A method, device, electronic device and storage medium for voice quality inspection

Abstract

The embodiments of the present application provide a speech quality inspection method, device, electronic device and storage medium, wherein the method comprises: obtaining audio data; converting the audio data into corresponding text data; performing quality inspection and analysis on the text data to obtain quality inspection and analysis data; and outputting quality inspection results according to the quality inspection and analysis data. The implementation of the embodiments of the present application solves the problem of separate use of text feature conditions and audio feature conditions in the speech quality inspection process. The text feature conditions and audio feature conditions can be used simultaneously when setting quality inspection rules, and the audio data can also be subjected to fine-grained audio feature quality inspection to improve the accuracy of the quality inspection results.

Description

Technical Field

[0001] The present application relates to the technical field of voice data processing, and in particular to a voice quality inspection method, device, electronic device and computer-readable storage medium. Background Art

[0002] Traditional voice quality inspection is usually performed manually by quality inspectors, which takes a lot of time when faced with large amounts of audio data.

[0003] To avoid this situation, the rule engine can be used for speech quality inspection. However, the current method of using the rule engine for speech quality inspection has some disadvantages. For example, the quality inspection rules cannot use text feature conditions and audio feature conditions at the same time; for example, the quality inspection rules cannot superimpose audio feature conditions on the part where specific semantic content appears; or the method of implementing the quality inspection function is relatively complicated, resulting in a very cumbersome speech quality inspection process, wasting a lot of computing time and computing costs, resulting in a high cost of speech quality inspection. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a speech quality inspection method, device, electronic device and computer-readable storage medium, which solves the problem of separate use of text feature conditions and audio features, and improves the accuracy of quality inspection results by performing audio feature quality inspection on audio data.

[0005] In a first aspect, an embodiment of the present application provides a method for speech quality inspection, the method comprising:

[0006] Get audio data;

[0007] Converting the audio data into corresponding text data;

[0008] Performing quality inspection and analysis on the text data to obtain quality inspection and analysis data;

[0009] Outputting quality inspection results according to the quality inspection analysis data.

[0010] In the above implementation process, by performing quality inspection after processing the audio data, both text conditions and audio conditions can be used for quality inspection at the same time, and the quality inspection results can be output. It supports the use of fine-grained quality inspection rules, and can complete the text rule and audio rule judgment at one time, thereby improving the accuracy of the quality inspection results and shortening the time of the quality inspection process.

[0011] Furthermore, the step of performing quality inspection and analysis on the text data to obtain quality inspection and analysis data includes:

[0012] Marking the text data with character coordinates to obtain the character start quality inspection coordinates and the character end quality inspection coordinates of the text data;

[0013] The quality inspection analysis data is obtained according to the character start quality inspection coordinates and the character end quality inspection coordinates.

[0014] In the above implementation process, the text data is marked with character coordinates, so that the coordinate information of the characters in the text data can be obtained, and the text data can be completely acquired without causing loss of the text data.

[0015] Furthermore, the step of obtaining the quality inspection analysis data according to the character start quality inspection coordinates and the character end quality inspection coordinates of the text data includes:

[0016] Convert the character start quality inspection coordinates into corresponding time coordinates to obtain the start time quality inspection coordinates;

[0017] Convert the character end quality inspection coordinates into corresponding time coordinates to obtain end time quality inspection coordinates;

[0018] The quality inspection analysis data is obtained according to the start time quality inspection coordinates and the end time quality inspection coordinates.

[0019] In the above implementation process, the character coordinates are converted into time coordinates, so that the time information corresponding to the characters can be obtained, which is convenient for matching text data and audio data without causing loss of audio data.

[0020] Furthermore, the step of obtaining quality inspection analysis data according to the start time quality inspection coordinates and the end time quality inspection coordinates includes:

[0021] Obtaining audio parameters in the text data;

[0022] Get quality inspection rule parameters;

[0023] The quality inspection analysis data is obtained by matching the quality inspection rule parameters corresponding to the start time quality inspection coordinates and the end time quality inspection coordinates according to the audio parameters.

[0024] In the above implementation process, the audio parameters include the audio information corresponding to the text data, so that the audio data will not lose the audio information due to conversion into text data, thereby ensuring that the quality inspection result is more accurate.

[0025] Furthermore, the step of converting the character end quality inspection coordinates into corresponding time coordinates to obtain the end time quality inspection coordinates includes:

[0026] Obtaining the text sequence length and the interval duration according to the character start quality inspection coordinates and the character end quality inspection coordinates;

[0027] Calculate the timestamp corresponding to each character in the text data according to the text sequence and the interval duration;

[0028] The end time quality inspection coordinates are obtained according to the start time quality inspection coordinates and the timestamp.

[0029] In the above implementation process, the timestamp corresponding to each character can be obtained through the text sequence length and the interval duration, which can ensure the integrity and validity of the audio information corresponding to each character and will not cause the loss of quality inspection analysis of a certain character.

[0030] Furthermore, the timestamp corresponding to each character in the text data is calculated according to the text sequence and the interval duration by the following formula:

[0031] The calculation formula of the timestamp is: G=D / L;

[0032] Among them, G is the timestamp, D is the interval duration, and L is the text sequence length.

[0033] Furthermore, the step of obtaining audio data includes:

[0034] receiving the audio data;

[0035] The audio data is converted to obtain converted audio data.

[0036] In the above implementation process, the audio data is converted to remove invalid information in the audio data and convert the audio data into a data format suitable for quality inspection analysis, so that the quality inspection result is more accurate.

[0037] In a second aspect, an embodiment of the present application further provides a speech quality inspection device, the device comprising:

[0038] An acquisition module, used to acquire audio data;

[0039] A conversion module, used for converting the audio data into corresponding text data;

[0040] A quality inspection module, used to perform quality inspection and analysis on the text data to obtain quality inspection and analysis data;

[0041] An output module is used to output quality inspection results based on the quality inspection analysis data.

[0042] In the above implementation process, by performing quality inspection after processing the audio data, both text conditions and audio conditions can be used for quality inspection at the same time, and the quality inspection results can be output. It supports the use of fine-grained quality inspection rules, and can complete the text rule and audio rule judgment at one time, thereby improving the accuracy of the quality inspection results and shortening the time of the quality inspection process.

[0043] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in any one of the first aspects when executing the computer program.

[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed on a computer, the computer executes the method as described in any one of the first aspects.

[0045] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when running on a computer, enables the computer to execute the method as described in any one of the first aspects.

[0046] Other features and advantages of the present disclosure will be set forth in the following description, or some features and advantages may be inferred or unambiguously determined from the description, or may be learned by implementing the above-mentioned technology of the present disclosure.

[0047] And it can be implemented according to the contents of the specification. The following is a detailed description of the preferred embodiments of the present application with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A flowchart of a speech quality inspection method provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of the structure of a speech quality inspection device provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of the structural composition of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0053] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0054] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0055] Embodiment 1

[0056] Figure 1 is a flow chart of the voice quality inspection method provided in the embodiment of the present application, such as Figure 1 As shown, the method includes:

[0057] S1, obtain audio data;

[0058] S2, converting the audio data into corresponding text data;

[0059] S3, performing quality inspection and analysis on the text data to obtain quality inspection and analysis data;

[0060] S4, outputting quality inspection results based on quality inspection analysis data.

[0061] Taking this embodiment as an example, by performing quality inspection after processing the audio data, both text conditions and audio conditions can be used for quality inspection at the same time, and the quality inspection results can be output. It supports the use of fine-grained quality inspection rules, and can complete the text rule and audio rule judgment at one time, thereby improving the accuracy of the quality inspection results and shortening the time of the quality inspection process.

[0062] Furthermore, S1 includes:

[0063] Receive audio data;

[0064] The audio data is converted to obtain converted audio data.

[0065] Taking this embodiment as an example, the audio data can come from a database website or from audio data collected from business scenarios, such as telephone recordings generated during telephone sales. After collecting the audio data, the encoding format and sampling rate of the audio data are converted to obtain the converted audio data.

[0066] By converting the audio data, invalid information in the audio data can be removed and the audio data can be converted into a data format suitable for quality inspection and analysis, making the quality inspection results more accurate.

[0067] In S2, the audio data is converted into corresponding text data, that is, the timestamp corresponding to the output text or text sequence is output. The text data includes parameters and audio features in the audio data.

[0068] Furthermore, S3 includes:

[0069] Mark the character coordinates of the text data to obtain the character start quality inspection coordinates and the character end quality inspection coordinates of the text data;

[0070] The quality inspection analysis data is obtained according to the character start quality inspection coordinates and the character end quality inspection coordinates.

[0071] The character coordinate system uses the number of characters in the input text data as the coordinate axis, counts them sequentially from 0 and uses them as coordinate values ​​to obtain the character start quality inspection coordinates and character end quality inspection coordinates of the text data.

[0072] Taking this embodiment as an example, by marking the character coordinates of the text data, the coordinate information of the characters in the text data can be obtained, and the text data can be completely acquired without causing the loss of the text data.

[0073] Furthermore, quality inspection analysis data is obtained according to the character start quality inspection coordinates and the character end quality inspection coordinates of the text data, including:

[0074] Convert the character start quality inspection coordinates into corresponding time coordinates to obtain the start time quality inspection coordinates;

[0075] Convert the character end quality inspection coordinates into corresponding time coordinates to obtain the end time quality inspection coordinates;

[0076] The quality inspection analysis data is obtained according to the quality inspection coordinates of the start time and the quality inspection coordinates of the end time.

[0077] Furthermore, quality inspection analysis data is obtained according to the start time quality inspection coordinates and the end time quality inspection coordinates, including:

[0078] Get audio parameters in text data;

[0079] Get quality inspection rule parameters;

[0080] According to the audio parameters, the quality inspection rule parameters corresponding to the start time quality inspection coordinates and the end time quality inspection coordinates are matched to obtain quality inspection analysis data.

[0081] Taking this embodiment as an example, the time coordinate is to use the time as the axis of the characters in the input text data, and use the time interval corresponding to the characters to obtain the characteristic time, such as the minimum value, average value, and maximum value, as the time coordinate value. The character coordinates and the time coordinates can be converted to each other, and the conversion basis is that the coordinates or coordinate intervals under the coordinate system correspond to the same characters. Through this conversion method, the character start quality inspection coordinates and the character end quality inspection coordinates of the text data are converted to the corresponding start time quality inspection coordinates and end time quality inspection coordinates. The quality inspection rule parameters include the audio information corresponding to the text data, so that the audio data will not lose the audio information due to conversion to text data, ensuring that the quality inspection results are more accurate.

[0082] The quality inspection rule parameters include parameters corresponding to the sound features such as volume, speaking speed, interruption, etc., which determine whether the audio data meets the quality inspection requirements. Among them, volume refers to the average volume of a sentence, a paragraph, or the entire audio interval, speaking speed refers to the number of words in the text data corresponding to a sentence, a paragraph, or the entire interval divided by the speaking time, interruption refers to when character A speaks, character B is speaking and character B finishes speaking before A, and interruption refers to when character A speaks, character B is speaking and character B finishes speaking later than A.

[0083] Furthermore, the character end quality inspection coordinates are converted into corresponding time coordinates to obtain the end time quality inspection coordinates, including:

[0084] The text sequence length and interval duration are obtained according to the character start quality inspection coordinates and the character end quality inspection coordinates;

[0085] The timestamp corresponding to each character in the text data is calculated based on the text sequence and interval duration;

[0086] The end time quality inspection coordinates are obtained based on the start time quality inspection coordinates and timestamp.

[0087] Taking this embodiment as an example, the timestamp corresponding to each character can be obtained through the text sequence length and the interval duration, which can ensure the integrity and validity of the audio information corresponding to each character and will not cause the loss of quality inspection analysis of a certain character.

[0088] Furthermore, the timestamp corresponding to each character in the text data is calculated according to the text sequence and the interval duration, including:

[0089] The calculation formula of the timestamp is: G = D / L;

[0090] Among them, G is the timestamp, D is the interval duration, and L is the text sequence length.

[0091] Exemplarily, an interpolation algorithm can be used to convert the time interval corresponding to the text sequence in the character coordinates into the time interval corresponding to each character in the sequence, calculate the text sequence length L, calculate the interval duration D, and obtain the timestamp G=D / L corresponding to each character time interval. The start value of the first character time interval is the start value S of the text sequence time interval, and the end value is its start value plus G; the start value of the second character time interval is the end value of the first character time interval, and the end value is the start value of the second character time interval plus G, and so on to complete the conversion of the entire text sequence. The text sequence length does not contain non-text characters (such as punctuation marks). When obtaining the timestamp corresponding to the characters, the non-text characters such as punctuation marks removed from the text sequence length can be ignored. Exemplarily, integers can be selected for calculating the interval duration, start time, and end time, and milliseconds, microseconds, etc. can be used as units of time.

[0092] Taking this embodiment as an example, by converting character coordinates into time coordinates, the time information corresponding to the characters can be obtained, which facilitates the matching of text data and audio data without causing the loss of audio data.

[0093] In S4, the quality inspection result is output according to the quality inspection analysis data.

[0094] For example, after obtaining the quality inspection and analysis data, it will be rated or scored to determine whether the quality inspection and analysis data meets the requirements, and the score or rating level will be recorded in a file, database or transmitted to a downstream system as the quality inspection result.

[0095] In the embodiment of the present application, quality inspection is performed on the audio data after processing, and text conditions and audio conditions are used simultaneously to perform quality inspection, and the quality inspection results are output without wasting a lot of computing time and computing cost, thereby improving the efficiency of quality inspection and reducing the cost of quality inspection.

[0096] Embodiment 2

[0097] In order to execute the method corresponding to the above embodiment 1 to achieve the corresponding functions and technical effects, a speech quality inspection device is provided below, such as Figure 2 As shown, the device comprises:

[0098] Acquisition module 1, used to acquire audio data;

[0099] Conversion module 2, used for converting audio data into corresponding text data;

[0100] Quality inspection module 3, used to perform quality inspection and analysis on text data to obtain quality inspection and analysis data;

[0101] The output module 4 is used to output the quality inspection results according to the quality inspection analysis data.

[0102] The acquisition module 1 is also used to:

[0103] Receive audio data;

[0104] The audio data is converted to obtain converted audio data.

[0105] The quality inspection module 3 is also used for:

[0106] Mark the character coordinates of the text data to obtain the character start quality inspection coordinates and the character end quality inspection coordinates of the text data;

[0107] The quality inspection analysis data is obtained according to the character start quality inspection coordinates and the character end quality inspection coordinates.

[0108] Convert the character start quality inspection coordinates into corresponding time coordinates to obtain the start time quality inspection coordinates;

[0109] Convert the character end quality inspection coordinates into corresponding time coordinates to obtain the end time quality inspection coordinates;

[0110] The quality inspection analysis data is obtained according to the quality inspection coordinates of the start time and the quality inspection coordinates of the end time.

[0111] Get audio parameters in text data;

[0112] Get quality inspection rule parameters;

[0113] According to the audio parameters, the quality inspection rule parameters corresponding to the start time quality inspection coordinates and the end time quality inspection coordinates are matched to obtain quality inspection analysis data.

[0114] The text sequence length and interval duration are obtained according to the character start quality inspection coordinates and the character end quality inspection coordinates;

[0115] The timestamp corresponding to each character in the text data is calculated based on the text sequence and interval duration;

[0116] The end time quality inspection coordinates are obtained based on the start time quality inspection coordinates and timestamp.

[0117] The calculation formula of the timestamp is: G = D / L;

[0118] Among them, G is the timestamp, D is the interval duration, and L is the text sequence length.

[0119] The above-mentioned speech quality inspection device can implement the method of the above-mentioned embodiment 1. The options in the above-mentioned embodiment 1 are also applicable to this embodiment and will not be described in detail here.

[0120] The rest of the contents of the embodiments of the present application can refer to the contents of the above-mentioned embodiment 1, and will not be repeated in this embodiment.

[0121] Embodiment 3

[0122] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the voice quality inspection method of embodiment 1.

[0123] Optionally, the above-mentioned electronic device may be a server.

[0124] See also Figure 3 , Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include a processor 31, a communication interface 32, a memory 33 and at least one communication bus 34. The communication bus 34 is used to realize direct connection and communication between these components. The communication interface 32 of the device in the embodiment of the present application is used to communicate signaling or data with other node devices. The processor 31 may be an integrated circuit chip with signal processing capabilities.

[0125] The processor 31 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor 31 can also be any conventional processor, etc.

[0126] The memory 33 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc. The memory 33 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 31, the device can execute the above-mentioned Figure 1 The method embodiment involves various steps.

[0127] Optionally, the electronic device may further include a storage controller and an input / output unit. The memory 33, the storage controller, the processor 31, the peripheral interface, and the input / output unit are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components may be electrically connected to each other via one or more communication buses 34. The processor 31 is used to execute executable modules stored in the memory 33, such as software function modules or computer programs included in the device.

[0128] The input and output unit is used to provide users with the task creation and to create a start optional time period or preset execution time for the task to realize the interaction between the user and the server. The input and output unit can be, but is not limited to, a mouse and a keyboard.

[0129] Understandably, Figure 3 The structure shown is for illustration only. The electronic device may also include Figure 3 More or fewer components as shown, or with Figure 3 Different configurations are shown. Figure 3 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0130] In addition, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which implements the speech quality inspection method of embodiment 1 when executed by a processor.

[0131] The embodiment of the present application also provides a computer program product, which, when running on a computer, enables the computer to execute the method described in the method embodiment.

[0132] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0133] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0134] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0135] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0136] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0137] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A speech quality inspection method, characterized in that: The method comprises: Get audio data; Converting the audio data into corresponding text data; Performing quality inspection and analysis on the text data to obtain quality inspection and analysis data; Outputting quality inspection results according to the quality inspection analysis data; The step of performing quality inspection and analysis on the text data to obtain quality inspection and analysis data comprises: Marking the text data with character coordinates to obtain the character start quality inspection coordinates and the character end quality inspection coordinates of the text data; Obtaining the quality inspection analysis data according to the character start quality inspection coordinates and the character end quality inspection coordinates; The step of obtaining the quality inspection analysis data according to the character start quality inspection coordinates and the character end quality inspection coordinates comprises: Convert the character start quality inspection coordinates into corresponding time coordinates to obtain the start time quality inspection coordinates; Convert the character end quality inspection coordinates into corresponding time coordinates to obtain end time quality inspection coordinates; Obtain quality inspection analysis data according to the start time quality inspection coordinates and the end time quality inspection coordinates; The step of obtaining quality inspection analysis data according to the start time quality inspection coordinates and the end time quality inspection coordinates includes: Obtaining audio parameters in the text data; Get quality inspection rule parameters; Matching the quality inspection rule parameters corresponding to the start time quality inspection coordinates and the end time quality inspection coordinates according to the audio parameters to obtain the quality inspection analysis data; The step of converting the character end quality inspection coordinates into corresponding time coordinates to obtain the end time quality inspection coordinates comprises: Obtaining the text sequence length and the interval duration according to the character start quality inspection coordinates and the character end quality inspection coordinates; Calculate the timestamp corresponding to each character in the text data according to the length of the text sequence and the interval duration; The end time quality inspection coordinates are obtained according to the start time quality inspection coordinates and the timestamp.

2. The method for voice quality inspection according to claim 1, characterized in that: The timestamp corresponding to each character in the text data is calculated according to the length of the text sequence and the duration of the interval using the following formula: The calculation formula of the timestamp is: G = D / L; Among them, G is the timestamp, D is the interval duration, and L is the text sequence length.

3. The method for voice quality inspection according to claim 2, characterized in that: The step of obtaining audio data comprises: receiving the audio data; The audio data is converted to obtain converted audio data.

4. A speech quality inspection device, characterized in that: The device comprises: An acquisition module, used to acquire audio data; A conversion module, used for converting the audio data into corresponding text data; A quality inspection module, used to perform quality inspection and analysis on the text data to obtain quality inspection and analysis data; An output module, used to output quality inspection results based on the quality inspection analysis data; The quality inspection module is also used for: Marking the text data with character coordinates to obtain the character start quality inspection coordinates and the character end quality inspection coordinates of the text data; Obtain the quality inspection analysis data according to the character start quality inspection coordinates and the character end quality inspection coordinates; Convert the character start quality inspection coordinates into corresponding time coordinates to obtain the start time quality inspection coordinates; Convert the character end quality inspection coordinates into corresponding time coordinates to obtain end time quality inspection coordinates; Obtain quality inspection analysis data according to the start time quality inspection coordinates and the end time quality inspection coordinates; Obtaining audio parameters in the text data; Get quality inspection rule parameters; Matching the quality inspection rule parameters corresponding to the start time quality inspection coordinates and the end time quality inspection coordinates according to the audio parameters to obtain the quality inspection analysis data; Obtaining the text sequence length and the interval duration according to the character start quality inspection coordinates and the character end quality inspection coordinates; Calculate the timestamp corresponding to each character in the text data according to the length of the text sequence and the interval duration; The end time quality inspection coordinates are obtained according to the start time quality inspection coordinates and the timestamp.

5. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the speech quality inspection method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the speech quality inspection method according to any one of claims 1 to 3.

Images