Voice quality assessment method and device

By playing preset voice files, receiving and comparing voice information transmitted by mobile networks, obtaining voice difference information, and combining text recognition rate, the problem of the existing technology failing to consider the time delay and amplitude changes is solved, and the mobile network is realized Effective evaluation of voice quality, the evaluation results are consistent with the user's feelings.

CN114071539BActive Publication Date: 2024-11-15CHINA TELECOM CORP LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010795964.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-08-10
Publication Date
2024-11-15
Estimated Expiration
2040-08-10

AI Technical Summary

Technical Problem

The prior art fails to consider the impact of delay and encoding introduced by mobile network transmission on sound amplitude when evaluating voice quality, and cannot be effectively applied to mobile network voice quality evaluation.

Method used

By playing preset voice files, receiving and comparing the voice information transmitted by the mobile network, obtaining voice difference information, including delay and amplitude change ratio, and combining text recognition rate, a specific evaluation formula is used to evaluate speech quality.

Benefits of technology

An effective evaluation of the voice quality of mobile networks is achieved. The evaluation results are positively correlated with the text recognition rate, and the speech delay and amplitude change ratio are negatively correlated, which can directly reflect users' feelings about the voice quality of mobile networks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114071539B_ABST
    Figure CN114071539B_ABST
Patent Text Reader

Abstract

The present disclosure provides a voice quality assessment method and device. The voice quality assessment device plays a preset first voice file through a mobile network; receives voice information played through a delayed mobile network to generate a second voice file; compares the delayed first voice file and the delayed second voice file to obtain voice difference information; performs voice recognition on the delayed second voice file, and determines the text recognition rate in the delayed second language file with reference to the text information associated with the delayed first voice file; evaluates the voice quality of the delayed mobile network based on the delayed voice difference information and the delayed text recognition rate to obtain an evaluation result. The present disclosure can achieve effective evaluation of the voice quality of the mobile network, and can directly evaluate the user's direct perception of the mobile network voice quality.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of communications, and in particular to a method and device for evaluating speech quality. Background Art

[0002] The voice quality of mobile networks is usually evaluated using the Mean Opinion Score (MOS) algorithm. Professional instruments are used to process the degraded signal after wireless network transmission through level adjustment, filtering and other processing steps. The transformed signal is compared with the original signal and then mapped to the prediction of the subjective mean opinion score through a cognitive model. Summary of the invention

[0003] The inventors have found through research that, when evaluating voice quality, the related technology does not take into account the delay introduced by mobile network transmission and the impact of encoding on the sound amplitude, so the related technology cannot be directly applied to mobile network voice quality evaluation.

[0004] Accordingly, the present disclosure provides a voice quality assessment solution that can effectively assess the voice quality of a mobile network.

[0005] According to a first aspect of an embodiment of the present disclosure, a voice quality assessment method is provided, comprising: playing a preset first voice file through a mobile network; receiving voice information played through the mobile network to generate a second voice file; comparing the first voice file and the second voice file to obtain voice difference information; performing voice recognition on the second voice file, and determining a text recognition rate in the second language file with reference to text information associated with the first voice file; and assessing the voice quality of the mobile network based on the voice difference information and the text recognition rate to obtain an assessment result.

[0006] In some embodiments, the voice difference information includes at least one of a voice delay of the second voice file relative to the first voice file, or a voice amplitude change ratio of the second voice file relative to the first voice file.

[0007] In some embodiments, the evaluation result is positively correlated with the text recognition rate, and negatively correlated with the speech delay and the speech amplitude change ratio.

[0008] In some embodiments, evaluating the voice quality of the mobile network according to the voice difference information and the text recognition rate includes: obtaining an evaluation result Score using the following formula:

[0009] Score=X-MIN((MAX(Y,a)-a) / a*b,c)-MIN(ABS(1-Z)*b,c)

[0010] Wherein MIN is the minimum value function, MAX is the maximum value function, ABS is the absolute value function, a, b, c are preset parameters, X is the text recognition rate, Y is the speech delay, and Z is the speech amplitude change ratio.

[0011] According to a second aspect of an embodiment of the present disclosure, a voice quality assessment device is provided, comprising: a playback module, configured to play a preset first voice file through a mobile network; a receiving module, configured to receive voice information played through the mobile network to generate a second voice file; a transmission analysis module, configured to compare the first voice file and the second voice file to obtain voice difference information; a voice recognition module, configured to perform voice recognition on the second voice file, and determine a text recognition rate in the second language file with reference to text information associated with the first voice file; and an assessment module, configured to assess the voice quality of the mobile network based on the voice difference information and the text recognition rate to obtain an assessment result.

[0012] In some embodiments, the voice difference information includes at least one of a voice delay of the second voice file relative to the first voice file, or a voice amplitude change ratio of the second voice file relative to the first voice file.

[0013] In some embodiments, the evaluation result is positively correlated with the text recognition rate, and negatively correlated with the speech delay and the speech amplitude change ratio.

[0014] In some embodiments, the evaluation module is configured to obtain the evaluation result Score using the following formula:

[0015] Score=X-MIN((MAX(Y,a)-a) / a*b,c)-MIN(ABS(1-Z)*b,c)

[0016] Wherein MIN is the minimum value function, MAX is the maximum value function, ABS is the absolute value function, a, b, c are preset parameters, X is the text recognition rate, Y is the speech delay, and Z is the speech amplitude change ratio.

[0017] According to a third aspect of an embodiment of the present disclosure, a speech quality assessment device is provided, comprising: a memory configured to store instructions; a processor coupled to the memory, the processor being configured to execute a method as described in any of the above embodiments based on the instructions stored in the memory.

[0018] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the method described in any of the above embodiments is implemented.

[0019] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0021] The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0022] Figure 1 is a flow chart of a method for evaluating speech quality according to an embodiment of the present disclosure;

[0023] Figure 2 is a structural schematic diagram of a speech quality assessment device according to an embodiment of the present disclosure;

[0024] Figure 3 It is a structural diagram of a speech quality assessment device according to another embodiment of the present disclosure.

[0025] It should be understood that the size of each part shown in the accompanying drawings is not drawn according to the actual proportional relationship. In addition, the same or similar reference numerals represent the same or similar components. DETAILED DESCRIPTION

[0026] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. The description of the exemplary embodiments is merely illustrative and is in no way intended to limit the present disclosure and its application or use. The present disclosure can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to make the present disclosure thorough and complete and to fully express the scope of the present disclosure to those skilled in the art. It should be noted that unless otherwise specifically stated, the relative arrangement of the components and steps, the composition of the materials, and the numerical values ​​set forth in these embodiments should be interpreted as being merely exemplary and not as limiting.

[0027] The words “include” or “comprising” and the like used in the present disclosure mean that the elements preceding the words include the elements listed after the words, and do not exclude the possibility of also including other elements.

[0028] All terms (including technical terms or scientific terms) used in the present disclosure have the same meanings as those understood by ordinary technicians in the field to which the present disclosure belongs, unless otherwise specifically defined. It should also be understood that terms defined in general dictionaries, such as general dictionaries, should be interpreted as having meanings consistent with their meanings in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined herein.

[0029] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0030] Figure 1 The figure is a flow chart of a method for evaluating speech quality according to an embodiment of the present disclosure. In some embodiments, the following steps of the method for evaluating speech quality are performed by a speech quality evaluating device.

[0031] In step 101, a preset first voice file is played via a mobile network.

[0032] It should be noted that the first voice file may be a voice file including any language of any country such as Chinese, English, French, etc. The first voice file may contain at least one of a male or a female voice. The first voice file contains voices of any age group.

[0033] In addition, the first voice file may be any media containing text, including movies, television programs, radio programs, Internet audio and video, etc.

[0034] In some embodiments, when playing the first voice file through the mobile network, the volume of the playback can be set, for example, to 80%. The playback mode can be continuous playback, interval playback or repeated playback.

[0035] In step 102, voice information played through a mobile network is received to generate a second voice file.

[0036] In step 103, the first voice file and the second voice file are compared to obtain voice difference information.

[0037] In some embodiments, the voice difference information includes at least one of a voice delay of the second voice file relative to the first voice file, or a voice amplitude change ratio of the second voice file relative to the first voice file.

[0038] In some embodiments, the corresponding time of the voice is obtained from the second voice file periodically (typically 8 seconds, 4 seconds, etc.) through waveform recognition, insertion of marker sounds, etc., and compared with the playback time of the corresponding voice in the first voice file to obtain the voice delay.

[0039] In some embodiments, the amplitude of the second voice file is determined by means of envelope detection or the like, and is compared with the amplitude of the first voice file to obtain the amplitude change ratio of the voice.

[0040] In step 104, speech recognition is performed on the second speech file, and a text recognition rate in the second language file is determined by referring to text information associated with the first speech file.

[0041] In step 105, the voice quality of the mobile network is evaluated according to the voice difference information and the text recognition rate to obtain an evaluation result.

[0042] In some embodiments, the evaluation result is positively correlated with the text recognition rate, and negatively correlated with the speech delay and the speech amplitude change ratio.

[0043] For example, the following formula is used to obtain the evaluation result Score:

[0044] Score=X-MIN((MAX(Y,a)-a) / a*b,c)-MIN(ABS(1-Z)*b,c)

[0045] Among them, MIN is the minimum function, MAX is the maximum function, ABS is the absolute value function, a, b, c are preset parameters, X is the text recognition rate, Y is the speech delay, and Z is the speech amplitude change ratio. For example, a is 20, b is 0.01, and c is 0.2.

[0046] In the voice quality assessment method provided in the above embodiment of the present disclosure, by evaluating the text recognition rate, voice delay, and voice amplitude change ratio of the voice information played by the mobile network, the voice quality of the mobile network can be effectively evaluated while directly evaluating the user's direct perception of the mobile network voice quality.

[0047] Figure 2 FIG. 1 is a schematic diagram of the structure of a speech quality assessment device according to an embodiment of the present disclosure. Figure 2 As shown, the speech quality assessment device includes a playing module 21 , a receiving module 22 , a transmission analysis module 23 , a speech recognition module 24 and an assessment module 25 .

[0048] The playing module 21 is configured to play a preset first voice file through a mobile network.

[0049] The receiving module 22 is configured to receive voice information played through a mobile network to generate a second voice file.

[0050] The transmission analysis module 23 is configured to compare the first voice file and the second voice file to obtain voice difference information.

[0051] In some embodiments, the voice difference information includes at least one of a voice delay of the second voice file relative to the first voice file, or a voice amplitude change ratio of the second voice file relative to the first voice file.

[0052] The speech recognition module 24 is configured to perform speech recognition on the second speech file, and determine a text recognition rate in the second language file with reference to text information associated with the first speech file.

[0053] The evaluation module 25 is configured to evaluate the voice quality of the mobile network according to the voice difference information and the text recognition rate to obtain an evaluation result.

[0054] In some embodiments, the evaluation result is positively correlated with the text recognition rate, and negatively correlated with the speech delay and the speech amplitude change ratio.

[0055] In some embodiments, the evaluation module 25 is configured to obtain the evaluation result Score using the following formula:

[0056] Score=X-MIN((MAX(Y,a)-a) / a*b,c)-MIN(ABS(1-Z)*b,c)

[0057] Among them, MIN is the minimum function, MAX is the maximum function, ABS is the absolute value function, a, b, c are preset parameters, X is the text recognition rate, Y is the speech delay, and Z is the speech amplitude change ratio. For example, a is 20, b is 0.01, and c is 0.2.

[0058] Figure 3 FIG. 1 is a schematic diagram of the structure of a speech quality assessment device according to another embodiment of the present disclosure. Figure 3 As shown, the speech quality assessment device includes a memory 31 and a processor 32 .

[0059] The memory 31 is used to store instructions. The processor 32 is coupled to the memory 31. The processor 32 is configured to execute the instructions stored in the memory to implement the following. Figure 1 The method of any one of the embodiments.

[0060] like Figure 3 As shown, the speech quality assessment device further includes a communication interface 33 for information exchange with other devices. At the same time, the speech quality assessment device further includes a bus 34, through which the processor 32, the communication interface 33, and the memory 31 communicate with each other.

[0061] The memory 31 may include high-speed RAM (Random Access Memory) and may also include NVM (Non-Volatile Memory). For example, at least one disk storage. The memory 31 may also be a storage array. The memory 31 may also be divided into blocks, and the blocks may be combined into virtual volumes according to certain rules.

[0062] In addition, the processor 32 may be a central processing unit, or may be an ASIC (Application Specific Integrated Circuit), or may be configured to implement one or more integrated circuits of the embodiments of the present disclosure.

[0063] The present disclosure also provides a computer-readable storage medium. The computer-readable storage medium stores computer instructions, which are executed by a processor to implement the following Figure 1 The method of any one of the embodiments.

[0064] In some embodiments, the above-mentioned functional modules can be implemented as a general-purpose processor, a programmable logic controller (PLC), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components or any appropriate combination thereof for performing the functions described in the present disclosure.

[0065] So far, the embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solutions disclosed herein.

[0066] Although some specific embodiments of the present disclosure have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified or some technical features may be replaced by equivalents without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for evaluating speech quality, include: Playing a preset first voice file via a mobile network; receiving voice information played through the mobile network to generate a second voice file; Comparing the first voice file with the second voice file to obtain voice difference information, wherein the voice difference information includes a voice delay of the second voice file relative to the first voice file, and a voice amplitude change ratio of the second voice file relative to the first voice file; Performing speech recognition on the second speech file, and determining a text recognition rate in the second speech file by referring to text information associated with the first speech file; Evaluating the voice quality of the mobile network according to the voice difference information and the text recognition rate to obtain an evaluation result; Among them, the evaluation result Score is: Wherein MIN is the minimum value function, MAX is the maximum value function, ABS is the absolute value function, a, b, c are preset parameters, X is the text recognition rate, Y is the speech delay, and Z is the speech amplitude change ratio.

2. The method according to claim 1, in, The evaluation result is positively correlated with the text recognition rate, and negatively correlated with the speech delay and the speech amplitude change ratio.

3. A speech quality assessment device, include: A playing module, configured to play a preset first voice file via a mobile network; A receiving module, configured to receive voice information played through the mobile network to generate a second voice file; A transmission analysis module, configured to compare the first voice file and the second voice file to obtain voice difference information, wherein the voice difference information includes a voice delay of the second voice file relative to the first voice file, and a voice amplitude change ratio of the second voice file relative to the first voice file; a speech recognition module configured to perform speech recognition on the second speech file and determine a text recognition rate in the second speech file with reference to text information associated with the first speech file; The evaluation module is configured to evaluate the voice quality of the mobile network according to the voice difference information and the text recognition rate to obtain an evaluation result, wherein the evaluation result Score is: Wherein MIN is the minimum value function, MAX is the maximum value function, ABS is the absolute value function, a, b, c are preset parameters, X is the text recognition rate, Y is the speech delay, and Z is the speech amplitude change ratio.

4. The device according to claim 3, in, The evaluation result is positively correlated with the text recognition rate, and negatively correlated with the speech delay and the speech amplitude change ratio.

5. A speech quality assessment device, include: a memory configured to store instructions; A processor is coupled to the memory, and the processor is configured to execute the method according to any one of claims 1 to 2 based on instructions stored in the memory.

6. A computer-readable storage medium, in, The computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the method according to any one of claims 1 to 2 is implemented.