Electrically-driven acoustic enhancement method, terminal and storage medium

Abstract

The invention discloses an electric drive acoustic enhancement method, a terminal and a storage medium. The method comprises the following steps: acquiring original electric drive sound of a target electric drive; performing acoustic enhancement processing on the original electric drive sound according to the enhancement strategy to obtain enhanced electric drive sound corresponding to the original electric drive sound; inputting the enhanced electrically-driven sound into the acoustic evaluation model to obtain a prediction score corresponding to the enhanced electrically-driven sound; according to the prediction score, processing the enhanced electric drive sound again by using a next enhancement strategy, and repeating the step of inputting the enhanced electric drive sound into the acoustic evaluation model to obtain the prediction score corresponding to the enhanced electric drive sound until the prediction score or the enhancement frequency meets the requirement; when the predicted score or the number of times of enhancement meets the requirement, obtaining an optimized path corresponding to the enhancement strategy and a final enhanced electric drive sound; finally, the enhanced electric drive sound is played in the vehicle. According to the scheme, the acoustic enhancement processing efficiency of the electric drive is improved.

Description

Technical Field

[0001] The present application relates to the field of new energy vehicle technology, and in particular to an acoustic enhancement method, terminal and storage medium for electric drive. Background Art

[0002] As my country's consumption level improves, consumers have increasingly stringent requirements for automotive products, and the vibration and noise performance of automobiles has gradually become a key indicator for measuring automobile quality. For new energy vehicles, the noise generated by the motor drive (electric drive) system is the main noise source. In order to improve the experience of drivers and passengers, the electric drive needs to be acoustically enhanced accordingly.

[0003] In related methods, in order to determine whether the sound quality effect after acoustic enhancement meets the requirements, multiple rounds of expert evaluation of the sound after acoustic enhancement are often required, which consumes a lot of time and greatly prolongs the processing cycle of acoustic enhancement. Summary of the invention

[0004] The present application provides an acoustic enhancement method, a terminal and a storage medium for electric drive.

[0005] A technical solution adopted in this application is to provide an acoustic enhancement method for electric drive, the method comprising:

[0006] Acquire the original electric drive sound of the target electric drive;

[0007] Performing acoustic enhancement processing on the original electric drive sound according to the enhancement strategy to obtain an enhanced electric drive sound corresponding to the original electric drive sound;

[0008] The enhanced electric drive sound is input into the acoustic evaluation model to obtain the prediction score corresponding to the enhanced electric drive sound;

[0009] According to the predicted score, the next enhancement strategy is used to process the enhanced electric drive sound again, and the enhanced electric drive sound is input into the acoustic evaluation model repeatedly to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meets the requirements;

[0010] When the predicted score or the number of enhancements meets the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained; the final enhanced electric drive sound is used for playing in the vehicle.

[0011] Optionally, performing acoustic enhancement processing on the original electric drive sound according to the enhancement strategy to obtain an enhanced electric drive sound corresponding to the original electric drive sound includes:

[0012] Obtaining a frequency-speed-energy diagram corresponding to the original electric drive sound, and obtaining a target energy corresponding to the main order of the target electric drive from the frequency-speed-energy diagram;

[0013] In response to the target energy being greater than a preset threshold, the target energy is reduced to obtain an enhanced electric drive sound;

[0014] and / or,

[0015] Determine the harmonic orders around the main order according to the preset step size;

[0016] A first electric drive sound is generated according to the harmonic order and the target energy corresponding to the main order, and the original electric drive sound and the first electric drive sound are superimposed to obtain an enhanced electric drive sound.

[0017] Optionally, performing acoustic enhancement processing on the original electric drive sound according to the enhancement strategy to obtain an enhanced electric drive sound corresponding to the original electric drive sound, further comprising:

[0018] Obtaining a target electric drive sound with a rotation speed higher than a preset rotation speed from the original electric drive sound;

[0019] In response to the energy of the first frequency range of the target electric drive sound being greater than a preset threshold, generating a second electric drive sound according to a second frequency range, wherein the second frequency range is smaller than the first frequency range;

[0020] The target electric drive sound and the second electric drive sound are superimposed to obtain an enhanced electric drive sound.

[0021] Optionally, in response to the target energy corresponding to the main order being greater than a preset threshold, the target energy is reduced to obtain enhanced electric drive sound, including:

[0022] In response to a target energy corresponding to the main order being greater than a preset threshold, performing harmonic injection processing on the target electric drive;

[0023] The electric drive sound of the target electric drive after the harmonic injection processing is obtained to obtain the enhanced electric drive sound.

[0024] Optionally, the enhanced electric drive sound is input into an acoustic evaluation model to obtain a prediction score corresponding to the enhanced electric drive sound, including:

[0025] Extracting objective parameters of the enhanced electric drive sound to obtain first objective parameters corresponding to the enhanced electric drive sound;

[0026] The first objective parameter is input into the acoustic evaluation model to obtain a prediction score corresponding to the enhanced electric drive sound.

[0027] Optionally, the acoustic evaluation model is constructed in advance in the following manner:

[0028] Acquire an original electric drive sound sample corresponding to the sample electric drive; and perform acoustic enhancement processing on the original electric drive sound sample according to the enhancement strategy to obtain an enhanced electric drive sound sample corresponding to the original electric drive sound sample;

[0029] Performing expert scoring on the original electric drive sound sample to obtain a first expert score corresponding to the original electric drive sound sample; and performing expert scoring on the enhanced electric drive sound sample to obtain a second expert score corresponding to the enhanced electric drive sound sample;

[0030] In response to the second expert score being greater than the first expert score, the enhanced electric drive sound is processed again using the next enhancement strategy, and the step of performing expert scoring on the enhanced electric drive sound sample to obtain a second expert score corresponding to the enhanced electric drive sound sample is repeated until the second expert score meets the requirement;

[0031] When the second expert score meets the requirements, the corresponding final enhanced electric-driven sound sample is obtained, and the acoustic evaluation model is constructed using the second expert score corresponding to the final enhanced electric-driven sound sample.

[0032] Optionally, using the second expert score corresponding to the final enhanced electric drive sound sample, an acoustic evaluation model is constructed, including:

[0033] Obtaining a second objective parameter corresponding to the enhanced electric-driven sound sample;

[0034] An acoustic evaluation model is constructed with the second objective parameter as input and the second expert score as output.

[0035] Optionally, obtaining objective parameters corresponding to the enhanced electric drive sound sample includes:

[0036] Obtaining initial objective parameters corresponding to the enhanced electric drive sound sample, the initial objective parameters include order distribution, frequency balance, and psychoacoustic parameters, and the psychoacoustic parameters include loudness, roughness, sharpness, and jitter;

[0037] The principal component extraction operation is performed on the initial objective parameters to obtain the objective parameters.

[0038] Another technical solution adopted by the present application is to provide a terminal device, the terminal device comprising a memory and a processor connected to the memory;

[0039] The memory is used to store program data, and the processor is used to execute the program data to implement the acoustic enhancement method of electric drive as described above.

[0040] Another technical solution adopted by the present application is to provide a computer storage medium, wherein the computer storage medium is used to store program data, and when the program data is executed by a computer, it is used to implement the acoustic enhancement method of the electric drive as described above.

[0041] The beneficial effects of the present application are: obtaining the original electric drive sound of the target electric drive, and acoustically enhancing the original electric drive sound according to the enhancement strategy to obtain the enhanced electric drive sound corresponding to the original electric drive sound; using the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, and to achieve the sound quality evaluation of the enhanced electric drive sound; based on the predicted score, the enhanced electric drive sound is processed again using the next enhancement strategy, and the enhanced electric drive sound is repeatedly input into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meet the requirements; when the predicted score or the number of enhancements meet the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained. The above scheme uses the acoustic evaluation model to acoustically evaluate the enhanced electric drive sound, and there is no need to conduct multiple rounds of expert evaluation on the enhanced electric drive sound, which improves the reliability of the evaluation and greatly improves the efficiency of obtaining the final electric drive sound. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 It is a flow chart of an embodiment of an acoustic enhancement method for electric drive provided by the present application;

[0044] Figure 2 is a flow chart of another embodiment of the electric drive acoustic enhancement method provided by the present application;

[0045] Figure 3 yes Figure 2 A schematic diagram of a flow chart of an embodiment of a method for constructing an acoustic evaluation model;

[0046] Figure 4 It is a structural diagram of an embodiment of a terminal device provided by the present application;

[0047] Figure 5 It is a structural diagram of an embodiment of a computer storage medium provided by the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] In the related art, the acoustic evaluation model constructed mainly performs acoustic evaluation on the original electric drive sound of the target electric drive, and the acoustic evaluation model cannot perform acoustic evaluation on the electric drive sound after acoustic enhancement. Based on this, the common electric drive acoustic enhancement method requires expert evaluation of the electric drive sound after acoustic enhancement, so this method is time-consuming and labor-intensive.

[0050] Please refer to Figure 1 , Figure 1 It is a flow chart of an embodiment of an acoustic enhancement method for electric drive provided in the present application.

[0051] like Figure 1 As shown, the acoustic enhancement method of the electric drive of the embodiment of the present application may specifically include the following steps:

[0052] S1, obtain the original electric drive sound of the target electric drive.

[0053] The electric drive acoustic enhancement method provided in the present application is mainly performed by an electric drive acoustic enhancement device. In some embodiments, the electric drive acoustic enhancement device can be a device for monitoring images, a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, and an autonomous vehicle, a robot, a security system, and any one or more products of glasses and helmets for augmented reality or virtual reality. In some possible implementations, the electric drive acoustic enhancement method can be implemented by a processor calling computer-readable instructions stored in a memory.

[0054] Specifically, the electric drive acoustic enhancement device obtains the original electric drive sound of the target electric drive.

[0055] In some embodiments, the electric drive acoustic enhancement device obtains the sound of the target electric drive at different rotational speeds and the torques corresponding to the different rotational speeds to obtain the original electric drive sound.

[0056] Exemplarily, the electric drive acoustic enhancement device obtains the original electric drive sound of the target electric drive at a speed of 1000rpm / min, 2000rpm / min, ..., 12000rpm / min, corresponding to no load, 50% forward maximum torque, 100% forward maximum torque, 50% reverse maximum torque, and 100% reverse maximum torque. It can be understood that in some application scenarios, in order to obtain richer original electric drive sound, the electric drive acoustic device can obtain a speed interval of 100rpm / min and a torque interval of 10% maximum torque.

[0057] In some embodiments, the electric drive acoustic enhancement device collects sound sample data of the entire operating condition. The data collection method is based on the industry standard five-point sound pressure method or three-point sound pressure method, which can obtain the noise characteristics of the target electric drive full envelope surface. The sound sample data formed is the superposition average of five points or three points.

[0058] S2, performing acoustic enhancement processing on the original electric drive sound according to the enhancement strategy to obtain an enhanced electric drive sound corresponding to the original electric drive sound.

[0059] Specifically, the electric drive acoustic enhancement device performs acoustic enhancement processing on the original electric drive sound according to the enhancement strategy to obtain the enhanced electric drive sound corresponding to the original electric drive sound.

[0060] In some embodiments, the enhancement strategy may include at least one of active noise reduction processing, order equalization processing, and spectrum profiling processing. Exemplarily, a certain enhancement strategy may be any one of active noise reduction processing, order equalization processing, and spectrum profiling processing on the original electric drive sound, or any two of active noise reduction processing, order equalization processing, and spectrum profiling processing on the original electric drive sound at the same time, or active noise reduction processing, order equalization processing, and spectrum profiling processing may be performed on the original electric drive sound at the same time.

[0061] It should be noted that the obtained enhanced electric drive sound may have a poor acoustic evaluation, so it is necessary to perform an acoustic evaluation on the enhanced electric drive sound.

[0062] S3, inputting the enhanced electric drive sound into the acoustic evaluation model to obtain a prediction score corresponding to the enhanced electric drive sound.

[0063] Specifically, the electric drive acoustic enhancement device inputs the enhanced electric drive sound into the acoustic evaluation model to obtain a prediction score corresponding to the enhanced electric drive sound.

[0064] In some embodiments, the prediction score is based on a 10-point system, and a higher prediction score indicates that the acoustic enhancement strategy adopted by the enhanced electric drive sound meets the evaluation requirements. In some possible embodiments, the prediction score of the enhanced electric drive sound is greater than 5, indicating that the sound quality of the enhanced electric drive sound is better than the sound quality of the original electric drive sound.

[0065] S4, based on the predicted score, the next enhancement strategy is used to process the enhanced electric drive sound again, and the enhanced electric drive sound is repeatedly input into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meets the requirements.

[0066] Specifically, the electric drive acoustic enhancement device uses the next enhancement strategy to process the enhanced electric drive sound again based on the predicted score, and repeats the step of inputting the enhanced electric drive sound into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meets the requirements.

[0067] In some possible embodiments, in response to the predicted score of the enhanced electric drive sound being higher than the predicted score of the original electric drive sound, the electric drive acoustic enhancement device uses the next enhancement strategy to process the enhanced electric drive sound again to obtain an updated enhanced electric drive sound. Further, the electric drive acoustic enhancement device inputs the updated enhanced electric drive sound into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound. In some possible application scenarios, after several enhancement iterations, until the predicted score of the enhanced electric drive sound updated for the mth time is less than the predicted score of the enhanced electric drive sound updated for the m-1th time, where m is an integer greater than 1. At this point, the predicted score meets the requirements, and the electric drive acoustic enhancement device stops the acoustic enhancement operation on the updated electric drive sound. In some possible application scenarios, if the number of enhancements is greater than n times, the electric drive acoustic enhancement device stops the acoustic enhancement operation on the electric drive sound updated for the nth time. Optionally, n is an integer greater than 1.

[0068] In some embodiments, when performing acoustic enhancement processing on the updated enhanced electric drive sound, the electric drive acoustic enhancement device will also record and update the optimized path.

[0069] S5, when the predicted score or the number of enhancements meets the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained.

[0070] Specifically, when the predicted score or the number of enhancements meets the requirements, the electric-drive acoustic enhancement device obtains the optimization path corresponding to the enhancement strategy and the final enhanced electric-drive sound.

[0071] In some possible application scenarios, after several enhancement iterations, until the prediction score of the enhanced electric drive sound updated for the mth time is less than the prediction score of the enhanced electric drive sound after the m-1th update, the electric drive acoustic device uses the enhanced electric drive sound updated for the m-1th time as the final enhanced electric drive sound, and obtains the optimization path corresponding to the above m-1 enhancement strategies, where m is an integer greater than 1.

[0072] In some possible application scenarios, if the number of enhancements is greater than n times, the acoustic enhancement operation on the electric drive sound updated for the nth time is stopped, the enhanced electric drive sound updated for the nth time is used as the final enhanced electric drive sound, and the optimization path corresponding to the above n enhancement strategies is obtained.

[0073] The above scheme obtains the original electric drive sound of the target electric drive, and acoustically enhances the original electric drive sound according to the enhancement strategy to obtain the enhanced electric drive sound corresponding to the original electric drive sound; uses the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, and realizes the sound quality evaluation of the enhanced electric drive sound; according to the predicted score, the enhanced electric drive sound is processed again using the next enhancement strategy, and the enhanced electric drive sound is repeatedly input into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meet the requirements; when the predicted score or the number of enhancements meet the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained. The above scheme uses the acoustic evaluation model to acoustically evaluate the enhanced electric drive sound, and there is no need to conduct multiple rounds of expert evaluation on the enhanced electric drive sound, which improves the reliability of the evaluation and greatly improves the efficiency of obtaining the final electric drive sound.

[0074] Another embodiment of the electric drive acoustic enhancement method provided in the present application may specifically include the following steps:

[0075] S11, obtaining the original electric drive sound of the target electric drive.

[0076] S12, obtaining a frequency-rotation speed-energy diagram corresponding to the original electric drive sound, and obtaining a target energy corresponding to the main order of the target electric drive from the frequency-rotation speed-energy diagram.

[0077] Specifically, the electric-drive acoustic enhancement device uses the original electric-drive sound corresponding to different rotation speeds to perform time-frequency domain conversion, and then obtains a frequency-rotation speed-energy diagram.

[0078] The frequency-speed-energy diagram is presented in the form of a color diagram, with the horizontal axis being the frequency and the vertical axis being the speed. The color is used to represent the magnitude of the energy amplitude. There are bright oblique lines in the frequency-speed-energy diagram that emanate from the origin, and each bright oblique line corresponds to the order of the target electric drive.

[0079] Exemplarily, in the target electric drive, the meshing order of the reducer is 26, and the main order of the target electric drive is 26.

[0080] Further, after determining the main order of the target electric drive, the electric drive acoustic enhancement device determines the energy value corresponding to the main order, that is, the target energy, from the frequency-speed-energy diagram.

[0081] S13, in response to the target energy being greater than a preset threshold, reducing the target energy to obtain enhanced electric drive sound.

[0082] Specifically, in response to the target energy corresponding to the main order being greater than a preset threshold, the electrically driven acoustic enhancement device reduces the target energy to obtain enhanced electrically driven sound.

[0083] It can be understood that reducing the energy corresponding to the main order means reducing the ratio of the main order to the total energy, thereby improving the noise caused by the electric drive.

[0084] In some embodiments, S13 may specifically include the following sub-steps:

[0085] S131, in response to the target energy corresponding to the main order being greater than a preset threshold, performing harmonic injection processing on the target electric drive.

[0086] Specifically, in response to the target energy corresponding to the main order being greater than a preset threshold, the electric drive acoustic enhancement device performs harmonic injection processing on the target electric drive, and reduces the target energy corresponding to the main order by adjusting the motor parameters (such as current, voltage, etc.) in the electric drive.

[0087] Harmonic injection refers to the injection of specific current waveforms into the motor controller. These waveforms are precisely calculated and designed to offset the torque harmonics generated by the motor itself, which can significantly reduce the operating noise of the motor.

[0088] S132, acquiring the electric drive sound of the target electric drive after the harmonic injection processing to obtain the enhanced electric drive sound.

[0089] Specifically, the electric drive acoustic enhancement device obtains the electric drive sound of the target electric drive after harmonic injection processing to obtain the enhanced electric drive sound.

[0090] It should be noted that, under different acoustic enhancement strategies, the relevant parameters of the electric drive acoustic enhancement device for harmonic injection into the target electric drive may be the same or different.

[0091] S14, inputting the enhanced electric drive sound into an acoustic evaluation model to obtain a prediction score corresponding to the enhanced electric drive sound.

[0092] S15, based on the predicted score, the next enhancement strategy is used to process the enhanced electric drive sound again, and the enhanced electric drive sound is input into the acoustic evaluation model repeatedly to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meets the requirements.

[0093] S16, when the predicted score or the number of enhancements meets the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained.

[0094] The above scheme obtains the original electric drive sound of the target electric drive, and acoustically enhances the original electric drive sound according to the enhancement strategy to obtain the enhanced electric drive sound corresponding to the original electric drive sound; uses the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, and realizes the sound quality evaluation of the enhanced electric drive sound; according to the predicted score, the enhanced electric drive sound is processed again using the next enhancement strategy, and the enhanced electric drive sound is repeatedly input into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meet the requirements; when the predicted score or the number of enhancements meet the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained. The above scheme uses the acoustic evaluation model to acoustically evaluate the enhanced electric drive sound, and there is no need to conduct multiple rounds of expert evaluation on the enhanced electric drive sound, which improves the reliability of the evaluation and greatly improves the efficiency of obtaining the final electric drive sound.

[0095] Another embodiment of the electric drive acoustic enhancement method provided in the present application may specifically include the following steps:

[0096] S21, obtaining the original electric drive sound of the target electric drive.

[0097] S22, obtaining a frequency-speed-energy diagram corresponding to the original electric drive sound, and obtaining a main order corresponding to the target electric drive from the frequency-speed-energy diagram.

[0098] S23, determining harmonic orders around the main order according to a preset step size.

[0099] Specifically, the electrically driven acoustic enhancement device determines harmonic orders around the main order according to a preset step size.

[0100] In some embodiments, the electrically driven acoustic enhancement device determines the harmonic orders according to a preset step size with the main order as the center.

[0101] Optionally, the preset step size may be of order 5, 4, 3, 2, 1, 0.5, 1 / 3 or 0.1.

[0102] In some embodiments, under different enhancement strategies, the preset step sizes may be the same or different.

[0103] S24, generating a first electric drive sound according to the harmonic order and the target energy corresponding to the main order, and superimposing the original electric drive sound and the first electric drive sound to obtain an enhanced electric drive sound.

[0104] Specifically, the electric drive acoustic enhancement device generates a first electric drive sound according to the harmonic order and the target energy corresponding to the main order, and performs a superposition operation on the original electric drive sound and the first electric drive sound to obtain the enhanced electric drive sound.

[0105] For example, the main order is 26, and the energy value corresponding to the main order (i.e., the target energy) is 68 dB. The electric-driven acoustic enhancement device determines that the harmonic order is 24, and the energy value corresponding to the harmonic order is 65 dB. The first electric-driven sound is generated according to the harmonic order and the energy value corresponding to the harmonic order to adjust the ratio between the main order component and the total energy.

[0106] In some embodiments, under different enhancement strategies, the energy value corresponding to the harmonic order may be increased or decreased.

[0107] S25, inputting the enhanced electric drive sound into an acoustic evaluation model to obtain a prediction score corresponding to the enhanced electric drive sound.

[0108] S26, based on the predicted score, the next enhancement strategy is used to process the enhanced electric drive sound again, and the enhanced electric drive sound is input into the acoustic evaluation model repeatedly to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meets the requirements.

[0109] S27, when the predicted score or the number of enhancements meets the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained.

[0110] The above scheme obtains the original electric drive sound of the target electric drive, and acoustically enhances the original electric drive sound according to the enhancement strategy to obtain the enhanced electric drive sound corresponding to the original electric drive sound; uses the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, and realizes the sound quality evaluation of the enhanced electric drive sound; according to the predicted score, the enhanced electric drive sound is processed again using the next enhancement strategy, and the enhanced electric drive sound is repeatedly input into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meet the requirements; when the predicted score or the number of enhancements meet the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained. The above scheme uses the acoustic evaluation model to acoustically evaluate the enhanced electric drive sound, and there is no need to conduct multiple rounds of expert evaluation on the enhanced electric drive sound, which improves the reliability of the evaluation and greatly improves the efficiency of obtaining the final electric drive sound.

[0111] Another embodiment of the electric drive acoustic enhancement method provided in the present application may specifically include the following steps:

[0112] S31, obtaining the original electric drive sound of the target electric drive.

[0113] S32, obtaining a frequency-rotation speed-energy diagram corresponding to the original electric drive sound, and obtaining a target energy corresponding to the main order corresponding to the target electric drive from the frequency-rotation speed-energy diagram.

[0114] S33, in response to the target energy being greater than a preset threshold, reducing the target energy to obtain enhanced electric drive sound.

[0115] S34, determining harmonic orders around the main order according to a preset step size.

[0116] S35 , generating a first electric drive sound according to the harmonic order and the target energy corresponding to the main order, and superimposing the original electric drive sound and the first electric drive sound to obtain an enhanced electric drive sound.

[0117] S36, inputting the enhanced electric drive sound into an acoustic evaluation model to obtain a prediction score corresponding to the enhanced electric drive sound.

[0118] S37, based on the predicted score, the next enhancement strategy is used to process the enhanced electric drive sound again, and the enhanced electric drive sound is input into the acoustic evaluation model repeatedly to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meets the requirements.

[0119] S38, when the predicted score or the number of enhancements meets the requirements, obtaining the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound.

[0120] The above scheme obtains the original electric drive sound of the target electric drive, and acoustically enhances the original electric drive sound according to the enhancement strategy to obtain the enhanced electric drive sound corresponding to the original electric drive sound; uses the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, and realizes the sound quality evaluation of the enhanced electric drive sound; according to the predicted score, the enhanced electric drive sound is processed again using the next enhancement strategy, and the enhanced electric drive sound is repeatedly input into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meet the requirements; when the predicted score or the number of enhancements meet the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained. The above scheme uses the acoustic evaluation model to acoustically evaluate the enhanced electric drive sound, and there is no need to conduct multiple rounds of expert evaluation on the enhanced electric drive sound, which improves the reliability of the evaluation and greatly improves the efficiency of obtaining the final electric drive sound.

[0121] Another embodiment of the electric drive acoustic enhancement method provided in the present application may specifically include the following steps:

[0122] S41, obtaining the original electric drive sound of the target electric drive.

[0123] S42, obtaining a target electric drive sound having a rotation speed higher than a preset rotation speed from the original electric drive sound.

[0124] Specifically, the electric drive acoustic enhancement device obtains a target electric drive sound having a rotation speed higher than a preset rotation speed from the original electric drive sound.

[0125] Exemplarily, the preset speed is 7000 rpm or above, which is not limited here.

[0126] It should be noted that when the motor is running at high speed, the higher energy at certain high frequencies may make the user feel that the sound is harsh. Therefore, it is necessary to perform corresponding acoustic enhancement operations on the electric drive sound at high speed.

[0127] S43 , in response to the energy of the first frequency range of the target electric drive sound being greater than a preset threshold, generating a second electric drive sound according to a second frequency range, wherein the second frequency range is smaller than the first frequency range.

[0128] Specifically, in response to the energy of the first frequency range of the target electric drive sound being greater than a preset threshold, the electric drive acoustic enhancement device generates corresponding low-frequency sound to improve the user's auditory experience.

[0129] In some possible embodiments, the electrically driven acoustic enhancement device generates a second electrically driven sound in a second frequency range in a 1 / 3 octave manner.

[0130] S44, performing a superposition operation on the target electric drive sound and the second electric drive sound to obtain an enhanced electric drive sound.

[0131] Specifically, the electric drive acoustic enhancement device performs a superposition operation on the target electric drive sound and the second electric drive sound to obtain an enhanced electric drive sound.

[0132] By generating a second electric drive sound with a certain low-frequency energy and superimposing the target electric drive sound and the second electric drive sound, the component ratio of the enhanced electric drive sound at different frequencies is made more balanced, so as to improve the user experience.

[0133] S45, inputting the enhanced electric drive sound into an acoustic evaluation model to obtain a prediction score corresponding to the enhanced electric drive sound.

[0134] S46, based on the predicted score, the next enhancement strategy is used to process the enhanced electric drive sound again, and the enhanced electric drive sound is input into the acoustic evaluation model repeatedly to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meets the requirements.

[0135] S47, when the predicted score or the number of enhancements meets the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained.

[0136] The above scheme obtains the original electric drive sound of the target electric drive, and acoustically enhances the original electric drive sound according to the enhancement strategy to obtain the enhanced electric drive sound corresponding to the original electric drive sound; uses the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, and realizes the sound quality evaluation of the enhanced electric drive sound; according to the predicted score, the enhanced electric drive sound is processed again using the next enhancement strategy, and the enhanced electric drive sound is repeatedly input into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meet the requirements; when the predicted score or the number of enhancements meet the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained. The above scheme uses the acoustic evaluation model to acoustically evaluate the enhanced electric drive sound, and there is no need to conduct multiple rounds of expert evaluation on the enhanced electric drive sound, which improves the reliability of the evaluation and greatly improves the efficiency of obtaining the final electric drive sound.

[0137] Another embodiment of the electric drive acoustic enhancement method provided in the present application may specifically include the following steps:

[0138] S51, obtaining the original electric drive sound of the target electric drive.

[0139] S52, performing acoustic enhancement processing on the original electric drive sound according to the enhancement strategy to obtain an enhanced electric drive sound corresponding to the original electric drive sound.

[0140] S53, extracting objective parameters of the enhanced electric drive sound to obtain first objective parameters corresponding to the enhanced electric drive sound.

[0141] Specifically, the electric drive acoustic enhancement device extracts objective parameters of the enhanced electric drive sound to obtain first objective parameters corresponding to the enhanced electric drive sound.

[0142] In some possible embodiments, the first objective parameter may include at least one of order distribution, frequency balance, and psychoacoustic parameters, wherein the psychoacoustic parameters include at least one of loudness, roughness, sharpness, and jitter.

[0143] Among them, loudness is used to reflect people's subjective perception of sound pressure level, with a higher weight on low frequencies. Roughness and jitter are modulation characteristics. Sharpness describes the frequency components of high frequencies.

[0144] S54, inputting the first objective parameter into the acoustic evaluation model to obtain a prediction score corresponding to the enhanced electric drive sound.

[0145] Specifically, the electric-drive acoustic enhancement device inputs the first objective parameter into the acoustic evaluation model to obtain a prediction score corresponding to the enhanced electric-drive sound.

[0146] S55, based on the predicted score, the next enhancement strategy is used to process the enhanced electric drive sound again, and the enhanced electric drive sound is input into the acoustic evaluation model repeatedly to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meets the requirements.

[0147] S56, when the predicted score or the number of enhancements meets the requirements, obtaining the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound.

[0148] The above scheme obtains the original electric drive sound of the target electric drive, and acoustically enhances the original electric drive sound according to the enhancement strategy to obtain the enhanced electric drive sound corresponding to the original electric drive sound; uses the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, and realizes the sound quality evaluation of the enhanced electric drive sound; according to the predicted score, the enhanced electric drive sound is processed again using the next enhancement strategy, and the enhanced electric drive sound is repeatedly input into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meet the requirements; when the predicted score or the number of enhancements meet the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained. The above scheme uses the acoustic evaluation model to acoustically evaluate the enhanced electric drive sound, and there is no need to conduct multiple rounds of expert evaluation on the enhanced electric drive sound, which improves the reliability of the evaluation and greatly improves the efficiency of obtaining the final electric drive sound.

[0149] In some embodiments, the acoustic evaluation model is constructed in advance by using the following steps:

[0150] S61, obtaining an original electric drive sound sample corresponding to the sample electric drive, and performing acoustic enhancement processing on the original electric drive sound sample according to the enhancement strategy to obtain an enhanced electric drive sound sample corresponding to the original electric drive sound sample.

[0151] Specifically, the electric drive acoustic enhancement device obtains an original electric drive sound sample corresponding to the sample electric drive, and performs acoustic enhancement processing on the original electric drive sound sample according to the enhancement strategy to obtain an enhanced electric drive sound sample corresponding to the original electric drive sound sample.

[0152] In some embodiments, there are multiple sample electric drives, that is, the final enhanced electric drive sound obtained corresponds to different sample electric drives.

[0153] Illustratively, the sample electric drives may be electric drives of different manufacturers and models.

[0154] Exemplarily, the electric drive acoustic enhancement device uses more than 20 electric drives of different manufacturers and models as sample electric drives, and collects data for each sample electric drive using the five-point sound pressure method or the three-point sound pressure method to obtain the global working condition sound sample data corresponding to each sample electric drive. The sound sample data is the original sound sample data. In some possible application scenarios, the original sound sample data is the superposition average of three or five points.

[0155] Furthermore, the electric-driven acoustic enhancement device performs acoustic enhancement processing on the original electric-driven sound sample according to the multiple enhancement strategies mentioned above to obtain an enhanced electric-driven sound sample.

[0156] It should be noted that a single original electric drive sound sample may correspond to several enhanced electric drive sound samples.

[0157] S62, performing expert scoring on the original electric drive sound sample to obtain a first expert score corresponding to the original electric drive sound sample, and performing expert scoring on the enhanced electric drive sound sample to obtain a second expert score corresponding to the enhanced electric drive sound sample.

[0158] Specifically, the electric drive acoustic enhancement device performs expert scoring on the original electric drive sound sample to obtain a first expert score corresponding to the original electric drive sound sample, and the electric drive acoustic enhancement device performs expert scoring on the enhanced electric drive sound sample to obtain a second expert score corresponding to the enhanced electric drive sound sample.

[0159] In some embodiments, the electric drive acoustic enhancement device needs to perform expert scoring on the obtained enhanced electric drive sound samples and the original electric drive sound samples. In some application scenarios, in order to improve the effectiveness of expert scoring, a scoring method of comparative test is adopted, and the original electric drive sound sample and its corresponding enhanced electric drive sound sample are taken as a group for expert comparative scoring. Exemplarily, a 10-point scoring standard is adopted, and the original electric drive sound sample is set to 5 points. If the score of the enhanced electric drive sound sample is higher than 5 points, it indicates that there is an optimization effect, and the enhanced electric drive sound is processed again using the next enhancement strategy; if the score of the enhanced electric drive sound is lower than 5 points, it indicates that there is no optimization effect, and the enhanced sound sample is discarded.

[0160] S63, in response to the second expert score being greater than the first expert score, the enhanced electric drive sound is processed again using the next enhancement strategy, and the step of performing expert scoring on the enhanced electric drive sound sample to obtain a second expert score corresponding to the enhanced electric drive sound sample is repeated until the second expert score meets the requirement.

[0161] Specifically, in response to the second expert score being greater than the first expert score, the electric drive acoustic enhancement device uses the next enhancement strategy to process the enhanced electric drive sound again, and repeats the step of performing expert scoring on the enhanced electric drive sound sample to obtain the second expert score corresponding to the enhanced electric drive sound sample until the second expert score meets the requirements.

[0162] S64, when the second expert score meets the requirements, obtain the corresponding final enhanced electric drive sound sample.

[0163] Specifically, when the second expert score meets the requirements, the electric-drive acoustic enhancement device obtains the corresponding final enhanced electric-drive sound sample.

[0164] In some possible embodiments, the second expert score of the i-th enhanced electric drive sound is higher than the second expert score of all the i+1-th enhanced electric drive sounds, that is, the second expert score of the i-th enhanced electric drive sound meets the requirements, which means that the final enhanced electric drive sound sample has been obtained. Wherein, i is an integer greater than 1.

[0165] S65, constructing an acoustic evaluation model using the second expert score corresponding to the final enhanced electric drive sound sample.

[0166] Specifically, the electric-drive acoustic enhancement device uses the second expert scores corresponding to the final enhanced electric-drive sound samples as a sample set, and uses the sample set to construct an acoustic evaluation model.

[0167] In some embodiments, S65 includes the following sub-steps:

[0168] S651, obtaining a second objective parameter corresponding to the final enhanced electric-drive sound sample.

[0169] Specifically, the electrically driven acoustic enhancement device obtains a second objective parameter corresponding to the final enhanced electrically driven sound sample.

[0170] It can be understood that the second objective parameter is a quantifiable acoustic parameter.

[0171] In some embodiments, the second objective parameter is the first objective parameter mentioned above.

[0172] In some embodiments, S651 includes the following sub-steps:

[0173] S6511, obtaining initial objective parameters corresponding to the final enhanced electric drive sound sample.

[0174] Among them, the initial objective parameters include order distribution, frequency balance, and psychoacoustic parameters. The psychoacoustic parameters include loudness, roughness, sharpness, and jitter.

[0175] Among them, loudness is used to describe people's subjective perception of sound pressure level, with a higher weight on low frequencies. Roughness and jitter are modulation characteristics, and sharpness is used to describe the frequency components of high frequencies.

[0176] S6512, performing a principal component extraction operation on the initial objective parameter to obtain a second objective parameter.

[0177] Specifically, the electric-driven acoustic enhancement device performs a principal component extraction operation on the final enhanced electric-driven sound sample, while retaining the amount of information of the original data as much as possible, reducing the number of dimensions of the initial objective parameters to reduce the subsequent amount of calculation and reduce interference factors.

[0178] S652, constructing an acoustic evaluation model with the second objective parameter as input and the second expert score as output.

[0179] Specifically, the electric-driven acoustic enhancement device constructs an acoustic evaluation model with the second objective parameter as input and the second expert score as output.

[0180] In some possible embodiments, the electrically driven acoustic device uses a radial basis function (RBF) neural network to fit the mapping relationship between the second objective parameter as input and the second expert parameter as output. In some embodiments, the hidden layer of the radial basis function neural network is trained and initialized using a K-means algorithm. Furthermore, the trained radial basis function neural network is the acoustic evaluation model.

[0181] The above scheme obtains the original electric drive sound of the target electric drive, and acoustically enhances the original electric drive sound according to the enhancement strategy to obtain the enhanced electric drive sound corresponding to the original electric drive sound; uses the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, and realizes the sound quality evaluation of the enhanced electric drive sound; according to the predicted score, the enhanced electric drive sound is processed again using the next enhancement strategy, and the enhanced electric drive sound is repeatedly input into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meet the requirements; when the predicted score or the number of enhancements meet the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained. The above scheme uses the acoustic evaluation model to acoustically evaluate the enhanced electric drive sound, and there is no need to conduct multiple rounds of expert evaluation on the enhanced electric drive sound, which improves the reliability of the evaluation and greatly improves the efficiency of obtaining the final electric drive sound.

[0182] like Figure 2 As shown, another embodiment of the electric drive acoustic enhancement method provided by the present application may specifically include the following steps:

[0183] S201, collecting the original electric drive sound of the target electric drive.

[0184] Specifically, the electric drive acoustic enhancement device collects the original electric drive sound of the target electric drive.

[0185] In some embodiments, the electric drive acoustic enhancement device adopts a three-point sound pressure method or a five-point sound pressure method to obtain the acoustic characteristics of the target electric drive full envelope surface. Furthermore, the electric drive acoustic enhancement device averages the sound pressure collected at three or five points to obtain the original electric drive sound.

[0186] S202, performing an acoustic enhancement operation to obtain enhanced electric drive sound.

[0187] Specifically, the electric-drive acoustic enhancement device performs at least one of active noise reduction, order equalization, and spectrum profiling on the original electric-drive sound.

[0188] In some embodiments, the active noise reduction operation is to adjust the ratio between the energy of the main order and the overall energy according to the energy amplitude of the main order, or to adjust the relationship between the order sound pressure level and the sound pressure level slope. Exemplarily, the harmonic injection mentioned above is one of the active noise reduction operations.

[0189] In some embodiments, the order equalization operation is to adjust the ratio of the electric drive dominant order and the harmonic order according to the order information of the original electric drive sound, and increase the order component. Exemplarily, S23-S24 is one of the order equalization operations.

[0190] In some embodiments, the spectrum profiling operation is to adjust the ratio of low, medium and high frequency components according to the frequency information of the original electric drive sound. Exemplarily, S42-S44 is one of the spectrum profiling operations.

[0191] S203, inputting the enhanced electric drive sound into an acoustic evaluation model to obtain a prediction evaluation result corresponding to the enhanced electric drive sound.

[0192] Specifically, the electric-drive acoustic enhancement device inputs the enhanced electric-drive sound into the acoustic evaluation model to obtain a prediction evaluation result corresponding to the enhanced electric-drive sound.

[0193] In some embodiments, the predicted evaluation results are used to characterize the expert evaluation of the enhanced electric drive sound.

[0194] like Figure 3 As shown in the figure, the acoustic evaluation model is pre-built through the following steps:

[0195] S301, collecting electric drive sound samples.

[0196] Specifically, the electric drive acoustic enhancement device uses several electric drives of different models from different manufacturers as sample objects to collect sound sample data of the entire working condition. The data collection method is based on the industry standard five-point sound pressure method, which can obtain the acoustic characteristics of the entire envelope surface of the electric drive. The resulting sound sample data is the superposition average of the five points.

[0197] S302, objective parameter analysis is performed on the electric drive sound sample.

[0198] Specifically, the electrically driven acoustic enhancement device calculates and counts objective parameters of the obtained sound samples to obtain a correspondence table between the electrically driven sound samples and the objective parameters.

[0199] The dimensions of calculation are as follows: order distribution, frequency balance, and psychoacoustic parameters. Psychoacoustic parameters include loudness, roughness, sharpness, and jitter. Loudness is the subjective perception of sound pressure level by people, with a higher weight on low frequencies; roughness and jitter are expressed as modulation characteristics; and sharpness describes the frequency components of high frequencies.

[0200] S303, processing the electric drive sound sample and generating a superimposed sound to obtain a superimposed sound sample.

[0201] Taking the electric-driven sound sample a as an example, the electric-driven acoustic enhancement device processes the electric-driven sound sample a by using at least one of active noise reduction operation, order equalization operation, and spectrum profiling operation.

[0202] Exemplarily, the active noise reduction operation is represented by A, the order equalization operation is represented by B, the spectrum profiling operation is represented by C, and the obtained superimposed sound samples may include aA, aB, aC, aAB, aAC, aBC, and aABC.

[0203] In some embodiments, the electrically driven acoustic enhancement device generates batch superposition sound using an orthogonal testing method.

[0204] In some embodiments, the superimposed sound is divided into a target sound and a control sound. The target sound is the sound generated when the electric drive is running. In some embodiments, the target sound corresponds to the original electric drive sound mentioned above. The control sound is the sound added by means of parameter adjustment, harmonic injection, etc. In some embodiments, the control sound corresponds to the first electric drive sound or the second electric drive sound mentioned above. Furthermore, the target sound and the control sound are naturally superimposed in the sound field to form a superimposed sound.

[0205] In some possible application scenarios, during the experimental stage, the electric drive enhancement device can use Matlab to superimpose the target sound and the control sound to form a superimposed sound, and use these superimposed sounds to evaluate the sound quality. During the actual vehicle testing stage, the control sound is played through the in-car audio system, and in the in-car sound field, the electric drive operation sound and the control sound are naturally superimposed to form the in-car sound field.

[0206] S304, performing acoustic evaluation on the superimposed sound sample and the original sound sample, and determining whether the superimposed sound sample meets the conditions.

[0207] If the judgment result is yes, jump to S305. If the judgment result is no, jump to S306.

[0208] Specifically, the electric drive acoustic enhancement device performs an expert evaluation experiment on the superimposed sound sample and the original sound sample obtained in S303. The experiment adopts a comparative test method, and the sound sample before optimization (for example, the original sound sample) and the sound sample after optimization (for example, the superimposed sound sample) are compared and scored as a group, using a 10-point scoring standard, the sound sample before optimization is 5 points, and the sound sample after optimization is higher than 5 points, indicating that there is an optimization effect and can be stored in the sample library, and the superimposed sound sample with a score lower than 5 points is discarded.

[0209] S305, discard the superimposed sound samples.

[0210] Specifically, the electrically driven acoustic enhancement device discards superimposed sound samples with a score lower than 5 points.

[0211] S306, determining whether the superimposed sound sample meets the iteration condition.

[0212] If the judgment result is yes, jump to S302. If the judgment result is no, jump to S307.

[0213] Specifically, the electric-driven acoustic enhancement device determines whether there are new samples in the sample library. If so, it jumps to S302. If not, it stops iterating and jumps to S307.

[0214] S307, establishing a sample library.

[0215] Specifically, the electrically driven acoustic enhancement device establishes a sample library.

[0216] S308, data dimension reduction, model fitting, and obtaining an acoustic evaluation model.

[0217] Specifically, the electric-driven acoustic enhancement device can reduce the number of dimensions of the objective parameters of sound quality while retaining the amount of source data information as much as possible, thereby reducing the amount of calculation and interference factors. The objective parameters of sound quality are the objective parameters of the sound samples in S302.

[0218] Furthermore, the electric-driven acoustic enhancement device is fitted through the RBF neural network model. The input layer of the RBF is the PCA principal component after data dimensionality reduction, the hidden layer is trained and initialized using the K-means algorithm, and the output layer is the expert evaluation score.

[0219] Please review Figure 2 .

[0220] S204: judging whether the enhanced electric drive sound meets the iteration condition according to the prediction evaluation result.

[0221] If the judgment result is yes, jump to S202. If the judgment result is no, jump to S205.

[0222] Specifically, the electric-driven acoustic enhancement device performs iterative judgment according to the prediction evaluation result and the number of iterations. When the iteration converges without a better result or the number of iterations exceeds the limit, the iteration ends and jumps to S205. Otherwise, the iteration continues and jumps to S202 to continue the adaptive optimization (i.e., the acoustic enhancement operation).

[0223] S205, generating an acoustic enhancement strategy and generating a final enhanced electric drive sound.

[0224] Specifically, the electrically driven acoustic enhancement device obtains the final enhanced electrically driven sound, and according to the circulation structure, obtains the acoustic enhancement strategy.

[0225] S206, confirming the final enhanced electric drive sound.

[0226] Specifically, the electric drive acoustic enhancement device conducts an expert evaluation test on a plurality of final enhanced electric drive sounds with similar predicted evaluation results, and selects the best one to select the better final enhanced electric drive sound.

[0227] The above scheme obtains the original electric drive sound of the target electric drive, and acoustically enhances the original electric drive sound according to the enhancement strategy to obtain the enhanced electric drive sound corresponding to the original electric drive sound; uses the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, and realizes the sound quality evaluation of the enhanced electric drive sound; according to the predicted score, the enhanced electric drive sound is processed again using the next enhancement strategy, and the enhanced electric drive sound is repeatedly input into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound, until the predicted score or the number of enhancements meet the requirements; when the predicted score or the number of enhancements meet the requirements, the optimization path corresponding to the enhancement strategy and the final enhanced electric drive sound are obtained. The above scheme uses the acoustic evaluation model to acoustically evaluate the enhanced electric drive sound, and there is no need to conduct multiple rounds of expert evaluation on the enhanced electric drive sound, which improves the reliability of the evaluation and greatly improves the efficiency of obtaining the final electric drive sound.

[0228] Please continue to see Figure 4 , Figure 4 The terminal device 500 of the embodiment of the present application includes a processor 51 and a memory 52 .

[0229] The processor 51 and the memory 52 are connected to the bus. The memory 52 stores program data. The processor 51 is used to execute the program data to implement the acoustic enhancement method of the electric drive described in the above embodiment.

[0230] In the embodiment of the present application, the processor 51 may also be referred to as a CPU (Central Processing Unit). The processor 51 may be an integrated circuit chip having the ability to process signals. The processor 51 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or the processor 51 may also be any conventional processor, etc.

[0231] This application also provides a computer storage medium, please continue to refer to Figure 5 , Figure 5 It is a structural diagram of an embodiment of a computer storage medium provided in the present application. The computer storage medium 600 stores program data 61. When the program data 61 is executed by a processor, it is used to implement the acoustic enhancement method of the electric drive of the above embodiment.

[0232] When the embodiments of the present application are implemented in the form of software functional units 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 application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0233] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Equivalent structures or equivalent process changes made by utilizing the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An acoustic enhancement method for electric drive, characterized in that: The method comprises: Acquire the original electric drive sound of the target electric drive; Performing acoustic enhancement processing on the original electric drive sound according to the enhancement strategy to obtain an enhanced electric drive sound corresponding to the original electric drive sound; Inputting the enhanced electric drive sound into an acoustic evaluation model to obtain a prediction score corresponding to the enhanced electric drive sound; According to the predicted score, the enhanced electric drive sound is processed again using the next enhancement strategy, and the step of inputting the enhanced electric drive sound into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound is repeated until the predicted score or the number of enhancements meets the requirements; When the predicted score or the number of enhancements meets the requirements, an optimization path corresponding to the enhancement strategy and a final enhanced electric drive sound are obtained; the final enhanced electric drive sound is used for playing in the vehicle.

2. The method according to claim 1, characterized in that The acoustic enhancement process is performed on the original electric drive sound according to the enhancement strategy to obtain the enhanced electric drive sound corresponding to the original electric drive sound, including: Obtaining a frequency-speed-energy diagram corresponding to the original electric drive sound, and obtaining a target energy corresponding to the main order of the target electric drive from the frequency-speed-energy diagram; In response to the target energy being greater than a preset threshold, reducing the target energy to obtain the enhanced electric drive sound; and / or, Determining harmonic orders around the main order according to a preset step size; A first electric drive sound is generated according to the harmonic order and the target energy corresponding to the main order, and the original electric drive sound and the first electric drive sound are superimposed to obtain the enhanced electric drive sound.

3. The method according to claim 1, characterized in that The acoustic enhancement process is performed on the original electric drive sound according to the enhancement strategy to obtain the enhanced electric drive sound corresponding to the original electric drive sound, and further includes: Acquire a target electric drive sound having a rotation speed higher than a preset rotation speed from the original electric drive sound; In response to the energy of the first frequency range of the target electric drive sound being greater than a preset threshold, generating a second electric drive sound according to a second frequency range, wherein the second frequency range is smaller than the first frequency range; The target electric drive sound and the second electric drive sound are superimposed to obtain the enhanced electric drive sound.

4. The method according to claim 2, characterized in that: In response to the target energy corresponding to the main order being greater than a preset threshold, reducing the target energy to obtain the enhanced electric drive sound, comprises: In response to the target energy corresponding to the main order being greater than a preset threshold, performing harmonic injection processing on the target electric drive; The electric drive sound of the target electric drive after the harmonic injection processing is acquired to obtain the enhanced electric drive sound.

5. The method according to claim 1, characterized in that The step of inputting the enhanced electric drive sound into an acoustic evaluation model to obtain a prediction score corresponding to the enhanced electric drive sound includes: Extracting objective parameters of the enhanced electric drive sound to obtain first objective parameters corresponding to the enhanced electric drive sound; The first objective parameter is input into the acoustic evaluation model to obtain the predicted score corresponding to the enhanced electric drive sound.

6. The method according to claim 1, characterized in that The acoustic evaluation model is constructed in advance in the following manner: Acquiring an original electric drive sound sample corresponding to the sample electric drive; and performing acoustic enhancement processing on the original electric drive sound sample according to the enhancement strategy to obtain an enhanced electric drive sound sample corresponding to the original electric drive sound sample; Performing expert scoring on the original electric drive sound sample to obtain a first expert score corresponding to the original electric drive sound sample; and performing expert scoring on the enhanced electric drive sound sample to obtain a second expert score corresponding to the enhanced electric drive sound sample; In response to the second expert score being greater than the first expert score, the enhanced electric drive sound is processed again using a next enhancement strategy, and the step of performing expert scoring on the enhanced electric drive sound sample to obtain a second expert score corresponding to the enhanced electric drive sound sample is repeated until the second expert score meets the requirement; When the second expert score meets the requirements, the corresponding final enhanced electric drive sound sample is obtained, and the acoustic evaluation model is constructed using the second expert score corresponding to the final enhanced electric drive sound sample.

7. The method according to claim 6, characterized in that The method of constructing the acoustic evaluation model by using the second expert score corresponding to the final enhanced electric drive sound sample includes: Acquiring a second objective parameter corresponding to the final enhanced electric-driven sound sample; The acoustic evaluation model is constructed with the second objective parameter as input and the second expert score as output.

8. The method according to claim 7, characterized in that The obtaining of the second objective parameter corresponding to the final enhanced electric-driven sound sample comprises: Acquiring initial objective parameters corresponding to the final enhanced electric drive sound sample, wherein the initial objective parameters include order distribution, frequency balance, and psychoacoustic parameters, wherein the psychoacoustic parameters include loudness, roughness, sharpness, and jitter; A principal component extraction operation is performed on the initial objective parameter to obtain the second objective parameter.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory connected to the processor, wherein: The memory stores program instructions; The processor is configured to execute program instructions stored in the memory to implement the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed, the method according to any one of claims 1 to 8 is implemented.

Images