Examination room hearing examination detection method and device

Abstract

The invention discloses an examination room hearing examination detection method and device, and the method and device are applied to a sound pickup in an examination room, and the method comprises the steps: collecting a plurality of pieces of detection data circularly played by a hearing broadcasting system before an examination; each piece of detection data is composed of a sine wave pure tone signal and a first recognition voice, and the sine wave pure tone signal of each piece of detection data is the same in amplitude and different in frequency; the sound pick-up and the hearing broadcasting system are located in the same examination room; detecting a broadcasting effect of the hearing broadcasting system according to the sine wave pure tone signal and the first recognition voice; if the broadcasting effect is qualified, collecting examination listening content and second recognition voice in the examination process; and detecting the correctness of the examination listening content according to the examination listening content and the second recognition voice. According to the method, the broadcasting effect can be optimal, and in addition, whether the broadcasting system normally operates or not can be timely and accurately judged in the examination process, so that the situation that the examination listening content is wrongly played due to various reasons is reduced.

Description

Technical Field

[0001] The present application belongs to the technical field of audio monitoring, and specifically relates to a method and device for detecting listening comprehension in an examination room. Background Art

[0002] It is not difficult to understand that the broadcasting effect of the listening test broadcasting system has a great impact on the test takers' scores. There are often complaints about the effectiveness of the test broadcasting system and the resulting bad test experience. Specifically, the existing test broadcasting system has the following problems:

[0003] 1. The effectiveness of the listening test broadcasting system mainly depends on the subjective judgment of the on-site construction workers. Different construction workers have different perceptions of sound, which leads to differences in the broadcasting effects, which may affect the fairness of the test.

[0004] 2. In addition to being used for listening tests, the campus broadcasting system will also have other uses, so there is a risk of artificially changing the status of the broadcasting system. This change in status is difficult to detect in a timely manner by humans, and if the problem is serious, the listening test will not be able to proceed normally.

[0005] 3. Once a problem occurs in the listening test system during the test (such as partial missing of listening content or incorrect listening content being played, etc.), the superior management department will be delayed in obtaining information and often cannot obtain relevant information in a timely manner. Summary of the invention

[0006] One object of the present invention is to provide a method for testing a listening test in an examination room. Without changing the hardware facilities of the existing listening test broadcasting system, on the one hand, the broadcasting effect of the listening test broadcasting system is tested before the test to optimize the broadcasting effect, which greatly improves the test taker's listening experience. On the other hand, during the test (including the pre-playing stage of listening before the test), the correctness of the test listening content is judged to reduce the situation of incorrect playback of the test listening content due to various reasons.

[0007] Another object of the present invention is to provide an examination room listening test detection device. Another object of the present invention is to provide an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the examination room listening test detection method when executing the computer program. Another object of the present invention is to provide a readable medium, on which a computer program is stored, and when the computer program is executed by the processor, the steps of the examination room listening test detection method are implemented.

[0008] In order to solve the technical problems in the background technology of this application, the present invention provides the following technical solutions:

[0009] In a first aspect, the present invention provides a method for detecting a listening test in an examination room, which is applied to a microphone in the examination room. The method includes:

[0010] Before the examination, collect a plurality of detection data cyclically played by the listening broadcast system; wherein each detection data consists of a sine wave pure tone signal and a first recognition voice, and the amplitudes of the sine wave pure tone signals of each detection data are the same, but the frequencies are different; the microphone and the listening broadcast system are located in the same examination room;

[0011] Detect the broadcast effect of the listening broadcast system according to the sine wave pure tone signal and the first recognition voice;

[0012] If the broadcast effect is qualified, during the examination, collect the examination listening content and a second recognition voice;

[0013] Detect the correctness of the examination listening content according to the examination listening content and the second recognition voice.

[0014] In some embodiments of the present invention, the lengths of each of the first recognition voices are the same, and the number of elements with different sounds at the same position in the plurality of first recognition voices is greater than two-thirds of the length of the first recognition voice.

[0015] In some embodiments of the present invention, the first recognition voice is placed in front of the sine wave pure tone signal; detecting the broadcast effect of the listening broadcast system according to the sine wave pure tone signal and the first recognition voice includes:

[0016] Perform the following operations on all detection data:

[0017] Perform a first voice recognition on the first recognition voice of the current detection data;

[0018] If the result of the first voice recognition of the current detection data is correct, perform signal analysis on the sine wave pure tone signal of the current detection data;

[0019] If the signal analysis result of the current detection data is qualified, switch to the next detection data;

[0020] Detect the broadcast effect of the listening broadcast system according to the results of the first voice recognition and the signal analysis of all the detection data.

[0021] In some embodiments of the present invention, detecting the broadcast effect of the listening broadcast system according to the results of the first voice recognition and the signal analysis of all the detection data includes:

[0022] If the results of the signal analysis of all the detected data are qualified, and the recognition results of the first recognition voice of all the detected data are correct, the broadcast effect of the hearing broadcast system is detected as qualified;

[0023] Otherwise, the broadcast effect of the hearing broadcast system is detected as unqualified.

[0024] In some embodiments of the present invention, detecting the correctness of the exam listening content according to the exam listening content and the second recognition voice includes:

[0025] Performing second voice recognition on the exam listening content and the second recognition voice, and detecting the correctness of the exam listening content according to the results of the second voice recognition.

[0026] In some embodiments of the present invention, the number of the second recognition voices is an odd number not less than 3; detecting the correctness of the exam listening content according to the results of the second voice recognition includes:

[0027] If the number of correct recognition results for the exam listening content in the results of the second voice recognition is greater than a preset value; and / or

[0028] If the number of correct recognition results for the second recognition voice in the results of the second voice recognition is greater than two-thirds of the number of the second recognition voices, it is detected that the exam listening content is correct;

[0029] Otherwise, it is detected that the exam listening content is incorrect.

[0030] In some embodiments of the present invention, a method for detecting an exam listening test further includes:

[0031] Receiving a collection instruction for the detected data through a camera at the local end to start collecting the detected data;

[0032] Sending the detection result of the broadcast effect and the detection result of the correctness of the exam listening content to a remote server through the camera.

[0033] In some embodiments of the present invention, performing signal analysis on the sine wave pure tone signal of the current detected data includes:

[0034] Calculating the signal amplitude, distortion data, sampling analysis, and frequency response data of the sine wave pure tone signal;

[0035] Comparing the signal amplitude, the distortion data, the sampling analysis, and the frequency response data with the standard data of the pre-generated sine wave pure tone signal to determine whether the signal analysis result is qualified.

[0036] Second aspect, the present invention provides an examination hall listening test detection device, which is applied to a microphone in an examination hall. The device includes:

[0037] A detection data acquisition module, configured to acquire a plurality of detection data cyclically played by a listening broadcast system before the exam; wherein each detection data consists of a sine wave pure tone signal and a first recognition voice, and the amplitudes of the sine wave pure tone signals of each detection data are the same, but the frequencies are different; the microphone and the listening broadcast system are located in the same examination hall;

[0038] A broadcast effect detection module, configured to detect the broadcast effect of the listening broadcast system according to the sine wave pure tone signal and the first recognition voice;

[0039] A listening content acquisition module, configured to, if the broadcast effect is qualified, acquire the examination listening content and a second recognition voice during the exam;

[0040] A listening content correctness detection module, configured to detect the correctness of the examination listening content according to the examination listening content and the second recognition voice.

[0041] In some embodiments of the present invention, the lengths of each first recognition voice are the same, and the number of elements with different sounds at the same position in the plurality of first recognition voices is greater than two-thirds of the length of the first recognition voice.

[0042] In some embodiments of the present invention, the first recognition voice is placed before the sine wave pure tone signal; the broadcast effect detection module includes:

[0043] A detection data loop operation unit, configured to perform the following operations on all detection data:

[0044] A current detection data voice recognition unit, configured to perform a first voice recognition on the first recognition voice of the current detection data;

[0045] A current detection data signal analysis unit, configured to, if the result of the first voice recognition of the current detection data is correct, perform signal analysis on the sine wave pure tone signal of the current detection data;

[0046] A next detection data switching unit, configured to switch to the next detection data if the signal analysis result of the current detection data is qualified;

[0047] A broadcast effect detection unit, configured to detect the broadcast effect of the listening broadcast system according to the results of the first voice recognition and the signal analysis of all the detection data.

[0048] In some embodiments of the present invention, the broadcast effect detection unit includes:

[0049] The first unit for detecting the broadcast effect is used to detect that the broadcast effect of the hearing broadcast system is qualified if the results of the signal analysis of all the detected data are qualified and the recognition results of the first recognized voice of all the detected data are correct;

[0050] The second unit for detecting the broadcast effect is used to detect that the broadcast effect of the hearing broadcast system is unqualified otherwise.

[0051] In some embodiments of the present invention, the module for detecting the correctness of the hearing content includes:

[0052] The unit for detecting the correctness of the hearing content is used to perform second voice recognition on the examination hearing content and the second recognized voice, and detect the correctness of the examination hearing content according to the results of the second voice recognition.

[0053] In some embodiments of the present invention, the number of the second recognized voices is an odd number not less than 3; the unit for detecting the correctness of the hearing content includes:

[0054] The first unit for detecting the examination hearing content is used to detect that the examination hearing content is correct if the number of correct recognition results for the examination hearing content in the results of the second voice recognition is greater than a preset value; and / or

[0055] If the number of correct recognition results for the second recognized voice in the results of the second voice recognition is greater than two-thirds of the number of the second recognized voices, detect that the examination hearing content is correct;

[0056] The second unit for detecting the examination hearing content is used to detect that the examination hearing content is incorrect otherwise.

[0057] In some embodiments of the present invention, an examination hall hearing examination detection device further includes:

[0058] The acquisition instruction receiving module is used to receive the acquisition instruction for acquiring the detected data through the camera at the local end to start acquiring the detected data;

[0059] The detection result sending module is used to send the detection result of the broadcast effect and the detection result of the correctness of the examination hearing content to the remote server through the camera.

[0060] In some embodiments of the present invention, the current detected data signal analysis unit includes:

[0061] The signal parameter calculation unit is used to calculate the signal amplitude, distortion data, sampling analysis and frequency response data of the sine wave pure tone signal;

[0062] An analysis result judgment unit is configured to compare the signal amplitude, the distortion data, the sampling analysis, and the frequency response data with the standard data of the pre-generated sine wave pure tone signal to determine whether the signal analysis result is qualified.

[0063] In a third aspect, the present invention provides a computer program product, including a computer program / instructions, which when executed by a processor implement the steps of a method for detecting an in-examination listening test.

[0064] In a fourth aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, it implements the steps of the method for detecting an in-examination listening test.

[0065] In a fifth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the method for detecting an in-examination listening test.

[0066] As can be seen from the above description, the embodiments of the present invention provide a method and device for detecting an in-examination listening test, which are applied to a pick-up microphone in an examination room. The corresponding method includes: First, before the examination, collect a plurality of detection data cyclically played by the listening broadcast system; wherein, each detection data consists of a sine wave pure tone signal and a first recognition voice, and the amplitudes of the sine wave pure tone signals of each detection data are the same, but the frequencies are different; the pick-up microphone and the listening broadcast system are located in the same examination room; detect the broadcast effect of the listening broadcast system according to the sine wave pure tone signal and the first recognition voice; then, if the broadcast effect is qualified, during the examination, collect the examination listening content and the second recognition voice; finally, detect the correctness of the examination listening content according to the examination listening content and the second recognition voice.

[0067] In summary, without modifying the hardware facilities of the existing listening examination broadcast system, on the one hand, the present invention detects the broadcast effect of the listening examination broadcast system before the examination to make the broadcast effect optimal, greatly improving the listening experience of candidates. On the other hand, during the examination, it makes timely and accurate judgments on the correctness of the examination listening content and whether the broadcast system is operating normally, so as to reduce the situation where the examination listening content is played incorrectly due to various reasons. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0069] Figure 1 Flow schematic of a test room listening test detection method in an embodiment of the present invention Figure 1 ;

[0070] Figure 2 Schematic diagram of performing first speech recognition on a single detection data in an embodiment of the present invention;

[0071] Figure 3 Flow schematic diagram of step 200 of a test room listening test detection method in an embodiment of the present invention;

[0072] Figure 4 Flow schematic diagram of step 205 of a test room listening test detection method in an embodiment of the present invention;

[0073] Figure 5 Flow schematic diagram of the step of "detecting the correctness of the test listening content according to the result of the second speech recognition" in an embodiment of the present invention;

[0074] Figure 6 Flow schematic of a test room listening test detection method in an embodiment of the present invention Figure 2 ;

[0075] Figure 7 Flow schematic diagram of step 201 of a test room listening test detection method in an embodiment of the present invention;

[0076] Figure 8 Schematic diagram of the positional relationship among the pickup 2, the listening broadcast system 1, and the test room in an embodiment of the present invention;

[0077] Figure 9 Flow schematic diagram of a test room listening test detection method in a specific embodiment of the present invention;

[0078] Figure 10 Mind map of a test room listening test detection method in a specific embodiment of the present invention;

[0079] Figure 11 Block diagram of a test room listening test detection device in an embodiment of the present invention Figure 1 ;

[0080] Figure 12 Block diagram of the broadcast effect detection module 20 in an embodiment of the present invention;

[0081] Figure 13 Block diagram of the broadcast effect detection unit 20e in an embodiment of the present invention;

[0082] Figure 14A block diagram of the listening content correctness detection unit in an embodiment of the present invention;

[0083] Figure 15 A block diagram of a test room listening exam detection device in an embodiment of the present invention Figure 2 ;

[0084] Figure 16 A block diagram of the current detection data signal analysis unit 20c in an embodiment of the present invention;

[0085] Figure 17 A schematic structural diagram of an electronic device in an embodiment of the present invention. Detailed implementation manners

[0086] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0087] Those skilled in the art should understand that the embodiments of the present invention may be provided as a method, a system, or a computer program product. Therefore, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0088] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above accompanying drawings are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices. Without conflict, the embodiments in this application and the features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0089] The embodiments of the present invention provide a specific implementation manner of a test room listening exam detection method, which is applied to a microphone in a test room. Refer to Figure 1 , and the method specifically includes the following contents:

[0090] Step 100: Before the exam, collect multiple detection data cyclically played by the listening broadcast system; wherein, each detection data consists of a sine wave pure tone signal and a first recognition voice, and the amplitudes of the sine wave pure tone signals of each detection data are the same, but the frequencies are different; the pick-up microphone and the listening broadcast system are located in the same examination room;

[0091] Step 200: Detect the broadcast effect of the listening broadcast system according to the sine wave pure tone signal and the first recognition voice;

[0092] Step 300: If the broadcast effect is qualified, during the exam, collect the exam listening content and a second recognition voice;

[0093] Step 400: Detect the correctness of the exam listening content according to the exam listening content and the second recognition voice.

[0094] As can be seen from the above description, the embodiment of the present invention provides a detection method for an exam listening test, which is applied to a pick-up microphone in an examination room and includes: First, before the exam, collect multiple detection data cyclically played by the listening broadcast system; wherein, each detection data consists of a sine wave pure tone signal and a first recognition voice, and the amplitudes of the sine wave pure tone signals of each detection data are the same, but the frequencies are different; the pick-up microphone and the listening broadcast system are located in the same examination room; detect the broadcast effect of the listening broadcast system according to the sine wave pure tone signal and the first recognition voice; Then, if the broadcast effect is qualified, during the exam, collect the exam listening content and a second recognition voice; Finally, detect the correctness of the exam listening content according to the exam listening content and the second recognition voice.

[0095] In summary, without modifying the hardware facilities of the existing listening exam broadcast system, on the one hand, the present invention detects the broadcast effect of the listening exam broadcast system before the exam to optimize the broadcast effect, greatly improving the listening experience of the examinees. On the other hand, during the exam, it makes timely and accurate judgments on the correctness of the exam listening content and whether the broadcast system is operating normally, so as to reduce the situation where the exam listening content is played incorrectly due to various reasons.

[0096] It should be noted that in steps 100 to 400, that is, the execution subject of the examination room listening test detection method proposed in this application is a pickup, which can be set on an existing camera. Specifically, the pickup includes: a single-chip computer system (Microcontroller Unit, MCU) for speech recognition, speech synthesis, and signal analysis, a power amplifier circuit, a built-in speaker, a built-in microphone, and a sound pickup and signal noise reduction and amplification circuit. Among them, the sound pickup circuit is connected to the audio input and output interface of the camera, and the signal noise reduction and amplification circuit is connected to the alarm input and output interface of the camera (digital input interface DigitalInput and digital output interface Digital Output, that is, DI / DO).

[0097] It should be noted that steps 100 and 200 are implemented before the official exam, such as one day or several days before the official exam. After steps 100 and 200 are implemented, the parameter configuration of the listening test broadcast system in the corresponding examination room should no longer be modified.

[0098] Correspondingly, steps 300 and 400 are implemented during the official exam (in this application, playing example voices (usually used to help candidates get familiar with the voice of the broadcaster as soon as possible) before playing the official exam listening content is also regarded as part of the official exam).

[0099] For steps 100 and 200, each detection data collected by the pickup through the built-in microphone includes a sine wave pure tone signal and a first recognized voice. The amplitudes of the sine wave pure tone signals in each detection data are the same, but the frequencies are different (signals with different frequencies and the same amplitude, after being broadcast by the listening test broadcast system, the amplitudes collected by the pickup should also be the same or relatively close), which are used for signal analysis of the listening broadcast system, including: calculating the signal amplitude, distortion data, sampling analysis, and frequency response data of the sine wave pure tone signal, etc. Multiple first recognized voices are used to detect the broadcast effect of the listening test broadcast system. Specifically, the pickup recognizes the first recognized voice, and when the result of the first speech recognition of the first recognized voice meets the expectation, it is determined that the broadcast effect of the listening test broadcast system is qualified at this time.

[0100] In each detection data, the sine wave pure tone signal can be placed before or after the corresponding first recognized voice.

[0101] For steps 300 and 400, after the broadcast effect of the listening exam broadcast system passes the parameter adjustment, the exam listening content and the second recognition voice are collected through the microphone built into the pickup. Both the exam listening content and the second recognition voice are used to judge the correctness of the exam listening content. Preferably, the second recognition voice can be interspersed in the actual content of the exam listening content. However, considering the security and confidentiality of the exam listening content, the second recognition voice can also be placed before the actual content of the exam listening content.

[0102] In some embodiments of the present invention, each first recognition voice has the same length, and the number of elements with different sounds at the same position in multiple first recognition voices is greater than two-thirds of the length of the first recognition voice.

[0103] According to the characteristics of speech recognition technology, to improve the detection results, data transmission, and recognition accuracy, some voices should be converted to expand the differences between voices, so that relevant personnel can understand the meaning and improve the automatic recognition accuracy to prevent misrecognition. Here, the first recognition voice is taken as an example (the second recognition voice is similar). When the signal lengths of each first recognition voice are the same, the number of different sounds at the same position in multiple first recognition voices should be greater than two-thirds. For example, for multiple first recognition voices with a length of 3 bytes, there should be a significant difference in the pronunciation of two bytes at the same position.

[0104] "Setting One" is transmitted as the voice "Setting One";

[0105] "Setting Two" is transmitted as the voice "Two Settings";

[0106] …

[0107] "Frequency Three" is transmitted as the voice "Frequency Three";

[0108] "Frequency Four" is transmitted as the voice "Four Frequencies";

[0109] "Frequency Five" is transmitted as the voice "Five Frequency Points";

[0110] …

[0111] "1" is transmitted as the voice "Data One";

[0112] "2" is transmitted as the voice "Two Data";

[0113] "3" is transmitted as the voice "Numerical Value Three".

[0114] In some embodiments of the present invention, the first recognition voice is placed before the sine wave pure tone signal;

[0115] It should be noted that using the voice (the first recognized voice) as a guide in front of the sine-wave pure-tone signal can ensure the detection of the sine-wave pure-tone signal at the correct position (see Figure 2 ), and at the same time, the number of the first recognized voices is recognized, and the quality of the broadcast information is evaluated from another perspective.

[0116] Next, referring to Figure 3 , step 200 includes:

[0117] Step 201: Perform the following operations on all the detection data:

[0118] Step 202: Perform the first voice recognition on the first recognized voice of the current detection data;

[0119] Step 203: If the result of the first voice recognition of the current detection data is correct, perform signal analysis on the sine-wave pure-tone signal of the current detection data;

[0120] That is, if the result of the first voice recognition of the previous detection data is incorrect or the first recognized voice cannot be detected, stop performing signal analysis on the sine-wave pure-tone signal.

[0121] Performing signal analysis on the hearing broadcast system according to the sine-wave pure-tone signal includes the following contents: calculating the signal amplitude, distortion data, sampling analysis, and frequency response data of the sine-wave pure-tone signal:

[0122] The amplitude of the sine-wave pure-tone signal is the distance of the wave crest (maximum value) or wave trough (minimum value) relative to the center line. It can be calculated by the following formula:

[0123] x(t) = Asin(ωt + φ)

[0124] where A is the amplitude of the sine-wave pure-tone signal; ω is the angular frequency (which can be obtained by calculating the f frequency); φ is the phase.

[0125] In the time-domain data, the amplitude A can be obtained by finding the maximum and minimum values of the sine-wave pure-tone signal and calculating its amplitude (the maximum value minus the minimum value and then divided by 2):

[0126]

[0127] Distortion usually refers to the difference between the sine-wave pure-tone signal and the ideal sine waveform, and can be measured by the following methods:

[0128] Total Harmonic Distortion (THD): Calculate the ratio of the harmonic components in the signal to the fundamental frequency component:

[0129]

[0130] Among them, V 1 is the fundamental frequency component, and V 2 , V 3 , …, V n are harmonic components.

[0131] The sampling frequency should be at least twice the highest frequency of the sine wave pure tone signal.

[0132] The frequency response data is used to reflect the response of the listening test broadcast system to sine wave pure tone signals of different frequencies and can be obtained by the following method:

[0133] Frequency response function: It represents the gain and phase response of the system at different frequencies. For a linear time-invariant system, the transfer function H(f) is preferably used:

[0134]

[0135] Among them, X(f) is the spectrum of the input signal, and Y(f) is the spectrum of the output signal.

[0136] Step 204: If the signal analysis result of the current detection data is qualified, switch to the next detection data;

[0137] Step 205: Detect the broadcast effect of the listening broadcast system according to the results of the first speech recognition of all the detection data and the results of the signal analysis.

[0138] In some embodiments of the present invention, referring to Figure 4 , step 205 includes:

[0139] Step 2051: If the signal analysis results of all the detection data are qualified and the recognition results of the first recognized speech of all the detection data are correct, detect that the broadcast effect of the listening broadcast system is qualified;

[0140] Step 2052: Otherwise, detect that the broadcast effect of the listening broadcast system is unqualified.

[0141] In step 2051 and step 2052, specifically, when and only when the signal analysis results of all the detection data are qualified and the recognition results of the first recognized speech of all the detection data are correct, it is determined that the broadcast effect of the listening broadcast system is qualified.

[0142] In some embodiments of the present invention, step 400 includes: performing second speech recognition on the test listening content and the second recognized speech, and detecting the correctness of the test listening content according to the results of the second speech recognition.

[0143] Specifically, the pick-up microphone MCU performs speech recognition on the exam listening content and the second recognition speech. It can be understood that the languages of the exam listening content are diverse, so it is difficult to ensure the accuracy of the recognition result by the pick-up microphone MCU. Therefore, additional speech recognition of the second speech recognition is required. Of course, if the speech recognition result of the exam listening content reaches the expected value, the second recognition speech may not be subjected to speech recognition.

[0144] In some embodiments of the present invention, the number of the second recognition speeches is an odd number not less than 3 within a specified time (such as within 30 seconds); see Figure 5 , detecting the correctness of the exam listening content according to the result of the second speech recognition includes:

[0145] Step 4011: If the number of correct recognition results for the exam listening content in the result of the second speech recognition is greater than a preset value; and / or

[0146] If the number of correct recognition results for the second recognition speech in the result of the second speech recognition is greater than two-thirds of the number of the second recognition speeches, detect that the exam listening content is correct;

[0147] Step 4012: Otherwise, detect that the exam listening content is incorrect.

[0148] In some embodiments of the present invention, the playing duration of the sine wave pure tone signal of each frequency is the same, and the acquisition time for acquiring the plurality of detection data satisfies:

[0149] T 1 ≥(N + 2)×T 2 ;

[0150] Wherein, T 1 is the acquisition time; N is the number of the sine wave pure tone signals; T 2 is the playing duration of each detection data (each first recognition speech combined with the sine wave pure tone signal).

[0151] It can be understood that setting the acquisition time of the plurality of detection data according to the above formula can ensure the acquisition of the plurality of detection data within one cycle (loop playback).

[0152] In some embodiments of the present invention, see Figure 6 , a detection method for an exam listening test in an examination room further includes:

[0153] Step 90: Receive an acquisition instruction for acquiring the detection data through a camera at the local end to start acquiring the detection data;

[0154] Specifically, the remote server (e.g., the management computer at the remote end of the monitoring system) automatically connects to the monitoring cameras in different examination rooms and activates the two-way voice intercom of the cameras, sending voice commands to the pickups in the examination rooms. After the pickups recognize the voice commands (collection instructions), they start the operation of collecting and detecting data as described above. It can be understood that step 90 does not perform any hardware transformation on the existing listening examination broadcast system ((It can be understood that most of the existing listening examination broadcast systems contain multiple third-party hardware and supporting software. If improvements are made to them, it will inevitably bring a lot of complex work)), and only uses the existing hardware configuration to achieve the optimal broadcast effect, greatly improving the listening experience of candidates and reducing the situation where the broadcast of the listening content of the examination is incorrect due to various reasons.

[0155] Step 500: Send the detection result of the broadcast effect and the detection result of the correctness of the examination listening content to the remote server through the camera.

[0156] Specifically, send the detection result of the broadcast effect of the first recognized voice and the sine wave pure tone signal through the audio channel of the camera; send the detection result of the correctness of the examination listening content through the on-off quantity level pulse of the tone alarm input port.

[0157] It should be noted that during the progress of the listening examination, for the instructions before the examination and the explanatory content during the examination played by the broadcast system, a second recognized voice is set, and the second recognized voice is recognized and judged. When it is judged that the second recognized voice is received, an on-off quantity is output to the alarm input (DI) port of the monitoring camera, and the monitoring camera reports a confirmation message to the remote server in the form of an alarm message.

[0158] A confirmation message receiving server and a processing computer are set in the monitoring system, and the computer monitors the cameras in the monitoring network that need to report confirmation information. In addition, a limited time also needs to be set for the computer software. When there are still cameras that have not reported confirmation messages after exceeding the limited time, an alarm is sent to the staff and the information of the problem cameras and the examination rooms where they are located is provided.

[0159] In some embodiments of the present invention, referring to Figure 7 , step 201 includes:

[0160] Step 2011: Calculate the signal amplitude, distortion data, sampling analysis, and frequency response data of the sine wave pure tone signal;

[0161] Step 2012: Compare the signal amplitude, the distortion data, the sampling analysis, and the frequency response data with the standard data of the pre-generated sine wave pure tone signal to determine whether the signal analysis result is qualified.

[0162] Specifically, the pre-generated standard sine wave pure tone signal gives a fixed amplitude A std , and the amplitude of the standard sine wave pure tone signal is usually known at the time of generation. By extracting the maximum and minimum values from the sine wave pure tone signal, the actual signal amplitude A is calculated act .

[0163] Judgment criterion: If |A act - A std | is within a predetermined tolerance range (e.g., less than ±5%), the signal amplitude is qualified.

[0164] If it exceeds the tolerance range, it indicates that there is an amplitude error in the signal, which may be due to noise, distortion, or other signal processing problems.

[0165] Comparison of sampling analysis. Specifically, by checking the sampling frequency, the number of sampling points, and the discretization accuracy to evaluate whether the signal is correctly sampled. The pre-generated standard data should include the specified sampling frequency (such as 1000 Hz), the number of sampling points (such as 1000 points), and the sampling should conform to the Nyquist theorem, that is, the sampling frequency should be greater than twice the signal frequency.

[0166] Actually calculated sampling data: The sampling frequency f s and the number of sampling points N should be consistent with the standard data. Perform a Fourier transform (FFT) on the sampled signal and compare its spectrum with the spectrum of the standard signal.

[0167] If the sampling frequency is less than twice the signal frequency (Nyquist theorem), aliasing will occur and the signal is unqualified.

[0168] If the sampling frequency and the number of sampling points are consistent with the standard data, and there is no obvious aliasing or error in the spectrum, the sampling is qualified.

[0169] Comparison of frequency response data: If the actual frequency response data has a large difference in gain and phase from the standard data, it means that there are problems with the system's response to different frequencies (e.g., due to system non-linearity, imperfect filters, etc.). The standard data usually gives an ideal frequency response range (e.g., the gain change is within ±1 dB). If the frequency response of the actual signal deviates greatly, the signal analysis result is unqualified.

[0170] In some embodiments of the present invention Figure 8 , the distance of the pickup 2 from the hearing broadcast system 1 (the external object can be a speaker) (the distance along the length L of the examination room 1 direction) L 1 is at one-third of the length L of the examination room 2 .

[0171] To further illustrate the solution, the present invention also provides a specific implementation manner of a detection method for an in-examination hall listening test. Refer to Figure 9 and Figure 10 , which specifically includes the following steps:

[0172] S1: The listening test broadcast system repeatedly plays sine wave pure tone signals of multiple frequencies and the same amplitude that are pre-recorded.

[0173] Sine wave pure tone signals of N frequencies, and the playing duration of each frequency is T 2 , then the continuous cycle period of the broadcast signal is N×T 2 . For the convenience of accurate identification and detection, a section of voice signal, such as frequency 1, frequency 2, etc., can be prefixed (or suffixed) to each frequency sine wave pure tone signal for the pick-up microphone MCU to identify.

[0174] S2: The remote computer of the monitoring system issues a "broadcast detection" instruction.

[0175] Specifically, the remote computer program or hardware device of the monitoring system automatically connects to the monitoring cameras at different locations (classroom examination halls), activates the camera intercom function, and sends an audio voice instruction, such as "broadcast detection", to the cameras.

[0176] S3: The pick-up microphone identifies the voice password.

[0177] The pick-up microphone MCU receives the voice instruction signal from the audio output port of the camera, identifies the voice password, and then starts to detect the listening test broadcast system.

[0178] S4: The pick-up microphone collects the broadcast signal.

[0179] The pick-up microphone MCU collects and receives the broadcast signal through the built-in microphone, and the collection duration is ≥(N + 2)×T 2 . The MCU performs voice recognition and signal analysis on the collected broadcast signal, including signal amplitude, distortion, etc., and checks the audio signal frequency response of the listening test broadcast system according to the amplitudes of the sine wave pure tone signals of different frequencies received.

[0180] The MCU compares the calculated signal amplitude, distortion, and frequency response data with the pre-stored parameters, makes a judgment on whether the broadcast signal meets the requirements, and transmits the result in voice form through the audio input port of the camera to the remote computer program or hardware device of the monitoring system. The computer program or hardware device makes corresponding processing after identifying and judging the received voice.

[0181] It should be noted that the pick-up microphone MCU can upload the detection data by voice, or can also upload the data by using Dual-tone multi-frequency (DTMF) or other audio carrier methods.

[0182] A remote computer program or hardware device can set parameters through voice download to change the judgment criteria of the broadcast signal, or can also use DTMF (Dual-Tone Multi-Frequency) or other audio carrier methods for transmission.

[0183] S5: During the listening exam, detect the broadcast content at different stages in the listening exam broadcast system.

[0184] For example, detect keywords or key phrases (second recognition voice) in the content broadcast from 20 minutes before the exam to the start of the exam at different stages, or detect the broadcast content at different stages during the exam. Each group of judgments sets 3, 5 or more odd numbers of keywords or key phrases for detection. The judgment of keywords or phrases adopts the majority judgment rule. When there are 3 keywords or key phrases, when 2 or more are recognized, it is determined to pass the detection; when there are 5 keywords or key phrases, when 3 or more are recognized, it is determined to pass the detection.

[0185] S6: The pick-up microphone sends a confirmation message through the switch quantity level pulse of the camera alarm input port.

[0186] When the keywords or key phrases detected in the broadcast stage reach the specified quantity, the pick-up microphone sends a confirmation message through the switch quantity level pulse of the camera alarm input port (DI), and the camera transmits the confirmation message to the remote computer program or hardware device of the monitoring system. The remote computer program or hardware device of the monitoring system records and statistics the confirmation messages received from cameras at different locations (classroom examination rooms), and gives an alarm prompt for cameras at locations (classroom examination rooms) that do not receive confirmation messages after the specified time point, and the staff will conduct a review and other corresponding processing.

[0187] As can be seen from the above description, the specific implementation manner of the present invention provides a method and device for detecting a listening exam in an examination room, which is applied to a pick-up microphone in the examination room. The corresponding method includes: First, before the exam, collect a plurality of detection data cyclically played by the listening broadcast system; wherein, each detection data is composed of a sine wave pure tone signal and a first recognition voice, and the amplitudes of the sine wave pure tone signals of each detection data are the same, but the frequencies are different; the pick-up microphone and the listening broadcast system are located in the same examination room; detect the broadcast effect of the listening broadcast system according to the sine wave pure tone signal and the first recognition voice; Then, if the broadcast effect is qualified, during the exam, collect the exam listening content and the second recognition voice; Finally, detect the correctness of the exam listening content according to the exam listening content and the second recognition voice.

[0188] In summary, without modifying the hardware facilities of the existing listening exam broadcast system, on the one hand, the listening exam broadcast system is tested for broadcast effect before the exam to optimize the broadcast effect, greatly improving the listening experience of the examinees. On the other hand, during the exam, the correctness of the listening exam content is judged to reduce the situation where the listening exam content is played incorrectly due to various reasons.

[0189] Based on the same inventive concept, an embodiment of the present application also provides a detection device for listening exams in an examination room, which can be used to implement the method described in the above embodiment, as in the following embodiment. Since the principle of the detection device for listening exams in an examination room to solve problems is similar to that of the detection method for listening exams in an examination room, the implementation of the detection device for listening exams in an examination room can refer to the implementation of the detection method for listening exams in an examination room, and the repeated parts will not be elaborated. Hereinafter, the term "unit" or "module" may refer to a combination of software and / or hardware that can achieve a predetermined function. Although the system described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0190] An embodiment of the present invention provides a specific implementation manner of a detection device for listening exams in an examination room that can implement the detection method for listening exams in an examination room. Refer to Figure 11 A detection device for listening exams in an examination room (applied to a microphone in the examination room) specifically includes the following:

[0191] A detection data acquisition module 10, configured to collect a plurality of detection data cyclically played by the listening broadcast system before the exam; wherein each detection data consists of a sine wave pure tone signal and a first recognition voice, and the amplitudes of the sine wave pure tone signals of each detection data are the same, but the frequencies are different; the microphone and the listening broadcast system are located in the same examination room;

[0192] A broadcast effect detection module 20, configured to detect the broadcast effect of the listening broadcast system according to the sine wave pure tone signal and the first recognition voice;

[0193] A listening content acquisition module 30, configured to collect the listening exam content and a second recognition voice during the exam if the broadcast effect is qualified;

[0194] A listening content correctness detection module 40, configured to detect the correctness of the listening exam content according to the listening exam content and the second recognition voice.

[0195] In some embodiments of the present invention, the lengths of each first recognition voice are the same, and the number of elements with different sounds at the same position in the multiple first recognition voices is greater than two-thirds of the length of the first recognition voice.

[0196] In some embodiments of the present invention, the first recognition voice is placed before the sine wave pure tone signal; see Figure 12 , the broadcast effect detection module 20 includes:

[0197] A detection data loop operation unit 20a for performing the following operations on all detection data:

[0198] A current detection data speech recognition unit 20b for performing a first speech recognition on the first recognition voice of the current detection data;

[0199] A current detection data signal analysis unit 20c for performing signal analysis on the sine wave pure tone signal of the current detection data if the result of the first speech recognition of the current detection data is correct;

[0200] A next detection data switching unit 20d for switching to the next detection data if the signal analysis result of the current detection data is qualified;

[0201] A broadcast effect detection unit 20e for detecting the broadcast effect of the hearing broadcast system according to the results of the first speech recognition and the signal analysis of all the detection data.

[0202] In some embodiments of the present invention, see Figure 13 , the broadcast effect detection unit 20e includes:

[0203] A first broadcast effect detection unit 20e1 for detecting that the broadcast effect of the hearing broadcast system is qualified if the results of the signal analysis of all the detection data are qualified and the recognition results of the first recognition voices of all the detection data are correct;

[0204] A second broadcast effect detection unit 20e2 for otherwise detecting that the broadcast effect of the hearing broadcast system is unqualified.

[0205] In some embodiments of the present invention, the hearing content correctness detection module 40 includes:

[0206] A hearing content correctness detection unit for performing a second speech recognition on the exam hearing content and the second recognition voice, and detecting the correctness of the exam hearing content according to the result of the second speech recognition.

[0207] In some embodiments of the present invention, the number of the second recognition voices is an odd number not less than 3; see Figure 14 , the hearing content correctness detection unit includes:

[0208] The first unit 40a1 of the test listening content detection is used when the number of correct recognition results for the test listening content in the result of the second voice recognition is greater than a preset value; and / or

[0209] If the number of correct recognition results for the second recognized voice in the result of the second voice recognition is greater than two-thirds of the number of the second recognized voices, it is detected that the test listening content is correct;

[0210] The second unit 40a2 of the test listening content detection is used to otherwise detect that the test listening content is incorrect.

[0211] In some embodiments of the present invention, refer to Figure 15 , an examination hall listening test detection device further includes:

[0212] The acquisition instruction receiving module 09 is used to receive the acquisition instruction for acquiring the detection data through the camera at the local end to start acquiring the detection data;

[0213] The detection result sending module 50 is used to send the detection result of the broadcast effect and the detection result of the correctness of the test listening content to the remote server through the camera.

[0214] In some embodiments of the present invention, refer to Figure 16 , the current detection data signal analysis unit 20c includes:

[0215] The signal parameter calculation unit 20c1 is used to calculate the signal amplitude, distortion data, sampling analysis and frequency response data of the sine wave pure tone signal;

[0216] The analysis result judgment unit 20c2 is used to compare the signal amplitude, the distortion data, the sampling analysis and the frequency response data with the standard data of the pre-generated sine wave pure tone signal to judge whether the signal analysis result is qualified.

[0217] As can be seen from the above description, an embodiment of the present invention provides a detection device for an examination hall listening test, which is applied to a microphone in the examination hall and includes: a detection data acquisition module, configured to collect a plurality of detection data cyclically played by a listening broadcast system before the examination; wherein each detection data consists of a sine wave pure tone signal and a first recognition voice, and the sine wave pure tone signals of each detection data have the same amplitude but different frequencies; the microphone and the listening broadcast system are located in the same examination hall; a broadcast effect detection module, configured to detect the broadcast effect of the listening broadcast system according to the sine wave pure tone signal and the first recognition voice; a listening content acquisition module, configured to collect the examination listening content and a second recognition voice during the examination if the broadcast effect is qualified; and a listening content correctness detection module, configured to detect the correctness of the examination listening content according to the examination listening content and the second recognition voice.

[0218] In summary, without modifying the hardware facilities of the existing listening test broadcast system, on the one hand, the present invention detects the broadcast effect of the listening test broadcast system before the examination to optimize the broadcast effect, greatly improving the listening experience of the examinees. On the other hand, during the examination, it discriminates the correctness of the examination listening content to reduce the situation where the examination listening content is played incorrectly due to various reasons.

[0219] An embodiment of the present application also provides a specific implementation manner of an electronic device that can implement all steps in the above-mentioned detection method for an examination hall listening test in the embodiment. Refer to Figure 17 , and the electronic device specifically includes the following contents:

[0220] A processor (1201), a memory (1202), a communication interface (1203), and a bus (1204);

[0221] Among them, the processor (1201), the memory (1202), and the communication interface (1203) complete mutual communication through the bus (1204); the communication interface (1203) is used to implement information transmission between related devices such as a server-side device and a user-side device;

[0222] The processor (1201) is used to call a computer program in the memory (1202), and when the processor executes the computer program, it implements all steps in the above-mentioned detection method for an examination hall listening test. For example, when the processor executes the computer program, it implements the following steps:

[0223] Step 100: Before the examination, collect a plurality of detection data cyclically played by the listening broadcast system; wherein each detection data consists of a sine wave pure tone signal and a first recognition voice, and the sine wave pure tone signals of each detection data have the same amplitude but different frequencies; the microphone and the listening broadcast system are located in the same examination hall;

[0224] Step 200: Detect the broadcast effect of the hearing broadcast system according to the sine-wave pure tone signal and the first recognition speech;

[0225] Step 300: If the broadcast effect is qualified, during the exam, collect the exam listening content and the second recognition speech;

[0226] Step 400: Detect the correctness of the exam listening content according to the exam listening content and the second recognition speech.

[0227] An embodiment of the present application further provides a computer-readable storage medium capable of implementing all steps in the above-mentioned exam listening test detection method in the examination room. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, all steps of the above-mentioned exam listening test detection method in the examination room are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0228] Step 100: Before the exam, collect a plurality of detection data cyclically played by the hearing broadcast system; wherein, each detection data is composed of a sine-wave pure tone signal and a first recognition speech, and the amplitudes of the sine-wave pure tone signals of each detection data are the same, but the frequencies are different; the pick-up microphone and the hearing broadcast system are located in the same examination room;

[0229] Step 200: Detect the broadcast effect of the hearing broadcast system according to the sine-wave pure tone signal and the first recognition speech;

[0230] Step 300: If the broadcast effect is qualified, during the exam, collect the exam listening content and the second recognition speech;

[0231] Step 400: Detect the correctness of the exam listening content according to the exam listening content and the second recognition speech.

[0232] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the hardware + program type embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0233] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the accompanying drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0234] Although this application provides method operation steps such as in the embodiments or flowcharts, based on routine or non-creative labor, there may be more or fewer operation steps. The order of steps listed in the embodiments is only one way among many possible execution orders and does not represent the only execution order. When the actual device or client product is executed, it can be executed in the order shown in the embodiments or the drawings or in parallel (e.g., in an environment with parallel processors or multi-threaded processing).

[0235] For convenience of description, when describing the above device, it is divided into various modules according to functions for separate description. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same or multiple software and / or hardware, or the modules implementing the same function can be realized by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0236] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0237] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash RAM). The memory is an example of computer-readable media.

[0238] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple. For relevant parts, reference can be made to the corresponding description in the method embodiments. In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the embodiments of this specification. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples.

[0239] The above are only the embodiments of the embodiments of this specification and are not used to limit the embodiments of this specification. For those skilled in the art, various changes and modifications can be made to the embodiments of this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of this specification shall be included within the scope of the claims of the embodiments of this specification.

Claims

1. A listening test detection method in an examination room, characterized in that: The microphones used in the examination room include: Before the test, a plurality of test data cyclically played by the listening broadcast system are collected; wherein each test data is composed of a sine wave pure tone signal and a first recognized voice, and the sine wave pure tone signal of each test data has the same amplitude and different frequencies; the microphone and the listening broadcast system are located in the same examination room; Detecting the broadcasting effect of the hearing broadcasting system according to the sine wave pure tone signal and the first recognized voice; If the broadcast effect is satisfactory, during the test, the test listening content and the second recognized voice are collected; The correctness of the test listening content is detected according to the test listening content and the second recognized speech.

2. The listening test detection method in the examination room according to claim 1, characterized in that: The length of each first recognized speech is the same, and the number of elements in the same position and with different sounds of the plurality of first recognized speech is greater than two thirds of the length of the first recognized speech.

3. The listening test detection method in the examination room according to claim 1, characterized in that: The first recognized voice is placed before the sine wave pure tone signal; and the broadcasting effect of the hearing broadcasting system is detected according to the sine wave pure tone signal and the first recognized voice, including: Perform the following operations on all detection data: Performing first speech recognition on the first recognized speech of the current detection data; If the result of the first speech recognition of the current detection data is correct, performing signal analysis on the sine wave pure tone signal of the current detection data; If the signal analysis result of the current detection data is qualified, switch to the next detection data; The broadcasting effect of the listening broadcasting system is detected based on the results of the first speech recognition and the results of the signal analysis of all the detection data.

4. The listening test detection method in the examination room according to claim 3, characterized in that: Detecting the broadcasting effect of the listening broadcasting system according to the first speech recognition result and the signal analysis result of all the detection data includes: If the signal analysis results of all the detection data are qualified, and the recognition results of the first recognition voice of all the detection data are correct, the broadcasting effect of the listening broadcasting system is detected to be qualified; Otherwise, the broadcasting effect of the listening broadcasting system is detected to be unqualified.

5. The listening test detection method in an examination room according to claim 1, characterized in that: Detecting the correctness of the test listening content according to the test listening content and the second recognized voice includes: Performing second voice recognition on the test listening content and the second recognized voice, and detecting the correctness of the test listening content according to the result of the second voice recognition.

6. The listening test detection method in an examination room according to claim 5, characterized in that: The number of the second recognized speech is an odd number not less than 3; and detecting the correctness of the test listening content according to the result of the second speech recognition includes: If the number of correct recognition results for the test listening content in the second speech recognition results is greater than a preset value; and / or If the number of correct recognition results for the second recognized speech in the results of the second speech recognition is greater than two-thirds of the number of the second recognized speech, the test listening content is detected to be correct; Otherwise, the test listening content is detected to be wrong.

7. The examination listening test detection method according to any one of claims 1 to 6, characterized in that: Also includes: Receiving a collection instruction for collecting the detection data through a local camera to start collecting the detection data; The detection result of the broadcast effect and the detection result of the correctness of the test listening content are sent to a remote server through the camera.

8. The listening test detection method in an examination room according to claim 3, characterized in that: Performing signal analysis on the sine wave pure tone signal of the current detection data includes: Calculating the signal amplitude, distortion data, sampling analysis and frequency response data of the sine wave pure tone signal; The signal amplitude, the distortion data, the sampling analysis and the frequency response data are compared with the pre-generated standard data of the sine wave pure tone signal to determine whether the signal analysis result is qualified.

9. A listening test detection device for an examination room, characterized in that: The microphones used in the examination room include: A test data acquisition module is used to collect a plurality of test data played cyclically by the hearing broadcasting system before the test; wherein each test data is composed of a sine wave pure tone signal and a first recognized voice, and the sine wave pure tone signal of each test data has the same amplitude and different frequencies; the microphone and the hearing broadcasting system are located in the same examination room; A broadcast effect detection module, used for detecting the broadcast effect of the hearing broadcast system according to the sine wave pure tone signal and the first recognized voice; A listening content collection module, used for collecting the test listening content and the second recognized voice during the test if the broadcast effect is qualified; The listening content correctness detection module is used to detect the correctness of the test listening content according to the test listening content and the second recognized speech.

10. The listening test detection device for examination room according to claim 9, characterized in that: The length of each first recognized speech is the same, and the number of elements in the same position and with different sounds of the plurality of first recognized speech is greater than two thirds of the length of the first recognized speech.

11. The listening test detection device for examination room according to claim 9, characterized in that: The first recognized voice is placed before the sine wave pure tone signal; the broadcast effect detection module includes: The detection data cycle operation unit is used to perform the following operations on all detection data: A current detection data speech recognition unit, used for performing a first speech recognition on a first recognition speech of the current detection data; a current detection data signal analysis unit, configured to perform signal analysis on a sine wave pure tone signal of the current detection data if a result of the first speech recognition of the current detection data is correct; A next detection data switching unit, used for switching to the next detection data if the signal analysis result of the current detection data is qualified; The broadcast effect detection unit is used to detect the broadcast effect of the listening broadcast system according to the results of the first voice recognition and the signal analysis of all the detection data.

12. The listening test detection device for examination room according to claim 11, characterized in that: The broadcast effect detection unit comprises: A first broadcast effect detection unit, used for detecting whether the broadcast effect of the listening broadcast system is qualified if the signal analysis results of all the detection data are qualified and the recognition results of the first recognized voice of all the detection data are correct; The second broadcast effect detection unit is used to detect that the broadcast effect of the listening broadcast system is unqualified.

13. The listening test detection device for examination room according to claim 9, characterized in that: The listening content correctness detection module includes: The listening content correctness detection unit is used to perform second voice recognition on the test listening content and the second recognized voice, and detect the correctness of the test listening content according to the result of the second voice recognition.

14. The listening test detection device for examination room according to claim 13, characterized in that: The number of the second recognized speech is an odd number not less than 3; the listening content correctness detection unit includes: The first unit for testing the listening content of the test is used to detect if the number of correct recognition results of the second speech recognition for the listening content of the test is greater than a preset value; and / or If the number of correct recognition results for the second recognized speech in the results of the second speech recognition is greater than two-thirds of the number of the second recognized speech, the test listening content is detected to be correct; The second unit for detecting the test listening content is used to detect that the test listening content is wrong.

15. The test device for listening comprehension in an examination room according to any one of claims 9 to 14, characterized in that: Also includes: A collection instruction receiving module, used for receiving a collection instruction for collecting the detection data through a local camera to start collecting the detection data; The detection result sending module is used to send the detection result of the broadcast effect and the detection result of the correctness of the test listening content to a remote server through the camera.

16. The listening test detection device for examination room according to claim 11, characterized in that: The current detection data signal analysis unit comprises: A signal parameter calculation unit, used to calculate the signal amplitude, distortion data, sampling analysis and frequency response data of the sine wave pure tone signal; The analysis result judgment unit is used to compare the signal amplitude, the distortion data, the sampling analysis and the frequency response data with the pre-generated standard data of the sine wave pure tone signal to determine whether the signal analysis result is qualified.

17. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the examination room listening test detection method described in any one of claims 1 to 8 are implemented.

18. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the examination room listening test detection method according to any one of claims 1 to 8 are implemented.

19. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the examination room listening test detection method according to any one of claims 1 to 8 are implemented.

Images