Method and system for evaluating spoken language ability and storage medium

Abstract

The invention provides a method and system for evaluating spoken language ability and a storage medium, and relates to the technical field of spoken language evaluation.The method comprises the steps that environment audio signals of an input environment are collected and preprocessed, environment noise power used for reflecting the power value of environment noise is generated, correlation analysis is conducted on the environment noise power, and the spoken language ability is evaluated; the method comprises the following steps: generating an environmental noise influence evaluation index which reflects the influence degree of environmental noise on an input signal, setting a standard spoken language set, collecting spoken language parameters of a spoken language ability training object, analyzing the spoken language parameters, and generating a speech speed accuracy evaluation index which is used for evaluating the relationship between the speech speed of a to-be-tested person and the equipment output accuracy; after comprehensive analysis, a spoken language evaluation comprehensive index used for reflecting comprehensive evaluation in combination with the current environment and the speech speed of the to-be-tested person is generated and compared with an accurate threshold value, then the spoken language ability evaluation accuracy level of the to-be-tested person is output, and the spoken language ability evaluation accuracy is evaluated.

Description

Technical Field

[0001] The present invention relates to the technical field of oral evaluation, and specifically to a method, a system and a storage medium for evaluating oral ability. Background Art

[0002] In recent years, speech recognition technology has made remarkable progress and become an important tool for evaluating oral ability. It converts human speech signals into readable text, thereby analyzing and evaluating an individual's language expression ability. In the field of education, especially in foreign language learning, speech recognition systems can provide real-time feedback on learners' pronunciation, speech rate, and fluency, helping them identify and correct pronunciation errors, and improving the accuracy and confidence of oral expression. At the same time, this technology can also automatically score in oral tests, providing more objective and fair evaluation results, and reducing the workload of teachers. Through in-depth analysis of speech data, speech recognition systems can not only recognize the content of speech, but also evaluate the fluency and naturalness of oral speech by analyzing elements such as the rhythm, intonation, and stress of speech. In addition, speech recognition technology is adaptable and can be optimized according to the pronunciation habits and language backgrounds of different learners, thus providing a personalized learning experience. The application of this technology not only improves the efficiency and accuracy of oral ability evaluation, but also provides learners with richer learning resources, promoting the motivation for autonomous learning and continuous progress.

[0003] Generally, when evaluating oral ability based on speech recognition, due to the different speech rates of the candidates to be evaluated, the accuracy of the candidates whose speech rates are closer to the standard oral speech rate will be relatively high, while the accuracy of the candidates whose speech rates deviate from the standard oral speech rate will be relatively low. At the same time, environmental noise will affect the collected audio signals and also affect the evaluation accuracy.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a method, a system and a storage medium for evaluating oral ability to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A method for evaluating oral ability, the specific steps of the present invention include:

[0008] S1. Collect the environmental audio signal of the input environment;

[0009] S2. Preprocess the environmental audio signal to generate a discrete-time signal, and perform a short-time Fourier transform on the environmental audio signal in combination with the discrete-time signal to generate an environmental audio frequency-domain signal. The discrete-time signal is used to reflect the signal strength at each discrete time point, and the environmental audio frequency-domain signal is used to reflect the amplitude of the environmental audio at the corresponding frequency and time.

[0010] S3. Perform a correlation analysis on the environmental audio frequency-domain signal to generate an environmental audio power spectrum, and perform a correlation analysis on the environmental audio power spectrum to generate an environmental noise power. The environmental audio power spectrum is used to reflect the power value of the environmental audio at the corresponding frequency and time, and the environmental noise power is used to reflect the power value of the environmental noise.

[0011] S4. Perform a correlation analysis on the environmental noise power to generate an environmental noise impact assessment index HZP. The environmental noise impact assessment index HZP is used to reflect the degree of influence of the environmental noise on the input signal.

[0012] S5. Set a standard spoken language set, have 20 spoken language ability training objects repeat after the standard spoken language set, collect the spoken language parameters during the repetition process. The spoken language parameters include speech rate and recognition accuracy. Perform a correlation analysis on the spoken language parameters during the repetition process to generate an accuracy expression. Conduct a spoken language test on the person to be tested using a speech recognition device. Based on the speech rate of the person to be tested and the accuracy expression, generate a speech rate accuracy assessment index YZP. The speech rate accuracy assessment index YZP is the recognition accuracy of the speech recognition device for the speech rate of the person to be tested. The person to be tested is the person whose spoken language ability will be evaluated using speech recognition.

[0013] S6. Perform a correlation analysis on the speech rate accuracy assessment index YZP and the environmental noise impact assessment index HZP to generate a comprehensive spoken language evaluation index KPZ. The comprehensive spoken language evaluation index KPZ is used to reflect a comprehensive evaluation by combining the current environment and the speech rate of the person to be tested.

[0014] S7. Compare the comprehensive spoken language evaluation index KPZ with the accuracy threshold and output the accuracy level of the spoken language ability evaluation of the person to be tested.

[0015] Further, in the recording environment, set a microphone on each side of the recording point, connect the microphones through an audio acquisition device, and store the environmental audio signals collected by the two microphones as a time series signal.

[0016] Further, preprocess the environmental audio signal to generate a discrete-time signal , and the formula is:

[0017] Among them, , is the sampling frequency, n is a positive integer, used to index discrete sampling time points, and the discrete-time signal is used to reflect the signal strength at each discrete time point.

[0018] Furthermore, the short-time Fourier transform is performed on the environmental audio signal in combination with the discrete-time signal to generate the environmental audio frequency-domain signal , and the formula is:

[0019] Among them, represents the imaginary number, is the window function, used to limit the time range, , where N is the size of the window, , and the environmental audio frequency-domain signal is used to reflect the amplitude of the environmental audio at frequency f and time t.

[0020] Furthermore, correlation analysis is performed on the environmental audio frequency-domain signal to generate the environmental audio power spectrum , and the formula is:

[0021] The environmental audio power spectrum is used to reflect the power value of the environmental audio at the corresponding frequency f and time t, is the modulo operation.

[0022] Furthermore, correlation analysis is performed on the environmental audio power spectrum to generate the environmental noise power , and the formula is:

[0023] Among them, F is the maximum frequency value, T is the time for the microphone to collect the environmental audio signal, in seconds, and the environmental noise power is used to reflect the power value of the environmental noise;

[0024] Correlation analysis is performed on the environmental noise power to generate the environmental noise impact assessment index HZP, and the formula is:

[0025]

[0026] Among them, is the input power of the microphone, is the input sensitivity weight factor of the microphone, The value range of , and the environmental noise impact assessment index HZP is used to reflect the degree of influence of environmental noise on the input signal.

[0027] Further, the standard spoken language set is a spoken language comparison audio, including the standard speech rate SR, and the speech rate is the number of repeated words per minute of the i-th spoken language ability training object, and the recognition accuracy is the accuracy of word recognition output by the i-th spoken language ability training object using a speech recognition device. Perform a correlation analysis on the spoken language parameters during the repetition process to generate an accuracy expression AR. The formula based on is:

[0028]

[0029] Substitute the corresponding spoken language parameters of all spoken language ability training objects collected into the above formula, substitute the speech rate into v, and substitute the recognition accuracy into AR. Use MATLAB software to fit and generate the values of a and b;

[0030] Perform a correlation analysis on the accuracy expression AR to generate a speech rate accuracy evaluation index YZP. The formula based on is:

[0031]

[0032] where V is the speech rate of the person to be tested, and the speech rate accuracy evaluation index YZP is used to evaluate the relationship between the speech rate of the person to be tested and the output accuracy of the device;

[0033] Perform a correlation analysis on the speech rate accuracy evaluation index YZP and the environmental noise impact evaluation index HZP to generate a comprehensive spoken language evaluation index KPZ. The formula based on is:

[0034]

[0035] where, is the speech rate accuracy weight factor, The value range of is, and the comprehensive spoken language evaluation index KPZ is used to reflect the accuracy of comprehensively evaluating the spoken language ability test by combining the current environment and the speech rate of the person to be tested.

[0036] Further, the accurate threshold takes the value of 15.7. Compare the comprehensive spoken language evaluation index KPZ with the accurate threshold When , it means that the accuracy of the spoken language ability evaluation of the person to be tested in the current environment is level two, and the spoken language ability evaluation is inaccurate; when , it means that the accuracy of the spoken language ability evaluation of the person to be tested in the current environment is level one, and the spoken language ability evaluation is accurate.

[0037] The present invention also proposes a system for evaluating spoken language ability, which is used to execute the method for evaluating spoken language ability, including:

[0038] A signal acquisition module for acquiring the environmental audio signal of the input environment;

[0039] An environmental audio signal processing module for preprocessing the environmental audio signal to generate a discrete-time signal, and performing a short-time Fourier transform on the environmental audio signal in combination with the discrete-time signal to generate an environmental audio frequency-domain signal;

[0040] A frequency-domain signal analysis module for performing a correlation analysis on the environmental audio frequency-domain signal to generate an environmental audio power spectrum, and performing a correlation analysis on the environmental audio power spectrum to generate an environmental noise power;

[0041] An environmental noise power analysis module for performing a correlation analysis on the environmental noise power to generate an environmental noise impact assessment index;

[0042] A speech rate analysis module for setting a standard spoken language set, setting 20 speech ability training objects to repeat after the standard spoken language set, collecting the speech parameters during the repetition process, performing a correlation analysis on the speech parameters during the repetition process to generate an accuracy expression, and performing a correlation analysis on the accuracy expression to generate a speech rate accuracy assessment index;

[0043] A comprehensive analysis module for performing a correlation analysis on the speech rate accuracy assessment index YZP and the environmental noise impact assessment index HZP to generate a comprehensive oral evaluation index KPZ, and the comprehensive oral evaluation index KPZ is used to reflect a comprehensive evaluation in combination with the current environment and the speech rate of the person to be tested.

[0044] The present invention also proposes a storage medium, on which computer program instructions are stored, and the computer program instructions are executed by a processor to perform the method described above.

[0045] Compared with the prior art, the beneficial effects of the present invention are:

[0046] The present invention acquires the environmental audio signal of the input environment, preprocesses it to generate an environmental noise power reflecting the power value of the environmental noise, performs a correlation analysis on it to generate an environmental noise impact assessment index reflecting the degree of influence of the environmental noise on the input signal, sets a standard spoken language set at the same time, collects the speech parameters of the speech ability training objects, and generates a speech rate accuracy assessment index for evaluating the relationship between the speech rate of the person to be tested and the output accuracy of the device after analysis. After comprehensive analysis, a comprehensive oral evaluation index reflecting a comprehensive evaluation in combination with the current environment and the speech rate of the person to be tested is generated, and the accuracy level of the oral ability evaluation of the person to be tested is output after comparison with the accurate threshold, and the accuracy of the oral ability evaluation is evaluated. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0048] Figure 2 This is a schematic diagram of the overall system process of the present invention. Detailed implementation manners

[0049] To make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with specific embodiments.

[0050] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those with ordinary skills in the field to which the present invention pertains. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. The terms such as "comprising" or "including" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0051] Embodiment:

[0052] Please refer to Figure 1 and Figure 2 The present invention provides a technical solution:

[0053] Referring to Figure 1 a method for evaluating oral language ability, which is used to evaluate the accuracy of speech recognition-based oral language evaluation. When evaluating oral language ability, due to the limited human resources, speech recognition is often used to evaluate the accuracy of oral language ability. However, since the speech rates of the candidates to be evaluated are different, the accuracy rate of the candidates whose speech rates are relatively close to the standard oral language rate will be relatively high, while the accuracy rate of the candidates whose speech rates deviate from the standard oral language rate will be relatively low. At the same time, environmental noise will affect the collected audio signals and also affect the accuracy rate. To evaluate the influence of speech rate and environment on the accuracy of oral language evaluation, the specific steps include:

[0054] Step 1: Collect the environmental audio signals of the recording environment;

[0055] To collect the audio signals of the environment, in the recording environment, a microphone is respectively arranged on both sides of the recording point, and the microphone is connected to an audio acquisition device. The environmental audio signals collected by the two microphones are stored as time series signals. The environmental audio signals are collected by the two microphones and subjected to averaging processing, so as to improve the accuracy.

[0056] Step 2: To better analyze the environmental audio signal, it is necessary to perform a short-time Fourier transform on it to more intuitively display the relationship between time, frequency, and signal intensity. Preprocess the environmental audio signal to generate a discrete-time signal, and perform a short-time Fourier transform on the environmental audio signal in combination with the discrete-time signal to generate an environmental audio frequency-domain signal. The discrete-time signal is used to reflect the signal intensity at each discrete time point, and the environmental audio frequency-domain signal is used to reflect the amplitude of the environmental audio at the corresponding frequency and time;

[0057] Preprocess the environmental audio signal to generate a discrete-time signal , and the formula is:

[0058] where , is the sampling frequency, n is a positive integer used to index discrete sampling time points, and the interval of the time points for sampling the environmental audio signal by the microphone is . Starting from zero, the discrete-time signal is used to reflect the signal intensity at each discrete time point.

[0059] Perform a short-time Fourier transform on the environmental audio signal in combination with the discrete-time signal to generate an environmental audio frequency-domain signal , and the formula is:

[0060] where represents the imaginary number, is the window function used to limit the time range, , where N is the size of the window, , and the environmental audio frequency-domain signal is used to reflect the amplitude of the environmental audio at frequency f and time t.

[0061] Step 3: To analyze the power of the environmental audio, perform a correlation analysis on the environmental audio frequency-domain signal to generate an environmental audio power spectrum, and perform a correlation analysis on the environmental audio power spectrum to generate environmental noise power. The environmental audio power spectrum is used to reflect the power value of the environmental audio at the corresponding frequency and time, and the environmental noise power is used to reflect the power value of the environmental noise;

[0062] Perform a correlation analysis on the environmental audio frequency-domain signal to generate an environmental audio power spectrum , and the formula is:

[0063] The environmental audio power spectrum is used to reflect the power value of the environmental audio at the corresponding frequency f and time t, It is modular arithmetic.

[0064] Perform a correlation analysis on the ambient audio power spectrum to generate the ambient noise power , and the formula is:

[0065] where F is the maximum frequency value, T is the time for the microphone to collect the ambient audio signal in seconds, and the ambient noise power is used to reflect the power value of the ambient noise; the larger the value of the ambient noise power , the higher the degree of participation of the ambient noise in speech recognition, that is, the lower the accuracy of speech recognition.

[0066] Step 4: Perform a correlation analysis on the ambient noise power to generate the ambient noise impact assessment index HZP. The ambient noise impact assessment index HZP is used to reflect the degree of influence of the ambient noise on the input signal;

[0067] Perform a correlation analysis on the ambient noise power to generate the ambient noise impact assessment index HZP. The formula is:

[0068]

[0069] where is the input power of the microphone, is the input sensitivity weight factor of the microphone, The value range of is

[0070] Since the speech speeds of the candidates to be evaluated vary, the accuracy of the candidates who are closer to the standard spoken speech speed will be relatively high, while the accuracy of the candidates who deviate from the standard spoken speech speed will be relatively low. Therefore, the speech speed of the candidates to be evaluated will affect the accuracy of the oral evaluation. Analyze this relationship through the following steps:

[0071] Step 5: Set a standard spoken language set. Have 20 spoken language ability training objects repeat after the standard spoken language set, and collect the spoken language parameters during the repetition process. The spoken language parameters include the speaking speed and the recognition accuracy rate. The recognition accuracy rate is a ratio, that is, the ratio of the number of words correctly recognized by the speech recognition device for the content repeated by the spoken language ability training object to the total number of words in the content repeated by the spoken language ability training object. Conduct a correlation analysis on the spoken language parameters during the repetition process to generate an accuracy rate expression. Conduct a spoken language test on the person to be tested using the speech recognition device. Based on the speaking speed of the person to be tested and the accuracy rate expression, generate the speaking speed accuracy rate evaluation index YZP. The speaking speed accuracy rate evaluation index YZP is the recognition accuracy rate of the speech recognition device for the speaking speed of the person to be tested. The person to be tested is the person whose spoken language ability will be evaluated using speech recognition;

[0072] Step 6: Conduct a correlation analysis on the speaking speed accuracy rate evaluation index YZP and the environmental noise impact evaluation index HZP to generate the comprehensive spoken language evaluation index KPZ. The comprehensive spoken language evaluation index KPZ is used to reflect the comprehensive evaluation by combining the current environment and the speaking speed of the person to be tested;

[0073] The standard spoken language set is a spoken language comparison audio, including the standard speaking speed SR. The speaking speed is the number of words repeated per minute by the i-th spoken language ability training object. The recognition accuracy rate is the accuracy rate of word recognition output by the i-th spoken language ability training object using the speech recognition device. Conduct a correlation analysis on the spoken language parameters during the repetition process to generate the accuracy rate expression AR. The formula based on is:

[0074]

[0075] Substitute the corresponding spoken language parameters of all the spoken language ability training objects collected into the above formula. Substitute the speaking speed into v and the recognition accuracy rate into AR, and use MATLAB software to fit and generate the values of a and b;

[0076] Conduct a correlation analysis on the accuracy rate expression AR to generate the speaking speed accuracy rate evaluation index YZP. The formula based on is:

[0077]

[0078] Among them, V is the speaking speed of the person to be tested. The speaking speed accuracy rate evaluation index YZP is used to evaluate the relationship between the speaking speed of the person to be tested and the output accuracy rate of the device;

[0079] Conduct a correlation analysis on the speaking speed accuracy rate evaluation index YZP and the environmental noise impact evaluation index HZP to generate the comprehensive spoken language evaluation index KPZ. The formula based on is:

[0080]

[0081] Among them, is the weight factor of speech rate accuracy, The value range of is, and the weight factor of speech rate accuracy is used to adjust the influence degree of speech rate on accuracy. The larger the value, the higher the weight. The comprehensive oral evaluation index KPZ is used to reflect the accuracy of comprehensively evaluating the oral ability test by combining the current environment and the speech rate of the person to be tested. The larger the value of the comprehensive oral evaluation index KPZ, the lower the accuracy of the comprehensive evaluation of the oral ability test.

[0082] Step 7: Compare the comprehensive oral evaluation index KPZ with the accuracy threshold and output the accuracy level of the oral ability evaluation of the person to be tested.

[0083] The accuracy threshold takes the value of 15.7. Compare the comprehensive oral evaluation index KPZ with the accuracy threshold . When , it means that the accuracy of the oral ability evaluation of the person to be tested in the current environment is level two, and the oral ability evaluation is inaccurate; when , it means that the accuracy of the oral ability evaluation of the person to be tested in the current environment is level one, and the oral ability evaluation is accurate. The larger the value of the comprehensive oral evaluation index KPZ, the lower the accuracy of the oral ability test. When the accuracy of the oral ability evaluation of the person to be tested is level two, re-measurement is required.

[0084] Referring to Figure 2 , the present invention also proposes a system for evaluating oral ability, which is used to execute the method for evaluating oral ability, including:

[0085] A signal acquisition module, which is used to acquire the environmental audio signal of the input environment;

[0086] An environmental audio signal processing module, which is used to preprocess the environmental audio signal to generate a discrete-time signal, and perform a short-time Fourier transform on the environmental audio signal in combination with the discrete-time signal to generate an environmental audio frequency-domain signal;

[0087] A frequency-domain signal analysis module, which is used to perform a correlation analysis on the environmental audio frequency-domain signal to generate an environmental audio power spectrum, and perform a correlation analysis on the environmental audio power spectrum to generate an environmental noise power;

[0088] An environmental noise power analysis module, which is used to perform a correlation analysis on the environmental noise power to generate an environmental noise impact assessment index;

[0089] The speech rate analysis module is used to set a standard spoken language set, enable 20 speech ability training objects to repeat after the standard spoken language set, collect the speech parameters during the repetition process, perform a correlation analysis on the speech parameters during the repetition process, generate an accuracy expression, perform a correlation analysis on the accuracy expression, and generate a speech rate accuracy evaluation index;

[0090] The comprehensive analysis module is used to perform a correlation analysis on the speech rate accuracy evaluation index YZP and the environmental noise impact evaluation index HZP, generate a comprehensive oral evaluation index KPZ, and the comprehensive oral evaluation index KPZ is used to reflect the comprehensive evaluation by combining the current environment and the speech rate of the person to be tested.

[0091] The present invention also provides a storage medium, on which computer program instructions are stored, and the computer program instructions are executed by a processor to perform the method described above.

[0092] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0093] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0094] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0095] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application.

Claims

1. A method for evaluating oral language ability, characterized in that The specific steps include: S1. Collect the environmental audio signal of the input environment; S2. Preprocess the environmental audio signal to generate a discrete-time signal, and perform a short-time Fourier transform on the environmental audio signal in combination with the discrete-time signal to generate an environmental audio frequency-domain signal. The discrete-time signal is used to reflect the signal strength at each discrete time point, and the environmental audio frequency-domain signal is used to reflect the amplitude of the environmental audio at the corresponding frequency and time; S3. Perform a correlation analysis on the environmental audio frequency-domain signal to generate an environmental audio power spectrum, and perform a correlation analysis on the environmental audio power spectrum to generate an environmental noise power. The environmental audio power spectrum is used to reflect the power value of the environmental audio at the corresponding frequency and time, and the environmental noise power is used to reflect the power value of the environmental noise; S4. Perform a correlation analysis on the environmental noise power to generate an environmental noise impact assessment index HZP. The environmental noise impact assessment index HZP is used to reflect the degree of influence of the environmental noise on the input signal; S5. Set a standard spoken language set, set 20 oral ability training objects to repeat according to the standard spoken language set, collect the oral parameters during the repetition process. The oral parameters include speech rate and recognition accuracy. Perform a correlation analysis on the oral parameters during the repetition process to generate an accuracy expression. Use a speech recognition device to conduct an oral test on the person to be tested. Based on the speech rate of the person to be tested and the accuracy expression, generate a speech rate accuracy assessment index YZP. The speech rate accuracy assessment index YZP is the recognition accuracy of the speech recognition device for the speech rate of the person to be tested. The person to be tested is the person whose oral ability will be evaluated using speech recognition; S6. Perform a correlation analysis on the speech rate accuracy assessment index YZP and the environmental noise impact assessment index HZP to generate an oral evaluation comprehensive index KPZ. The oral evaluation comprehensive index KPZ is used to reflect the comprehensive evaluation by combining the current environment and the speech rate of the person to be tested; S7. Compare the comprehensive oral evaluation index KPZ with the accuracy threshold to output the accuracy level of the oral ability evaluation of the person to be tested. When the accuracy level of the oral ability evaluation of the person to be tested is level one, there is no need to re-determine the oral ability evaluation through speech recognition. When the accuracy level of the oral ability evaluation of the person to be tested is level two, it is necessary to re-determine the oral ability evaluation through speech recognition.

2. The method for evaluating oral language ability according to claim 1, characterized in that: In the input environment, a microphone is respectively arranged on both sides of the input point, and the microphone is connected through an audio acquisition device. The ambient audio signals collected by the two microphones are stored as time series signals.

3. The method for evaluating oral language ability according to claim 2, wherein: Preprocess the environmental audio signal to generate a discrete-time signal , based on the formula: Among them, , is the sampling frequency, n is a positive integer used to index discrete sampling time points, and the discrete-time signal is used to reflect the signal strength at each discrete time point.

4. The method for evaluating oral language ability according to claim 3, wherein: Perform a short-time Fourier transform on the environmental audio signal in combination with the discrete-time signal to generate an environmental audio frequency-domain signal , and the formula is as follows: Among them, represents an imaginary number, is a window function used to limit the time range, , where N is the size of the window, , the environmental audio frequency-domain signal is used to reflect the amplitude of the environmental audio at frequency f and time t.

5. The method for evaluating oral language ability according to claim 4, characterized in that: Perform a correlation analysis on the environmental audio frequency-domain signal to generate the environmental audio power spectrum , and the formula used is as follows: Environmental audio power spectrum Used to reflect the power value of environmental audio at the corresponding frequency f and time t, which is a modulo operation.

6. The method for evaluating oral language ability according to claim 5, wherein: Perform a correlation analysis on the ambient audio power spectrum to generate the ambient noise power , and the formula used is as follows: where F is the maximum frequency value, T is the time for the microphone to collect the environmental audio signal in seconds, and the environmental noise power is the power value used to reflect the environmental noise; Perform a correlation analysis on the environmental noise power to generate an environmental noise impact assessment index HZP. The formula used is as follows: Among them, is the input power of the microphone, is the input sensitivity weight factor of the microphone, The value range of is , and the environmental noise impact assessment index HZP is used to reflect the impact degree of environmental noise on the input signal.

7. The method for evaluating oral language ability according to claim 1, characterized in that: The standard spoken language set is a spoken language comparison audio, including the standard speech rate SR, and the speech rate is the number of words repeated per minute by the i-th spoken language ability training object, and the recognition accuracy is the accuracy of word recognition output by the i-th spoken language ability training object using a speech recognition device. Perform a correlation analysis on the spoken language parameters during the repetition process to generate an accuracy expression AR. The formula based on is as follows: Substitute the oral parameters of all the oral ability training objects collected into the above formula. Substitute the speech rate into v and the recognition accuracy into AR, and use MATLAB software to fit and generate the values of a and b; Perform a correlation analysis on the accuracy expression AR to generate a speech rate accuracy assessment index YZP. The formula is: where V is the speech rate of the person to be tested, and the speech rate accuracy assessment index YZP is used to evaluate the relationship between the speech rate of the person to be tested and the output accuracy of the device; Perform a correlation analysis on the speech rate accuracy assessment index YZP and the environmental noise impact assessment index HZP to generate an oral evaluation comprehensive index KPZ. The formula is: Among them, is the speech rate accuracy weight factor, The value range of is , and the comprehensive oral evaluation index KPZ is used to reflect the accuracy of comprehensively evaluating the oral ability test by combining the current environment and the speech rate of the person to be tested.

8. The method for evaluating oral language ability according to claim 7, characterized in that: Accurate threshold takes the value of 15.

7. The comprehensive index of oral evaluation KPZ is compared with the accurate threshold . When , it indicates that the accuracy of the oral ability evaluation of the person to be tested in the current environment is level two, and the oral ability evaluation is inaccurate; when , it indicates that the accuracy of the oral ability evaluation of the person to be tested in the current environment is level one, and the oral ability evaluation is accurate.

9. A system for evaluating oral language ability, for performing the method for evaluating oral language ability according to claim 1, characterized in that, Including: A signal acquisition module for collecting the environmental audio signal of the input environment; An environmental audio signal processing module for preprocessing the environmental audio signal to generate a discrete-time signal, and performing a short-time Fourier transform on the environmental audio signal in combination with the discrete-time signal to generate an environmental audio frequency-domain signal; A frequency-domain signal analysis module for performing a correlation analysis on the environmental audio frequency-domain signal to generate an environmental audio power spectrum, and performing a correlation analysis on the environmental audio power spectrum to generate an environmental noise power; An environmental noise power analysis module, which is used to perform correlation analysis on the environmental noise power and generate an environmental noise impact assessment index; A speech rate analysis module, which is used to set a standard spoken language set, set 20 speech ability training objects to repeat after the standard spoken language set, collect the speech parameters during the repetition process, perform correlation analysis on the speech parameters during the repetition process, generate an accuracy expression, and perform correlation analysis on the accuracy expression to generate a speech rate accuracy assessment index; A comprehensive analysis module, which is used to perform correlation analysis on the speech rate accuracy assessment index YZP and the environmental noise impact assessment index HZP to generate a comprehensive oral evaluation index KPZ. The comprehensive oral evaluation index KPZ is used to reflect the comprehensive evaluation by combining the current environment and the speech rate of the person to be tested.

10. A storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described in claim 1 is implemented.

Images