Vehicle audio test method and device, electronic equipment and storage medium

By calculating the correlation between the audio data of the car computer voice and the original audio data, the target segments are extracted and matched, the problems of slow speed and low accuracy of the existing car computer voice test are solved, and the rapid and high accuracy of the test results are achieved .

CN119012107APending Publication Date: 2024-11-22BEI DOU ZHI LIAN KE JI YOU XIAN GONG SI +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411075397.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The existing vehicle phone voice testing methods are slow and have low accuracy, which cannot meet the fast and high accuracy testing needs.

Method used

The acquisition device obtains the external amplifier test audio data of the vehicle terminal, calculates the correlation with the original audio data, extracts the maximum correlation segment as the target segment, and calculates its matching value with the original audio data to obtain the test results and filters out the Interfere with audio and improve test accuracy.

Benefits of technology

Fast and automatic voice testing of the car and machine are realized, which significantly improves the testing efficiency and accuracy and reduces labor costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119012107A_ABST
    Figure CN119012107A_ABST
Patent Text Reader

Abstract

The invention provides an in-vehicle audio test method and device, electronic equipment and a storage medium, and belongs to the technical field of tests.The method comprises the steps that test audio data of an external power amplifier of an in-vehicle terminal are acquired through acquisition equipment, and original audio data corresponding to the test audio data are called; calculating correlation between the test audio data and the original audio data to obtain a plurality of correlation values; according to the correlation value, extracting a target fragment from the test audio data; and calculating a matching value between the target fragment and the original audio data, and obtaining a test result of the test audio data according to the matching value. Thus, through the correlation value, the correlation between the target fragment and the original audio data is the maximum as far as possible, interference audio in the test audio data is filtered out, and then the matching value of the target fragment and the original audio data is calculated to obtain the test result, so that the test audio can be quickly and automatically analyzed, and the test result can be more accurately obtained.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of testing technology, and in particular to a vehicle audio testing method, device, electronic equipment and storage medium. Background Art

[0002] The car computer is an in-vehicle infotainment product installed in the car. It can realize information communication between people and cars, cars and the outside world (including cars and cars). With the development of automobile technology, the third-generation car computer integrates driving assistance system, 3D panoramic driving visual assistance system, new ChangUI2.0 information aggregation desktop and other functional systems to better meet the application needs of users in daily driving.

[0003] In actual applications, car computers usually use voice transmission and reception to achieve control, reminder and other functions. In order to ensure the normal use of the voice function of the car computer, the voice test of the car computer is particularly important. However, the current car computer voice test is usually performed by human ears, which has a slow test speed and low test accuracy. Therefore, a fast and high-accuracy car computer voice test method is urgently needed. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a vehicle audio testing method, device, electronic device and storage medium, so as to perform vehicle audio testing quickly and with high accuracy.

[0005] In a first aspect, the present invention provides a vehicle audio testing method, which is applied to an analysis device, wherein the analysis device is communicatively connected to a collection device, and the method comprises:

[0006] Acquire the test audio data of the external power amplifier at the vehicle terminal through the acquisition device, and retrieve the original audio data corresponding to the test audio data;

[0007] Calculating the correlation between the test audio data and the original audio data to obtain a correlation array; wherein the correlation array includes a plurality of correlation values;

[0008] extracting a segment from the test audio data as a target segment according to the correlation value;

[0009] A matching value between the target segment and the original audio data is calculated, and a test result of the test audio data is obtained according to the matching value.

[0010] Optionally, the step of calculating the correlation between the test audio data and the original audio data to obtain a correlation array includes:

[0011] Normalizing the test audio data and the original audio data respectively to obtain a first test audio and a first original audio;

[0012] removing the silent segment in the first test audio to obtain a second test audio;

[0013] Sliding the first original audio as a sliding window on the second test audio to obtain a plurality of overlapping windows of the sliding window on the second test audio;

[0014] The correlation values ​​between the sliding window and each of the overlapping windows are calculated respectively to obtain a correlation array composed of each of the correlation values.

[0015] Optionally, the step of respectively calculating the correlation values ​​between the sliding window and each overlapping window includes:

[0016] For each overlapping window, dot products are performed on the data in the sliding window and the data in the overlapping window one by one, and the obtained dot product values ​​are accumulated to obtain the correlation value between the sliding window and the overlapping window.

[0017] Optionally, the test audio data includes audio data at each test moment in the test period, and the audio data includes amplitude;

[0018] The step of removing the silent segment in the first test audio to obtain the second test audio includes:

[0019] For each of the test moments, extracting the test audio amplitude at the test moment from the test audio data, and calculating the test audio energy at the test moment according to the test audio amplitude;

[0020] When the energy of the test audio is less than the preset silence critical energy, the data corresponding to the test time in the first test audio is deleted.

[0021] Optionally, the step of extracting a segment from the test audio data as a target segment according to the correlation value includes:

[0022] Extracting the maximum correlation value from the correlation array as the target value;

[0023] Taking the overlapping window corresponding to the target value as a starting point, extracting a segment having the same length as the first original audio from the second test audio as a target segment.

[0024] Optionally, the step of calculating a matching value between the target segment and the original audio data includes:

[0025] Extracting multiple test audio amplitudes of the target segment from the test audio data, and performing norm calculation on the multiple test audio amplitudes to obtain the test audio energy of the target segment;

[0026] Extracting multiple original audio amplitudes of the first original audio from the original audio data, and performing norm calculation on the multiple original audio amplitudes to obtain original audio energy of the first original audio;

[0027] The correlation value of the target segment is normalized using the test audio energy and the original audio energy to obtain a matching value between the target segment and the original audio data.

[0028] Optionally, the sampling end of the acquisition device is connected to the output end of the audio converter, and the input end of the audio converter is connected to an external power amplifier at the vehicle end;

[0029] The step of acquiring the test audio data of the external power amplifier at the vehicle terminal through the acquisition device includes:

[0030] Receive test audio data transmitted by the acquisition device; wherein the test audio data is obtained by the acquisition device sampling the audio signal output by the audio converter, and the audio converter reduces the power of the audio signal of the external power amplifier and then outputs it.

[0031] In a second aspect, the present invention provides a vehicle audio test device, which is applied to an analysis device, wherein the analysis device is communicatively connected with a collection device, and the vehicle audio test device comprises a data acquisition module, a correlation analysis module, a target extraction module and a matching module;

[0032] The data acquisition module is used to acquire the test audio data of the external power amplifier at the vehicle terminal through the acquisition device, and retrieve the original audio data corresponding to the test audio data;

[0033] The correlation analysis module is used to calculate the correlation between the test audio data and the original audio data to obtain a correlation array; wherein the correlation array includes a plurality of correlation values;

[0034] The target extraction module is used to extract a segment from the test audio data as a target segment according to the correlation value;

[0035] The matching module is used to calculate the matching value between the target segment and the original audio data, and obtain the test result of the test audio data according to the matching value.

[0036] In a third aspect, the present invention provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the vehicle audio testing method as described in the first aspect.

[0037] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the vehicle audio testing method as described in the first aspect.

[0038] The vehicle audio test method, device, electronic device and storage medium provided by the embodiment of the present invention include: obtaining the test audio data of the external power amplifier of the vehicle terminal through the acquisition device, and retrieving the original audio data corresponding to the test audio data; calculating the correlation between the test audio data and the original audio data to obtain a correlation array composed of multiple correlation values; extracting a segment from the test audio data as the target segment according to the correlation value; calculating the matching value between the target segment and the original audio data, and obtaining the test result of the test audio data according to the matching value. In this way, firstly extract the target segment from the test audio data according to the correlation between the test audio data and the original audio data, so that the target segment has the maximum correlation with the original audio data as much as possible to filter out the interference audio in the test audio data, and then calculate the matching value between the target segment and the original audio data to obtain the test result, so that the test audio can be analyzed quickly and automatically, and the test result can be obtained more accurately.

[0039] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 A block diagram of a vehicle audio testing system provided by an embodiment of the present invention is shown.

[0042] Figure 2 A block diagram of an electronic device provided by an embodiment of the present invention is shown.

[0043] Figure 3 The figure shows a flow chart of a vehicle audio testing method provided by an embodiment of the present invention.

[0044] Figure 4 Shows Figure 3 Schematic diagram of the process flow of some sub-steps of step 13.

[0045] Figure 5 Shows Figure 4 A flowchart of some sub-steps of step 133 in FIG.

[0046] Figure 6 Shows Figure 3 Schematic diagram of the process of some sub-steps of step 15.

[0047] Figure 7 Shows Figure 3 Schematic diagram of the process of some sub-steps of step 17.

[0048] Figure 8 The schematic diagram shows the structure of a vehicle audio testing device provided by an embodiment of the present invention.

[0049] Explanation of the accompanying drawings: 10-vehicle audio test system; 110-vehicle terminal; 120-external amplifier; 130-acquisition equipment; 140-analysis equipment; 150-audio converter; 20-electronic equipment; 210-memory; 220-processor; 230-communication module; 30-vehicle audio test device; 310-data acquisition module; 320-correlation analysis module; 330-target extraction module; 340-matching module. DETAILED DESCRIPTION

[0050] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0051] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0052] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0053] The vehicle audio testing method provided by the embodiment of the present invention can be applied to Figure 1 In the vehicle audio test system 10 shown, the vehicle audio test system 10 includes a vehicle terminal 110, an external power amplifier 120, a collection device 130 and an analysis device 140. The external power amplifier 120 is connected to the vehicle terminal 110, and the analysis device 140 can be communicated with the analysis device 140 through wired, wireless or other connection methods.

[0054] An audio library is pre-deployed in the analysis device 140 , and the audio library stores original audio data corresponding to various functions of the vehicle terminal 110 .

[0055] The external amplifier 120 is used to play the voice information output by the vehicle terminal 110. The voice information can be the voice information output by the vehicle terminal 110 controlled by the tester, or the voice information specified by the test instruction output by the vehicle terminal 110 to the external amplifier 120 after the analysis device 140 issues the test instruction.

[0056] The acquisition device 130 is used to acquire the voice information played by the external power amplifier 120 , obtain test audio data, and send the test audio data to the analysis device 140 .

[0057] The analysis device 140 is used to implement the vehicle audio testing method provided by the embodiment of the present invention.

[0058] The external amplifier 120 may be, but is not limited to, a speaker, a loudspeaker, a stereo, etc. The analysis device 140 may be, but is not limited to, a personal computer, a notebook computer, an independent server, a server cluster, a tablet computer, etc. The acquisition device 130 may be a sound sensor, a sound acquisition card, etc.

[0059] In order to reduce noise in the test audio data, the vehicle audio test system 10 may further include an audio converter 150 , the input end of the audio converter 150 is connected to the external power amplifier 120 of the vehicle end 110 , and the sampling end of the acquisition device 130 is connected to the output end of the audio converter 150 .

[0060] The audio converter 150 is used to reduce the power of the audio signal output by the external power amplifier 120. For example, the voltage of the audio signal can be converted from high frequency to low frequency. The acquisition device 130 can be an audio acquisition card, which is used to convert the audio signal output by the audio converter 150 into a digital signal to obtain test audio data.

[0061] Compared with the traditional method of collecting sound or audio through a microphone or other sound sensor that does not require a wired connection, the above-mentioned collection device 130 and the audio converter 150 are directly wired to the external power amplifier 120 of the vehicle end 110 to directly collect the voltage and current of the audio signal output by the external power amplifier 120 as test audio data, which greatly reduces the interference of external noise, reduces the noise of the test audio data, and increases the amount of effective data.

[0062] In addition, the volume and power of the audio signal output by the external power amplifier 120 of the vehicle terminal 110 are amplified, and the corresponding voltage and current are relatively large, which easily exceeds the voltage and current range of the audio capture card, causing the audio capture card to burn out. Therefore, the power (i.e., volume) of the audio signal output by the external power amplifier 120 is reduced by the audio converter 150 to control the voltage and current of the audio signal output by the audio converter 150 within the range of the audio capture card, so that the audio capture card can normally capture audio and reduce the probability of damage to the audio capture card.

[0063] Please refer to Figure 2 , is a block diagram of an electronic device 20, which may be Figure 2 The analysis device 140 in the vehicle audio test system 10 is shown. The electronic device 20 includes a memory 210, a processor 220 and a communication module 230. The memory 210, the processor 220 and the communication module 230 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0064] The memory 210 is used to store programs or data. The memory 210 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0065] The processor 220 is used to read / write data or programs stored in the memory 210 and execute corresponding functions. For example, Figure 2The processor 220 of the analysis device 140 in the vehicle audio test system 10 shown executes the computer program stored in the memory 210 to implement the vehicle audio test method provided by the embodiment of the present invention.

[0066] The communication module 230 is used to establish a communication connection between the electronic device 20 and other communication terminals through the network, and to send and receive data through the network. Figure 2 The analysis device 140 in the vehicle audio test system 10 shown can receive the test audio signal collected by the collection device 130 through the communication module 230 .

[0067] It should be understood that Figure 2 The structure shown is only a schematic diagram of the structure of the electronic device 20. The electronic device 20 may also include Figure 2 More or fewer components as shown, or with Figure 2 Different configurations shown. Figure 2 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0068] Please refer to Figure 3 , an embodiment of the present invention provides a vehicle audio testing method, comprising the following steps 11 to 17. In this embodiment, Figure 1 The analysis device 140 may Figure 2 According to the structure shown in , the above steps 11 to 17 are executed to implement the vehicle audio testing method.

[0069] Step 11, obtaining the test audio data of the external power amplifier on the vehicle side through the acquisition device, and retrieving the original audio data corresponding to the test audio data.

[0070] Step 13, calculating the correlation between the test audio data and the original audio data to obtain a correlation array.

[0071] The correlation array includes multiple correlation values.

[0072] Step 15: extract a segment from the test audio data according to the correlation value as the target segment.

[0073] Step 17, calculating the matching value between the target segment and the original audio data, and obtaining the test result of the test audio data according to the matching value.

[0074] For example, in combination Figure 1In the vehicle audio test system 10 shown, when the audio function of the vehicle terminal 110 (such as whether it can make a sound) needs to be tested, the tester first determines the original audio data to be tested, and sends an audio test instruction to the vehicle terminal 110 by manual input or control of the analysis device 140. The vehicle terminal 110 outputs an audio signal to the external power amplifier 120 according to the original audio information specified by the audio test instruction, and the external power amplifier 120 makes a sound. At this time, the acquisition device 130 takes the sound emitted by the external power amplifier 120 to obtain the test audio data, and sends the test audio data to the analysis device 140.

[0075] The analysis device 140 records the test audio data transmitted by the acquisition device 130 through the pyaudio.PyAudio() function of the python third-party library. After the recording is completed, the collected test audio data is stored in a wav file to obtain complete test audio data, and the original audio data of the test audio data is retrieved, that is, the original audio data specified by the audio test instruction received by the vehicle terminal 110. The analysis device 140 calculates the correlation between the test audio data and the original audio data to obtain a correlation array including multiple correlation values. According to the correlation value, the analysis device 140 extracts a segment from the test audio data as the target segment, and the target segment is the segment in the test audio data with the greatest correlation with the original audio data. Furthermore, the analysis device 140 calculates the matching value between the target segment and the original audio data, and obtains the test result of the test audio data according to the matching value.

[0076] The test result may be correct or incorrect, or true or false, which is not limited in this embodiment.

[0077] Compared with the traditional audio testing method, the above-mentioned vehicle audio testing method, through steps 11 to 17, first extracts the target segment from the test audio data according to the correlation between the test audio data and the original audio data, so that the target segment has the maximum correlation with the original audio data as much as possible to filter out the interference audio in the test audio data, and then calculates the matching value of the target segment and the original audio data to obtain the test result, thereby not only being able to quickly and automatically analyze the test audio, but also being able to obtain the test result more accurately.

[0078] In step 11, a collection device 130 such as a microphone, a receiver, or a sound sensor that does not need to be wired to the external power amplifier 120 can be used to collect the test audio data of the external power amplifier 120 of the vehicle terminal 110, or a wired connection can be used to collect the test audio data of the external power amplifier 120 of the vehicle terminal 110. The above method is only an example and is not limited in this embodiment.

[0079] In order to reduce the noise in the collected test audio data and increase the amount of effective data, the idea of ​​collecting the audio signal of the external power amplifier 120 of the vehicle terminal 110 by wired connection is introduced in step 11 of this embodiment. Figure 1 The sampling end of the acquisition device 130 (which may be an audio acquisition card) is connected to the output end of the audio converter 150, and the input end of the audio converter 150 is connected to the external power amplifier 120 of the vehicle terminal 110. The audio acquisition card may be connected to the analysis device 140 via a USB interface.

[0080] On this basis, in step 11, the audio converter 150 reduces the power of the audio signal played by the external power amplifier 120, and the audio signal after power reduction is output from the output end of the audio converter 150. The acquisition device 130 samples the audio signal output by the audio converter 150 to obtain test audio data, and the analysis device 140 receives the test audio data transmitted by the acquisition device 130.

[0081] The test audio data collected by the audio capture card is transmitted to the analysis device 140 through the USB interface. The analysis device 140 records the received test audio data through the pyaudio.PyAudio() function of the python third-party library. After the recording is completed, the recorded complete test audio data is stored in a wav file.

[0082] A wired sampling circuit is formed between the acquisition device 130, the audio converter 150 and the external power amplifier 120 of the vehicle terminal 110, so that the acquisition device 130 directly acquires the voltage and current of the audio signal output by the external power amplifier 120 as the test volume data, which greatly reduces the interference of external noise, reduces the noise of the test audio data, and increases the amount of effective data. At the same time, the power (i.e., volume) of the audio signal output by the external power amplifier 120 is reduced by the audio converter 150 to control the voltage and current of the audio signal output by the audio converter 150 within the range of the audio acquisition card, so that the audio acquisition card can normally acquire audio and reduce the probability of damage to the audio acquisition card.

[0083] Furthermore, in step 13, the correlation between the test audio data and the original audio data can be calculated in a variety of ways. For example, after the audio features of the test audio data and the original audio data are obtained respectively, the similarity between the audio features can be used as the correlation, or the correlation can be calculated using a correlation measurement algorithm (such as a cross-correlation algorithm, etc.). The above methods are only examples, and the implementation methods are not limited in this embodiment.

[0084] In order to enable the obtained correlation array to describe the correlation between each segment of the test audio data and the original test audio, the concept of first normalizing and then using the logic of the cross-correlation function to calculate the correlation is introduced in the process of calculating the correlation in step 13. Figure 4 , step 13 may include steps 131 to 137.

[0085] Step 131 , normalize the test audio data and the original audio data respectively to obtain a first test audio and a first original audio.

[0086] The normalization method can be flexibly selected, for example, it can be Z-score normalization, S regularization, stability normalization, etc., and the above normalization method is only an example, and its specific implementation method is not limited.

[0087] By normalizing the test audio data and the original audio data respectively, the test audio data and the original audio data are converted into data under the same dimension, that is, the first test audio and the first original audio, so as to facilitate the subsequent calculation of the correlation value.

[0088] Step 133: remove the silent segment in the first test audio to obtain the second test audio.

[0089] It should be noted that the test audio data includes the audio data of each test moment in the test period, and the audio data of each test moment is essentially a voltage value or a current value, so the audio data includes an amplitude (i.e., the amplitude of the voltage or current). On this basis, the method of identifying and removing silent segments can be flexibly set. For example, silent segments can be identified according to preset rules, or silent segments can be identified using a pre-trained neural network model, which is not limited in this embodiment.

[0090] To quickly and accurately remove the silence segments in the first test audio, refer to Figure 5 , step 133 may include step 1331 to step 1332.

[0091] Step 1331: for each test moment, extract the test audio amplitude at the test moment from the test audio data, and calculate the test audio energy at the test moment according to the test audio amplitude.

[0092] The method for calculating the energy of the test audio can be flexibly set. For example, the energy can be calculated using a norm, or it can be calculated according to a preset rule, which is not limited in this embodiment.

[0093] When the norm is used to calculate the test audio energy, the test audio energy at each test moment is equal to the square value of the test audio amplitude at that test moment, that is, E i =x i2 , where x i represents the test audio amplitude at the i-th test moment, E i represents the test audio energy at the i-th test moment.

[0094] Step 1332: When the test audio energy is less than the preset silence critical energy, the data corresponding to the test time in the first test audio is deleted.

[0095] The silent critical energy may be a value obtained by fitting historical experience data, or a value obtained by fitting calibration experimental data, and the specific implementation method is not limited.

[0096] For example, after loading multiple audio files with sound, each audio file is a one-dimensional array. According to the specified block size, the audio file is divided into multiple blocks of data. When the total length of the audio file data is 10 and the specified block size is 2, it is divided into 5 blocks of data. Using the norm, combined with the audio amplitude at each moment, the sum of the squares of the audio amplitude at each moment of the block data, or the value obtained by taking the square root of the sum of squares, is used as the audio energy of each block data. From the audio energy of each block data, the maximum and minimum values ​​are counted. At the same time, multiple audio files without sound are collected, and the maximum and minimum values ​​of the audio energy are counted in the same way. Then, the maximum and minimum values ​​of the audio energy without sound and the maximum and minimum values ​​of the audio energy with sound are compared, and the critical values ​​of the audio energy with sound and without sound are calculated as the critical silent energy.

[0097] Through the above steps 1331 to 1332, a second test audio with silence segments removed can be obtained, and the second test audio has been normalized.

[0098] Step 135: Slide the first original audio as a sliding window on the second test audio to obtain a plurality of overlapping windows of the sliding window on the second test audio.

[0099] It should be understood that the length of the sliding window is consistent with the length of the overlapping window. When the sliding window slides on the second test audio, there may be no duplication between adjacent overlapping windows, that is, there is no repeated data segment between the previous overlapping window and the next overlapping window. For example, if the length of the second test audio is 10s and the length of the sliding window is 2 seconds, the overlapping windows have a total of 5 lengths, and the length of each overlapping window is 2 seconds.

[0100] In order to avoid the effective data being cut, which results in the subsequent calculated correlation value being insufficient to describe the correlation between the original audio and the test audio, there may be repetitions between adjacent overlapping windows, that is, there are repeated data segments between the previous overlapping window and the next overlapping window. The length of the repeated data segment can be flexibly set, for example, it can be 2 seconds or 1 second, and its specific value is not limited.

[0101] Taking the sliding window length of 2 seconds, the sliding window length of 10 seconds, and the repeated segment length of 1 second as an example, there are a total of 9 overlapping windows, and the 9 overlapping windows correspond to 1-2 seconds, 2-3 seconds, 3-4 seconds, 4-5 seconds, 5-6 seconds, 6-7 seconds, 7-8 seconds, 8-9 seconds, and 9-10 seconds of data of the second test audio respectively.

[0102] Step 137, respectively calculating the correlation values ​​between the sliding window and each overlapping window to obtain a correlation array composed of the correlation values.

[0103] In step 137, the correlation values ​​between the overlapping windows of the sliding window can be calculated in a variety of ways. For example, the Mel-frequency cepstral coefficients (i.e., MFCC features) of the sliding window can be extracted as sliding features, and the Mel-frequency cepstral coefficients of the overlapping window can be extracted as overlapping features. The correlation value between the sliding feature and the overlapping feature can be calculated by Euclidean distance or cosine similarity. Alternatively, for each overlapping window, the data in the sliding window can be dot-producted with the data in the overlapping window one by one, and the dot-product values ​​obtained can be accumulated to obtain the correlation value between the sliding window and the overlapping window, i.e. or f(τ) represents the sliding window, g i (t) represents the overlapping window, C i represents the correlation value, and n represents the length of the overlapping window. The above method is only an example, and the specific implementation method is not limited.

[0104] In order to improve the similarity of the correlation value, the concept of using different correlation value calculation methods according to the quality and complexity of the test audio data is introduced. For example, the volume difference and time offset between the test audio data and the original audio data are calculated. When the volume difference is greater than the preset sound difference critical value, or the time offset is greater than the preset offset threshold, the Mel frequency cepstral coefficients (i.e., MFCC features) of the sliding window are extracted from the original audio data as sliding features, and the Mel frequency cepstral coefficients of the overlapping window are extracted from the test audio data as overlapping features. The correlation value between the sliding feature and the overlapping feature is calculated by Euclidean distance or cosine similarity. When the volume difference is less than or equal to the preset sound difference critical value, and the time offset is less than or equal to the preset offset threshold, the data in the sliding window are dot-producted with each data of the overlapping window one by one, and the dot product values ​​obtained are accumulated to obtain the correlation value between the sliding window and the overlapping window.

[0105] In this way, when the volume difference and time offset are large (that is, when the complexity of the test audio data is high), the MFCC features are used to calculate the correlation values. When the volume difference and time offset are small (that is, when the complexity of the test audio data is low), the cross-correlation is used to calculate the correlation values, so as to more accurately analyze the correlation between the test audio and the original audio.

[0106] After the correlation value is calculated, the method of extracting the target segment in step 15 can be flexibly set. For example, the overlapping window with the largest correlation value can be extracted as the target segment. Figure 6 , step 15 can go through step 151 to step 153.

[0107] Step 151, extracting the maximum correlation value from the correlation array as the target value.

[0108] Step 153, starting from the overlapping window corresponding to the target value, extracting a segment of the same length as the first original audio from the second test audio as the target segment.

[0109] In addition, a correlation value greater than a preset correlation critical value may be extracted as a target value, and an overlapping window corresponding to the target value may be taken as a target segment.

[0110] By means of the above method, the target segment with the greatest correlation with the original audio is extracted quickly and accurately from the second test audio.

[0111] After the target segment is extracted, the matching value can be calculated in step 17 in a variety of ways. For example, the target segment and the first original audio can be input into a pre-trained matching model, and the matching value of the target segment and the first original audio can be generated using the matching model. The matching value can also be calculated according to a preset rule. In this embodiment, the calculation method of the matching value is not limited.

[0112] In order to eliminate the influence of the different amplitude or energy levels between the target segment and the first original audio on the matching value and improve the accuracy of the matching value, the concept of normalizing the relevant value by audio energy is introduced in the process of calculating the matching value in step 17. Figure 7 , step 17 can calculate the matching value between the target segment and the original audio data through steps 171 to 175.

[0113] Step 171: extract multiple test audio amplitudes of the target segment from the test audio data, and perform norm calculation on the multiple test audio amplitudes to obtain the test audio energy of the target segment.

[0114] Step 173: extract multiple original audio amplitudes of the first original audio from the original audio data, and perform norm calculation on the multiple original audio amplitudes to obtain original audio energy of the first original audio.

[0115] Step 175 , using the test audio energy and the original audio energy, normalize the correlation value of the target segment to obtain a matching value between the target segment and the original audio data.

[0116] In calculating the audio energy in steps 171 to 173, the sum of the squares of the audio amplitudes can be used as the audio energy. In order to make the audio energy have the same dimension as the initially set audio data, in steps 171 to 173, the sum of the squares of the audio amplitudes can be calculated first, and then the square root of the sum of the squares can be taken to obtain the audio energy. In this case, the audio energy can be expressed as: N represents the length of the target segment or the first original audio, and x(i) represents the i-th audio amplitude.

[0117] In step 175, the matching value can be expressed as: A represents the original audio energy, B represents the test audio energy, and C represents the correlation value between the target segment and the first original audio.

[0118] Then, after the matching value is obtained, the matching value and the preset matching threshold (i.e., the matching rate to be achieved) are compared in step 17. If the matching value is greater than the matching threshold, it indicates that the matching degree is high, the original audio data and the test audio data are the same audio segment, and the collected test audio data is correct. If the matching value is less than the matching threshold, it indicates that the matching degree is low, the original audio data and the test audio data are not the same audio segment, and the collected test audio data is wrong.

[0119] The matching threshold is a value determined based on multiple stress tests or a value obtained by fitting historical data, and is the minimum matching degree for two audios to be the same audio segment.

[0120] Through the above steps 171 to 175, the influence of different amplitudes or energy levels on the matching value is eliminated, making the matching value more accurate, thereby improving the robustness of the matching judgment (ie, the test result).

[0121] Based on the same inventive concept as the above-mentioned vehicle audio test method, Figure 8 The embodiment of the present invention provides a vehicle audio testing device 30, which can be applied to Figure 1 The analysis device 140 in the vehicle audio test device 30 includes a data acquisition module 310, a correlation analysis module 320, a target extraction module 330 and a matching module 340.

[0122] The data acquisition module 310 is used to acquire the test audio data of the external power amplifier at the vehicle terminal through the acquisition device, and retrieve the original audio data corresponding to the test audio data.

[0123] The correlation analysis module 320 is used to calculate the correlation between the test audio data and the original audio data to obtain a correlation array, wherein the correlation array includes multiple correlation values.

[0124] The target extraction module 330 is used to extract a segment from the test audio data according to the correlation value as a target segment.

[0125] The matching module 340 is used to calculate the matching value between the target segment and the original audio data, and obtain the test result of the test audio data according to the matching value.

[0126] The above-mentioned vehicle audio test device 30, through the coordinated action of the data acquisition module 310, the correlation analysis module 320, the target extraction module 330 and the matching module 340, first extracts the target segment from the test audio data according to the correlation between the test audio data and the original audio data, so that the target segment has the maximum correlation with the original audio data as much as possible to filter out the interference audio in the test audio data, and then calculates the matching value of the target segment and the original audio data to obtain the test result, so that the test audio can be analyzed quickly and automatically, and the test result can be obtained more accurately.

[0127] For the specific implementation and effect of the vehicle audio test device 30, please refer to the description of the implementation of the vehicle audio test method above, such as, for the specific implementation and effect of the data acquisition module 310, please refer to the description of the relevant content of step 11 above, for the specific implementation and effect of the correlation analysis module 320, please refer to the description of the relevant content of step 13 above, for the specific implementation and effect of the target extraction module 330, please refer to the description of the relevant content of step 15 above, for the specific implementation and effect of the matching module 340, please refer to the description of the relevant content of step 17 above, and no further details will be given here.

[0128] In addition, each module in the above-mentioned vehicle audio test device 30 can be implemented in whole or in part by software, hardware, or a combination thereof. The above-mentioned modules can be embedded in or independent of the processor 220 in the electronic device 20 in the form of hardware, or can be stored in the memory 210 of the electronic device 20 in the form of software, so that the processor 220 can call and execute the operations corresponding to the above-mentioned modules to implement the vehicle audio test method provided above.

[0129] Based on the same inventive concept as the above-mentioned vehicle audio test method, an embodiment of the present invention also provides an electronic device 20, including a processor 220 and a memory 210, the memory 210 stores a computer program that can be executed by the processor 220, and the processor 220 can execute the computer program to implement the vehicle audio test method proposed in the embodiment of the present invention.

[0130] The embodiment of the present invention further provides a storage medium on which a computer program is stored. When the computer program is executed by the processor 220, the vehicle audio testing method proposed in the embodiment of the present invention is implemented.

[0131] In addition, an embodiment of the present invention further provides a computer program product, which includes computer instructions, wherein when the computer instructions are executed by the processor 220, the vehicle audio test method proposed in the embodiment of the present invention is implemented.

[0132] In summary, the vehicle audio testing method provided by the embodiment of the present invention has at least the following beneficial effects:

[0133] (1) High test efficiency and reduced costs: The test results are automatically analyzed during the test process, which greatly improves the test efficiency and does not require manual intervention, greatly reducing labor costs;

[0134] (2) High test accuracy: First, the silent segments in the test audio data are filtered out, and then the target segment with the greatest correlation with the first original audio is extracted from the second test audio after the silent segments are filtered out. The target segment is matched with the first original audio, filtering out interference and irrelevant data, greatly improving the matching accuracy and test accuracy.

[0135] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that 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, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0136] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0137] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory 210 (ROM, Read-Only Memory), random access memory 210 (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0138] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A vehicle audio testing method, characterized in that: Applied to an analysis device, the analysis device is communicatively connected with a collection device, and the method comprises: Acquire the test audio data of the external power amplifier at the vehicle terminal through the acquisition device, and retrieve the original audio data corresponding to the test audio data; Calculating the correlation between the test audio data and the original audio data to obtain a correlation array; wherein the correlation array includes a plurality of correlation values; extracting a segment from the test audio data as a target segment according to the correlation value; A matching value between the target segment and the original audio data is calculated, and a test result of the test audio data is obtained according to the matching value.

2. The vehicle audio testing method according to claim 1, characterized in that: The step of calculating the correlation between the test audio data and the original audio data to obtain a correlation array comprises: Normalizing the test audio data and the original audio data respectively to obtain a first test audio and a first original audio; removing the silent segment in the first test audio to obtain a second test audio; Sliding the first original audio as a sliding window on the second test audio to obtain a plurality of overlapping windows of the sliding window on the second test audio; The correlation values ​​between the sliding window and each of the overlapping windows are calculated respectively to obtain a correlation array composed of each of the correlation values.

3. The vehicle audio testing method according to claim 2, characterized in that: The step of respectively calculating the correlation values ​​between the sliding window and each of the overlapping windows comprises: For each overlapping window, dot products are performed on the data in the sliding window and the data in the overlapping window one by one, and the obtained dot product values ​​are accumulated to obtain the correlation value between the sliding window and the overlapping window.

4. The vehicle audio testing method according to claim 2, characterized in that: The test audio data includes audio data at each test moment in the test period, and the audio data includes amplitude; The step of removing the silent segment in the first test audio to obtain the second test audio includes: For each of the test moments, extracting the test audio amplitude at the test moment from the test audio data, and calculating the test audio energy at the test moment according to the test audio amplitude; When the energy of the test audio is less than the preset silence critical energy, the data corresponding to the test time in the first test audio is deleted.

5. The vehicle audio testing method according to claim 2, characterized in that: The step of extracting a segment from the test audio data as a target segment according to the correlation value comprises: Extracting the maximum correlation value from the correlation array as the target value; Taking the overlapping window corresponding to the target value as a starting point, extracting a segment having the same length as the first original audio from the second test audio as a target segment.

6. The vehicle audio testing method according to claim 5, characterized in that: The step of calculating the matching value between the target segment and the original audio data comprises: Extracting multiple test audio amplitudes of the target segment from the test audio data, and performing norm calculation on the multiple test audio amplitudes to obtain the test audio energy of the target segment; Extracting multiple original audio amplitudes of the first original audio from the original audio data, and performing norm calculation on the multiple original audio amplitudes to obtain original audio energy of the first original audio; The correlation value of the target segment is normalized using the test audio energy and the original audio energy to obtain a matching value between the target segment and the original audio data.

7. The vehicle audio testing method according to any one of claims 1 to 6, characterized in that: The sampling end of the acquisition device is connected to the output end of the audio converter, and the input end of the audio converter is connected to the external power amplifier at the vehicle end; The step of acquiring the test audio data of the external power amplifier at the vehicle terminal through the acquisition device includes: Receive test audio data transmitted by the acquisition device; wherein the test audio data is obtained by the acquisition device sampling the audio signal output by the audio converter, and the audio converter reduces the power of the audio signal of the external power amplifier and then outputs it.

8. A vehicle audio testing device, characterized in that: Applied to an analysis device, the analysis device is communicatively connected with a collection device, and the vehicle audio test device includes a data acquisition module, a correlation analysis module, a target extraction module and a matching module; The data acquisition module is used to acquire the test audio data of the external power amplifier at the vehicle terminal through the acquisition device, and retrieve the original audio data corresponding to the test audio data; The correlation analysis module is used to calculate the correlation between the test audio data and the original audio data to obtain a correlation array; wherein the correlation array includes a plurality of correlation values; The target extraction module is used to extract a segment from the test audio data as a target segment according to the correlation value; The matching module is used to calculate the matching value between the target segment and the original audio data, and obtain the test result of the test audio data according to the matching value.

9. An electronic device, characterized in that: The invention comprises a processor and a memory, wherein the memory stores a computer program executable by the processor, and the processor can execute the computer program to implement the vehicle audio testing method according to any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the vehicle audio testing method according to any one of claims 1 to 7 is implemented.

Citation Information

Cited By

  • Vehicle machine audio identification method and system

    CN120748440A