Sound source localization test method and device, equipment and storage medium
By generating and inputting multi-channel test sound data, the equipment to be tested is positioned for sound source, which solves the problem of high testing costs in the existing technology, and achieves more efficient and accurate sound source positioning testing.
Patent Information
- Application Number
- CN202311390251.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-10-24
- Publication Date
- 2025-04-25
AI Technical Summary
The existing sound source positioning testing methods require additional arrangement of test scenarios and sound sources, resulting in high testing costs.
By acquiring the number of microphones in the microphone array in the device to be tested, multi-channel test sound data are generated, and inputting them into each microphone of the microphone array respectively, so that the device to be tested can locate the sound source based on the received test sound data.
No additional arrangement of test scenes and sound sources is required, which reduces the cost of sound source positioning testing and improves the accuracy and efficiency of testing.
Smart Images
Figure CN119881799A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of sound source localization, and in particular to a test method, device, equipment, and storage medium for sound source localization. Background Art
[0002] Sound source localization is widely used in human-computer interaction, noise source identification, and emergency response. In the process of sound source localization, the position of an unknown sound source can be determined by a microphone array at a known position. For devices with sound source localization function, the sound source localization test can be used to evaluate its sound source localization capability.
[0003] At present, in the process of sound source localization test, multiple sound sources (for example, multiple speakers) can be pre-arranged at different positions of the device under test in the test scene, and the multiple sound sources can be manually controlled to play sounds. The device under test can locate the sound sources in different positions to realize the sound source localization test of the device under test.
[0004] However, during the above-mentioned sound source localization test, additional test scenes and sound sources need to be arranged, resulting in a high cost for the sound source localization test. Summary of the invention
[0005] The embodiments of the present disclosure provide a sound source localization test method, device, equipment, and storage medium, which can reduce the cost of sound source localization testing.
[0006] In a first aspect, an embodiment of the present disclosure provides a method for testing sound source localization, including:
[0007] Get the number of microphones in the microphone array of the device under test;
[0008] Generate multi-channel test sound data based on the number of microphones in the microphone array and the test case; wherein the number of channels of the test sound data is the same as the number of microphones in the microphone array;
[0009] The test sound of each channel in the test sound data is input into each microphone of the microphone array respectively, so that the device under test performs sound source localization based on the received test sound data and outputs the sound source localization result.
[0010] In a second aspect, an embodiment of the present disclosure provides a test device for sound source localization, comprising:
[0011] An information acquisition module, used to obtain the number of microphones in the microphone array of the device under test;
[0012] A sound generation module, used for generating multi-channel test sound data based on the number of microphones of the microphone array and the test case; wherein the number of channels of the test sound data is the same as the number of microphones of the microphone array;
[0013] The sound transmission module is used to input the test sound of each channel in the test sound data into each microphone of the microphone array, so that the device under test can locate the sound source based on the received test sound data and output the sound source localization result.
[0014] In a third aspect, an embodiment of the present disclosure provides a device including a processor and a memory storing program instructions, wherein the processor is configured to execute the test method for sound source localization of the first aspect when running the program instructions.
[0015] In a fourth aspect, an embodiment of the present disclosure provides a storage medium storing program instructions, wherein the program instructions, when run, execute the test method for sound source localization of the first aspect.
[0016] The test method, device, equipment, and storage medium for sound source localization provided by the embodiments of the present disclosure can achieve the following technical effects:
[0017] During the sound source localization test, multi-channel test sound data can be generated according to the number of microphone arrays in the device under test and the test cases. Moreover, in the multi-channel test sound data, the test sounds of each channel can be respectively input into the microphones of the microphone array, so that the device under test performs sound source localization based on the test sounds received by each microphone of the microphone array, and outputs the sound source localization result. Thus, the sound source localization test of the device under test is realized. In this way, during the sound source localization test, since the test sound data suitable for the device under test is generated based on the user's test case simulation, there is no need to arrange the test scene and sound source according to the test requirements during the sound source localization test. Thus, the cost of the sound source localization test can be reduced.
[0018] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:
[0020] Figure 1 This is a schematic diagram of the environment for traditional sound source localization testing;
[0021] Figure 2 is a schematic diagram of an environment applicable to a sound source localization test method provided by an embodiment of the present disclosure;
[0022] Figure 3is a schematic diagram of a sound source localization testing method provided by an embodiment of the present disclosure;
[0023] Figure 4 is a schematic diagram of another sound source localization testing method provided by an embodiment of the present disclosure;
[0024] Figure 5 is a schematic diagram of a sound source localization testing device provided by an embodiment of the present disclosure;
[0025] Figure 6 It is a schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0026] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.
[0027] In the embodiments of the present disclosure, the terms "includes", "has", and any variations thereof are intended to cover non-exclusive inclusions.
[0028] Unless otherwise specified, the term "plurality" means two or more than two. The term "multi-channel" means two or more than two channels.
[0029] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.
[0030] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.
[0031] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.
[0032] Sound source localization is widely used in human-computer interaction, noise source identification, and emergency response. In the process of sound source localization, the position of an unknown sound source can be determined by a microphone array at a known position. For devices with sound source localization function, the sound source localization test can be used to evaluate its sound source localization capability.
[0033] In the traditional way, when performing a sound source localization test, multiple sound sources (for example, multiple speakers) can be pre-arranged at different positions of the device under test in the test scene, and multiple sound sources can be manually controlled to play sounds. The device under test can locate the sound sources in different positions to achieve the sound source localization test of the device under test. Figure 1 shown.
[0034] Combination Figure 1 As shown, a conventional sound source localization test environment may include a sound source localization device 10 and a plurality of preset sound sources, wherein the plurality of sound sources may include a sound source A, a sound source B and a sound source C. Wherein:
[0035] The sound source localization device 10 may be a device with a sound source localization function, and the sound source localization device 10 includes a sound source collection device 11, and the sound collection device 11 may be a microphone array. The sound collection device 11 is used to simultaneously receive test sounds played by multiple sound sources (sound source A, sound source B, and sound source C), and perform sound source localization based on the test sounds of the multiple sound sources, or to separately receive test sounds played by multiple sound sources (sound source A, sound source B, and sound source C), and perform sound source localization based on the test sounds of each sound source. Accordingly, the multiple sound sources may separately receive control instructions from the user, and play test sounds simultaneously or separately according to the control instructions.
[0036] However, in the process of conducting a sound source localization test based on a traditional sound source localization test environment, additional test scenes and sound sources need to be arranged in the traditional sound source localization test environment, resulting in a high cost for the sound source localization test.
[0037] In view of this, the embodiments of the present disclosure provide a sound source localization test method, apparatus, device, and storage medium, which can reduce the cost of the sound source localization test.
[0038] Combination Figure 2 As shown, the embodiment of the present disclosure provides an environment applicable to a test method for sound source localization, the environment comprising an electronic device 21, a device to be tested 22 and a speech synthesis device 23.
[0039] In the disclosed embodiment, the electronic device 21 may be a server, a mobile terminal or a PC (Personal Computer). The electronic device 21 may determine the parameter information required to generate the test sound source data according to the user's test case, and input the parameter information into the speech synthesis device 23, so that the speech synthesis device 23 generates the test sound data according to the parameter information, and transmits the test sound data to the electronic device 21. The electronic device 21 may also input the test sound data into the microphone array 24 of the device under test 22, so that the device under test 22 performs sound source localization according to the test sound data received by the microphone array 24, and outputs the sound source localization result. The electronic device 21 may also obtain the sound source localization result from the device under test 22, and evaluate the sound source localization capability of the device under test 22 based on the sound source localization result.
[0040] A test case refers to a description of a test task for a specific product, reflecting the test plan, method, technology and strategy. The content of the test case includes test objectives, test scenarios, input data, test steps, expected results, test scripts, etc. In the embodiment of the present disclosure, the electronic device 21 can determine the parameter information required to generate the test sound source data based on the test case. It should be noted that the test case is used to reflect the user's test requirements and test conditions for the device under test 22. Among them, the test requirements include the position information of the test point during the sound source positioning test, and the test point corresponds to the sound source arranged in the real test scene, that is, the position information of the test point corresponds to the position information of the sound source in the real test scene. The test point can be one or more, which can be set according to the test requirements in the test case, and the embodiment of the present disclosure is not limited. The test conditions include the scene information in the real test scene. For example, when the test scene is a conference room, the scene information can be the space information of the conference room and the material information of the wall of the conference room. The test conditions also include the preset sound content corresponding to the test sound data, and the preset sound content can be text content, or it can be the sound recorded by the user from the application scene of the device under test.
[0041] In the embodiment of the present disclosure, the device under test 22 has a sound source localization function. The device under test 22 can obtain the location of the sound source through a sound source localization algorithm based on the test sound received by each microphone in the microphone array 24. Specifically, the device under test 22 can perform a sound source localization calculation based on the phase difference of the test sound received by each microphone in the microphone array 24 to obtain the location of the sound source.
[0042] In the disclosed embodiment, the speech synthesis device 23 may be a hardware device with speech synthesis function, or a software device integrated with a speech synthesis model. The speech synthesis device 23 may be installed in the device under test 22. The installation relationship described here is not limited to being placed inside the device under test 22, but also includes the installation connection with the components of the device under test, including but not limited to physical connection, electrical connection or signal transmission connection, etc. It can be understood by those skilled in the art that the speech synthesis device 23 may also be adapted to the electronic device 21, thereby realizing a feasible embodiment.
[0043] In the embodiment of the present disclosure, the speech synthesis model may be a neural network model. During the speech synthesis model training process, the user may use the sounds collected from the application scenario of the device under test 22 as sample data, and use the sample data to train the speech synthesis model. In this way, since the sample data used to train the speech synthesis model is collected from the application scenario of the device under test 22, the test sound data synthesized by the speech synthesis model during the sound source localization test has a higher matching degree with the test scenario.
[0044] Combination Figure 3 As shown, the embodiment of the present disclosure provides a method for testing sound source localization, and the execution subject of the method can be Figure 2 The electronic device of the present invention comprises:
[0045] S31, obtaining the number of microphones in the microphone array of the device under test.
[0046] S32, based on the number of microphones in the microphone array and the test case, generate multi-channel test sound data, wherein the number of channels of the test sound data is the same as the number of microphones in the microphone array.
[0047] S33, inputting the test sound of each channel in the test sound data into each microphone of the microphone array respectively, so that the device under test performs sound source localization based on the received test sound data, and outputs the sound source localization result.
[0048] By adopting the test method for sound source localization provided by the embodiment of the present disclosure, multi-channel test sound data can be generated according to the number of microphone arrays in the device under test and the test cases during the sound source localization test. Moreover, in the multi-channel test sound data, the test sounds of each channel can be respectively input into the microphones of the microphone array, so that the device under test performs sound source localization based on the test sounds received by each microphone of the microphone array, and outputs the sound source localization result. Thus, the sound source localization test of the device under test is implemented. In this way, in the process of performing the sound source localization test, since the test sound data applicable to the device under test is generated based on the user's test case simulation, then in the process of performing the sound source localization test, there is no need to arrange the test scene and sound source additionally according to the test requirements. Thus, the cost of the sound source localization test can be reduced.
[0049] In addition, since the traditional sound source localization test method relies on manually controlling the sound source to play the sound for testing, it is easy to cause manual misoperation, which affects the reliability of the sound source localization test, that is, affects the accuracy of the sound source localization test. In the sound source localization test method provided by the embodiment of the present disclosure, since the test sound data is simulated and generated according to the test case during the sound source localization test, compared with the traditional sound source localization test method, the impact of the test sound data on the sound source localization result can be reduced. Thereby, the accuracy of the sound source localization test is improved. Furthermore, in the sound source localization test method provided by the embodiment of the present disclosure, the test sound data can be automatically simulated and generated and input into the device to be tested. Compared with the process of manually controlling the sound source to play the sound in the traditional sound source localization test method, the efficiency of the sound source localization test can also be improved.
[0050] In the disclosed embodiment, in order to ensure that the generated test data can adapt to the device under test, in the process of generating the test sound data, it is necessary to refer to the number of microphones in the microphone array of the device under test. Specifically, multi-channel test sound data can be generated based on the number of microphones in the microphone array and the test case, and the number of channels of the test sound data is the same as the number of microphones in the microphone array. In this way, it can be ensured that the test sounds of each channel in the test sound data can be input into each microphone of the microphone array respectively, so that the test sound data corresponds to the device under test and the availability of the test sound data is improved.
[0051] In the disclosed embodiment, in order to further ensure the reliability of the sound source localization test, the generated test data needs to be as consistent as possible with the sound collected in the real test environment. For example, when collecting sound in the real test environment, it is possible to collect noise in the real test environment, and the sound collected in the real test environment may also have reverberation. In view of this, when the preset sound content in the test case is a sound pre-recorded by the user from the real test environment, the preset sound content itself already includes the noise and reverberation in the real test environment. In this way, there is no need to consider the noise and reverberation in the real environment during the generation of test sound data. Optionally, the process of generating test sound data can be as follows: according to the test case, determine the positional relationship information between the device to be tested and the point to be tested. Based on the number of microphones of the microphone array, the preset sound content in the test case, and the positional relationship information between the device to be tested and the point to be tested, generate multi-channel test sound data. Specifically, the number of microphones of the microphone array, the preset sound content in the test case, and the positional relationship information between the device to be tested and the point to be tested can be input into the speech synthesis model so that the speech synthesis model generates multi-channel test sound data.
[0052] Optionally, since the test case records the location information of the device to be tested and the point to be tested, the location information of the device to be tested and the point to be tested can be determined according to the location information of the device to be tested and the point to be tested in the test case.
[0053] Exemplarily, a three-dimensional coordinate system can be constructed for the test scene in the test case, and the position information of the device to be tested and the point to be tested in the test case can be represented by different coordinates. For example, when the coordinates of the device to be tested are (1, 1, 0) and the coordinates of the point to be tested are (1, 2, 0), the point to be tested is located in front of the device to be tested. For another example, when the coordinates of the device to be tested are (1, 1, 0) and the coordinates of the point to be tested are (2, 2, 0), the point to be tested is located in front of the right side of the device to be tested.
[0054] In this implementation, in the process of generating test sound data, the test requirements of the device under test in the test case need to be considered, that is, the positional relationship information between the device under test and the point under test needs to be considered. Exemplarily, if it is necessary to test the ability of the device under test to locate the sound source in front of it, the phase difference between the test sounds of each channel in the test sound data needs to correspond to the test conditions in front of the device under test. If it is necessary to test the ability of the device under test to locate the sound source behind it, the phase difference between the test sounds of each channel in the test sound data needs to correspond to the test conditions in front of the device under test. Moreover, when the device under test is tested in different directions, the generated test sound data is also different. In this way, in the process of generating test sound data, test sound data corresponding to the test requirements can be generated according to the positional relationship between the device under test and the point under test to test the ability of the device under test to locate the sound sources in different directions.
[0055] When the preset sound content in the test case is text content preset by the user, the noise and reverberation in the real environment need to be considered in the process of generating the test sound data. Optionally, the process of generating the test sound data can be as follows: according to the test case, determine the positional relationship information between the device to be tested and the point to be tested, and determine the noise data and reverberation time. Based on the number of microphones in the microphone array, the preset sound content in the test case, the positional relationship information between the device to be tested and the point to be tested, as well as the noise data and the reverberation time, generate multi-channel test sound data. Specifically, the number of microphones in the microphone array, the preset sound content in the test case, the positional relationship information between the device to be tested and the point to be tested, as well as the noise data and the reverberation time can be input into the speech synthesis model so that the speech synthesis model generates multi-channel test sound data.
[0056] Since the noise generated in the actual test scene is related to the scene information of the test scene, optionally, the process of determining the noise data may be as follows: determining the noise data according to the test scene information preset in the test case. Exemplarily, in the case where the actual test scene is a conference room, the air conditioner and / or fan in the conference room may generate noise, the preset test scene information may include the air conditioner and / or fan, and the noise data of the air conditioner and / or fan may be calculated.
[0057] Since sound reverberation may also be generated in the actual test scene, the reverberation time is also related to the scene information of the test scene (for example, when the test scene is a conference room, the space size and wall material of the test scene). Optionally, the process of determining the reverberation time can be as follows: determine the reverberation time according to the test scene information preset in the test case. Exemplarily, when the actual test scene is a conference room, the space size and wall material of the conference room will affect the reverberation time, and the reverberation time can be obtained by calculation.
[0058] Optionally, after the device under test outputs the sound source localization result, the electronic device can also evaluate the sound source localization capability of the device under test based on the sound source localization result. Specifically, the electronic device can obtain the sound source localization result of the device under test. The sound source location information in the sound source localization result is compared with the location information of the test point in the test case. According to the comparison result, the sound source localization capability of the device under test is determined.
[0059] In this implementation, the sound source location information located by the device under test is recorded in the sound source localization result. By comparing the sound source localization information and the location information of the point under test, the deviation between the sound source location and the point under test can be determined. In the case where the deviation between the sound source location and the point under test is large, it means that the positioning ability of the device under test is poor. In the case where the deviation between the sound source location and the point under test is small or the locations are close, it means that the positioning ability of the device under test is good. In this way, the sound source localization ability of the device under test does not need to be manually evaluated, but is automatically evaluated by the electronic device, which can improve the efficiency of evaluating the sound source localization ability of the device under test.
[0060] Combination Figure 4 As shown, the embodiment of the present disclosure also provides another test method for sound source localization, and the execution subject of the method can be Figure 2 The electronic device of the present invention comprises:
[0061] S41, obtaining the number of microphones in the microphone array of the device under test.
[0062] S42, based on the number of microphones in the microphone array and the test case, generate multi-channel test sound data, wherein the number of channels of the test sound data is the same as the number of microphones in the microphone array.
[0063] S43, determining adjustment parameters of the test sound of each channel in the test sound data according to the preset test conditions;
[0064] S44, inputting the adjustment parameters of the test sounds of each channel into the speech synthesis model, so that the speech synthesis model adjusts the test sounds of each channel according to the corresponding adjustment parameters;
[0065] S45, inputting the adjusted test sound of each channel into each microphone of the microphone array respectively, so that the device under test performs sound source localization based on the received test sound data, and outputs the sound source localization result.
[0066] During the sound source localization test, the user may need to temporarily change the test requirements. Since the test case is usually predetermined before the test, it is easy to cause the multi-channel test sound data generated based on the test case and the device under test to fail to meet the user's temporarily changed test requirements. For example, the user may think that the test sound data is too loud or too soft.
[0067] The test method for sound source localization provided by the embodiment of the present disclosure can obtain the test conditions temporarily changed by the user after generating multi-channel test sound data. According to the test conditions, the test sound of each channel in the test sound data can be adjusted. For example, the frequency and / or intensity of the test sound of each channel can be adjusted. Then, the adjusted test sound of each channel is input into each microphone of the microphone array of the device to be tested. Thus, the device to be tested can be tested based on the temporarily changed test conditions, which improves the flexibility of the sound source localization test.
[0068] Combination Figure 5 As shown, the embodiment of the present disclosure provides a test device for sound source localization, which can be integrated into Figure 2 The electronic device comprises an information acquisition module 501, a sound generation module 502 and a sound transmission module 503.
[0069] The information acquisition module 501 is used to obtain the number of microphones in the microphone array of the device under test.
[0070] The sound generation module 502 is used to generate multi-channel test sound data based on the number of microphones in the microphone array and the test case; wherein the number of channels of the test sound data is the same as the number of microphones in the microphone array.
[0071] The sound transmission module 503 is used to input the test sound of each channel in the test sound data into each microphone of the microphone array, so that the device under test performs sound source localization based on the received test sound data and outputs the sound source localization result.
[0072] Optionally, the sound generation module 502 is further used to determine the positional relationship information between the device under test and the test point according to the test case, and to generate multi-channel test sound data based on the number of microphones in the microphone array, the preset sound content in the test case, and the positional relationship information between the device under test and the test point.
[0073] Optionally, the sound generation module 502 is specifically used to input the number of microphones in the microphone array, the preset sound content in the test case, and the positional relationship information between the device to be tested and the test point into the speech synthesis model, so that the speech synthesis model generates multi-channel test sound data.
[0074] Optionally, the sound generation module 502 is further used to determine the positional relationship information between the device to be tested and the point to be tested, as well as the noise data and the reverberation time according to the test case. Based on the number of microphones in the microphone array, the preset sound content in the test case, the positional relationship information between the device to be tested and the point to be tested, as well as the noise data and the reverberation time, multi-channel test sound data is generated.
[0075] Optionally, the sound generation module 502 is specifically used to input the number of microphones in the microphone array, the preset sound content in the test case, the positional relationship information between the device to be tested and the test point, as well as the noise data and the reverberation time into the speech synthesis model, so that the speech synthesis model generates multi-channel test sound data.
[0076] Optionally, the sound source localization test device provided by the embodiment of the present disclosure also includes a sound adjustment module 504, which is used to determine the adjustment parameters of the test sound of each channel in the test sound data according to preset test conditions. The adjustment parameters of the test sound of each channel are input into the speech synthesis model so that the speech synthesis model adjusts the test sound of each channel according to the corresponding adjustment parameters. Correspondingly, the sound transmission module 503 is also used to input the adjusted test sound of each channel into each microphone of the microphone array, so that the device under test performs sound source localization based on the received test sound data and outputs the sound source localization result.
[0077] Optionally, the sound source localization test device provided in the embodiment of the present disclosure further includes a localization evaluation module 505, which is used to obtain the sound source localization result of the device under test. The sound source location information in the sound source localization result is compared with the location information of the test point in the test case. According to the comparison result, the sound source localization capability of the device under test is determined.
[0078] The test device for sound source localization provided in the embodiment of the present disclosure can execute the actions of the electronic device in the above embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.
[0079] Combination Figure 6 As shown, the electronic device 21 provided in the embodiment of the present disclosure includes a processor 100 and a memory 101. Optionally, the device may also include a communication interface 102 and a bus 103. The processor 100, the communication interface 102, and the memory 101 may communicate with each other through the bus 103. The communication interface 102 may be used for information transmission. The processor 100 may call the logic instructions in the memory 101 to execute the test method for sound source localization of the above embodiment.
[0080] In addition, the logic instructions in the memory 101 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.
[0081] The memory 101 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 100 executes the functional application and data processing by running the program instructions / modules stored in the memory 101, that is, the test method for sound source localization in the above embodiment is implemented.
[0082] The memory 101 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 101 may include a high-speed random access memory and may also include a non-volatile memory.
[0083] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned test method for sound source localization.
[0084] The above-mentioned storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.
[0085] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes, or a transient storage medium.
[0086] The above description and accompanying drawings fully illustrate the embodiments of the present disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible variations. Unless explicitly required, separate components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments.
[0087] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.
[0088] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.
Claims
1. A method for testing sound source localization, characterized in that: include: Get the number of microphones in the microphone array of the device under test; Generate multi-channel test sound data based on the number of microphones in the microphone array and the test case; wherein the number of channels of the test sound data is the same as the number of microphones in the microphone array; The test sound of each channel in the test sound data is respectively input into each microphone of the microphone array, so that the device under test performs sound source localization based on the received test sound data and outputs a sound source localization result.
2. The method according to claim 1, characterized in that Based on the number of microphones in the microphone array and the test case, multi-channel test sound data is generated, including: According to the test case, determining the position relationship information between the device to be tested and the point to be tested; The multi-channel test sound data is generated based on the number of microphones in the microphone array, the preset sound content in the test case, and the positional relationship information between the device to be tested and the test point.
3. The method according to claim 2, characterized in that The method further comprises: generating the multi-channel test sound data based on the number of microphones in the microphone array, the preset sound content in the test case, and the positional relationship information between the device to be tested and the test point, including: The number of microphones in the microphone array, the preset sound content in the test case, and the positional relationship information between the device to be tested and the test point are input into the speech synthesis model so that the speech synthesis model generates the multi-channel test sound data.
4. The method according to claim 1, characterized in that Based on the number of microphones in the microphone array and the test case, multi-channel test sound data is generated, including: According to the test case, determining the positional relationship information between the device to be tested and the point to be tested, and determining the noise data and the reverberation time; The multi-channel test sound data is generated based on the number of microphones in the microphone array, the preset sound content in the test case, the positional relationship information between the device to be tested and the test point, and the noise data and the reverberation time.
5. The method according to claim 4, characterized in that Based on the number of microphones in the microphone array, the preset sound content in the test case, the positional relationship information between the device to be tested and the point to be tested, and the noise data and the reverberation time, the multi-channel test sound data is generated, including: The number of microphones in the microphone array, the preset sound content in the test case, the positional relationship information between the device to be tested and the test point, as well as the noise data and the reverberation time are input into the speech synthesis model so that the speech synthesis model generates the multi-channel test sound data.
6. The method according to any one of claims 1 to 5, characterized in that: After generating the multi-channel test sound data, the method further includes: Determining adjustment parameters of the test sound of each channel in the test sound data according to preset test conditions; Inputting the adjustment parameters of the test sounds of each channel into the speech synthesis model, so that the speech synthesis model adjusts the test sounds of each channel according to the corresponding adjustment parameters; The adjusted test sounds of each channel are respectively input into each microphone of the microphone array, so that the device under test performs sound source localization based on the received test sound data and outputs the sound source localization result.
7. The method according to any one of claims 1 to 5, characterized in that: After the device under test outputs the sound source localization result, the method further includes: Obtaining a sound source localization result of the device under test; Comparing the sound source location information in the sound source localization result with the location information of the point to be tested in the test case; According to the comparison result, the sound source localization capability of the device to be tested is determined.
8. A sound source localization test device, characterized in that: include: An information acquisition module, used to obtain the number of microphones in the microphone array of the device under test; A sound generation module, used for generating multi-channel test sound data based on the number of microphones of the microphone array and the test case; wherein the number of channels of the test sound data is the same as the number of microphones of the microphone array; The sound transmission module is used to input the test sound of each channel in the test sound data into each microphone of the microphone array, so that the device under test can perform sound source localization based on the received test sound data and output the sound source localization result.
9. An electronic device, characterized in that: The method comprises a processor and a memory storing program instructions, wherein the processor is configured to execute the sound source localization test method according to any one of claims 1 to 7 when running the program instructions.
10. A storage medium storing program instructions, characterized in that: When the program instructions are executed, the test method for sound source localization according to any one of claims 1 to 7 is executed.