Sound source positioning accuracy testing system
By designing a sound source positioning accuracy test system including sound source equipment, equipment to be tested and load bearing equipment with adjustable height and rotation, the problem that the prior art cannot test the sound source positioning accuracy of intelligent voice interactive electronic devices in the vertical horizontal plane is solved, and a comprehensive test of the sound source positioning accuracy of the device in three-dimensional space is achieved.
Patent Information
- Application Number
- CN202420763039.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-12
- Publication Date
- 2025-03-28
- Estimated Expiration
- 2034-04-12
AI Technical Summary
The existing sound source positioning accuracy test scheme can only test the sound source positioning accuracy of intelligent voice interactive electronic devices on the horizontal plane, and cannot test the sound source positioning accuracy of the equipment on the vertical horizontal plane.
A sound source positioning accuracy testing system is designed, which includes a sound source device, an intelligent voice interactive electronic device to be tested, a first bearer device and a second bearer device. The first load-bearing device can adjust the height to simulate the test angle of the vertical horizontal plane, and the second load-bearing device can rotate about the central axis on the horizontal plane to simulate the positional relationship in three-dimensional space. Through the combination of these devices, the system can test the accuracy of sound source positioning of intelligent voice interactive electronic devices in three-dimensional space.
The test of the accuracy of sound source positioning of intelligent voice interactive electronic devices in three-dimensional space is realized, and the sound source positioning capability of the device can be more comprehensively evaluated, meeting the needs of intelligent voice interactive electronic devices in multi-directional sound source positioning.
Smart Images

Figure CN222689899U_ABST
Abstract
Description
Technical Field
[0001] The utility model relates to the technical field of testing, and more specifically to a sound source localization accuracy testing system. Background Art
[0002] Sound source localization refers to locating the location of the sound source. Intelligent voice interactive electronic devices (such as sweeping robots, smart air conditioners, smart TVs, smart cameras, smart speakers, companion robots and other products with intelligent voice interactive functions) must have a sound source localization function to ensure that they can effectively identify the source of the voice commands issued by the user. During the research and development of intelligent voice interactive electronic devices, the accuracy of sound source localization of intelligent voice interactive electronic devices needs to be tested.
[0003] With the development of intelligent voice interactive electronic devices, in addition to being able to rotate and locate the sound source in the horizontal plane, more and more intelligent voice interactive electronic devices have added functions such as "head-up gaze" and "visual follow-up". Therefore, it is necessary to test the sound source positioning accuracy of intelligent voice interactive electronic devices in both the horizontal plane and the vertical plane. However, the current sound source positioning accuracy test scheme can only test the sound source positioning accuracy of intelligent voice interactive electronic devices in the horizontal plane.
[0004] Therefore, how to provide a sound source localization accuracy test solution to test the sound source localization accuracy of intelligent voice interactive electronic devices in three-dimensional space has become a technical problem that needs to be urgently solved by technical personnel in this field. Utility Model Content
[0005] In view of this, the utility model provides a sound source localization accuracy testing system to test the sound source localization accuracy of an intelligent voice interactive electronic device in three-dimensional space.
[0006] In order to achieve the above purpose, the utility model provides the following technical solutions:
[0007] A sound source localization accuracy testing system, the system comprising:
[0008] A sound source device, an intelligent voice interactive electronic device to be tested, a first carrier device and a second carrier device;
[0009] The first carrying device can adjust the height based on the test angle of the vertical horizontal plane, and the sound source device can be detachably fixed on the top; the second carrying device can rotate around the central axis on the horizontal plane based on the test angle of the horizontal plane, and the intelligent voice interaction electronic device to be tested can be detachably fixed on the top;
[0010] The sound source device is used to play the test audio, and the intelligent voice interaction electronic device to be tested is used to perform sound source positioning response to the test audio.
[0011] Optionally, the system further comprises a control device;
[0012] The control device is connected to the intelligent voice interaction electronic device to be tested, and is used to obtain the result of the sound source localization response of the intelligent voice interaction electronic device to be tested to the test audio, and determine the test result based on the result, wherein the result includes the actual visual adjustment angle in the horizontal plane and the actual visual adjustment angle in the vertical horizontal plane.
[0013] Optionally, the system further comprises:
[0014] A laser irradiation component and a laser reflection component;
[0015] The laser irradiation component is fixed on the intelligent voice interactive electronic device to be tested, and the laser irradiation component is used to emit laser, and the laser irradiation direction of the laser irradiation component is the same as the sound source positioning direction of the intelligent voice interactive electronic device to be tested;
[0016] The laser reflection component is fixed on the front side of the sound source device, and is used to reflect laser. The center of the laser reflection component corresponds to the center of the sound unit of the sound source device, and the size of the laser reflection component is determined based on a preset sound source positioning accuracy test accuracy.
[0017] Optionally, the second carrying device can also rotate around the central axis on a vertical or horizontal plane; the control device is also connected to the second carrying device,
[0018] The control device is also used to control the second supporting device to rotate around the central axis on a vertical horizontal plane so that the angle between the intelligent voice interaction electronic device to be tested and the horizontal plane reaches the actual visual adjustment angle on the vertical horizontal plane.
[0019] Optionally, the control device is also used to control the second supporting device to rotate around the central axis on a vertical horizontal plane, so that the intelligent voice interaction electronic device to be tested is reset on the vertical horizontal plane.
[0020] Optionally, the control device is also used to control the second supporting device to rotate around the central axis on the horizontal plane based on the horizontal plane test angle and the actual visual adjustment angle on the horizontal plane, so that the intelligent voice interaction electronic device to be tested is reset on the horizontal plane.
[0021] Optionally, the first supporting device is a lifting table.
[0022] Optionally, the second carrying device is a hemispherical turntable.
[0023] Optionally, the control device is also connected to the sound source device, and the control device is used to control the sound source device to play the test audio.
[0024] Optionally, the control device is also connected to the first carrying device, and the control device is further used to control the first carrying device to adjust its height.
[0025] It can be known from the above technical scheme that compared with the prior art, the utility model discloses a sound source positioning accuracy test system, which includes a sound source device, an intelligent voice interactive electronic device to be tested, a first carrier device and a second carrier device, the sound source device is detachably fixed on the top of the first carrier device, and the intelligent voice interactive electronic device to be tested is detachably fixed on the top of the second carrier device, the first carrier device can adjust the height based on the test angle of the vertical horizontal plane, and the second carrier device can rotate around the central axis on the horizontal plane based on the horizontal plane test angle. By adjusting the height of the first carrier device and the rotation angle of the second carrier device around the central axis on the horizontal plane, the positional relationship between the sound source device and the intelligent voice interactive electronic device to be tested in three-dimensional space can be simulated. After the sound source device plays the test audio, the intelligent voice interactive electronic device to be tested performs a sound source positioning response to the test audio, and the test result can be determined based on the sound source positioning response. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] In order to more clearly illustrate the embodiments of the utility model or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only embodiments of the utility model. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0027] Figure 1 This is a schematic diagram of the existing sound source localization accuracy test scheme;
[0028] Figure 2 It is a structural schematic diagram of a sound source localization accuracy testing system disclosed in the utility model;
[0029] Figure 3 It is a structural schematic diagram of another sound source localization accuracy testing system disclosed in the utility model;
[0030] Figure 4 It is a structural schematic diagram of another sound source localization accuracy testing system disclosed in the utility model;
[0031] Figure 5It is a structural schematic diagram of another sound source localization accuracy testing system disclosed in the utility model;
[0032] Figure 6 The utility model discloses another structure diagram of a sound source localization accuracy testing system. DETAILED DESCRIPTION
[0033] The following will be combined with the drawings in the embodiments of the utility model to clearly and completely describe the technical solutions in the embodiments of the utility model. Obviously, the described embodiments are only part of the embodiments of the utility model, not all of the embodiments. Based on the embodiments in the utility model, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the utility model.
[0034] In order to better understand the technical solution of the present invention, the current sound source localization accuracy test solution is briefly introduced as follows:
[0035] The current sound source localization accuracy test scheme mainly involves placing multiple corpus excitation speakers (specifically, Figure 1 As shown in the figure, during the test, different corpus excitation speakers are used to play sound source localization test corpora to stimulate the machine under test. The machine under test adjusts the visual angle of the horizontal plane. The actual visual adjustment angle of the horizontal plane of the machine under test is compared with the initial angle difference between the corpus excitation speaker that plays the sound source localization test corpus and the machine under test. The sound source localization accuracy of the machine under test is evaluated by calculation methods such as root mean square error or angle error.
[0036] However, the current sound source localization accuracy test scheme can only test the sound source localization accuracy of the intelligent voice interactive electronic device in the horizontal plane, but cannot test the sound source localization accuracy of the intelligent voice interactive electronic device in the vertical plane.
[0037] In view of the problems existing in the above-mentioned sound source localization accuracy test scheme, the utility model proposes a sound source localization accuracy test system to test the sound source localization accuracy of an intelligent voice interactive electronic device in three-dimensional space.
[0038] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.
[0039] Reference Figure 2 , Figure 2 The structure diagram of a sound source localization accuracy test system disclosed in the utility model is as follows: Figure 2As shown, the system includes: a sound source device 11, an intelligent voice interaction electronic device to be tested 12, a first carrier device 13 and a second carrier device 14;
[0040] The first carrying device 13 can adjust the height based on the test angle of the vertical horizontal plane, and the sound source device 11 can be detachably fixed on the top; the second carrying device 14 can rotate around the central axis on the horizontal plane based on the test angle of the horizontal plane, and the intelligent voice interaction electronic device 12 to be tested can be detachably fixed on the top;
[0041] The sound source device 11 is used to play the test audio, and the intelligent voice interaction electronic device to be tested 12 is used to perform sound source localization response to the test audio.
[0042] In the present invention, the sound source device may include but is not limited to: a traditional loudspeaker, a simulated person widely used in sound testing, an artificial mouth, and any other device with a sound playback function, and the present invention does not impose any limitation on this.
[0043] In the present utility model, the intelligent voice interaction electronic device to be tested can be any product with intelligent voice interaction function, such as a sweeping robot, a smart air conditioner, a smart TV, a smart camera, a smart speaker, a companion robot, etc. The present utility model does not impose any limitation on this.
[0044] In the present invention, the test audio can be accurately distinguished for different voice interaction performance test indicators, that is, different test audios can be set corresponding to different voice interaction performance test indicators. For example, the test audio may include but is not limited to: a first test audio for waking up an intelligent voice interaction electronic device (such as "Hello, Xiaofei"), a second test audio for instructing an intelligent voice interaction electronic device to perform a target task (such as "lower the temperature", etc.), etc.
[0045] In the present invention, the first bearing device may be any device with a lifting function. As an implementable embodiment, the first bearing device may be a lifting table.
[0046] In the present invention, the second carrying device may be any device having a horizontal plane rotation function. As an implementable embodiment, the second carrying device may be a hemispherical turntable.
[0047] In the present invention, the height of the first supporting device can be determined based on the test angle of the vertical horizontal plane and the distance between the first supporting device and the second supporting device. There are many ways to adjust the height of the first supporting device, such as manual adjustment, remote control adjustment, etc., and the present invention does not impose any limitation on this.
[0048] In the utility model, the visual angle of the intelligent voice interaction electronic device to be tested fixed on the top of the second supporting device in the horizontal plane is directly facing the first supporting device. After determining the test angle of the horizontal plane, the second supporting device can be rotated counterclockwise or clockwise around the central axis in the horizontal plane, so that the visual angle of the intelligent voice interaction electronic device to be tested on the top of the second supporting device in the horizontal plane and the angle between the horizontal plane of the first supporting device reach the said horizontal plane test angle.
[0049] After the sound source device plays the test audio, the intelligent voice interactive electronic device to be tested can respond to the test audio by locating the sound source, and adjust the visual angle in the horizontal plane and the vertical horizontal plane, that is, rotate in the horizontal plane and "look up and look at each other" or "visually follow" in the vertical horizontal plane. By observing the rotation amplitude of the intelligent voice interactive electronic device to be tested in the horizontal plane, the tester can roughly determine the accuracy of the sound source positioning of the intelligent voice interactive electronic device to be tested in the horizontal plane, and by observing the "look up and look at each other" or "visually follow" action of the intelligent voice interactive electronic device to be tested, the tester can roughly determine the accuracy of the sound source positioning of the intelligent voice interactive electronic device to be tested in the vertical plane, and then roughly determine the test results.
[0050] The present embodiment discloses a sound source localization accuracy test system, which includes a sound source device, an intelligent voice interactive electronic device to be tested, a first carrier device and a second carrier device, wherein the sound source device is detachably fixed on the top of the first carrier device, and the intelligent voice interactive electronic device to be tested is detachably fixed on the top of the second carrier device, the first carrier device can adjust the height based on a test angle of a vertical horizontal plane, and the second carrier device can rotate around a central axis on a horizontal plane based on a horizontal plane test angle, and by adjusting the height of the first carrier device and the rotation angle of the second carrier device around the central axis on the horizontal plane, the positional relationship between the sound source device and the intelligent voice interactive electronic device to be tested in three-dimensional space can be simulated, and after the sound source device plays a test audio, the intelligent voice interactive electronic device to be tested performs a sound source localization response to the test audio, and the test result can be determined based on the sound source localization response.
[0051] Considering that the test results are determined by the tester observing the sound source localization response of the intelligent voice interactive electronic device to the test audio, which is limited by the observation accuracy of the tester, resulting in low accuracy of the test results, in order to solve this problem, a control device can also be set in the sound source localization accuracy test system.
[0052] Reference Figure 3 , Figure 3 FIG. 1 is a structural diagram of another sound source localization accuracy testing system disclosed in the utility model, such as Figure 3As shown, the system also includes a control device 15; the control device is connected to the intelligent voice interaction electronic device 12 to be tested, and is used to obtain the result of the sound source localization response of the intelligent voice interaction electronic device to be tested to the test audio, and determine the test result based on the result, wherein the result includes the actual visual adjustment angle in the horizontal plane and the actual visual adjustment angle in the vertical horizontal plane.
[0053] In the present invention, the control device can be any device, such as a laptop computer, a desktop computer, a server, an industrial computer, a smart phone, a PAD, etc., and the present invention does not impose any limitation on this. The connection between the control device and the intelligent voice interactive electronic device to be tested can be a wired connection or a wireless connection, and the present invention does not impose any limitation on this.
[0054] As an implementable embodiment, the specific way in which the control device determines the test result based on the result may be to calculate the error between the actual visual adjustment angle in the horizontal plane and the test angle in the horizontal plane, and the error between the actual visual adjustment angle in the vertical plane and the test angle in the vertical plane, and then determine the test result.
[0055] In this embodiment, by adding a control device to the sound source localization accuracy test system, the control device obtains the result of the sound source localization response of the intelligent voice interaction electronic device to be tested to the test audio, and determines the test result based on the result, so that a quantified test result can be obtained, which is more accurate.
[0056] Reference Figure 4 , Figure 4 FIG. 1 is a structural diagram of another sound source localization accuracy testing system disclosed in the utility model, such as Figure 4 As shown, the control device can also be connected to the sound source device, and the control device is also used to control the sound source device to play the test audio. When the control device controls the sound source device to play the test audio, the volume can be determined according to the test angle and the distance between the sound source device and the intelligent voice interactive electronic device to be tested, and sent to the sound source device, and the sound source device plays the test audio of the corresponding volume. It should be noted that the connection method between the control device and the sound source device can be a wired connection or a wireless connection, and the utility model does not impose any limitation on this.
[0057] Reference Figure 5 , Figure 5 FIG. 1 is a structural diagram of another sound source localization accuracy testing system disclosed in the utility model, such as Figure 5As shown, the control device can also be connected to the first bearing device, and the control device is also used to control the first bearing device to adjust the height. It should be noted that the connection between the control device and the first bearing device can be a wired connection or a wireless connection, and the utility model does not impose any limitation on this.
[0058] In actual applications, the intelligent voice interactive electronic device to be tested has a "head-up gaze" function. However, due to the small amplitude of the movement, it may not be easy for the tester to observe. Therefore, in the utility model, in order to solve this problem, a laser irradiation component and a laser reflection component can also be set in the sound source localization accuracy test system.
[0059] Reference Figure 6 , Figure 6 FIG. 1 is a structural diagram of another sound source localization accuracy testing system disclosed in the utility model, such as Figure 6 As shown, the system also includes a laser irradiation component 16 and a laser reflection component 17; wherein, the laser irradiation component 16 is fixed on the intelligent voice interaction electronic device 12 to be tested, and the laser irradiation component is used to emit laser, and the laser irradiation direction of the laser irradiation component is the same as the sound source positioning direction of the intelligent voice interaction electronic device to be tested; as an implementable embodiment, the laser irradiation component can be fixed at the zero-degree angle position of the audio collection component of the intelligent voice interaction electronic device to be tested.
[0060] The laser reflection component 17 is fixed to the front side of the sound source device 11. The laser reflection component is used to reflect laser light. The center of the laser reflection component corresponds to the center of the sound unit of the sound source device. The size of the laser reflection component is determined based on the preset sound source positioning accuracy test accuracy. The shape of the laser reflection component can be square, round, etc., and this application does not impose any restrictions on this. It should be noted that the fixing method of the laser reflection component on the sound source device should try to ensure that it does not affect the sound effect of the sound source device.
[0061] In the present invention, the laser irradiation component may be in a state of emitting laser all the time, or may emit laser after the intelligent voice interactive electronic device to be tested makes a sound source localization response. Specifically, the laser emission may be manually controlled or remotely controlled, and the present invention does not impose any limitation on this.
[0062] In this embodiment, the tester can determine whether the sound source positioning accuracy of the intelligent voice interactive electronic device to be tested in the vertical plane meets the error requirement by observing whether the laser emitted by the laser irradiation component irradiates the laser reflection component. If the laser emitted by the laser irradiation component irradiates the laser reflection component, it can be determined that the sound source positioning accuracy of the intelligent voice interactive electronic device to be tested in the vertical plane meets the error requirement; otherwise, it is determined that the sound source positioning accuracy of the intelligent voice interactive electronic device to be tested in the vertical plane does not meet the error requirement.
[0063] In some scenarios, the intelligent voice interactive electronic device to be tested does not have the function of "head-up gaze" but only has the function of "visual following". In this case, the tester cannot determine whether the sound source positioning accuracy of the intelligent voice interactive electronic device to be tested in the vertical plane meets the error requirements by observing whether the laser emitted by the laser irradiation component irradiates the laser reflection component. To solve this problem, the second bearing device can also be provided with a function of rotating around the central axis in the vertical plane, and the second bearing device is connected to the control device. The connection method between the control device and the second bearing device can be a wired connection or a wireless connection, and the utility model does not impose any limitation on this.
[0064] The control device is also used to control the second supporting device to rotate around the central axis on the vertical horizontal plane, so that the angle between the intelligent voice interaction electronic device to be tested and the horizontal plane reaches the actual visual adjustment angle on the vertical horizontal plane.
[0065] After the angle between the intelligent voice interactive electronic device to be tested and the horizontal plane reaches the actual visual adjustment angle in the vertical plane, it can be observed whether the laser emitted by the laser irradiation component irradiates the laser reflection component, and then determine whether the sound source positioning accuracy of the intelligent voice interactive electronic device to be tested in the vertical plane meets the error requirement. If the laser emitted by the laser irradiation component irradiates the laser reflection component, it can be determined that the sound source positioning accuracy of the intelligent voice interactive electronic device to be tested in the vertical plane meets the error requirement, otherwise, it is determined that the sound source positioning accuracy of the intelligent voice interactive electronic device to be tested in the vertical plane does not meet the error requirement.
[0066] It should be noted that after a test is completed, each device in the system can be reset for the convenience of the next test. Specifically, the control device is also used to control the second bearing device to rotate around the central axis on a vertical horizontal plane, so that the intelligent voice interactive electronic device to be tested is reset on a vertical horizontal plane. And, the control device is also used to control the second bearing device to rotate around the central axis on the horizontal plane based on the horizontal plane test angle and the actual visual adjustment angle on the horizontal plane, so that the intelligent voice interactive electronic device to be tested is reset on the horizontal plane.
[0067] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
[0068] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A sound source localization accuracy test system, characterized in that: The system comprises: A sound source device, an intelligent voice interactive electronic device to be tested, a first carrier device and a second carrier device; The first carrying device can adjust the height based on the test angle of the vertical horizontal plane, and the sound source device can be detachably fixed on the top; the second carrying device can rotate around the central axis on the horizontal plane based on the test angle of the horizontal plane, and the intelligent voice interaction electronic device to be tested can be detachably fixed on the top; The sound source device is used to play the test audio, and the intelligent voice interaction electronic device to be tested is used to perform sound source positioning response to the test audio.
2. The system according to claim 1, characterized in that The system also includes a control device; The control device is connected to the intelligent voice interaction electronic device to be tested, and is used to obtain the result of the sound source localization response of the intelligent voice interaction electronic device to be tested to the test audio, and determine the test result based on the result, wherein the result includes the actual visual adjustment angle in the horizontal plane and the actual visual adjustment angle in the vertical horizontal plane.
3. The system according to claim 2, characterized in that The system further comprises: A laser irradiation component and a laser reflection component; The laser irradiation component is fixed on the intelligent voice interactive electronic device to be tested, and the laser irradiation component is used to emit laser, and the laser irradiation direction of the laser irradiation component is the same as the sound source positioning direction of the intelligent voice interactive electronic device to be tested; The laser reflection component is fixed on the front side of the sound source device, and is used to reflect laser. The center of the laser reflection component corresponds to the center of the sound unit of the sound source device, and the size of the laser reflection component is determined based on a preset sound source positioning accuracy test accuracy.
4. The system according to claim 3, characterized in that The second carrying device can also rotate around the central axis on a vertical or horizontal plane; the control device is also connected to the second carrying device, The control device is also used to control the second supporting device to rotate around the central axis on a vertical horizontal plane so that the angle between the intelligent voice interaction electronic device to be tested and the horizontal plane reaches the actual visual adjustment angle on the vertical horizontal plane.
5. The system according to claim 4, characterized in that The control device is also used to control the second supporting device to rotate around the central axis on a vertical horizontal plane, so that the intelligent voice interaction electronic device to be tested is reset on the vertical horizontal plane.
6. The system according to claim 4, characterized in that The control device is also used to control the second supporting device to rotate around the central axis on the horizontal plane based on the horizontal plane test angle and the actual visual adjustment angle on the horizontal plane, so that the intelligent voice interaction electronic device to be tested is reset on the horizontal plane.
7. The system according to claim 1, characterized in that The first carrying device is a lifting table.
8. The system according to claim 1, characterized in that The second carrying device is a hemispherical turntable.
9. The system according to claim 2, characterized in that The control device is also connected to the sound source device, and the control device is used to control the sound source device to play the test audio.
10. The system according to claim 2, characterized in that The control device is also connected to the first carrying device, and is further used to control the first carrying device to adjust its height.