CN118038891A - Method and device for evaluating quality of car window lifting sound, computer equipment and storage medium - Google Patents
Method and device for evaluating quality of car window lifting sound, computer equipment and storage medium Download PDFInfo
- Publication number
- CN118038891A CN118038891A CN202211415721.XA CN202211415721A CN118038891A CN 118038891 A CN118038891 A CN 118038891A CN 202211415721 A CN202211415721 A CN 202211415721A CN 118038891 A CN118038891 A CN 118038891A
- Authority
- CN
- China
- Prior art keywords
- sound
- steady
- quality
- loudness
- transient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 230000001052 transient effect Effects 0.000 claims abstract description 116
- 230000005236 sound signal Effects 0.000 claims abstract description 102
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000013441 quality evaluation Methods 0.000 claims abstract description 29
- 238000000605 extraction Methods 0.000 claims description 7
- 238000005520 cutting process Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 abstract description 45
- 238000012360 testing method Methods 0.000 description 21
- 239000005357 flat glass Substances 0.000 description 11
- 230000000875 corresponding effect Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 239000011521 glass Substances 0.000 description 6
- 238000012417 linear regression Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000012356 Product development Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000001303 quality assessment method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to the field of sound quality evaluation, and discloses a vehicle window lifting sound quality evaluation method, a device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring a car window lifting sound signal; extracting transient impact sound characteristics, steady motor noise characteristics and steady friction sound characteristics from a car window lifting sound signal; determining the transient impact sound quality of the window lifting sound signal according to the transient impact sound characteristics; determining the steady motor noise quality of the window lifting sound signal according to the steady motor noise characteristics; determining the steady friction sound quality of the window lifting sound signal according to the steady friction sound characteristics; and processing the transient impact sound quality, the steady motor noise quality and the steady friction sound quality through the overall sound quality evaluation model to obtain the overall sound quality of the car window lifting sound signal. The invention can improve the evaluation efficiency and the evaluation quality of the lifting sound of the vehicle window.
Description
Technical Field
The present invention relates to the field of acoustic quality evaluation, and in particular, to a method and apparatus for evaluating the quality of lifting and lowering car window, a computer device, and a storage medium.
Background
With the development of the automobile industry, the requirements of users on the comfort of vehicles are continuously improved. Vehicle comfort is often related to vehicle NVH performance (Noise, vibration, harshness, noise, vibration, and harshness). At present, the requirements of users on NVH performance are not only concerned with the noise sound pressure level, but also pursue the quality of the sound of the whole car. Moreover, compared with the traditional fuel oil vehicle, the interior of the electric vehicle is more silent, and the lifting noise of the electric window glass is very easy to cause uncomfortable feeling of a user.
In order to achieve improvement of the quality of the power window lifting sound, it is necessary to clearly evaluate how the quality of the glass lifting sound is perceived and how subjective feeling is objectively quantified. At present, the evaluation of the lifting sound of the power window of a vehicle is mostly limited to the evaluation of the sound pressure level of an objective index, the quality sense cannot be evaluated only by the total sound pressure level, and the situation that the sound pressure level is not large but the subjective quality sense is poor may exist. In addition, the sound pressure level of the sound signal is only judged on the overall sound level, and the specific subdivision dimension cannot be positioned, so that the sound quality optimization design is not guided.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, and a storage medium for evaluating the quality of a car window lift, so as to improve the efficiency and quality of evaluating the quality of the car window lift.
A vehicle window lifting sound quality evaluation method comprises the following steps:
Acquiring a car window lifting sound signal;
extracting transient impact sound characteristics, steady motor noise characteristics and steady friction sound characteristics from the window lift sound signals;
Determining the transient impact sound quality of the window lifting sound signal according to the transient impact sound characteristics; determining the steady motor noise quality of the window lifting acoustic signal according to the steady motor noise characteristics; determining the steady friction sound quality of the window lifting sound signal according to the steady friction sound characteristics;
And processing the transient impact sound quality, the steady motor noise quality and the steady friction sound quality through a total sound quality evaluation model to obtain the total sound quality of the vehicle window lifting sound signal.
A vehicle window lift sound quality evaluation device, comprising:
the sound signal acquisition module is used for acquiring a car window lifting sound signal;
The feature extraction module is used for extracting transient impact sound features, steady motor noise features and steady friction sound features from the car window lifting sound signals;
The sound quality determining module is used for determining the transient impact sound quality of the window lifting sound signal according to the transient impact sound characteristics; determining the steady motor noise quality of the window lifting acoustic signal according to the steady motor noise characteristics; determining the steady friction sound quality of the window lifting sound signal according to the steady friction sound characteristics;
And the total sound quality module is used for processing the transient impact sound quality, the steady motor noise quality and the steady friction sound quality through a total sound quality evaluation model to obtain the total sound quality of the vehicle window lifting sound signal.
A computer device comprising a memory, a processor and computer readable instructions stored in the memory and executable on the processor, the processor implementing the above method of evaluating window lift quality when executing the computer readable instructions.
One or more readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform a method of vehicle window lift quality assessment as described above.
According to the vehicle window lifting sound quality evaluation method, the vehicle window lifting sound quality evaluation device, the computer equipment and the storage medium, the transient impact sound characteristics, the steady motor noise characteristics and the steady friction sound characteristics are extracted from the vehicle window lifting sound signals, and then the three sound characteristics are evaluated respectively to obtain the sound quality of three sounds, so that the sound dimension needing to be improved in quality can be positioned, and the optimization design of the vehicle window sound quality is guided; the three sound qualities are combined to obtain the overall sound quality, so that the overall sound quality of the lifting of the electric vehicle window glass is effectively predicted, subjective evaluation tests can be replaced, and the cost of manpower, material resources and product development period is greatly reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for evaluating the quality of a window lift in accordance with an embodiment of the present invention;
fig. 2 is a schematic diagram of window-raising and lowering acoustic signals acquired by a digital binaural artificial head in an embodiment of the invention;
FIG. 3 is a plot of the loudness of a window lift acoustic signal in an embodiment of the present invention;
FIG. 4 is a schematic view of a device for evaluating quality of a car window lift according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a computer device in accordance with an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In one embodiment, as shown in fig. 1, there is provided a method for evaluating the quality of a window regulator sound, including the following steps S10 to S40.
S10, acquiring a car window lifting sound signal.
The window regulator acoustic signal may be an in-vehicle noise signal during a power window regulator operation of the vehicle. The window lift acoustic signal includes acoustic information of the complete stroke of the glass lift.
The window lifting sound signals can be acquired through the digital double-ear artificial head and the data acquisition system. As shown in fig. 2, the measuring points are arranged at the double-ear positions of a driver (digital double-ear artificial head), the front and back of a seat can be adjusted to the middle position, the upper and lower of the seat can be adjusted to the vertical ground according to the noise test standard in an automobile of national standard GB/T18697-2002. The distance between the digital binaural artificial head and the seat cushion may be 0.7m. The sampling frequency of the data acquisition system can be set to be 44.1kHz, and the test data is in a range of 2/3. The test stroke comprises the whole window glass lifting operation process, the test process ensures that no other noise interference exists, and meanwhile, the reliability of the tested acoustic signal data is ensured.
S20, extracting transient impact sound characteristics, steady motor noise characteristics and steady friction sound characteristics from the car window lifting sound signals.
It is understood that the transient impact sound characteristic, the steady motor noise characteristic, and the steady friction sound characteristic may be three sound characteristics that have a large influence on the overall sound quality, which are determined based on the subjective evaluation test results. And evaluating the car window lifting sound signal through a subjective evaluation test to generate a subjective evaluation test result.
In one example, in preparation for subjective evaluation testing, the playback system frequency response needs to be corrected to ensure that the playback acoustic signal is substantially consistent with the glass-run acoustic signal heard by the real vehicle. Before subjective evaluation test, subjective evaluation personnel should be trained in listening test to ensure that the evaluation personnel evaluate how to evaluate the glass-run noise. And in the subjective evaluation test process, no other noise interference is ensured, and the evaluation time is avoided to be too long. And (3) preprocessing and checking the evaluation result, and eliminating obvious outlier data. The validity of subjective evaluation results is ensured by means of a glabros test and the like.
Subjective evaluation subdivision dimensions can be divided according to noise characteristics in the window glass lifting process. In some examples, three sounds that have the greatest impact on the overall sound quality may be picked by examining a plurality of pre-enumerated evaluation dimensions. These three sounds include transient impact sounds, steady motor noise, and steady friction sounds.
Transient impact sounds are characterized by the transient impact sounds at the start/end of a power window, with a focus on the sound level and energy decay time. And the noise characteristic of the steady motor is the characteristic of motor noise in the glass lifting steady operation stage. The steady-state motor noise is mainly based on the motor fundamental frequency and the harmonic frequency thereof, and the salient degree of the motor harmonic frequency noise and the fluctuation sensation of the tone are judged in an important way. The characteristic of the steady-state friction sound is the characteristic of the steady-state friction sound. The steady friction sound is the sound of the water cutting friction between the glass and the car door in the process of lifting the glass and is the sound of a wide frequency band. The steady-state friction sound characteristics are used for judging the overall magnitude and definition of sound.
S30, determining the transient impact sound quality of the window lifting sound signal according to the transient impact sound characteristics; determining the steady motor noise quality of the window lifting acoustic signal according to the steady motor noise characteristics; and determining the steady friction sound quality of the window lifting sound signal according to the steady friction sound characteristics.
It is understood that the respective sound quality can be calculated from the sound characteristics of the various sounds, respectively. Objective parameters related to sound quality are many, such as sharpness, roughness, loudness, jitter, tone scheduling, speech intelligibility, etc. The objective parameters corresponding to the three sounds are obtained by analyzing according to the characteristics of the glass lifting noise and the subjective and objective correlation, and the objective parameters strongly correlated with the subjective evaluation are selected and determined finally. A regression model (acoustic quality of a certain sound) between the acoustic quality and the acoustic features may be constructed, and regression coefficients of the regression model may be calculated from a plurality of sets of acoustic samples. The regression model is established by verifying the fitting precision of the model through a regression coefficient R 2. If R 2 is more than or equal to 0.8, the regression model has better fitting precision and can be used for predicting sound quality.
And S40, processing the transient impact sound quality, the steady motor noise quality and the steady friction sound quality through a total sound quality evaluation model to obtain the total sound quality of the vehicle window lifting sound signal.
It is understandably possible to calculate the overall sound quality from the sound quality of the various sounds, respectively. A regression model (overall sound quality) between the overall sound quality and the sound quality may be constructed, and regression coefficients of the regression model may be calculated from the plurality of sets of sound samples. When the regression coefficient R 2 of the regression model meets the fitting requirement, the regression model can be used for calculating the total sound quality of other window lifting sound signals.
In one example, the overall acoustic quality assessment model includes:
SQ＝D1×SQ1+D2×SQ2+D3×SQ3+D4
Where SQ represents the overall sound quality;
SQ 1 is the transient impact sound quality;
SQ 2 is the steady state motor noise quality;
SQ 3 is the steady state motor noise quality;
D 1、D2、D3 and D 4 are constant coefficients.
According to the embodiment, the transient impact sound characteristics, the steady motor noise characteristics and the steady friction sound characteristics are extracted from the car window lifting sound signals, and then the three sound characteristics are evaluated respectively to obtain sound quality of three sounds, so that sound dimension which needs to be improved in quality can be positioned, and the optimal design of car window sound quality is guided; the three sound qualities are combined to obtain the overall sound quality, so that the overall sound quality of the lifting of the electric vehicle window glass is effectively predicted, subjective evaluation tests can be replaced, and the cost of manpower, material resources and product development period is greatly reduced.
Optionally, the transient impulse sound features include a transient loudness peak and an decay delay;
step S30, determining the transient impact sound quality of the window lift sound signal according to the transient impact sound feature, including:
S301, processing the transient loudness peak value and the attenuation delay through a transient impulse sound quality model to generate the transient impulse sound quality; the transient impulse sound quality model includes:
SQ1＝A1×LMax+A2×TDelay+A3
Wherein SQ 1 is the transient impact sound quality;
L Max is the transient loudness peak;
T Delay is the decay delay;
a 1、A2 and a 3 are constant coefficients.
Understandably, transient impact sounds focus on sound level and energy decay time. Thus, transient impulse sound quality may be quantified using transient loudness peaks and decay delays. The transient loudness peak value refers to the maximum loudness of the transient impact sound, and can reflect the degree of the ringing of the transient impact sound; the decay time may reflect the energy decay time.
The transient impulse quality model is a linear regression model constructed based on subjective evaluation scores of transient impulses and two transient impulse characteristics. The transient impulse sound characteristics of a plurality of samples and the corresponding subjective evaluation scores are substituted into the transient impulse sound quality model, and the model coefficients (A 1、A2 and A 3) of the transient impulse sound quality model can be obtained through fitting calculation. And substituting the transient impact sound characteristics of the test set into the transient impact sound quality model, calculating corresponding SQ 1, comparing SQ 1 with the actual subjective evaluation score, and if the difference between the SQ 1 and the actual subjective evaluation score is smaller, indicating that the transient impact sound quality model has better prediction capability and the obtained transient impact sound quality is high in accuracy.
In this embodiment, the subjective evaluation score of the transient impact sound, that is, the quality of the transient impact sound, may be calculated by two objective parameters, that is, the transient loudness peak value and the decay delay.
Optionally, step S20, that is, extracting a transient impact sound feature from the window lift sound signal, includes:
s201, processing the vehicle window lifting sound signal through a preset loudness algorithm to generate a loudness change curve;
s202, determining the maximum loudness value in the loudness variation curve as the transient loudness peak value;
S203, determining the attenuation delay according to the time difference between the first moment and the second moment; the first moment is the moment before and nearest to the transient loudness peak value, and the loudness value is the first loudness; the second moment is a moment after and nearest to the transient loudness peak value, where the loudness value is the second loudness.
It is understood that the preset loudness algorithm may be set according to actual needs, for example, the international standard ISO 532 loudness algorithm may be selected. After processing by a preset loudness algorithm, a loudness change curve can be generated. As shown in fig. 3, fig. 3 is a loudness variation curve of the window regulator sound signal. On the loudness variation curve, there are multiple transient impact sounds (3 in fig. 3). The transient loudness peak is the maximum value of the transient impulse (the peak of the 3 rd transient impulse in fig. 3), that is, L Max =max (L), and L is the time-domain loudness. The attenuation delay can be defined according to actual needs, for example, the attenuation delay can be a time difference between a first moment and a second moment, wherein the first moment is a moment before and nearest to the transient loudness peak value, and the loudness value is a first loudness; the second moment is the moment after and nearest to the transient loudness peak, and the loudness value is the second loudness, that is, T Delay＝T2-T1,TDelay is the decay delay, T 2 is the second moment, and T 1 is the first moment. In an example, the first loudness may be 10 sones (loudness units) and the second loudness may be 12 sones.
The embodiment is used for extracting two transient impact sound characteristics, namely a transient loudness peak value and an attenuation delay.
Optionally, the stationary motor noise characteristics include a pitch schedule and a jitter;
step S30, namely determining the steady motor noise quality of the window lifting acoustic signal according to the steady motor noise feature, including:
S302, processing the sound schedule and the jitter degree through a steady motor noise quality model to generate the steady motor noise quality; the transient impulse sound quality model includes:
SQ2＝B1×Tonality+B2×Fluction+B3
Wherein SQ 2 is the steady state motor noise quality;
tonality is the tone schedule;
Fluction is the jitter;
B 1、B2 and B 3 are constant coefficients.
Understandably, the steady motor noise is motor noise in the window glass lifting steady operation stage, and is mainly based on the fundamental frequency and harmonic frequency of the motor; the emphasis is on judging the salient degree of harmonic noise of the motor and the fluctuation sense of the tone. Thus, steady state motor noise can be quantified using tone scheduling and jitter. The steady-state operation section sound signal can be cut out from the car window lifting sound signal, then the steady-state operation section sound signal is analyzed by using sound quality parameter analysis software, steady-state operation section sound scheduling and steady-state operation section jitter are obtained, and arithmetic average values of the steady-state operation section sound scheduling and the steady-state operation section jitter are calculated, namely the sound scheduling and the jitter are obtained.
The steady-state motor noise quality model is a linear regression model constructed based on subjective evaluation scores of steady-state motor noise and two motor noise acoustic features. The steady-state motor noise characteristics of a plurality of samples and the corresponding subjective evaluation scores are substituted into a steady-state motor noise quality model, and model coefficients (B 1、B2 and B 3) of the steady-state motor noise quality model can be obtained through fitting calculation. And substituting the noise characteristics of the steady-state motor of the test set into a steady-state motor noise quality model, calculating corresponding SQ 2, comparing SQ 2 with the actual measured subjective evaluation score, and if the difference between the SQ 2 and the actual measured subjective evaluation score is smaller, indicating that the steady-state motor noise quality model has better prediction capability and the obtained steady-state motor noise quality is high in accuracy.
According to the embodiment, the subjective evaluation score of the noise of the steady motor, namely the quality of the noise of the steady motor, can be calculated through two objective parameters, namely the sound scheduling and the jitter degree.
Optionally, step S20, that is, extracting the steady-state motor noise feature from the window lift acoustic signal, includes:
S204, cutting off a steady-state operation section sound signal from the car window lifting sound signal;
s205, analyzing the steady operation section sound signal to obtain steady operation section sound scheduling and steady operation section jitter;
s206, calculating an average value of the steady operation segment tone scheduling to obtain the tone degree; and calculating the average value of the jitter of the steady-state operation section to obtain the jitter.
It is understood that the steady-state operating segment sound signal may be truncated from the window lift sound signal. In the example of fig. 3, the steady-state operating segment acoustic signal includes two segments of steady-state operating travel acoustic signals. Inputting the cut steady-state operation section sound signal into sound characteristic analysis software, calculating steady-state operation section sound scheduling and steady-state operation section jitter, and calculating arithmetic average value to obtain sound scheduling and jitter.
The embodiment is used for extracting noise characteristics of two stable motors, namely sound scheduling and jitter degree.
Optionally, the stationary frictional sound features include average loudness and speech intelligibility index;
Step S30, namely determining the steady-state frictional sound quality of the window lift sound signal according to the steady-state frictional sound feature, including:
S303, processing the average loudness and the voice definition index through a steady-state friction sound quality model to generate the steady-state friction sound quality; the steady-state frictional sound quality model includes:
SQ3＝C1×LAVG+C2×AI+C3
Wherein SQ 3 is the steady state frictional sound quality;
l AVG is the average loudness;
AI is the speech intelligibility index;
C 1、C2 and C 3 are constant coefficients.
Understandably, the steady friction sound is the sound of the water cutting friction of the window glass and the door in the stable operation stage of the lifting of the window glass, and is the sound of a wide frequency band; the overall magnitude and definition of the sound are evaluated with emphasis. Thus, steady-state fricatives may be quantified using average loudness (L AVG) and speech intelligibility index (AI). The method comprises the steps that a steady-state operation section sound signal can be cut out from a car window lifting sound signal, and the steady-state operation section sound signal is processed through a preset loudness algorithm to obtain steady-state operation section loudness data; and processing the steady-state operation section sound signal through a preset definition algorithm to obtain a voice definition index, and calculating the average value of the steady-state operation section loudness data to obtain the average loudness.
The steady-state frictional sound quality model is a linear regression model constructed based on subjective evaluation scores of steady-state frictional sound and two steady-state frictional sound features. The steady-state frictional sound characteristics of a plurality of samples and corresponding subjective evaluation scores are substituted into a steady-state frictional sound quality model, and model coefficients (C 1、C2 and C 3) of the steady-state frictional sound quality model can be obtained through fitting calculation. And substituting the steady-state friction sound characteristics of the test set into a steady-state friction sound quality model, calculating corresponding SQ 3, comparing SQ 3 with the actual measured subjective evaluation score, and if the difference between the SQ 3 and the actual measured subjective evaluation score is smaller, indicating that the steady-state friction sound quality model has better prediction capability and the obtained steady-state friction sound quality is high in accuracy.
In this embodiment, the subjective evaluation score of the steady frictional sound, that is, the steady frictional sound quality, may be calculated by using two objective parameters, that is, the average loudness and the speech clarity index.
Optionally, step S20, that is, extracting the stationary friction sound feature from the window lift sound signal, includes:
S207, cutting off a steady-state operation section sound signal from the car window lifting sound signal;
S208, processing the steady-state operation section sound signal through a preset loudness algorithm to obtain steady-state operation section loudness data; processing the steady-state operation section sound signal through a preset definition algorithm to obtain the voice definition index;
s209, calculating the average value of the loudness data of the steady-state running segments to obtain the average loudness.
It is understood that the steady-state operating segment sound signal may be truncated from the window lift sound signal. In the example of fig. 3, the steady-state operating segment acoustic signal includes two segments of steady-state operating travel acoustic signals. Inputting the cut steady-state operation section sound signals into sound characteristic analysis software, calculating steady-state operation section loudness data and a voice definition index, and then calculating an arithmetic average value to obtain average loudness. Here, the speech intelligibility index may be calculated using the national standard GB/T1548 speech intelligibility index algorithm.
The embodiment is used for extracting two stable frictional sound features, namely average loudness and voice definition index.
In an application example, noise in the power window glass lifting operation process of the 20 trolleys is respectively collected through the digital double-ear manual head, the validity of the data is checked, and a window lifting sound signal evaluation sample with the same duration is intercepted from the noise signal.
And (3) organizing a subjective evaluation test based on a semantic subdivision method, finishing the total score of the lifting sound quality of the window glass and the subjective scores of 3 sub-dimensions, obtaining subjective evaluation results, and recording the subjective evaluation results in a subjective evaluation table shown in table 1. And after the subjective evaluation results are subjected to data validity rejection and inspection, normalizing to obtain 20 groups of subjective evaluation results of the lifting sound quality of the window glass.
Table 1 subjective evaluation table of car window sound quality
The transient loudness peak value L Max, the decay delay T Delay, the pitch (tonality), the jitter (fluction), the average loudness (L AVG) and the speech intelligibility index (AI) can be obtained by processing the window lift acoustic signal evaluation samples by acoustic feature analysis software, respectively. All acoustic features are summarized in table 2.
Table 2 acoustic signature of window lift acoustic signal
16 Of the 20 acoustic samples are randomly selected as a sample set for establishing a regression model, and 4 test sets for testing the accuracy of establishing a prediction model are left. And carrying out subjective/objective consistency analysis on 16 sample data, carrying out correlation analysis of subjective scores and corresponding acoustic features in each dimension by utilizing analysis software, and establishing a subjective/objective regression model if the correlation coefficient is high.
Establishing a multiple linear regression model of subjective scores and objective parameters, and respectively establishing objective prediction models (a transient impact sound quality model, a steady motor noise quality model and a steady friction sound quality model) of three-dimensional subjective scores by taking the subjective scores in the table 1 as dependent variables and the corresponding objective parameters in the table 2 as independent variables; and then, taking the overall score as a dependent variable and each sub-dimension score as an independent variable, and establishing an overall sound quality evaluation model. And finally, verifying the fitting precision of the model through a regression coefficient R 2 of the regression model, wherein R 2 is more than or equal to 0.8, and the fitting precision of the model is high.
Finally, the acoustic characteristics of the four acoustic samples in the test set are brought into the model, the sub-dimensional acoustic quality SQ 1、SQ2、SQ3 and the total acoustic quality SQ are respectively obtained, the acoustic quality score output by the model is compared with the actual measured subjective evaluation, and the accuracy of the regression model is verified.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
In one embodiment, a window regulator quality evaluation device is provided, which corresponds to the window regulator quality evaluation method in the above embodiment one by one. As shown in fig. 4, the window regulator sound quality evaluation device includes an acoustic signal acquisition module 10, a feature extraction module 20, a sound quality determination module 30, and an overall sound quality module 40. The functional modules are described in detail as follows:
The sound signal acquisition module 10 is used for acquiring a car window lifting sound signal;
a feature extraction module 20 for extracting transient impact sound features, steady motor noise features, and steady friction sound features from the window lift sound signal;
A determining sound quality module 30 for determining a transient impact sound quality of the window lift sound signal according to the transient impact sound characteristic; determining the steady motor noise quality of the window lifting acoustic signal according to the steady motor noise characteristics; determining the steady friction sound quality of the window lifting sound signal according to the steady friction sound characteristics;
And the total sound quality module 40 is configured to process the transient impact sound quality, the steady motor noise quality and the steady friction sound quality through a total sound quality evaluation model to obtain a total sound quality of the window lifting sound signal.
Optionally, the transient impulse sound features include a transient loudness peak and an decay delay;
The determine sound quality module 30 includes:
The transient impulse sound quality generating unit is used for processing the transient loudness peak value and the attenuation delay through a transient impulse sound quality model to generate the transient impulse sound quality; the transient impulse sound quality model includes:
SQ1＝A1×LMax+A2×TDelay+A3
Wherein SQ 1 is the transient impact sound quality;
L Max is the transient loudness peak;
T Delay is the decay delay;
a 1、A2 and a 3 are constant coefficients.
Optionally, the feature extraction module 20 includes:
The loudness change curve generating unit is used for processing the window lifting sound signal through a preset loudness algorithm to generate a loudness change curve;
A transient loudness peak determining unit, configured to determine a loudness maximum value in the loudness variation curve as the transient loudness peak;
The attenuation delay unit is used for determining the attenuation delay according to the time difference between the first moment and the second moment; the first moment is the moment before and nearest to the transient loudness peak value, and the loudness value is the first loudness; the second moment is a moment after and nearest to the transient loudness peak value, where the loudness value is the second loudness.
Optionally, the stationary motor noise characteristics include a pitch schedule and a jitter;
The determine sound quality module 30 includes:
generating a steady-state motor noise quality unit, which is used for processing the sound schedule and the jitter degree through a steady-state motor noise quality model to generate the steady-state motor noise quality; the transient impulse sound quality model includes:
SQ2＝B1×Tonality+B2×Fluction+B3
Wherein SQ 2 is the steady state motor noise quality;
tonality is the tone schedule;
Fluction is the jitter;
B 1、B2 and B 3 are constant coefficients.
Optionally, the feature extraction module 20 includes:
The steady-state operation section sound signal extracting unit is used for extracting a steady-state operation section sound signal from the car window lifting sound signal;
The analysis sound scheduling and jitter degree unit is used for analyzing the steady operation section sound signal to obtain steady operation section sound scheduling and steady operation section jitter degree;
a tone scheduling and jitter degree generating unit for calculating the average value of the steady operation section tone scheduling to obtain the tone degree; and calculating the average value of the jitter of the steady-state operation section to obtain the jitter.
Optionally, the stationary frictional sound features include average loudness and speech intelligibility index;
The determine sound quality module 30 includes:
generating a steady-state frictional sound quality unit, which is used for processing the average loudness and the voice definition index through a steady-state frictional sound quality model to generate the steady-state frictional sound quality; the steady-state frictional sound quality model includes:
SQ3＝C1×LAVG+C2×AI+C3
Wherein SQ 3 is the steady state frictional sound quality;
l AVG is the average loudness;
AI is the speech intelligibility index;
C 1、C2 and C 3 are constant coefficients.
Optionally, the feature extraction module 20 includes:
The steady-state operation section sound signal extracting unit is used for extracting a steady-state operation section sound signal from the car window lifting sound signal;
the voice definition index unit is used for processing the steady-state operation section sound signal through a preset loudness algorithm to obtain steady-state operation section loudness data; processing the steady-state operation section sound signal through a preset definition algorithm to obtain the voice definition index;
and the average loudness obtaining unit is used for calculating the average value of the steady-state running section loudness data and obtaining the average loudness.
The specific limitation of the device for evaluating the quality of the lifting sound of the vehicle window can be referred to as the limitation of the method for evaluating the quality of the lifting sound of the vehicle window, and will not be described in detail herein. The respective modules in the above-described window regulator sound quality evaluation device may be realized in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a readable storage medium, an internal memory. The readable storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the execution of an operating system and computer-readable instructions in a readable storage medium. The database of the computer device is used for storing data related to the vehicle window lifting sound quality evaluation method. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer readable instructions when executed by the processor implement a method of evaluating vehicle window lift quality. The readable storage medium provided by the present embodiment includes a nonvolatile readable storage medium and a volatile readable storage medium.
In one embodiment, a computer device is provided that includes a memory, a processor, and computer readable instructions stored on the memory and executable on the processor, when executing the computer readable instructions, performing the steps of:
Acquiring a car window lifting sound signal;
extracting transient impact sound characteristics, steady motor noise characteristics and steady friction sound characteristics from the window lift sound signals;
Determining the transient impact sound quality of the window lifting sound signal according to the transient impact sound characteristics; determining the steady motor noise quality of the window lifting acoustic signal according to the steady motor noise characteristics; determining the steady friction sound quality of the window lifting sound signal according to the steady friction sound characteristics;
And processing the transient impact sound quality, the steady motor noise quality and the steady friction sound quality through a total sound quality evaluation model to obtain the total sound quality of the vehicle window lifting sound signal.
In one embodiment, one or more computer-readable storage media are provided having computer-readable instructions stored thereon, the readable storage media provided by the present embodiment including non-volatile readable storage media and volatile readable storage media. The readable storage medium has stored thereon computer readable instructions which when executed by one or more processors perform the steps of:
Acquiring a car window lifting sound signal;
extracting transient impact sound characteristics, steady motor noise characteristics and steady friction sound characteristics from the window lift sound signals;
determining the transient impact sound quality of the window lifting sound signal according to the transient impact sound characteristics;
Determining the steady motor noise quality of the window lifting acoustic signal according to the steady motor noise characteristics;
determining the steady friction sound quality of the window lifting sound signal according to the steady friction sound characteristics;
And processing the transient impact sound quality, the steady motor noise quality and the steady friction sound quality through a total sound quality evaluation model to obtain the total sound quality of the vehicle window lifting sound signal.
Those skilled in the art will appreciate that implementing all or part of the above described embodiment methods may be accomplished by instructing the associated hardware by computer readable instructions stored on a non-volatile readable storage medium or a volatile readable storage medium, which when executed may comprise the above described embodiment methods. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (10)
1. The method for evaluating the quality of the lifting sound of the vehicle window is characterized by comprising the following steps of:
Acquiring a car window lifting sound signal;
extracting transient impact sound characteristics, steady motor noise characteristics and steady friction sound characteristics from the window lift sound signals;
Determining the transient impact sound quality of the window lifting sound signal according to the transient impact sound characteristics; determining the steady motor noise quality of the window lifting acoustic signal according to the steady motor noise characteristics; determining the steady friction sound quality of the window lifting sound signal according to the steady friction sound characteristics;
And processing the transient impact sound quality, the steady motor noise quality and the steady friction sound quality through a total sound quality evaluation model to obtain the total sound quality of the vehicle window lifting sound signal.
2. The vehicle window lift quality evaluation method of claim 1, wherein the transient impact sound features include a transient loudness peak and an attenuation delay;
the determining the transient impact sound quality of the window lift sound signal according to the transient impact sound characteristics comprises the following steps:
Processing the transient loudness peak value and the attenuation delay through a transient impulse sound quality model to generate the transient impulse sound quality; the transient impulse sound quality model includes:
SQ1＝A1×LMax+A2×TDelay+A3
Wherein SQ 1 is the transient impact sound quality;
L Max is the transient loudness peak;
T Delay is the decay delay;
a 1、A2 and a 3 are constant coefficients.
3. The vehicle window regulator quality evaluation method according to claim 2, wherein the extracting transient impact sound features from the vehicle window regulator sound signal includes:
processing the window lifting sound signal through a preset loudness algorithm to generate a loudness change curve;
determining a loudness maximum in the loudness variation curve as the transient loudness peak;
determining the decay time delay according to the time difference between the first time and the second time; the first moment is the moment before and nearest to the transient loudness peak value, and the loudness value is the first loudness; the second moment is a moment after and nearest to the transient loudness peak value, where the loudness value is the second loudness.
4. The vehicle window lift quality evaluation method of claim 1, wherein the stationary motor noise signature includes a pitch schedule and a jitter;
the determining the steady motor noise quality of the window lift acoustic signal according to the steady motor noise characteristics includes:
processing the sound schedule and the jitter degree through a steady-state motor noise quality model to generate the steady-state motor noise quality; the transient impulse sound quality model includes:
SQ2＝Bi×Tonality+B2×Fluction+B3
Wherein SQ 2 is the steady state motor noise quality;
tonality is the tone schedule;
Fluction is the jitter;
B 1、B2 and B 3 are constant coefficients.
5. The vehicle window lift quality evaluation method of claim 4, wherein the extracting steady-state motor noise features from the vehicle window lift acoustic signal comprises:
Cutting off a steady-state operation section sound signal from the car window lifting sound signal;
Analyzing the steady operation section sound signal to obtain steady operation section sound scheduling and steady operation section jitter;
Calculating the average value of the steady operation segment voice schedule to obtain the tone degree; and calculating the average value of the jitter of the steady-state operation section to obtain the jitter.
6. The vehicle window lift quality evaluation method of claim 1, wherein the stationary frictional sound characteristics include average loudness and a speech intelligibility index;
the determining the steady-state frictional sound quality of the window lift acoustic signal according to the steady-state frictional sound characteristics includes:
processing the average loudness and the voice definition index through a steady frictional sound quality model to generate the steady frictional sound quality; the steady-state frictional sound quality model includes:
SQ3＝C1×LAVG+C2×AI+C3
Wherein SQ 3 is the steady state frictional sound quality;
l AVG is the average loudness;
AI is the speech intelligibility index;
C 1、C2 and C 3 are constant coefficients.
7. The vehicle window lift quality evaluation method of claim 6, wherein the extracting stationary frictional acoustic features from the vehicle window lift acoustic signal comprises:
Cutting off a steady-state operation section sound signal from the car window lifting sound signal;
Processing the steady-state operation section sound signal through a preset loudness algorithm to obtain steady-state operation section loudness data; processing the steady-state operation section sound signal through a preset definition algorithm to obtain the voice definition index;
and calculating the average value of the loudness data of the steady-state running segment to obtain the average loudness.
8. A vehicle window regulator sound quality evaluation device, comprising:
the sound signal acquisition module is used for acquiring a car window lifting sound signal;
The feature extraction module is used for extracting transient impact sound features, steady motor noise features and steady friction sound features from the car window lifting sound signals;
The sound quality determining module is used for determining the transient impact sound quality of the window lifting sound signal according to the transient impact sound characteristics; determining the steady motor noise quality of the window lifting acoustic signal according to the steady motor noise characteristics; determining the steady friction sound quality of the window lifting sound signal according to the steady friction sound characteristics;
And the total sound quality module is used for processing the transient impact sound quality, the steady motor noise quality and the steady friction sound quality through a total sound quality evaluation model to obtain the total sound quality of the vehicle window lifting sound signal.
9. A computer device comprising a memory, a processor and computer readable instructions stored in the memory and executable on the processor, wherein the processor, when executing the computer readable instructions, implements the method of evaluating vehicle window lift quality as claimed in any one of claims 1 to 7.
10. One or more readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the method of evaluating vehicle window lift quality of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211415721.XA CN118038891A (en) | 2022-11-11 | 2022-11-11 | Method and device for evaluating quality of car window lifting sound, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211415721.XA CN118038891A (en) | 2022-11-11 | 2022-11-11 | Method and device for evaluating quality of car window lifting sound, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118038891A true CN118038891A (en) | 2024-05-14 |
Family
ID=90999274
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211415721.XA Pending CN118038891A (en) | 2022-11-11 | 2022-11-11 | Method and device for evaluating quality of car window lifting sound, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118038891A (en) |
-
2022
- 2022-11-11 CN CN202211415721.XA patent/CN118038891A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109451188B (en) | Method and device for differential self-help response, computer equipment and storage medium | |
| AU2016201436A1 (en) | Emotional and/or psychiatric state detection | |
| JP5542206B2 (en) | Method and system for determining perceptual quality of an audio system | |
| CN111311327A (en) | Service evaluation method, device, equipment and storage medium based on artificial intelligence | |
| Dubey et al. | Non-intrusive speech quality assessment using several combinations of auditory features | |
| KR101330923B1 (en) | Method for sound quality analysis of vehicle noise using gammatone filter and apparatus thereof | |
| CN107123427A (en) | A kind of method and device for determining sound quality | |
| CN114387987A (en) | Method and device for measuring ecological noise source, terminal and storage medium | |
| CN112133289B (en) | Voiceprint identification model training method, voiceprint identification device, voiceprint identification equipment and voiceprint identification medium | |
| CN109600697A (en) | The outer playback matter of terminal determines method and device | |
| CN118038891A (en) | Method and device for evaluating quality of car window lifting sound, computer equipment and storage medium | |
| CN115683318A (en) | Method for evaluating sound quality and determining limit value of driving motor system | |
| CN113963719A (en) | Deep learning-based sound classification method and apparatus, storage medium, and computer | |
| CN116230018A (en) | Synthetic voice quality evaluation method for voice synthesis system | |
| CN115544745A (en) | Feature extraction method for objectively evaluating sound quality of electric drive assembly | |
| Perera et al. | Automatic Evaluation Software for Contact Centre Agents’ voice Handling Performance | |
| CN110335616A (en) | Voice data noise-reduction method, device, computer equipment and storage medium | |
| Tan et al. | Evaluation method of vehicle sound quality | |
| CN113096691A (en) | Detection method, device, equipment and computer storage medium | |
| CN112233693A (en) | Sound quality evaluation method, device and equipment | |
| CN112216285A (en) | Multi-person session detection method, system, mobile terminal and storage medium | |
| CN117612566B (en) | Audio quality assessment method and related product | |
| Höbel-Müller et al. | Investigation of the influence of standing waves on distant speech emotion recognition | |
| CN117393002B (en) | Read-aloud quality assessment method based on artificial intelligence and related device | |
| CN111741168B (en) | Communication equipment testing method and device, computer readable medium and equipment thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |