Audio quality detection, abnormality processing method and device, electronic equipment and medium

Abstract

The present disclosure relates to an audio quality detection and exception processing method and device, electronic equipment and a medium, the method comprising: sending a page control instruction to a terminal test device; obtaining page playing test content of the terminal test device, the page playing test content being obtained by the terminal test device executing the page control instruction; and performing audio quality detection on the page playing test content to determine an audio detection result of the page playing test content. Thus, the page playing of the terminal test device can be controlled through a communication connection with the terminal test device, the page playing test content can be effectively detected, human cost can be saved, and audio detection efficiency can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to an audio quality detection, anomaly handling method, apparatus, electronic device, and medium. Background Technology

[0002] Audio playback applications can play multimedia content based on user actions, enriching users' daily lives. The multimedia content in audio playback applications is mostly created and uploaded by other users.

[0003] During the uploading process of multimedia content, issues such as network links may cause the audio quality of the multimedia content to deteriorate. In current technology, the main approach is to manually download the multimedia content and perform audio testing.

[0004] However, using existing technologies results in high labor costs and low testing efficiency. Summary of the Invention

[0005] To address the aforementioned technical problems, this disclosure provides an audio quality detection, anomaly handling method, apparatus, electronic device, and medium.

[0006] In a first aspect, this disclosure provides an audio quality detection method, including:

[0007] Send page control commands to the terminal test device;

[0008] The page playback test content of the terminal test device is obtained, and the page playback test content is obtained by the terminal test device executing the page control command;

[0009] Perform audio quality testing on the page playback test content, and determine the audio test results of the page playback test content.

[0010] In one possible design, sending page control instructions to the terminal testing device includes:

[0011] Based on the attribute information corresponding to the page control component of the terminal test device, the control instructions corresponding to the page control component are determined. The page control component includes: play and pause.

[0012] Send the control command corresponding to the page control component to the terminal test device.

[0013] In one possible design, the audio quality detection includes at least one of the following: phase detection, volume detection, pop detection, noise detection, and sound quality detection.

[0014] In one possible design, when the audio quality detection is a sound quality detection, the step of performing audio quality detection on the page playback test content and determining the audio detection result of the page playback test content includes:

[0015] A preset audio classification algorithm is invoked to classify the page playback test content, resulting in a first category and a second category. The first category describes the audio content in the page playback test content, and the second category describes the music content in the page playback test content.

[0016] The audio quality of the first category of content is tested to obtain the first test result;

[0017] The second category of content is subjected to sound quality testing to obtain the second test result;

[0018] The first detection result and the second detection result are used as the results of the sound quality detection.

[0019] In one possible design, the step of performing sound quality detection on the first category of content to obtain a first detection result includes:

[0020] The first category content is subjected to sound quality detection based on at least one detection dimension to obtain a first detection score corresponding to at least one of the detection dimensions;

[0021] The first detection result is determined based on the first detection score corresponding to at least one of the detection dimensions and the preset first threshold.

[0022] In one possible design, determining the first detection result based on a first detection score corresponding to at least one of the detection dimensions and a preset first threshold includes:

[0023] If the first detection score is less than the preset first threshold, then the audio quality abnormality type of the first category content is determined;

[0024] The types of sound quality anomalies correspond to the detection dimensions.

[0025] In one possible design, the detection dimensions include at least one of the following: overall sound quality detection, sound coloration detection, noise detection, continuous detection, and loudness equalization detection; and / or

[0026] The types of abnormal sound quality include: overall abnormal sound quality, sound coloration, noisy sound, discontinuous sound, and uneven sound loudness.

[0027] In one possible design, the step of performing sound quality detection on the second category of content to obtain a second detection result includes:

[0028] The second category content is classified and predicted to obtain the second detection score;

[0029] If the second detection score is less than the preset second threshold, then the audio quality of the second category content is determined to be abnormal.

[0030] Secondly, this disclosure provides an exception handling method for page playback content processing nodes, including:

[0031] If the audio detection result of the page playback test content mentioned in the first aspect is determined to be an audio anomaly, an early warning message for the page playback test content is generated.

[0032] Send the warning information, which is used to instruct the processing node that plays the test content on the page to perform abnormal handling.

[0033] Thirdly, this disclosure provides an audio quality detection device, comprising:

[0034] The sending module is used to send page control commands to the terminal test device;

[0035] The acquisition module is used to acquire the page playback test content of the terminal test device, wherein the page playback test content is obtained by the terminal test device executing the page control command;

[0036] The determination module is used to perform audio quality detection on the page playback test content and determine the audio detection result of the page playback test content.

[0037] In one possible design, the sending module is specifically used for:

[0038] Based on the attribute information corresponding to the page control component of the terminal test device, the control instructions corresponding to the page control component are determined. The page control component includes: play and pause.

[0039] Send the control command corresponding to the page control component to the terminal test device.

[0040] In one possible design, the audio quality detection includes at least one of the following: phase detection, volume detection, pop detection, noise detection, and sound quality detection.

[0041] In one possible design, when the audio quality detection is a sound quality detection, the determination module includes: a classification unit, a first detection unit, a second detection unit, and a determination unit;

[0042] The classification unit is used to call a preset audio classification algorithm to classify the page playback test content to obtain a first category content and a second category content. The first category content is used to describe the audio content in the page playback test content, and the second category content is used to describe the music content in the page playback test content.

[0043] The first detection unit is used to perform sound quality detection on the first category of content and obtain a first detection result;

[0044] The second detection unit is used to perform sound quality detection on the second category content to obtain a second detection result;

[0045] A determining unit is used to take the first detection result and the second detection result as the result of the sound quality detection.

[0046] In one possible design, the first detection unit is specifically used for:

[0047] The first category content is subjected to sound quality detection based on at least one detection dimension to obtain a first detection score corresponding to at least one of the detection dimensions;

[0048] The first detection result is determined based on the first detection score corresponding to at least one of the detection dimensions and the preset first threshold.

[0049] In one possible design, the first detection unit is specifically used for:

[0050] If the first detection score is less than the preset first threshold, then the audio quality abnormality type of the first category content is determined;

[0051] The types of sound quality anomalies correspond to the detection dimensions.

[0052] In one possible design, the detection dimensions include at least one of the following: overall sound quality detection, sound coloration detection, noise detection, continuous detection, and loudness equalization detection; and / or

[0053] The types of abnormal sound quality include: overall abnormal sound quality, sound coloration, noisy sound, discontinuous sound, and uneven sound loudness.

[0054] In one possible design, the second detection unit is specifically used for:

[0055] The second category content is classified and predicted to obtain the second detection score;

[0056] If the second detection score is less than the preset second threshold, then the audio quality of the second category content is determined to be abnormal.

[0057] In one possible design, the device further includes: a generation module;

[0058] The generation module is used to determine that the audio detection result of the page playback test content is an audio anomaly, and generate a warning message for the page playback test content;

[0059] The sending module is also used to send the warning information, which is used to instruct the processing node that plays the test content of the page to perform abnormal handling.

[0060] Fourthly, this disclosure provides an electronic device, including: a memory and a processor; the memory is used to store program instructions; the processor is used to invoke the program instructions in the memory to cause the electronic device to execute the audio quality detection method in the first aspect and any possible design of the first aspect.

[0061] Fifthly, this disclosure provides a computer storage medium including computer instructions that, when executed on an electronic device, cause the electronic device to perform the audio quality detection method of the first aspect and any possible design of the first aspect.

[0062] In a sixth aspect, this disclosure provides a computer program product that, when run on a computer, causes the computer to execute the audio quality detection method of the first aspect and any possible design of the first aspect.

[0063] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0064] The audio quality detection, anomaly handling method, apparatus, electronic device, and medium provided in this disclosure embodiment establish a communication connection between a main control device and a terminal testing device. The main control device can send page control commands to the terminal testing device to control the page playback test content on the terminal testing device. After sending the page control commands, the main control device obtains the page playback test content obtained by executing the page control commands, and performs audio quality detection on the page playback test content to obtain the audio detection result. Therefore, through the communication connection with the terminal testing device, the main control device can control the page playback status of the terminal testing device and effectively detect the page playback test content, saving labor costs and improving audio detection efficiency. Attached Figure Description

[0065] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0066] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0067] Figure 1 This is a schematic flowchart of an audio quality detection method provided in an embodiment of this disclosure;

[0068] Figure 2 This is a schematic flowchart of another audio quality detection method provided in this embodiment of the disclosure;

[0069] Figure 3 This is a schematic diagram of an interaction with a terminal testing device provided in an embodiment of this disclosure;

[0070] Figure 4 This is a schematic diagram illustrating the operation of a page control component provided in an embodiment of this disclosure;

[0071] Figure 5 This is a schematic diagram of the attributes of a page control component provided in an embodiment of this disclosure;

[0072] Figure 6 This is an interactive flowchart of an early warning information provided in an embodiment of this disclosure;

[0073] Figure 7 This is a schematic diagram of the structure of a watermark processing device provided in an embodiment of the present disclosure. Detailed Implementation

[0074] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0075] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0076] For example, this disclosure provides an audio quality detection, anomaly handling method, apparatus, electronic device, and medium. A main control device communicates with a terminal testing device, enabling it to send page control commands to the terminal testing device to control the page playback test content on the terminal testing device. After sending the page control commands, the main control device obtains the page playback test content obtained by executing the page control commands, and performs audio quality detection on the page playback test content to obtain the audio detection result. Thus, through the communication connection with the terminal testing device, the main control device can control the page playback status of the terminal testing device and effectively detect the page playback test content, saving labor costs and improving audio detection efficiency.

[0077] The audio quality testing method disclosed herein is executed by a client installed in an electronic device. The electronic device can be a tablet computer, mobile phone, wearable device, in-vehicle device, augmented reality (AR) / virtual reality (VR) device, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), smart TV, smart screen, high-definition TV, 4K TV, smart speaker, smart projector, etc. This disclosure does not impose any restrictions on the specific type of electronic device.

[0078] This disclosure does not limit the type of operating system used in electronic devices. Examples include Android, Linux, Windows, and iOS.

[0079] Please see Figure 1 , Figure 1 This is a schematic flowchart illustrating an audio quality detection method provided in an embodiment of this disclosure. Figure 1 As shown, the audio quality detection method provided in this disclosure may include:

[0080] S110, Send page control instructions to the terminal test device.

[0081] Among them, the terminal test equipment is an electronic device with a first operating system. It can realize a remote call service through the server of the terminal test equipment, so that the main control device can call and control the application in the terminal test equipment through the interface.

[0082] Specifically, the main control device can pre-write an automation script, which can be used to communicate with the terminal test device (Remote Call Service WDA) based on an interface (such as an SDK interface). Figure 2As illustrated, the host (master control device) sends page control commands to the remote call service of the terminal test device through an execution interface by running an automated script, so that the terminal test device can automatically play / pause the content in the application (APP).

[0083] The execution interface corresponds to operations in the terminal test device, including but not limited to: searching, clicking, swiping, etc.

[0084] It should be noted that, through the communication method between the main control device and the terminal test device described above, Python automated scripts can be written to execute commands such as sliding video and clicking play / pause on the application in the terminal test device.

[0085] S120. Obtain the test content for playing on the page of the terminal test device.

[0086] When the terminal testing device receives a page playback command from the main control device, it can execute the page playback command on the application. After executing all the commands sent by the terminal testing device at once, it can obtain the page playback test content. The page playback test content of the terminal testing device is the page playback test content obtained by the application in the terminal testing device in response to the page playback command. It can be understood that the page playback test content can be a large number of sample playback materials generated and uploaded by testers.

[0087] For example, when the received page playback instruction is "play", the terminal test device can control application A to play the currently displayed content. When the received page playback instruction is "pause", the terminal test device can control the application to pause the currently displayed content. The page playback test content is the multimedia content displayed by the application during the pause period.

[0088] It should be noted that when the terminal test device finishes executing the page playback command, the remote call service can obtain the page playback test content from the application. Specifically, the terminal test device can return the page playback test content to the main control device through communication interaction with the main control device, based on the remote call service, so that the main control device can obtain the page playback test content.

[0089] S130. Perform audio quality testing on the page playback test content and determine the audio test results of the page playback test content.

[0090] The main control device can perform audio quality testing on the page playback test content based on a variety of preset detection methods, and obtain the audio detection results of the page playback test content.

[0091] It should be noted that the test content played on the page can be some pre-prepared test videos, such as a large number of synthesized test videos, which are uploaded and published by the test account. The test videos mainly cover: different audio parameters (such as loudness, sampling rate, channels, bit width), different audio quality content (such as pure music audio, pure speech audio, and audio mixed with different proportions of music and speech), etc.

[0092] The audio quality detection can include phase detection, volume detection, pop detection, noise detection, and sound quality detection. Correspondingly, the audio detection results for the page playback test content can include phase detection results, volume detection results, pop detection results, noise detection results, and sound quality detection results.

[0093] For example, for phase detection, a Pearson correlation coefficient analysis can be performed on the two channels. If the correlation coefficient obtained from the analysis is 1, the phase detection result is determined to be "pseudo-stereo". If the correlation coefficient obtained from the analysis is -1, the phase detection result is determined to be "phase out of phase".

[0094] The test content for page playback can be split into channels to obtain the left channel audio array L[x1,x2,...,x] n And the right channel audio array R[x1,x2,...,x] n ], where n is the number of frames (sampling rate * duration); calculate L[x1,x2,...,x n ] and R[x1,x2,...,x n The covariance (cov), standard deviation (stdL), and stdR of the variables are given. The covariance can represent the level at which two variables change together. The Pearson correlation coefficient can be calculated based on the following formula (1).

[0095]

[0096] For volume detection, energy analysis can be performed on the two channels separately. If one channel is silent, the volume detection result is "single channel silent". If the energy difference is too large, the volume detection result is "volume unbalanced".

[0097] The test content for page playback can be split into channels to obtain the left channel audio array L[x1,x2,...,x] n And the right channel audio array R[x1,x2,...,x] n ], where n is the number of frames (sampling rate * duration); calculate L[x1,x2,...,x n ] and R[x1,x2,...,x n The average RMS amplitude is shown in the following formula (2).

[0098]

[0099] For pop detection, the degree of audio clipping distortion can be predicted by forecasting the HASQI (Hearing Aid Sound Quality Index) value. If the HASQI score is too low, the pop detection result of the test content played on this page will be "clipping distortion".

[0100] The test content for page playback can be divided into 23ms audio blocks with a 50% overlap between each block. Features are extracted from each audio block, including spectral entropy, spectral skewness coefficient, Mel frequency cepstral coefficient, zero-crossing rate, and spectral flatness. These features are then combined and input into a random forest for classification prediction. The prediction results of all audio blocks are averaged to obtain the final overall audio prediction value. The correspondence between HASQI index values ​​and audio quality is shown in the table below.

[0101] 0.875<=HASQI<1 good 0.625<=HASQI<0.875 better 0.375<HASQI<0.625 normal 0.125<HASQI<=0.375 Poor 0<HASQI<=0.125 Difference

[0102] For noise detection, test content can be played on pages with low signal-to-noise ratio to determine the noise detection result as "excessive noise". The speech activity detection algorithm is used to separate human voice from noise to obtain noise segment and human voice segment. The average energy Es and En of speech segment and noise segment are calculated as follows (3).

[0103]

[0104] The signal-to-noise ratio is calculated using the following formula (4).

[0105]

[0106] For audio quality detection, a no-reference scoring algorithm can be used to predict the MOS scores of the speech and music audio quality included in the page playback test content, and the final audio quality detection result can be obtained.

[0107] In addition, the audio quality detection of the page playback test content in this disclosure may also include: intermittent detection, signal interference sound (such as POP) detection, noise detection, and current sound detection.

[0108] The audio quality detection method provided in this embodiment establishes a communication connection between the main control device and the terminal testing device. The main control device can send page control commands to the terminal testing device to control the page playback test content. After sending the page control commands, the main control device obtains the page playback test content obtained by executing the page control commands, and performs audio quality detection on the page playback test content to obtain the audio detection result. Therefore, through the communication connection with the terminal testing device, the main control device can control the page playback status of the terminal testing device and effectively detect the page playback test content, saving labor costs and improving audio detection efficiency.

[0109] Figure 3 This is a flowchart illustrating another audio quality detection method provided in this embodiment. Based on the above embodiments, after S130, this embodiment may further include:

[0110] S140. If the audio detection result of the page playback test content is determined to be an audio anomaly, generate a warning message for the page playback test content.

[0111] If the volume detection result of the page playback test content is determined to be an audio anomaly, an early warning message can be generated to provide a prompt, realizing an automatic alarm mechanism for audio analysis anomalies, so as to facilitate timely understanding of the detection results.

[0112] S150, Send warning information.

[0113] The warning information is used to instruct the processing nodes that handle the test content of the page playback to perform abnormal processing.

[0114] The processing nodes may include: uploading and publishing, distributing, and previewing.

[0115] like Figure 4 As illustrated, when sending an early warning message, the main control device can first send the early warning message to the robot server of another application through an automated script. The robot server then verifies the early warning message. After successful verification, the robot server saves the error data to the database and sends the response event to the contact person set in the application.

[0116] In this process, after the main control device analyzes the abnormal situation, it sends the abnormality to the contact person. This allows the contact person to use the bad audio as a starting point to locate the problem at each processing node of the audio, so as to optimize the network transmission link or other transmission / processing problems.

[0117] Based on the description of the above embodiments, when sending page control instructions to the terminal testing device, the corresponding control instructions can be generated and sent through the relevant information corresponding to the page control component in the terminal testing device.

[0118] Optionally, sending page control instructions to the terminal test device includes:

[0119] Based on the attribute information of the page control components of the terminal test device, determine the control instructions corresponding to the page control components. The page control components include: play and pause.

[0120] Send control commands corresponding to the page control components to the terminal test device.

[0121] When the main control device sends page control commands to the terminal test device, it can operate the control components of the terminal test device's application through different component control commands in the application of the terminal test device.

[0122] Among them, such as Figure 5 As illustrated, the component operation principle is to call a framework in the terminal testing device, such as the automated testing framework (Keep It Functional, KIF), to locate specific component controls through relevant attributes, and to operate page components based on interfaces.

[0123] It should be noted that the framework used in this disclosure itself needs to obtain control components across processes, and the execution time of component operations is usually 3-5 seconds. However, this framework operates the control components of the page within the application process, and the operation time can be within 30ms, which can better match the actual time of user operation of the application.

[0124] In addition, such as Figure 6 As illustrated, component properties of an application on a terminal testing device can be obtained through a testing tool in programming software (such as Xcode).

[0125] When testing the audio quality of the page playback test content, the audio quality test results can be obtained by classifying and testing the content.

[0126] Among them, the page playback test content can be classified by calling the preset audio classification algorithm to obtain the first category content and the second category content. The first category content is used to describe the audio content in the page playback test content, and the second category content is used to describe the music content in the page playback test content.

[0127] The audio quality of the first category of content is tested to obtain the first test result;

[0128] The audio quality of the second category of content is tested to obtain the second test result;

[0129] The first and second test results are used as the results of the sound quality test.

[0130] This involves classifying the audio content of the page playback test by separating human voices and music, and then performing sound quality testing on each separately. This allows for in-depth classification and testing of the page playback test content, refining the test results.

[0131] The first category may include multiple categories, and correspondingly, the first detection result may also include multiple sound quality detection results.

[0132] In some embodiments, when performing sound quality detection on the first category of content, the sound quality detection on the first category of content can be performed based on at least one detection dimension to obtain a first detection score corresponding to at least one detection dimension; and a first detection result is determined based on the first detection score corresponding to at least one detection dimension and a preset first threshold.

[0133] Each detection dimension can be based on a deep learning regression model to perform corresponding audio quality detection.

[0134] Overall sound quality detection predicts the overall sound quality of the audio in the first category. Sound coloration detection detects whether there are other timbres mixed in with the audio in the first category. Noise detection detects the purity of the audio in the first category. Continuity detection detects the continuity of the audio in the first category. Loudness equalization detection detects the loudness equalization of the audio in the first category.

[0135] For example, the overall sound quality of the first category of content can be detected based on the first deep learning regression model. If the first category of content is input into the first deep learning regression model, a detection score is obtained from the output of the first deep learning regression model. The overall sound quality detection result can be determined by comparing the detection score with a pre-set threshold.

[0136] The sound coloration of the first category of content is detected based on the second deep learning regression model. For example, the first category of content is input into the second deep learning regression model, and a detection score is obtained from the output of the second deep learning regression model. The sound coloration detection result can be determined by comparing the detection score with a pre-set threshold.

[0137] Noise detection for the first category of content is performed based on a third deep learning regression model. For example, if the first category of content is input into the third deep learning regression model, a detection score is obtained from the output of the third deep learning regression model. The noise detection result can be determined by comparing the detection score with a pre-set threshold.

[0138] The continuity of the first category of content is detected based on the fourth deep learning regression model. For example, the first category of content is input into the fourth deep learning regression model, and a detection score is obtained from the output of the fourth deep learning regression model. The continuity detection result can be determined by comparing the detection score with a pre-set threshold.

[0139] The loudness balance of the first category of content is detected based on the fifth deep learning regression model. If the first category of content is input into the fifth deep learning regression model, a detection score is obtained from the output of the fifth deep learning regression model. The loudness balance detection result can be determined by comparing the detection score with a pre-set threshold.

[0140] Therefore, by detecting the first category of content through multiple detection dimensions, in-depth detection of audio quality can be achieved, revealing specific audio anomalies.

[0141] The first detection result is determined based on a first detection score corresponding to at least one detection dimension and a preset first threshold, including:

[0142] If the first detection score is less than the preset first threshold, then the audio quality abnormality type of the first category of content is determined;

[0143] Among them, the types of sound quality abnormalities correspond to the detection dimensions. The types of sound quality abnormalities include: overall sound quality abnormality, sound coloration, sound noise, sound discontinuity, and sound loudness imbalance.

[0144] The preset first threshold can be 2.

[0145] The detection dimensions may include at least one of the following: overall sound quality detection, sound coloration detection, noise detection, continuity detection, and loudness equalization detection; and / or, the sound quality abnormality type may include at least one of the following: overall sound quality abnormality, sound coloration, sound noise, sound discontinuity, and sound loudness imbalance.

[0146] It should be noted that the detection dimensions correspond to the types of sound quality anomalies. In other words, when the detection dimension is overall sound quality detection, the corresponding sound quality anomaly type can be overall sound quality anomaly; when the detection dimension is sound coloration detection, the corresponding sound quality anomaly type can be sound coloration; when the detection dimension is noise detection, the corresponding sound quality anomaly type can be sound noise; when the detection dimension is continuous detection, the corresponding sound quality anomaly type can be sound discontinuity; and when the detection dimension is loudness equalization detection, the corresponding sound quality anomaly type can be sound loudness imbalance.

[0147] Based on the examples above, if the overall sound quality test score for the first category of content is less than 2 points, the sound quality anomaly type for the first category of content can be determined as overall sound quality anomaly. If the sound coloration test score for the first category of content is less than 2 points, the sound quality anomaly type for the first category of content can be determined as sound coloration. If the noise test score for the first category of content is less than 2 points, the sound quality anomaly type for the first category of content can be determined as sound noise. If the continuity test score for the first category of content is less than 2 points, the sound quality anomaly type for the first category of content can be determined as sound discontinuity. If the loudness balance test score for the first category of content is less than 2 points, the sound quality anomaly type for the first category of content can be determined as sound loudness imbalance. Therefore, the audio anomaly type for the first category of content can be determined more precisely, facilitating targeted optimization.

[0148] In other embodiments, when performing sound quality detection on the second category of content, a second detection score can be obtained based on the classification prediction of the second category of content; if the second detection score is less than a preset second threshold, it is determined that the sound quality of the second category of content is abnormal.

[0149] Among them, the second category content can be classified and predicted based on a random classification model to obtain the predicted score (second detection score) corresponding to the second category content.

[0150] It should be noted that the preset second threshold value can be the same as the preset first threshold value, that is, the preset second threshold value can be 2.

[0151] When the second detection score is determined to be less than 2 points, the audio of the second category of content can be determined to have abnormal sound quality. Thus, the sound quality of the music content in the page playback test content can be detected.

[0152] Figure 7 This is a schematic diagram of the structure of an audio quality testing device provided in this disclosure, such as... Figure 7 As shown, the audio quality detection device 700 of this embodiment includes: a sending module 710, an acquisition module 720, and a determining module 730, wherein:

[0153] The sending module 710 is used to send page control commands to the terminal test device;

[0154] The acquisition module 720 is used to acquire the page playback test content of the terminal test device, wherein the page playback test content is obtained by the terminal test device executing the page control command;

[0155] The determination module 730 is used to perform audio quality detection on the page playback test content and determine the audio detection result of the page playback test content.

[0156] In this embodiment, optionally, the sending module 710 is specifically used for:

[0157] Based on the attribute information corresponding to the page control component of the terminal test device, the control instructions corresponding to the page control component are determined. The page control component includes: play and pause.

[0158] Send the control command corresponding to the page control component to the terminal test device.

[0159] In this embodiment, optionally, the audio quality detection includes at least one of the following: phase detection, volume detection, pop detection, noise detection, and sound quality detection.

[0160] In this embodiment, optionally, when the audio quality detection is a sound quality detection, the determination module 730 includes: a classification unit, a first detection unit, a second detection unit, and a determination unit;

[0161] The classification unit is used to call a preset audio classification algorithm to classify the page playback test content to obtain a first category content and a second category content. The first category content is used to describe the audio content in the page playback test content, and the second category content is used to describe the music content in the page playback test content.

[0162] The first detection unit is used to perform sound quality detection on the first category of content and obtain a first detection result;

[0163] The second detection unit is used to perform sound quality detection on the second category content to obtain a second detection result;

[0164] A determining unit is used to take the first detection result and the second detection result as the result of the sound quality detection.

[0165] In this embodiment, optionally, the first detection unit is specifically used for:

[0166] The first category content is subjected to sound quality detection based on at least one detection dimension to obtain a first detection score corresponding to at least one of the detection dimensions;

[0167] The first detection result is determined based on the first detection score corresponding to at least one of the detection dimensions and the preset first threshold.

[0168] In this embodiment, optionally, the first detection unit is specifically used for:

[0169] If the first detection score is less than the preset first threshold, then the audio quality abnormality type of the first category content is determined;

[0170] The types of sound quality anomalies correspond to the detection dimensions.

[0171] In this embodiment, optionally, the detection dimensions include at least one of the following: overall sound quality detection, sound coloration detection, noise detection, continuous detection, and loudness equalization detection; and / or

[0172] The types of abnormal sound quality include: overall abnormal sound quality, sound coloration, noisy sound, discontinuous sound, and uneven sound loudness.

[0173] In this embodiment, optionally, the second detection unit is specifically used for:

[0174] The second category content is classified and predicted to obtain the second detection score;

[0175] If the second detection score is less than the preset second threshold, then the audio quality of the second category content is determined to be abnormal.

[0176] In this embodiment, optionally, the device further includes: a generation module;

[0177] The generation module is used to determine that the audio detection result of the page playback test content is an audio anomaly, and generate a warning message for the page playback test content;

[0178] The sending module 710 is also used to send the warning information, which is used to instruct the processing node of the page playback test content to perform abnormal processing.

[0179] The audio quality detection device provided in this disclosure can perform the above-described method embodiments. Its specific implementation principle and technical effects can be found in the above-described method embodiments, and will not be repeated here.

[0180] For example, this disclosure provides an electronic device including: one or more processors; a memory; and one or more computer programs; wherein the one or more computer programs are stored in the memory; and when the one or more processors execute the one or more computer programs, the electronic device causes the audio quality detection method of the preceding embodiments to be implemented.

[0181] For example, this disclosure provides a chip system applied to an electronic device including a memory and a sensor; the chip system includes: a processor; when the processor executes the audio quality detection method of the preceding embodiments.

[0182] For example, this disclosure provides a computer-readable storage medium having a computer program stored thereon, the computer program being processed by a processor to cause an electronic device to implement the audio quality detection method of the preceding embodiments.

[0183] For example, this disclosure provides a computer program product that, when run on a computer, causes the computer to execute the audio quality detection method described in the preceding embodiments.

[0184] In the above embodiments, all or part of the functionality can be implemented by software, hardware, or a combination of software and hardware. When implemented using software, it can be implemented wholly or partially in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this disclosure is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0185] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0186] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An audio quality detection method, characterized in that, include: Send page control commands to the terminal test device; The page playback test content of the terminal test device is obtained, and the page playback test content is obtained by the terminal test device executing the page control command; The audio quality of the page playback test content is tested to determine the audio test result of the page playback test content; wherein, the audio quality test includes sound quality testing; The step of performing audio quality testing on the page playback test content and determining the audio testing result of the page playback test content includes: A preset audio classification algorithm is invoked to classify the page playback test content, resulting in a first category and a second category. The first category describes the audio content in the page playback test content, and the second category describes the music content in the page playback test content. The sound quality of the first category content and the second category content is tested to obtain the sound quality test results.

2. The method according to claim 1, characterized in that, Sending page control instructions to the terminal testing device includes: Based on the attribute information corresponding to the page control component of the terminal test device, the control instructions corresponding to the page control component are determined. The page control component includes: play and pause. Send the control command corresponding to the page control component to the terminal test device.

3. The method according to claim 1, characterized in that, The audio quality detection also includes at least one of the following: phase detection, volume detection, pop detection, and noise detection.

4. The method according to claim 1, characterized in that, The step of performing sound quality detection on the first category content and the second category content to obtain the sound quality detection result includes: The audio quality of the first category of content is tested to obtain the first test result; The second category of content is subjected to sound quality testing to obtain the second test result; The first detection result and the second detection result are used as the results of the sound quality detection.

5. The method according to claim 4, characterized in that, The step of performing sound quality detection on the first category of content to obtain a first detection result includes: The first category content is subjected to sound quality detection based on at least one detection dimension to obtain a first detection score corresponding to at least one of the detection dimensions; The first detection result is determined based on the first detection score corresponding to at least one of the detection dimensions and the preset first threshold.

6. The method according to claim 5, characterized in that, The step of determining the first detection result based on the first detection score corresponding to at least one of the detection dimensions and a preset first threshold includes: If the first detection score is less than the preset first threshold, then the audio quality abnormality type of the first category content is determined; The types of sound quality anomalies correspond to the detection dimensions.

7. The method according to claim 6, characterized in that, The detection dimensions include at least one of the following: overall sound quality detection, sound coloration detection, noise detection, continuous detection, and loudness equalization detection; and / or The types of abnormal sound quality include: overall abnormal sound quality, sound coloration, noisy sound, discontinuous sound, and uneven sound loudness.

8. The method according to claim 4, characterized in that, The step of performing sound quality detection on the second category of content to obtain a second detection result includes: The second category content is classified and predicted to obtain the second detection score; If the second detection score is less than the preset second threshold, then the audio quality of the second category content is determined to be abnormal.

9. A method for handling exceptions in a page playback content processing node, characterized in that, include: If the audio detection result of the page playback test content as described in any one of claims 1-8 is determined to be an audio anomaly, an early warning message for the page playback test content is generated. Send the warning information, which is used to instruct the processing node that plays the test content on the page to perform abnormal handling.

10. An audio quality detection device, characterized in that, include: The sending module is used to send page control commands to the terminal test device; The acquisition module is used to acquire the page playback test content of the terminal test device, wherein the page playback test content is obtained by the terminal test device executing the page control command; The determining module is used to perform audio quality detection on the page playback test content and determine the audio detection result of the page playback test content; wherein, the audio quality detection includes sound quality detection; The determining module includes a classification unit and a detection unit; The classification unit is used to call a preset audio classification algorithm to classify the page playback test content to obtain a first category content and a second category content. The first category content is used to describe the audio content in the page playback test content, and the second category content is used to describe the music content in the page playback test content. The detection unit is used to perform sound quality detection on the first category content and the second category content to obtain the sound quality detection result.

11. An electronic device, comprising: One or more processors; Memory; And one or more computer programs; wherein the one or more computer programs are stored in the memory; characterized in that, when the one or more processors execute the one or more computer programs, the electronic device causes the electronic device to implement the audio quality detection method as described in any one of claims 1-9.

12. A computer storage medium, characterized in that, Includes computer instructions that, when executed on an electronic device, cause the electronic device to perform the method as described in any one of claims 1-9.

Images