Voice simulation system, voice performance test system, method, terminal and medium

Abstract

The application discloses a voice simulation system, a voice performance test system, a method, a terminal and a medium, wherein the voice simulation system comprises a mute room and a sound simulation device, the sound simulation device comprises an in-vehicle noise playback unit, a human voice instruction playback unit and a plurality of environmental noise playback units, the plurality of environmental noise playback units are placed around the vehicle to be tested and are used for playing the environmental noise of a real vehicle under different environmental conditions; the in-vehicle noise playback unit is placed in the vehicle to be tested and is used for playing the in-vehicle noise of the real vehicle under different driving conditions; and the human voice instruction playback unit is placed in the vehicle to be tested and is used for playing the human voice instructions of different tones which are recorded in advance. The application restores the interference of noise on human voice instructions under different conditions, can complete the test of the voice system in the laboratory, realizes the automation and standardization of the voice system test, and improves the accuracy of the performance test data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle testing, in particular to a voice simulation system, a voice performance testing system, a method, a terminal and a medium. BACKGROUND

[0002] As a vehicle standard, the vehicle-mounted voice system can timely know the intention of the vehicle occupants and timely provide personalized services, effectively avoiding the inconvenience caused by the driver's line of sight deviating from the road and distracted driving. The current vehicle-mounted voice system needs to provide corresponding services through the voice instructions of the occupants, so before the vehicle is shipped, the voice performance of the vehicle-mounted voice system needs to be tested to ensure the response performance of the vehicle-mounted voice system to voice instructions.

[0003] Because the actual working environment of the vehicle-mounted voice system is relatively complex, in order to ensure that the test data is close to the actual working condition, the traditional voice test scheme generally carries out vehicle road test, which needs to carry out dynamic road test on the actual road to test the response performance of the vehicle-mounted voice system to voice instructions under different forming conditions. However, the vehicle road test needs to be equipped with a special driver and tester to carry out manual testing and record data, and many uncontrollable factors (such as differences caused by different testers) are likely to occur during manual testing, which can lead to inaccurate test data and ultimately inaccurate performance evaluation of the vehicle-mounted voice system. SUMMARY

[0004] The present application provides a voice simulation system, a voice performance testing system, a method, a terminal and a medium to solve the problem that the performance test data of the vehicle road test in the voice test scheme is not accurate enough, which leads to inaccurate performance evaluation of the vehicle-mounted voice system.

[0005] A voice simulation system is provided for simulating the working environment of the voice system on the vehicle to be tested, which includes a soundproof room and a sound simulation device. The soundproof room includes soundproof walls and a shock-absorbing floor, and the interior of the soundproof room is a test space for the vehicle to be tested to enter and perform voice simulation testing.

[0006] The sound simulation device includes an in-vehicle noise playback unit, a human voice instruction playback unit and a plurality of environmental noise playback units. The plurality of environmental noise playback units are placed around the vehicle to be tested to play pre-recorded environmental noise of real vehicles under different environmental conditions.

[0007] The in-vehicle noise playback unit is placed in the vehicle to be tested to play pre-recorded in-vehicle noise of real vehicles under different driving conditions.

[0008] The human voice instruction playback unit is placed in the vehicle to be tested to play pre-recorded human voice instructions of different timbres.

[0009] Optionally, the environmental noise playback unit comprises at least two stereo speakers symmetrically arranged on both sides of the vehicle to be tested, and the center positions of the stereo speakers are on the same horizontal line as the center positions of the vehicle windows of the vehicle to be tested.

[0010] Optionally, the vocal instruction playback unit is an artificial mouth, and the artificial mouth is arranged at a seat headrest of the vehicle to be tested.

[0011] Optionally, the voice performance test system further comprises an audio recording device, and the audio recording device comprises a vocal instruction recording unit, an in-vehicle noise recording unit and an environmental noise recording unit, the vocal instruction recording unit is used to record vocal instructions with different timbres, the in-vehicle noise recording unit is used to record in-vehicle noise of a real vehicle under different driving conditions, and the environmental noise recording unit is used to record environmental noise of the real vehicle under different environmental conditions.

[0012] Optionally, the environmental noise recording unit comprises at least two units, and the two environmental noise recording units are symmetrically arranged on both sides of the vehicle to be tested, a connecting straight line between the two environmental noise recording units is perpendicular to the lane line of the driving road, and the distance between the two environmental noise recording units is less than a preset distance.

[0013] Optionally, the vocal instruction recording unit is arranged at a seat headrest of the vehicle to be tested, and the in-vehicle noise recording unit is arranged in a driver's cabin of the vehicle to be tested.

[0014] Optionally, the shock-absorbing ground comprises a floor layer, a shock-absorbing layer and a ground which are sequentially stacked from top to bottom, the floor layer is used for parking the vehicle to be tested, and the shock-absorbing layer comprises a plurality of damping shock-absorbing pads.

[0015] Optionally, the sound insulation wall comprises an inner wall and an outer wall which are arranged at intervals, and the inner wall and the outer wall are both provided with a sound-absorbing material layer.

[0016] A voice performance test system is provided for testing a voice system of a vehicle to be tested, and the voice performance test system comprises a test execution terminal and the voice simulation system, the test execution terminal is arranged outside a soundproof room, and the test execution terminal is connected with the voice simulation device and the voice system.

[0017] Optionally, the voice performance test system further comprises a response acquisition device connected with the test execution terminal, and the response acquisition device is used to acquire test response data of the voice system in a performance test process.

[0018] Optionally, the response acquisition device comprises a first microphone and a camera, the first microphone is arranged at a center console of the vehicle to be tested, and the camera is arranged above a vehicle machine screen of the vehicle to be tested.

[0019] Optionally, the voice performance test system further comprises a sound card connected with the test execution terminal and a sound feedback device connected with the sound card, and the sound feedback device is used to acquire sound played by the voice simulation device.

[0020] Optionally, the voice performance test system comprises a second microphone arranged in the vehicle to be tested and a third microphone arranged outside the vehicle to be tested.

[0021] A voice performance test method is provided, which is used in the voice performance test system, and the method comprises the following steps:

[0022] Obtaining environment data of the vehicle to be tested in an actual driving environment, and obtaining human voice instructions with different tones, wherein the environment data comprises in-vehicle noise of the vehicle under different driving conditions and environmental noise of the vehicle under different environmental conditions;

[0023] Restoring the in-vehicle noise, the environmental noise and the human voice instructions in the voice performance test system to test the performance of the voice system of the vehicle to be tested, so as to obtain test response data of the voice system to different human voice instructions;

[0024] Obtaining log data of the voice system during the test, and taking the log data and the test response data as performance test data of the voice system.

[0025] Further, the in-vehicle noise, the environmental noise and the human voice instructions are restored in the voice performance test system to test the performance of the voice system of the vehicle to be tested, so as to obtain test response data of the voice system to different human voice instructions, which comprises the following steps:

[0026] a. Selecting the environmental noise;

[0027] b. Selecting the in-vehicle noise;

[0028] c. Selecting the human voice instructions;

[0029] d. Controlling each playback unit in the sound simulation device to play the in-vehicle noise, the environmental noise and the human voice instructions at the same time, and adjusting the playing volume intensity of each playback unit in the sound simulation device through the sound card and the sound feedback device;

[0030] e. When the playing volume intensity of each playback unit is consistent with the volume intensity of the corresponding sound, obtaining the test response data of the voice system to the human voice instructions through the response acquisition device;

[0031] f. Changing the human voice instructions, and repeating steps d-e to obtain the test response data of the voice system to different human voice instructions;

[0032] g. Changing the in-vehicle noise, and repeating steps c-e to obtain the test response data of the voice system to different human voice instructions under different in-vehicle noises;

[0033] h. change the environmental noise, and repeat steps b-e to obtain the test response data of the voice system to different human voice instructions under different environmental noise and different in-vehicle noise.

[0034] Further, the sound simulation system adjusts the playing volume intensity of each playback unit in the sound simulation device through a sound card and a sound feedback device, including:

[0035] The first microphone collects the playing human voice instruction of the human voice playback unit, and the volume intensity of the human voice instruction is taken as the adjustment target, and the sound card adjusts the volume intensity of the playing human voice instruction;

[0036] The second microphone obtains the playing in-vehicle noise of the in-vehicle noise playback unit, and the volume intensity of the in-vehicle noise is taken as the adjustment target, and the sound card adjusts the volume intensity of the playing in-vehicle noise;

[0037] The third microphone obtains the playing environmental noise of the environmental noise playback unit, and the volume intensity of the environmental noise is taken as the adjustment target, and the sound card adjusts the volume intensity of the playing environmental noise.

[0038] The test execution terminal comprises:

[0039] The first acquisition module is configured to acquire environmental data of a to-be-tested vehicle in an actual driving environment, and acquire human voice instructions with different timbres, wherein the environmental data comprises in-vehicle noise of the vehicle under different driving conditions and environmental noise of the vehicle under different environmental conditions;

[0040] The test module is configured to restore the in-vehicle noise, the environmental noise and the human voice instructions in a voice performance test system, to perform performance testing on a voice system of the to-be-tested vehicle, and to obtain test response data of the voice system to different human voice instructions;

[0041] The second acquisition module is configured to acquire log data of the voice system during the testing, and take the log data and the test response data as performance testing data of the voice system.

[0042] The test execution terminal comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the voice performance testing method when executing the computer program.

[0043] A readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the voice performance testing method.

[0044] The voice simulation system, the voice performance test system, the method, the terminal and the medium provided by the application have the following beneficial effects:

[0045] The voice simulation system in the application comprises a soundproof room and a sound simulation device, the soundproof room comprises soundproof walls and shock-absorbing ground, and the soundproof room is internally provided with a test space for a vehicle to be tested to enter and perform performance test; the sound simulation device comprises an in-vehicle noise playback unit, a human voice instruction playback unit and a plurality of environmental noise playback units, the plurality of environmental noise playback units are placed around the vehicle to be tested, and are used for playing environmental noise of a real vehicle under different environmental conditions which is recorded in advance; the in-vehicle noise playback unit is placed in the vehicle to be tested, and is used for playing in-vehicle noise of the real vehicle under different driving conditions which is recorded in advance; and the human voice instruction playback unit is placed in the vehicle to be tested, and is used for playing human voice instructions of different tones which are recorded in advance; the voice simulation system restores the interference of noise on human voice instructions under different conditions through various environmental noise and in-vehicle noise recorded in advance, and can truly simulate the working environment of the voice system on the vehicle to be tested; on this basis, the voice simulation system is combined with other test devices, and the test of the voice system can be completed in the laboratory, the automation and standardization of the voice system test are realized, the influence of uncontrollable factors in manual test is eliminated, and the accuracy of performance test data is improved. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the application. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without any creative labor.

[0047] Figure 1 is a structural schematic view of a voice simulation system in an embodiment of the application;

[0048] Figure 2 is a structural schematic view of a soundproof room in an embodiment of the application;

[0049] Figure 3 is a position schematic view of an environmental noise recording unit in an embodiment of the application;

[0050] Figure 4 is a structural schematic view of a voice performance test system in an embodiment of the application;

[0051] Figure 5 is a flow schematic view of a voice performance test method in an embodiment of the application;

[0052] Figure 6 is a structural schematic view of a test execution terminal in an embodiment of the application;

[0053] Figure 7 is another structural schematic view of a test execution terminal in an embodiment of the application.

[0054] In the drawings:

[0055] 1-voice simulation system; 11-soundproof room; 111-soundproof wall; 112-damping floor; 113-soundproof door; 114-slope in front of the door; 12-environmental noise playback unit; 13-vehicle interior noise playback unit; 14-human voice instruction playback unit;

[0056] 2-vehicle to be tested; 3-test execution terminal; 4-sound card; 51-first microphone; 52-camera; 61-second microphone; 62-third microphone. DETAILED DESCRIPTION

[0057] In order to make the technical problems to be solved by the present application, technical solutions and beneficial effects more clearly understood, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0058] It should be noted that when an element is referred to as being "fixed to" or "disposed on" another element, it can be directly on the other element or indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or indirectly connected to the other element.

[0059] It should be understood that the terms "length", "width", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the present application and simplify the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.

[0060] Please see Figures 1 to 4 , now the voice simulation system 1 and the voice performance test system provided by the embodiment of the present application will be described.

[0061] Embodiment one

[0062] As Figures 1 to 4As shown, a voice simulation system 1 is provided for simulating the working environment of a voice system on a vehicle 2 under test, including a soundproof room and a sound simulation device. The soundproof room includes soundproof walls 111, shock-absorbing floor 112, and other basic communication and power supply interfaces. The soundproof room is internally a test space for the vehicle 2 under test to enter and perform voice simulation tests. The sound simulation device includes an in-vehicle noise playback unit 13, a human voice instruction playback unit 14, and a plurality of environmental noise playback units 12. The plurality of environmental noise playback units are placed around the vehicle 2 under test for playing pre-recorded environmental noise of a real vehicle under different environmental conditions. The in-vehicle noise playback unit 13 is placed inside the vehicle 2 under test for playing pre-recorded in-vehicle noise of a real vehicle under different driving conditions. The human voice instruction playback unit 14 is placed inside the vehicle 2 under test for playing pre-recorded human voice instructions of different tones.

[0063] When it is necessary to test the performance of the voice system on the vehicle 2 under test, the vehicle is driven into the interior of the soundproof room, and the noise playback environment needs to be in a low-noise environment for maximum restoration of the noise real environment. The soundproof walls 111 and shock-absorbing floor 112 of the soundproof room constitute a soundproof and shock-absorbing test space, which provides a low-noise environment for the vehicle 2 under test to ensure that it is not disturbed by other sounds during subsequent noise simulation restoration. The plurality of environmental noise playback units are arranged around the vehicle 2 under test in the test space, and the in-vehicle noise playback unit 13 and the human voice instruction playback unit 14 are arranged at corresponding positions inside the vehicle 2 under test, thereby completing the construction of the voice simulation system 1. After the voice simulation system 1 is constructed, the voice simulation system 1 can be controlled to perform noise simulation restoration of the noise disturbance received by the vehicle 2 under test. The plurality of environmental noise playback units are controlled to play in-vehicle noise of a real vehicle under different driving conditions. At this time, the environmental noise played by the plurality of environmental noise playback units is stereo sound, which can simulate in-vehicle noise of a real vehicle under different driving conditions. The plurality of environmental noise playback units are also controlled to play environmental noise of a real vehicle under different environmental conditions, which can simulate environmental noise of a real vehicle under different environmental conditions. The two noises combined constitute different condition noises of a real vehicle, i.e., the actual working environment of the voice system is simulated. On this basis, the human voice instruction playback unit 14 is controlled to play human voice instructions of different tones, and the performance of the voice system is tested. Performance test data of the voice system recognizing different human voice instructions under different conditions can be collected, and the performance test data can be analyzed to determine the performance of the voice system.

[0064] In summary, the embodiment restores the interference of noise on the human voice instruction under different working conditions by pre-recording various environmental noise and in-vehicle noise, can truly simulate the working environment of the voice system on the vehicle 2 to be tested, and on this basis, the voice simulation system 1 cooperates with other test devices to complete the test of the voice system in the laboratory, realizes the automation and standardization of the voice system test, eliminates the influence of uncontrollable factors in manual test, and improves the accuracy of performance test data.

[0065] Optionally, the voice performance test system further comprises an audio recording device, the audio recording device comprising a human voice instruction recording unit, an in-vehicle noise recording unit and an environmental noise recording unit, the human voice instruction recording unit being configured to record human voice instructions with different timbres, the in-vehicle noise recording unit being configured to record in-vehicle noise of a real vehicle under different driving conditions, and the environmental noise recording unit being configured to record environmental noise of the real vehicle under different environmental conditions. The audio recording device is used to pre-record different noise and human voice instructions, which can be used in the subsequent voice simulation system 1, providing a basis for truly restoring the working environment of the voice system, and can be reused, improving the efficiency of subsequent performance test of the voice system.

[0066] The in-vehicle noise recording unit is used to record in-vehicle noise of a real vehicle under different driving conditions, and the in-vehicle noise recording unit is placed in the vehicle 2 to be tested to collect running noise of the vehicle 2 to be tested such as wind noise, tire noise and engine vibration noise under different driving conditions, wherein the in-vehicle noise comprises sound information and noise intensity information; the environmental noise recording unit is used to record environmental noise of a real vehicle under different environmental conditions, and the pre-recorded environmental noise includes but is not limited to environmental noise under environmental conditions such as city, suburb and highway, and the environmental noise comprises sound information and noise intensity information; the environmental noise recording unit is placed on the driving road on both sides of the vehicle 2 to be tested when recording the environmental noise, so that noise more consistent with the actual environmental condition can be collected; the human voice instruction recording unit is used to record human voice instructions with different timbres, and the human voice instruction comprises sound information and sound intensity information; the pre-recorded human voice instruction includes but is not limited to human voice instructions of users with different genders, ages and languages, and the influence of human voice instructions of users with different genders, ages and languages on the voice system recognition is determined in the subsequent process, so as to improve the voice system performance test recognition effect.

[0067] Optionally, the human voice instruction recording unit is arranged at the seat headrest of the vehicle 2 to be tested, which can be more close to the situation when the driver issues a human voice instruction in the vehicle space, and is more close to the actual environment. The in-vehicle noise recording unit is arranged in the driver's cabin of the vehicle 2 to be tested, and since the voice system is generally arranged in the center console, the in-vehicle noise recording unit arranged in the driver's cabin of the vehicle 2 to be tested can effectively collect the influence of in-vehicle noise on the voice system.

[0068] Optionally, the in-vehicle noise recording unit includes at least two units. One unit can be positioned at the driver's ear in the cockpit to collect in-vehicle noise sound information. That is, the sound information collection location for in-vehicle noise is at the driver's ear, which is closer to the driver's actual experience. The other unit can be positioned at the microphone in the cockpit. That is, the noise intensity information collection location for in-vehicle noise is at the microphone location of the vehicle under test, making the collected noise intensity closer to the in-vehicle noise intensity received by the voice system, which is closer to the actual working environment.

[0069] Optionally, the environmental noise recording unit includes at least two units, which are symmetrically arranged on both sides of the vehicle under test 2. The connecting line between the two environmental noise recording units is perpendicular to the lane line of the driving road, and the distance between the two environmental noise recording units is less than a preset distance. Figure 3 As shown, when recording ambient noise, the vehicle under test 2 is placed on the actual driving road. The ambient noise recording units are required to be in pairs, with a pair of ambient noise recording units symmetrically placed on both sides of the vehicle under test 2, at the edge of the lane; the line connecting the pair of ambient noise recording units is perpendicular to the lane line, and the distance L between the pair of ambient noise recording units is... MIC The distance is less than a preset distance. The preset distance can be 4.2m. The lane width on a typical driving road is 2.4m to 4.2m. Setting the distance between a pair of environmental noise recording units to less than 4.2m allows for the collection of actual environmental noise measured while driving on the lane, making the collected environmental noise more closely resemble real-world conditions. In other embodiments, the distance L between a pair of environmental noise recording units... MIC It can be greater than or equal to 2.5m and less than or equal to 3.75m, that is, 2.5m ≤ L. MIC ≤3.75m, further reducing the distance L between a pair of ambient noise recording units. MIC This improves the accuracy of the collected environmental noise data.

[0070] Optionally, the environmental noise playback unit 12 includes at least two stereo speakers symmetrically arranged on both sides of the vehicle 2 to be tested, and the center of each stereo speaker is on the same horizontal line as the center of the window of the vehicle 2 to be tested. When the test voice simulation system 1 performs noise simulation restoration, the positions of the noise playback unit and the noise recording unit need to be consistent. Since at least two symmetrical environmental noise recording units are used to collect environmental noise when recording environmental noise, the number of environmental noise playback units 12 needs to be greater than or equal to the number of environmental noise playback units 12 in order to restore the noise as much as possible. That is, the number of environmental noise playback units 12 is at least two, and the two stereo speakers are symmetrically arranged on both sides of the vehicle 2 to be tested to improve the environmental noise playback effect and simulate the actual noise environment. At the same time, since the center of the window of the vehicle 2 to be tested has the worst sound insulation effect, the center of each stereo speaker needs to be on the same horizontal line as the center of the window of the vehicle 2 to be tested, so that the noise played by the environmental noise playback unit 12 can enter the vehicle 2 to be tested through the window to the greatest extent and be received by the voice system, thereby greatly restoring the interference of environmental noise on the voice system. In other embodiments, the environmental noise playback unit 12 can also be a related device that plays stereo sound or above to further improve the restoration degree of environmental noise and further improve the simulation accuracy of the voice system working environment, thereby obtaining more accurate voice system performance.

[0071] Optionally, the human voice instruction playback unit 14 is an artificial mouth, and the artificial mouth is arranged at the seat headrest of the vehicle 2 to be tested. The human voice instruction played by the artificial mouth can approach the sound source of a real human mouth, and placing the artificial mouth at the seat headrest can simulate the human voice instruction issued by the driver or passenger in a real scenario, thereby further improving the restoration degree of the human voice instruction.

[0072] Optionally, the damping floor 112 of the soundproof room includes a floor layer, a damping layer and a ground layer stacked from top to bottom, and the floor layer is used for parking the vehicle 2 to be tested, and the damping layer includes a plurality of damping pads. The damping floor 112 of the soundproof room is arranged as a ground layer containing damping pads to ensure a low-noise environment in the soundproof room, improve the restoration degree of the operating environment of the vehicle 2 to be tested, and further improve the restoration degree of the working environment of the voice system on the vehicle 2 to be tested.

[0073] Optionally, as shown in FIG. 1, the test voice simulation system 1 includes a soundproof room 100, a vehicle 2 to be tested, a noise recording unit 10, an environmental noise playback unit 12, a human voice instruction playback unit 14, a voice system 16, a test system 18 and a test data analysis system 20. Figure 2As shown, the sound insulation door 113 is installed on the sound insulation wall 111, and a door front slope 114 is arranged on the ground outside the sound insulation door 113 to facilitate the vehicle 2 to enter the test space in the quiet room, so that the vehicle 2 can enter and exit, and after the device in the vehicle 2 is changed, the voice simulation system 1 can be repeatedly used to simulate and test different voice systems, avoid repeated system construction, improve the utilization rate of the simulation device, and reduce the test cost.

[0074] Optionally, the floor layer includes an inner floor layer and an outer floor layer, the damping layer includes a first damping damping layer and a second damping damping layer, and the inner floor layer, the first damping damping layer, the outer floor layer, the second damping damping layer and the ground are sequentially stacked from top to bottom. The first damping damping layer is a damping layer composed of a plurality of damping pads; the second damping damping layer includes a plurality of low-frequency damping composite shock absorbers, the upper end of the low-frequency shock absorber abuts against the outer floor layer, and the lower end of the low-frequency damping composite shock absorber abuts against the ground. The damping layer including the first damping damping layer and the second damping damping layer can simultaneously eliminate high-frequency and low-frequency vibrations, further ensuring the low-noise environment of the quiet room.

[0075] Optionally, the sound insulation wall 111 includes an inner wall and an outer wall arranged at intervals, and the inner wall and the outer wall are both provided with a sound-absorbing material layer. The sound insulation wall 111 is a composite sound insulation wall 111, which includes an inner wall and an outer wall, and both the wall and the outer wall are provided with a sound-absorbing material layer to ensure the sound insulation performance of the quiet room and provide a low-noise environment. In addition, a plurality of sound insulation boards and a plurality of damping reduction layers are arranged between the inner wall and the outer wall, and a metal micro-porous interior decoration sound-absorbing layer is further arranged on the inner side of the inner wall (close to the test space side), further ensuring the sound insulation performance of the quiet room.

[0076] In this embodiment, the position of the sound simulation device is arranged according to the setting position of the audio recording device, and the sound simulation device is controlled to play the noise and the vocal instruction recorded by the audio recording device, wherein the environmental noise is played by using a stereo sound box, and the vocal instruction is played by using an artificial mouth, which can most realistically simulate and restore the working environment of the voice system, provides a solid foundation for subsequent performance testing of the voice system, realizes automation and standardization of voice system testing, eliminates the influence of uncontrollable factors during manual testing, improves the accuracy of performance test data, and further accurately determines the performance of the voice system.

[0077] Embodiment two

[0078] As Figure 4As shown, a voice performance test system is provided for testing the voice system of the vehicle 2 to be tested, which comprises a test execution terminal 3 and the voice simulation system 1 described above, the test execution terminal 3 is arranged outside the soundproof room, and the test execution terminal 3 is connected with the sound simulation device and the voice system. Among them, the voice system is the voice system of the vehicle machine on the vehicle 2 to be tested, the test execution terminal 3 is connected with the vehicle bus of the vehicle 2 to be tested, the vehicle bus is connected with the vehicle machine interface, the connection between the test execution terminal 3 and the voice system is realized, the test execution terminal 3 is used for controlling the output of test content and instructions, and collecting performance test data.

[0079] After the voice simulation system 1 is constructed, the test execution terminal 3 is connected with the environmental noise playback unit 12, the in-vehicle noise playback unit 13 and the human voice instruction playback unit 14 respectively, and the test execution terminal 3 is connected with the voice system of the vehicle 2 to be tested, and the voice performance test system is completed. When the voice performance test system tests the voice system of the vehicle 2 to be tested, the test execution terminal 3 outputs test content and instructions, that is, the environmental noise playback unit 12, the in-vehicle noise playback unit 13 and the human voice instruction playback unit 14 are controlled to play corresponding sound, so as to simulate the real working environment of the voice system and test the performance of the voice system; during the test, the test execution terminal 3 can directly obtain the log data of the voice system as the performance test data of the voice system recognizing different human voice instructions under different working conditions, and then analyze the performance test data to determine the performance of the voice system.

[0080] In this embodiment, the interference of noise on human voice instructions under different working conditions is restored by pre-recording various environmental noises and in-vehicle noises, which can truly simulate the working environment of the voice system on the vehicle 2 to be tested. On this basis, the voice simulation system 1 cooperates with the test execution terminal 3 to complete the test of the voice system in the laboratory without manual intervention, realizes the automation and standardization of the voice system test, eliminates the influence of uncontrollable factors in manual test, and improves the accuracy of performance test data.

[0081] Optionally, the voice performance test system of the embodiment further comprises a test monitoring system connected with the test execution terminal 3, which is used for managing, displaying and recording test task data, and obtaining performance test data fed back by the test execution terminal 3, and then analyzing the performance test data to output and display test reports, further improving the automation and standardization of the voice performance test system and reducing the test cost.

[0082] Optionally, the voice performance test system of the embodiment further comprises a response collecting device connected with the test execution terminal 3, the response collecting device being configured to collect test response data of the voice system during the performance test. On the basis of directly obtaining the voice system log data, the test response data of the voice system to the human voice instruction is obtained at the operation level of the voice system. During the test, the log data and the test response data of the voice system are taken as the performance test data. The log data and the test response data can be compared subsequently to determine whether the voice system software execution and the operation level response are consistent, and the accuracy of the performance test data is increased. The test response data can be voice response data and / or interface response data of the voice system.

[0083] Optionally, the response collecting device comprises a first microphone 51 and a camera 52. The first microphone 51 is arranged on the center console of the vehicle 2 to be tested, and the camera 52 is arranged above the screen of the vehicle machine of the vehicle 2 to be tested. The first microphone 51 arranged on the center console can collect the voice response data of the voice system during the performance test. The camera 52 arranged above the screen of the vehicle machine can collect the interface response data of the voice system during the performance test.

[0084] Optionally, the voice performance test system further comprises a sound card 4 and a sound feedback device connected with the sound card 4. The sound card 4 is connected with the test execution terminal 3 and is configured to control and adjust the output of the environmental noise, the in-vehicle noise, and the human voice instruction. The sound feedback device is configured to collect the sound played by the sound simulation device. The recorded environmental noise and in-vehicle noise both contain noise intensity, and the recorded human voice instruction also contains sound intensity. In order to ensure that the voice system can work in the real working environment accurately during the simulation and restoration of the noise and the instruction by the voice simulation system 1, the sound card 4 and the corresponding sound feedback device need to be arranged. The sound card 4 is connected with the sound feedback device. When the sound simulation device plays the pre-recorded environmental noise, in-vehicle noise, and human voice instruction, the sound feedback device collects the playing sound of the sound simulation device and feeds back the collected playing sound to the sound card 4. The sound card 4 adjusts the environmental noise, in-vehicle noise, and human voice instruction played by the sound simulation device according to the content of the playing sound, so that the playing volume intensity of the environmental noise, in-vehicle noise, and human voice instruction is consistent with the pre-recorded noise intensity and sound intensity.

[0085] Optionally, the voice performance test system comprises a second microphone 61 arranged in the vehicle 2 to be tested and a third microphone 62 arranged outside the vehicle 2 to be tested. When playing the environmental noise, the second microphone 61 needs to be arranged at a specific position outside the vehicle 2 to be tested to collect the playing noise intensity of the environmental noise played by the environmental noise playback unit 12, so as to adjust the output of the environmental noise playback unit 12 through the sound card 4, and ensure that the playing noise intensity collected at the specific position is consistent with the pre-recorded environmental noise intensity. Meanwhile, the second microphone 61 also needs to be arranged in the vehicle 2 to be tested to collect the playing noise intensity of the in-vehicle noise played by the in-vehicle noise playback unit 13, so as to adjust the output of the in-vehicle noise playback unit 13 through the sound card 4, and ensure that the playing noise intensity collected at the specific position is consistent with the pre-recorded in-vehicle noise intensity. The adjustment principle of the vocal instruction is similar, the fourth microphone is arranged to collect the playing volume intensity of the vocal instruction played by the vocal instruction playback unit 14, so as to adjust the output of the vocal instruction playback unit 14 through the sound card 4, and ensure that the playing intensity of the instruction collected at the specific position is consistent with the pre-recorded vocal instruction sound intensity.

[0086] In an embodiment, the first microphone 51 can be used as a vocal instruction sound feedback device, that is, the first microphone 51 is used as a response collection device and also as a vocal instruction sound feedback device, so as to optimize the test device and reduce the cost.

[0087] Optionally, the third microphone 62 is arranged at a position of 0.5L MIC from the center line of a pair of symmetrical environmental noise playback units 12, the center line being a straight line between the center positions of the environmental noise playback units 12. That is, the third microphone 62 is arranged at a position of 0.5L MIC from the midpoint of the midpoint line of a pair of symmetrical environmental noise playback units 12, L MIC being the distance between a pair of symmetrical environmental noise recording units. If the distance between a pair of symmetrical environmental noise playback units 12 is the same as the distance between a pair of symmetrical environmental noise recording units, both are L MIC , then the third microphone 62 is arranged at the midpoint of the midpoint line of a pair of symmetrical environmental noise playback units 12.

[0088] Embodiment three

[0089] The voice performance test method provided by the embodiment of the application is applied to the voice performance test system as shown in Figure 4 , and an execution end of the voice performance test method is a test execution terminal. The test execution terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and servers. The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0090] In an embodiment, as shown in Figure 5 A voice performance test method is provided, which is described by taking a test execution terminal in Figure 4 as an example, including the following steps:

[0091] S10: Obtain environmental data of the vehicle to be tested in an actual driving environment, and obtain human voice instructions of different timbres.

[0092] Before testing the performance of the voice system on the vehicle to be tested, environmental data of the vehicle to be tested in an actual driving environment needs to be obtained, and human voice instructions of different timbres need to be obtained, wherein the environmental data includes in-vehicle noise of the actual vehicle under different driving conditions, and environmental noise of the actual vehicle under different environmental conditions.

[0093] The in-vehicle noise of the actual vehicle under different driving conditions can be collected by the aforementioned in-vehicle noise recording unit; the environmental noise of the actual vehicle under different environmental conditions can be collected by the aforementioned environmental noise recording unit; the human voice instructions of different timbres can be collected by the aforementioned human voice instruction recording unit. The collection requirements of in-vehicle noise, environmental noise, and human voice instructions are as described above, and will not be repeated here.

[0094] S20: Restore in-vehicle noise, environmental noise, and human voice instructions in a voice performance test system to test the performance of the voice system of the vehicle to be tested, to obtain test response data of the voice system to different human voice instructions.

[0095] After obtaining the human voice instructions, the in-vehicle noise, and the environmental noise, restore the in-vehicle noise, the environmental noise, and the human voice instructions in a voice performance test system to test the performance of the voice system of the vehicle to be tested, to obtain test response data of the voice system to different human voice instructions. The voice simulation system of the voice performance test system is used to restore the in-vehicle noise, the environmental noise, and the human voice instructions to simulate the real working environment of the voice system. The specific testing process is as described above, and will not be repeated here.

[0096] S30: Obtain log data of the voice system during the test process, and take the log data and the test response data as performance test data of the voice system.

[0097] While the voice system is testing the response data of different human voice instructions, log data of the voice system during the test process also needs to be obtained, and the log data and the test response data are taken as performance test data of the voice system. The log data and the test response data can be compared later to determine whether the voice system software execution and operation layer response are consistent, and to increase the accuracy of the performance test data, so as to accurately test the performance of the voice system.

[0098] In this embodiment, the environmental data of the vehicle to be tested in the actual driving environment is obtained, and the human voice instructions of different timbres are obtained, the environmental data including the in-vehicle noise of the real vehicle under different driving conditions and the environmental noise of the real vehicle under different environmental conditions, then the in-vehicle noise, the environmental noise and the human voice instructions are restored in the voice performance test system to test the performance of the voice system of the vehicle to be tested, to obtain the test response data of the voice system to different human voice instructions, finally the log data of the voice system in the test process is obtained, and the log data and the test response data are taken as the performance test data of the voice system; various environmental noises and in-vehicle noises are recorded in advance, and the voice simulation system restores the interference of the noises on the human voice instructions under different conditions, which can truly simulate the working environment of the voice system on the vehicle to be tested. On this basis, the voice simulation system is combined with other test devices to complete the test of the voice system in the laboratory, realizes the automation and standardization of the voice system performance test, eliminates the influence of uncontrollable factors in manual test, and improves the accuracy of the performance test data.

[0099] In an embodiment, in step S20, that is, restoring the in-vehicle noise, the environmental noise and the human voice instructions in the voice performance test system to test the performance of the voice system of the vehicle to be tested to obtain the test response data of the voice system to different human voice instructions, specifically includes the following steps:

[0100] a. Select the environmental noise;

[0101] b. Select the in-vehicle noise;

[0102] c. Select the human voice instruction;

[0103] d. Control the playback units in the sound simulation device to play the in-vehicle noise, the environmental noise and the human voice instruction at the same time, and adjust the playback volume intensity of each playback unit in the sound simulation device through the sound card and the sound feedback device;

[0104] e. When the playback volume intensity of each playback unit is consistent with the volume intensity of the corresponding sound, obtain the test response data of the voice system to the human voice instruction through the response acquisition device;

[0105] f. Change the human voice instruction, and repeat steps d-e to obtain the test response data of the voice system to different human voice instructions;

[0106] g. Change the in-vehicle noise, and repeat steps c-e to obtain the test response data of the voice system to different human voice instructions under different in-vehicle noises;

[0107] h. Change the environmental noise, and repeat steps b-step e to obtain the test response data of the voice system to different voice instructions under different environmental noise and different in-vehicle noise.

[0108] In this embodiment, the specific process of restoring in-vehicle noise, environmental noise and voice instructions in the voice performance test system to test the performance of the voice system of the vehicle to be tested to obtain the test response data of the voice system to different voice instructions is determined. When the in-vehicle noise, environmental noise and voice instructions are restored, the played sound information is consistent with the pre-recorded information, and the played volume intensity is consistent with the pre-recorded sound intensity, which provides a basis for truly restoring the actual working environment of the voice system.

[0109] In an embodiment, in step d, the playing volume intensity of each playback unit in the sound simulation device is adjusted through the sound card and the sound feedback device, which specifically includes the following steps:

[0110] d1. The playing voice instructions of the voice playback unit are collected by the first microphone, and the volume intensity of the voice instructions is taken as the adjustment target to adjust the volume intensity of the playing voice instructions through the sound card.

[0111] d2. The playing in-vehicle noise of the in-vehicle noise playback unit is obtained by the second microphone, and the volume intensity of the in-vehicle noise is taken as the adjustment target to adjust the volume intensity of the playing in-vehicle noise through the sound card.

[0112] d3. The playing environmental noise of the environmental noise playback unit is obtained by the third microphone, and the volume intensity of the environmental noise is taken as the adjustment target to adjust the volume intensity of the playing environmental noise through the sound card.

[0113] In this embodiment, the sound feedback device includes a first microphone, a second microphone and a third microphone. When the performance of the voice system is tested, the first microphone collects the playing voice instructions of the voice playback unit, the second microphone obtains the playing in-vehicle noise of the in-vehicle noise playback unit, and the third microphone obtains the playing environmental noise of the environmental noise playback unit. After the first microphone, the second microphone and the third microphone collect the playing sound of the corresponding playback unit, the collected playing sound is fed back to the sound card, and the test execution terminal adjusts the playing sound intensity of each playback unit through the sound card to make the playing volume intensity of each playback unit consistent with the volume intensity of the pre-recorded sound. That is, the test execution terminal takes the volume intensity of the environmental noise as the adjustment target, takes the volume intensity of the voice instructions as the adjustment target, adjusts the volume intensity of the playing voice instructions through the sound card, takes the volume intensity of the in-vehicle noise as the adjustment target, adjusts the volume intensity of the playing in-vehicle noise, and takes the volume intensity of the environmental noise as the adjustment target, adjusts the volume intensity of the playing environmental noise.

[0114] In this embodiment, the playing voice instruction of the human voice playback unit is collected by the first microphone, and the volume intensity of the voice instruction is taken as the adjustment target, and the volume intensity of the playing voice instruction is adjusted by the sound card; the playing in-vehicle noise of the in-vehicle noise playback unit is obtained by the second microphone, and the volume intensity of the in-vehicle noise is taken as the adjustment target, and the volume intensity of the playing in-vehicle noise is adjusted by the sound card; the playing environmental noise of the environmental noise playback unit is obtained by the third microphone, and the volume intensity of the environmental noise is taken as the adjustment target, and the volume intensity of the playing environmental noise is adjusted by the sound card, which clearly shows the specific steps of adjusting the volume intensity of the playing of each playback unit in the sound simulation device by the sound card and the sound feedback device, provides a basis for the normal execution of performance testing, and further improves the automation and standardization of the test.

[0115] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0116] In an embodiment, a test execution terminal is provided, which corresponds to the voice performance test method in the above embodiment. As shown in the figure, the test execution terminal includes a first acquisition module 601, a test module 602 and a second acquisition module 603. The functions of each functional module are described in detail as follows: Figure 6

[0117] The first acquisition module 601 is configured to acquire environmental data of a vehicle to be tested in an actual driving environment, and acquire human voice instructions with different timbres, wherein the environmental data includes in-vehicle noise of the vehicle under different driving conditions and environmental noise of the vehicle under different environmental conditions.

[0118] The test module 602 is configured to restore the in-vehicle noise, the environmental noise and the human voice instruction in the voice performance test system to test the performance of the voice system of the vehicle to be tested, so as to obtain test response data of the voice system to different human voice instructions.

[0119] The second acquisition module 603 is configured to acquire log data of the voice system during the test, and take the log data and the test response data as performance test data of the voice system.

[0120] Further, the test module 602 is specifically configured to:

[0121] a. select the environmental noise;

[0122] b. select the in-vehicle noise;

[0123] c. select the human voice instruction;

[0124] ​d. controlling the playback units in the sound simulation device to simultaneously play the in-vehicle noise, the environmental noise and the voice instruction, and adjusting the volume intensity of the playback of each playback unit in the sound simulation device through the sound card and the sound feedback device;

[0125] e. when the volume intensity of the playback of each playback unit is consistent with the volume intensity of the corresponding sound, obtaining the test response data of the voice system to the voice instruction through the response acquisition device;

[0126] f. changing the voice instruction, and repeating steps d-e to obtain the test response data of the voice system to different voice instructions;

[0127] g. changing the in-vehicle noise, and repeating steps c-e to obtain the test response data of the voice system to different voice instructions under different in-vehicle noises;

[0128] h. changing the environmental noise, and repeating steps b-e to obtain the test response data of the voice system to different voice instructions under different environmental noises and different in-vehicle noises.

[0129] Further, the test module 602 is specifically further used for:

[0130] acquiring the playback of the voice instruction by the voice playback unit through the first microphone, and taking the volume intensity of the voice instruction as an adjustment target to adjust the volume intensity of the playback of the voice instruction through the sound card;

[0131] acquiring the playback of the in-vehicle noise by the in-vehicle noise playback unit through the second microphone, and taking the volume intensity of the in-vehicle noise as an adjustment target to adjust the volume intensity of the playback of the in-vehicle noise through the sound card;

[0132] acquiring the playback of the environmental noise by the environmental noise playback unit through the third microphone, and taking the volume intensity of the environmental noise as an adjustment target to adjust the volume intensity of the playback of the environmental noise through the sound card.

[0133] The specific limitations on the test execution terminal can be referred to the limitations on the voice performance test method in the above, which will not be repeated here. Each module in the above test execution terminal can be realized by software, hardware and combinations thereof in whole or in part. Each module above can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to call and execute the operations corresponding to each module by the processor.

[0134] In one embodiment, a test execution terminal is provided, which can be a computer device. The test execution terminal comprises a processor, a memory and an input device connected through a system bus. The processor of the test execution terminal is configured to provide computing and control capabilities. The memory of the test execution terminal comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The computer program, when executed by the processor, implements a voice performance testing method.

[0135] In one embodiment, as shown in Figure 7 a test execution terminal is provided, which comprises a memory, a processor and a computer program stored in the memory and executable in the processor, and the processor implements the steps of the voice performance testing method when executing the computer program.

[0136] In one embodiment, a readable storage medium is provided, which stores a computer program, and the computer program, when executed by a processor, implements the steps of the voice performance testing method.

[0137] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware, and the computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0138] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0139] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A speech simulation system, characterized by, The application relates to a sound system simulation environment for a vehicle to be tested, which comprises a soundproof room, a sound simulation device and an audio recording device. The soundproof room comprises soundproof walls and a shock-absorbing floor. The soundproof room is internally provided with a test space for the vehicle to be tested to enter and perform sound simulation tests. The shock-absorbing floor comprises a floor layer, a shock-absorbing layer and a ground layer which are sequentially stacked from top to bottom. The floor layer is used for parking the vehicle to be tested. The shock-absorbing layer comprises a plurality of damping shock-absorbing pads. The floor layer comprises an inner bottom plate layer and an outer floor layer. The shock-absorbing layer comprises a first damping shock-absorbing layer and a second damping shock-absorbing layer. The inner bottom plate layer, the first damping shock-absorbing layer, the outer floor layer, the second damping shock-absorbing layer and the ground layer are sequentially stacked from top to bottom. The first damping shock-absorbing layer is a shock-absorbing layer composed of a plurality of damping shock-absorbing pads. The second damping shock-absorbing layer comprises a plurality of low-frequency damping composite shock absorbers. The sound simulation device comprises an in-vehicle noise playback unit, a human voice instruction playback unit and a plurality of environmental noise playback units. The plurality of environmental noise playback units are placed around the vehicle to be tested and are used to play pre-recorded environmental noise of real vehicles under different environmental conditions. The in-vehicle noise playback unit is placed in the vehicle to be tested and is used to play pre-recorded in-vehicle noise of real vehicles under different driving conditions. The human voice instruction playback unit is placed in the vehicle to be tested and is used to play pre-recorded human voice instructions with different tones. The audio recording device comprises an environmental noise recording unit which is used to record environmental noise of real vehicles under different environmental conditions. The environmental noise recording unit comprises at least two units which are symmetrically arranged on the two sides of the vehicle to be tested. The connecting straight line between the two environmental noise recording units is perpendicular to the lane line of the driving road. The distance between the two environmental noise recording units is less than a preset distance.

2. The speech simulation system of claim 1, wherein, The environmental noise playback unit comprises at least two stereo sound boxes which are symmetrically arranged on the two sides of the vehicle to be tested. The center position of each stereo sound box is on the same horizontal line as the center position of the vehicle window of the vehicle to be tested.

3. The speech simulation system of claim 1, wherein, The human voice instruction playback unit is an artificial mouth which is arranged at the headrest of the seat of the vehicle to be tested.

4. The speech simulation system of claim 1, wherein, The audio recording device further comprises a human voice instruction recording unit and an in-vehicle noise recording unit. The human voice instruction recording unit is used to record human voice instructions with different tones. The in-vehicle noise recording unit is used to record in-vehicle noise of real vehicles under different driving conditions.

5. The speech simulation system of claim 4, wherein, The human voice instruction recording unit is arranged at the headrest of the seat of the vehicle to be tested. The in-vehicle noise recording unit is arranged in the driver's cabin of the vehicle to be tested.

6. The speech simulation system according to any one of claims 1 to 5, characterized in that, The soundproof walls comprise spaced inner walls and outer walls. The inner walls and the outer walls are provided with sound-absorbing material layers.

7. A voice performance test system for testing a voice system of a vehicle under test, characterized by The application further relates to a test execution terminal and a sound simulation system as described in any one of claims 1-5. The test execution terminal is arranged outside the soundproof room. The test execution terminal is connected with the sound simulation device and the sound system.

8. The speech performance testing system of claim 7, wherein, The voice performance test system further comprises a response acquisition device connected with the test execution terminal, and the response acquisition device is configured to acquire test response data of the voice system in the performance test process.

9. The speech performance testing system of claim 8, wherein, The response acquisition device comprises a first microphone and a camera, wherein the first microphone is arranged on a center console of the vehicle to be tested, and the camera is arranged above a screen of a vehicle machine of the vehicle to be tested.

10. The speech performance testing system of claim 7, wherein, The voice performance test system further comprises a sound card connected with the test execution terminal, and a sound feedback device connected with the sound card, and the sound feedback device is configured to acquire sound played by the sound simulation device.

11. The speech performance testing system of claim 7, wherein, The voice performance test system comprises a second microphone arranged in the vehicle to be tested and a third microphone arranged outside the vehicle to be tested.

12. A voice performance test method, characterized by, The voice performance test method is used in the voice performance test system as claimed in any one of claims 8-11, and the method comprises: acquiring environmental data of the vehicle to be tested in an actual driving environment, and acquiring human voice instructions with different timbres, wherein the environmental data comprises in-vehicle noise of the actual vehicle under different driving conditions and environmental noise of the actual vehicle under different environmental conditions; restoring the in-vehicle noise, the environmental noise and the human voice instructions in the voice performance test system to perform performance test on the voice system of the vehicle to be tested, so as to obtain test response data of the voice system to different human voice instructions; acquiring log data of the voice system in the test process, and taking the log data and the test response data as performance test data of the voice system.

13. The voice performance test method of claim 12, wherein, The voice performance test method is used in the voice performance test system as claimed in any one of claims 8-11, and the method comprises: a. selecting environmental noise; b. selecting in-vehicle noise; c. selecting human voice instructions; d. controlling each playback unit of the sound simulation device to play the in-vehicle noise, the environmental noise and the human voice instructions at the same time, and adjusting the playing volume intensity of each playback unit of the sound simulation device through the sound card and the sound feedback device; e. when the playing volume intensity of each playback unit is consistent with the volume intensity of the corresponding sound, acquiring test response data of the voice system to the human voice instructions through the response acquisition device; f. changing the human voice instructions, and repeating steps d-e to obtain test response data of the voice system to different human voice instructions; g. changing the in-vehicle noise, and repeating steps c-e to obtain test response data of the voice system to different human voice instructions under different in-vehicle noises; h. changing the environmental noise, and repeating steps b-e to obtain test response data of the voice system to different human voice instructions under different environmental noises and different in-vehicle noises.

14. The voice performance test method of claim 13, wherein, The adjusting of the playing volume intensity of each playback unit of the sound simulation device through the sound card and the sound feedback device comprises: The first microphone is used to collect the playing voice instruction of the voice instruction playback unit, and the volume intensity of the voice instruction is taken as an adjustment target, and the sound card is used to adjust the volume intensity of the playing voice instruction; The second microphone is used to collect the playing in-vehicle noise of the in-vehicle noise playback unit, and the volume intensity of the in-vehicle noise is taken as an adjustment target, and the sound card is used to adjust the volume intensity of the playing in-vehicle noise; The third microphone is used to collect the playing environmental noise of the environmental noise playback unit, and the volume intensity of the environmental noise is taken as an adjustment target, and the sound card is used to adjust the volume intensity of the playing environmental noise.

15. A test execution terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the steps of the voice performance test method in any one of claims 12 to 14.

16. A readable storage medium, the readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the voice performance test method in any one of claims 12 to 14.

Images