the embodiment of the application, the third audio is generated by using the first audio and the second audio, the first audio is the original audio, the second audio is the characteristic audio with preset frequency and amplitude, and the third audio is the target audio to be evaluated, and then the fourth audio is obtained by recording the third audio by using the scheduling system, the scheduling system is used to automatically control the audio recording process in the network live broadcast, and finally the noise suppression evaluation is performed based on the third audio and the fourth audio to obtain the evaluation result.

[0135] It is easily noticed that, by the embodiment of the present application, the target audio to be evaluated can be generated by using the original audio and the characteristic audio with preset frequency and amplitude, and then the target audio is recorded by using the scheduling system, and the evaluation result is obtained by evaluating the recorded audio.

[0136] Therefore, the embodiment of the present application achieves the purpose of quickly evaluating the noise suppression of the audio, thereby simplifying the operation process of the audio noise suppression evaluation, improving the evaluation efficiency and reducing the evaluation cost, and further solving the technical problems of low evaluation efficiency and high evaluation cost caused by the complex operation process of the audio noise suppression evaluation in the related art.

[0137] Those skilled in the art can understand that, Figure 8 The structure shown is only schematic, and the computer terminal can also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, or the like. Figure 8 The structure of the electronic device is not limited above. For example, the computer terminal can further include more or fewer components (such as a network interface, a display device, etc.) than Figure 8 or have a different configuration than Figure 8 shown.

[0138] Embodiment 5

[0139] According to the embodiment of the present application, an embodiment of a storage medium is also provided. Optionally, in the present embodiment, the storage medium can be used to save the program code executed by the audio noise suppression evaluation method provided in the embodiment 1.

[0140] Optionally, in the present embodiment, the storage medium can be located in any one of the computer terminals in the computer terminal group in the computer network, or in any one of the mobile terminals in the mobile terminal group.

[0141] Optionally, in the present embodiment, the storage medium is configured to store program code for performing the following steps: generating a third audio by using a first audio and a second audio, wherein the first audio is an original audio, the second audio is a characteristic audio with preset frequency and amplitude, and the third audio is a target audio to be evaluated; recording the third audio by using a scheduling system to obtain a fourth audio, wherein the scheduling system is used to automatically control the audio recording process in the network live broadcast; and performing noise suppression evaluation based on the third audio and the fourth audio to obtain an evaluation result.

[0142] Optionally, in the embodiment, the storage medium is configured to store program code for performing the following steps: obtaining the first audio, wherein the first audio comprises at least one type of pure noise audio and at least one type of fitted audio, the at least one type of fitted audio being fitted by a preset type of audio and the at least one type of pure noise audio at different signal-to-noise ratios; inserting the second audio at a preset position in the first audio to generate third audio.

[0143] Optionally, in the embodiment, the storage medium is configured to store program code for performing the following steps: using the scheduling system to schedule the first terminal to play the third audio, inputting the third audio into the sound card through the audio line, and inputting the third audio into the second terminal through the sound card; using the scheduling system to schedule the second terminal to push the third audio to the cloud server.

[0144] Optionally, in the embodiment, the storage medium is configured to store program code for performing the following steps: using the scheduling system to schedule the third terminal to pull the third audio from the cloud server, and using a preset recording parameter to record the third audio to obtain fourth audio.

[0145] Optionally, in the embodiment, the storage medium is configured to store program code for performing the following steps: obtaining at least one type of pure noise audio and at least one type of fitted audio from the fourth audio; obtaining a target difference curve using the at least one type of pure noise audio and the third audio, and obtaining a comparative analysis result using the at least one type of fitted audio and the third audio, wherein the target difference curve is used to find a noise reduction convergence point, and the comparative analysis result is used to determine the damage degree of the at least one type of fitted audio; performing noise suppression evaluation on the at least one type of pure noise audio based on the target difference curve, and performing noise suppression evaluation on the at least one type of fitted audio based on the comparative analysis result to obtain an evaluation result.

[0146] Optionally, in the embodiment, the storage medium is configured to store program code for performing the following steps: performing frame division and frequency calculation on the fourth audio to determine the insertion position of the second audio; obtaining a recorded audio segment corresponding to the first audio from the fourth audio using the insertion position of the second audio; and obtaining at least one type of pure noise audio and at least one type of fitted audio from the recorded audio segment.

[0147] Optionally, in the embodiment, the storage medium is configured to store program code for performing the following steps: obtaining a first curve and a second curve, wherein the first curve is a smooth amplitude reduction curve corresponding to at least one type of pure noise audio, and the second curve is a smooth amplitude reduction curve corresponding to the third audio; calculating the difference between the first curve and the second curve to obtain a target difference curve.

[0148] Optionally, in the embodiment, the storage medium is configured to store program code for performing the following steps: determining a recording duration of the fourth audio according to a preset duration of the third audio.

[0149] Those skilled in the art can understand that all or part of the steps in the above-mentioned various methods of the embodiments can be instructed by programs to terminal device related hardware, and the programs can be stored in a computer readable storage medium, which can include a flash disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0150] Embodiment 6

[0151] According to the embodiments of the present application, an embodiment of an audio noise suppression evaluation system is also provided.

[0152] Specifically, in the embodiment, the audio noise suppression evaluation system comprises a processor and a memory connected with the processor, and the memory is configured to provide the processor with instructions for processing the following steps:

[0153] Step 1, generating a third audio by using a first audio and a second audio, wherein the first audio is an original audio, the second audio is a characteristic audio with a preset frequency and amplitude, and the third audio is a target audio to be evaluated;

[0154] Step 2, recording the third audio by using a scheduling system to obtain a fourth audio, wherein the scheduling system is used for automatically controlling the audio recording process in the network live broadcast;

[0155] Step 3, performing noise suppression evaluation based on the third audio and the fourth audio to obtain an evaluation result.

[0156] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0157] In the above-mentioned embodiments of the present application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0158] In several embodiments provided in the present application, it should be understood that the disclosed technology can be implemented by other ways. Among them, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, units or modules, and can be electrical or other forms.

[0159] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0160] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0161] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0162] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A method of evaluating audio noise suppression, characterized by, The method comprises: generating a third audio by using a first audio and a second audio, wherein the first audio is original audio, the second audio is a characteristic audio with a preset frequency and amplitude, and the third audio is target audio to be evaluated, the first audio comprises at least one type of pure noise audio and at least one type of fitting audio, the at least one type of fitting audio is obtained by fitting a preset type audio and the at least one type of pure noise audio according to different signal-to-noise ratios, and the preset type audio is speech audio with different signal-to-noise ratios; recording the third audio by using a scheduling system to obtain fourth audio, wherein the scheduling system is used for automatically controlling the audio recording process in network live broadcast; performing noise suppression evaluation based on the third audio and the fourth audio to obtain evaluation results.

2. The audio noise suppression evaluation method of claim 1, wherein, The method for generating the third audio by using the first audio and the second audio comprises: obtaining the first audio; inserting the second audio at a preset position in the first audio to generate the third audio.

3. The audio noise suppression evaluation method of claim 1, wherein, The method further comprises: scheduling a first terminal to play the third audio by using the scheduling system, inputting the third audio to a sound card through an audio line, and inputting the third audio to a second terminal through the sound card; scheduling the second terminal to push the third audio to a cloud server by using the scheduling system.

4. The audio noise suppression evaluation method of claim 3, wherein, The method for recording the third audio by using the scheduling system to obtain the fourth audio comprises: scheduling a third terminal to pull the third audio from the cloud server by using the scheduling system, and recording the third audio by using preset recording parameters to obtain the fourth audio.

5. The method of claim 2, wherein, The method for performing noise suppression evaluation based on the third audio and the fourth audio to obtain the evaluation results comprises: parsing the at least one type of pure noise audio and the at least one type of fitting audio from the fourth audio; obtaining a target difference curve by using the at least one type of pure noise audio and the third audio, and obtaining a comparative analysis result by using the at least one type of fitting audio and the third audio, wherein the target difference curve is used for finding a noise reduction convergence point, and the comparative analysis result is used for determining a damage degree of the at least one type of fitting audio; performing noise suppression evaluation on the at least one type of pure noise audio based on the target difference curve, and performing noise suppression evaluation on the at least one type of fitting audio based on the comparative analysis result to obtain the evaluation results.

6. The audio noise suppression evaluation method of claim 5, wherein, The method for parsing the at least one type of pure noise audio and the at least one type of fitting audio from the fourth audio comprises: performing frame division and frequency calculation on the fourth audio to determine an insertion position of the second audio; parsing a recording audio segment corresponding to the first audio from the fourth audio by using the insertion position of the second audio; obtaining the at least one type of pure noise audio and the at least one type of fitting audio from the recording audio segment.

7. The method of claim 5, wherein, The method for obtaining the target difference curve by using the at least one type of pure noise audio and the third audio comprises: obtaining a first curve and a second curve, wherein the first curve is a smooth amplitude curve corresponding to the at least one type of pure noise audio, and the second curve is a smooth amplitude curve corresponding to the third audio; calculating a difference between the first curve and the second curve to obtain the target difference curve.

8. An audio noise suppression evaluation apparatus characterized by comprising: comprise: a generation module configured to generate a third audio by using a first audio and a second audio, wherein the first audio is an original audio, the second audio is a characteristic audio with a preset frequency and amplitude, and the third audio is a target audio to be evaluated, the first audio comprises at least one type of pure noise audio and at least one type of fitted audio, the at least one type of fitted audio is obtained by fitting a preset type audio and the at least one type of pure noise audio according to different signal-to-noise ratios, and the preset type audio is a speech audio with different signal-to-noise ratios; a recording module configured to record the third audio by using a scheduling system to obtain a fourth audio, wherein the scheduling system is configured to automatically control an audio recording process in a network live broadcast; an evaluation module configured to perform noise suppression evaluation based on the third audio and the fourth audio to obtain an evaluation result.

9. A storage medium, characterized by The storage medium comprises a stored program, wherein the program controls a device in which the storage medium is located to perform the audio noise suppression evaluation method in any one of claims 1 to 7 when the program is running.

10. An audio noise suppression evaluation system, characterized by, comprise: a processor; and a memory connected with the processor, configured to provide the processor with instructions for processing the following processing steps: Step 1, generating a third audio by using a first audio and a second audio, wherein the first audio is an original audio, the second audio is a characteristic audio with a preset frequency and amplitude, and the third audio is a target audio to be evaluated, the first audio comprises at least one type of pure noise audio and at least one type of fitted audio, the at least one type of fitted audio is obtained by fitting a preset type audio and the at least one type of pure noise audio according to different signal-to-noise ratios, and the preset type audio is a speech audio with different signal-to-noise ratios; Step 2, recording the third audio by using a scheduling system to obtain a fourth audio, wherein the scheduling system is configured to automatically control an audio recording process in a network live broadcast; Step 3, performing noise suppression evaluation based on the third audio and the fourth audio to obtain an evaluation result.

Images