In-vehicle speech clarity evaluation method, device, equipment and readable storage medium
By obtaining the speech recognition accuracy at different vehicle speeds, calculating and screening the voice clarity in the vehicle, and combining typical vehicle speeds, the problem of poor speech clarity evaluation accuracy caused by noise feature detection in the existing technology is solved, and more efficient In-car voice clarity evaluation.
Patent Information
- Application Number
- CN202210615084.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-05-31
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2042-05-31
AI Technical Summary
In the prior art, the in-vehicle voice clarity is detected through various characteristics of in-vehicle noise, resulting in poor accuracy of evaluation results.
Use short sentence speech recognition accuracy and long sentence speech recognition accuracy for each voice propagation direction corresponding to different vehicle speeds, calculate the in-car voice clarity corresponding to each vehicle speed, and filter out the first in-car voice clarity and the second in-car The voice clarity in the interior and voice clarity in the third car are calculated based on the preset typical vehicle speed.
The accuracy of the evaluation results of the in-car voice clarity is improved, making the evaluation results more intuitive, convenient, and closer to the actual situation.
Smart Images

Figure CN115019828B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of NVH performance testing and evaluation, and in particular to a method, device, equipment and readable storage medium for evaluating in-vehicle speech clarity. Background Art
[0002] With the development of the times, people's awareness of quality is getting stronger and stronger. In the field of automobile consumption, in-car voice clarity has become an important performance indicator of automobiles. In-car voice clarity describes the clarity of people's voice communication in the car when the vehicle is driving at high speed. It can be expressed as a percentage: 100% means that the speech can be heard clearly, and 0% means that the speech cannot be heard at all. At present, people are paying more and more attention to the in-car voice clarity, so major automobile manufacturers are also making every effort to improve the in-car voice clarity performance.
[0003] In the related art, the test and evaluation method for the in-car speech clarity is usually as follows: several microphones are arranged in the front and rear rows of the car to measure the in-car noise signal; the vehicle is driven at a certain speed (such as 120km / h) at a constant speed to measure the in-car noise under this condition; then the noise signal measured by the microphone is analyzed by FFT (Fast Fourier Transform) to obtain the in-car noise spectrum data; the noise spectrum data is then frequency-weighted, and the weighting coefficients at different frequencies are different; finally, the weighted results at each frequency are summed to obtain the in-car speech clarity. This method mainly uses various characteristics of in-car noise to characterize the clarity of voice communication between people in the car. It is an indirect expression method, which is not only unintuitive and inconvenient, but also because the various characteristics of in-car noise are the noise environment of voice communication between people in the car, rather than the voice communication itself, therefore, using this method to characterize the in-car speech clarity is inevitably different from the actual situation of the vehicle's in-car speech clarity (which can be called the true value), that is, there is a problem of poor accuracy of the in-car speech clarity evaluation result. Summary of the invention
[0004] The present application provides a method, device, equipment and readable storage medium for evaluating in-vehicle speech clarity, so as to solve the problem of poor evaluation result accuracy caused by using various characteristics of in-vehicle noise to detect in-vehicle speech clarity in the related art.
[0005] In a first aspect, a method for evaluating in-vehicle speech clarity is provided, comprising the following steps:
[0006] Obtain the short sentence speech recognition accuracy and long sentence speech recognition accuracy of each speech propagation direction corresponding to different vehicle speeds;
[0007] According to the order of vehicle speed, the in-vehicle speech intelligibility corresponding to each vehicle speed is calculated based on the short sentence speech recognition accuracy and the long sentence speech recognition accuracy of each speech propagation direction;
[0008] A first in-vehicle voice clarity, a second in-vehicle voice clarity and a third in-vehicle voice clarity are selected from the in-vehicle voice clarity corresponding to each vehicle speed, wherein the first in-vehicle voice clarity is the in-vehicle voice clarity that is less than a first clarity threshold for the first time, the second in-vehicle voice clarity is the in-vehicle voice clarity that is less than a second clarity threshold for the first time, and the third in-vehicle voice clarity is the in-vehicle voice clarity corresponding to a preset typical vehicle speed, and the first clarity threshold is greater than the second clarity threshold;
[0009] The speech clarity evaluation value of the entire vehicle is calculated according to the vehicle speed corresponding to the first in-vehicle speech clarity, the vehicle speed corresponding to the second in-vehicle speech clarity, the third in-vehicle speech clarity and a preset typical vehicle speed.
[0010] In some embodiments, the speech propagation direction includes a forward propagation direction in which speech is transmitted from the front row of the vehicle to the rear row of the vehicle and a backward propagation direction in which speech is transmitted from the rear row of the vehicle to the front row of the vehicle.
[0011] In some embodiments, before the step of obtaining the short sentence speech recognition accuracy and the long sentence speech recognition accuracy of each speech propagation direction corresponding to different vehicle speeds, the method further includes:
[0012] When the vehicle is at a first speed, the voice playback unit arranged at the front row of the vehicle plays the first short sentence text content and the first long sentence text content in sequence;
[0013] The voice receiving unit disposed at the rear seat of the vehicle receives a first short sentence voice signal corresponding to the first short sentence text content and a first long sentence voice signal corresponding to the first long sentence text content, and sends the first short sentence voice signal and the first long sentence voice signal to the voice recognition unit;
[0014] The speech recognition unit performs speech recognition on the first short sentence speech signal and the first long sentence speech signal respectively to obtain the recognized short sentence text content corresponding to the first short sentence speech signal and the recognized long sentence text content corresponding to the first long sentence speech signal;
[0015] Compare the recognized short sentence text content with the first short sentence text content to obtain the short sentence speech recognition accuracy in the forward propagation direction corresponding to the first vehicle speed;
[0016] The recognized long sentence text content is compared with the first long sentence text content to obtain the long sentence speech recognition accuracy in the forward propagation direction corresponding to the first vehicle speed.
[0017] In some embodiments, the calculation formula of the vehicle speech clarity evaluation value is as follows:
[0018]
[0019] In the formula, AI_score represents the speech clarity evaluation value of the whole vehicle, AI_vel(v z ) represents the third in-car speech clarity, y represents the first clarity threshold, V_y represents the vehicle speed corresponding to the first in-car speech clarity, x represents the second clarity threshold, V_x represents the vehicle speed corresponding to the second in-car speech clarity, v z Indicates preset typical vehicle speeds.
[0020] In a second aspect, a device for evaluating in-vehicle speech clarity is provided, comprising:
[0021] An acquisition unit, which is used to acquire the short sentence speech recognition accuracy and the long sentence speech recognition accuracy of each speech propagation direction corresponding to different vehicle speeds;
[0022] A calculation unit, which is used to calculate the in-vehicle speech clarity corresponding to each vehicle speed based on the short sentence speech recognition accuracy and the long sentence speech recognition accuracy in each speech propagation direction in the order of vehicle speed;
[0023] a screening unit, configured to screen out a first in-vehicle voice clarity, a second in-vehicle voice clarity, and a third in-vehicle voice clarity from the in-vehicle voice clarity corresponding to each vehicle speed, wherein the first in-vehicle voice clarity is the in-vehicle voice clarity that is less than a first clarity threshold for the first time, the second in-vehicle voice clarity is the in-vehicle voice clarity that is less than a second clarity threshold for the first time, the third in-vehicle voice clarity is the in-vehicle voice clarity corresponding to a preset typical vehicle speed, and the first clarity threshold is greater than the second clarity threshold;
[0024] A processing unit is used to calculate a whole vehicle speech clarity evaluation value according to a vehicle speed corresponding to a first in-vehicle speech clarity, a vehicle speed corresponding to a second in-vehicle speech clarity, a third in-vehicle speech clarity and a preset typical vehicle speed.
[0025] In some embodiments, the speech propagation direction includes a forward propagation direction in which speech is transmitted from the front row of the vehicle to the rear row of the vehicle and a backward propagation direction in which speech is transmitted from the rear row of the vehicle to the front row of the vehicle.
[0026] In some embodiments, the device further comprises a voice playing unit disposed in the front row of the vehicle, a voice receiving unit disposed in the rear row of the vehicle, and a voice recognition unit:
[0027] When the vehicle is at a first speed, the voice playback unit provided in the front row of the vehicle is used to play the first short sentence text content and the first long sentence text content in sequence;
[0028] The voice receiving unit provided in the rear row of the vehicle is used to receive a first short sentence voice signal corresponding to the first short sentence text content and a first long sentence voice signal corresponding to the first long sentence text content, and send the first short sentence voice signal and the first long sentence voice signal to the voice recognition unit;
[0029] The speech recognition unit is used to perform speech recognition on the first short sentence speech signal and the first long sentence speech signal respectively, obtain the recognized short sentence text content corresponding to the first short sentence speech signal and the recognized long sentence text content corresponding to the first long sentence speech signal, and send them to the processing unit;
[0030] The processing unit is also used to compare the text content of the recognized short sentence with the text content of the first short sentence to obtain the short sentence speech recognition accuracy rate in the forward propagation direction corresponding to the first vehicle speed; and to compare the text content of the recognized long sentence with the text content of the first long sentence to obtain the long sentence speech recognition accuracy rate in the forward propagation direction corresponding to the first vehicle speed.
[0031] In some embodiments, the calculation formula of the vehicle speech clarity evaluation value is as follows:
[0032]
[0033] In the formula, AI_score represents the speech clarity evaluation value of the whole vehicle, AI_vel(v z ) represents the third in-car speech clarity, y represents the first clarity threshold, V_y represents the vehicle speed corresponding to the first in-car speech clarity, x represents the second clarity threshold, V_x represents the vehicle speed corresponding to the second in-car speech clarity, v z Indicates preset typical vehicle speeds.
[0034] In a third aspect, an in-vehicle speech clarity evaluation device is provided, comprising: a memory and a processor, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the aforementioned in-vehicle speech clarity evaluation method.
[0035] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer storage medium stores a computer program, and when the computer program is executed by a processor, the aforementioned in-vehicle speech clarity evaluation method is implemented.
[0036] The beneficial effects brought about by the technical solution provided by this application include: it can effectively improve the accuracy of the in-vehicle speech clarity evaluation results.
[0037] The present application provides a method, device, equipment and readable storage medium for evaluating in-vehicle speech clarity, including obtaining short sentence speech recognition accuracy and long sentence speech recognition accuracy in each speech propagation direction corresponding to different vehicle speeds; calculating the in-vehicle speech clarity corresponding to each vehicle speed based on the short sentence speech recognition accuracy and long sentence speech recognition accuracy in each speech propagation direction in the order of vehicle speed; selecting a first in-vehicle speech clarity, a second in-vehicle speech clarity and a third in-vehicle speech clarity from the in-vehicle speech clarity corresponding to each vehicle speed, the first in-vehicle speech clarity is the in-vehicle speech clarity that is less than a first clarity threshold for the first time, the second in-vehicle speech clarity is the in-vehicle speech clarity that is less than a second clarity threshold for the first time, and the third in-vehicle speech clarity is the in-vehicle speech clarity corresponding to a preset typical vehicle speed; and calculating a whole vehicle speech clarity evaluation value according to the vehicle speed corresponding to the first in-vehicle speech clarity, the vehicle speed corresponding to the second in-vehicle speech clarity, the third in-vehicle speech clarity and the preset typical vehicle speed. The present application comprehensively considers the direction of speech propagation and the types of long and short sentences to calculate the speech recognition accuracy, and uses the speech recognition accuracy to characterize the in-car speech clarity at various vehicle speeds, and comprehensively considers the typical value of the in-car speech clarity and the attenuation characteristics of the in-car speech clarity with the vehicle speed, and finally obtains the overall speech clarity evaluation result of the vehicle. This evaluation method is more intuitive and convenient, and because it comprehensively considers various factors affecting the in-car speech clarity, the evaluation result obtained is closer to the actual situation of the in-car speech clarity, effectively improving the accuracy of the in-car speech clarity evaluation result. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] 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 creative work.
[0039] Figure 1 A flowchart of a method for evaluating in-vehicle speech clarity provided in an embodiment of the present application;
[0040] Figure 2 A schematic diagram of the layout of various test units for in-vehicle speech clarity provided in an embodiment of the present application;
[0041] Figure 3 A top view of the positional relationship between the voice playback unit and the voice receiving unit in the vehicle provided in the embodiment of the present application;
[0042] Figure 4 A front view of the positional relationship between the voice playback unit and the voice receiving unit provided in the embodiment of the present application in the vehicle;
[0043] Figure 5 A schematic diagram of the structure of an in-vehicle speech clarity evaluation device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are 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 making creative work are within the scope of protection of this application.
[0045] The embodiments of the present application provide a method, device, equipment and readable storage medium for evaluating in-vehicle speech clarity, which can solve the problem of poor evaluation result accuracy caused by using various characteristics of in-vehicle noise to detect in-vehicle speech clarity in related technologies.
[0046] Figure 1 A method for evaluating in-vehicle speech clarity provided by an embodiment of the present application includes the following steps:
[0047] Step S10: Obtaining the short sentence speech recognition accuracy and the long sentence speech recognition accuracy of each speech propagation direction corresponding to different vehicle speeds;
[0048] Furthermore, the speech propagation direction includes a forward propagation direction in which speech is transmitted from the front row of the vehicle to the rear row of the vehicle and a backward propagation direction in which speech is transmitted from the rear row of the vehicle to the front row of the vehicle.
[0049] Furthermore, before the step of obtaining the short sentence speech recognition accuracy and the long sentence speech recognition accuracy of each speech propagation direction corresponding to different vehicle speeds, the method further includes:
[0050] When the vehicle is at a first speed, the voice playback unit arranged at the front row of the vehicle plays the first short sentence text content and the first long sentence text content in sequence;
[0051] The voice receiving unit disposed at the rear seat of the vehicle receives a first short sentence voice signal corresponding to the first short sentence text content and a first long sentence voice signal corresponding to the first long sentence text content, and sends the first short sentence voice signal and the first long sentence voice signal to the voice recognition unit;
[0052] The speech recognition unit performs speech recognition on the first short sentence speech signal and the first long sentence speech signal respectively to obtain the recognized short sentence text content corresponding to the first short sentence speech signal and the recognized long sentence text content corresponding to the first long sentence speech signal;
[0053] Compare the recognized short sentence text content with the first short sentence text content to obtain the short sentence speech recognition accuracy in the forward propagation direction corresponding to the first vehicle speed;
[0054] The recognized long sentence text content is compared with the first long sentence text content to obtain the long sentence speech recognition accuracy in the forward propagation direction corresponding to the first vehicle speed.
[0055] For example, in this embodiment, see Figure 2 As shown, voice recognition and voice recognition accuracy calculation and judgment can be realized by arranging a voice playback unit, a voice receiving unit, a voice recognition unit and a microprocessor unit (including a power module) in the vehicle. Among them, the voice playback unit is used to receive data (text) transmitted by the microprocessor unit and convert the data into voice for playback; the voice receiving unit is used to convert the sound signal played by the voice playback unit into a digital signal and transmit the digital signal to the voice recognition unit; the voice recognition unit is used to convert the data sent by the voice receiving unit into text and transmit the text to the microprocessor unit; the microprocessor unit (including a power module) is used to send data (text) to the voice playback unit to control it to play voice, and receive data transmitted by the voice recognition unit to calculate the voice recognition accuracy; another function of the microprocessor unit is to supply power to itself and other units.
[0056] Specifically, when performing a voice recognition test, the placement of the voice playback unit and the voice receiving unit in the vehicle can be set as follows: Figure 3 As shown, in the lateral direction of the top view of the vehicle, the voice playback unit or the voice receiving unit may be located on the longitudinal axis of the vehicle; in the longitudinal direction of the top view of the vehicle, the voice playback unit or the voice receiving unit is flush with the center line of the head of the corresponding driver and passenger; see Figure 4 As shown, in the vertical direction of the front view of the vehicle, the voice playback unit or the voice receiving unit is also flush with the center line of the head of the corresponding driver and passenger.
[0057] Generally speaking, the higher the speed, the louder the noise inside the vehicle, so that the voice communication of the people inside the vehicle is less clear. Therefore, the higher the speed, the worse the voice clarity inside the vehicle, so this embodiment will fully consider the voice clarity state inside the vehicle at different speeds when evaluating the voice clarity inside the vehicle. In addition, when the vehicle is driving at high speed, since the vehicle inevitably has air leakage, the voice clarity in the two cases of voice from the front row of the vehicle to the back row of the vehicle and voice from the back row of the vehicle to the front row of the vehicle is different. Therefore, this embodiment will include the above two cases when testing the voice clarity inside the vehicle. Among them, in this embodiment, the voice is transmitted from the front row of the vehicle to the back row of the vehicle, which is called "forward propagation" (at this time, the front row plays the voice signal, and the voice playback unit is placed in the front row; the back row receives the voice signal, and the voice receiving unit is placed in the back row); and the voice is transmitted from the back row of the vehicle to the front row of the vehicle, which is called "backward propagation" (at this time, the back row plays the voice signal, and the voice playback unit is placed in the back row; the front row receives the voice signal, and the voice receiving unit is placed in the front row).
[0058] On the other hand, when people communicate in the car, according to the length of the voice, it can generally be divided into two situations: short sentence communication and long sentence communication. Among them, short sentences and long sentences are divided according to the time interval between the two sentences: the interval between short sentences is longer, and the interval between long sentences is shorter. In addition, the length of the text corresponding to the short sentence communication is generally 2-10 words, that is, usually a sentence, such as "turn up the volume", "turn up the air conditioning temperature", etc.; and the length of the text corresponding to the long sentence communication is generally greater than 300 words. Since the semantic content of the voice is generally the content of human chat, its scope is relatively wide. Therefore, when the vehicle is driving at high speed, in the two cases of short sentence communication and long sentence communication, the smoothness and comprehensibility of the voice communication of the people in the car are also different, that is, the voice clarity is different. Therefore, this embodiment will also include the above two situations when testing the voice clarity in the car.
[0059] It can be seen that in this embodiment, the text A stored in the microprocessor can be played by the voice playback unit installed in the front (rear) row of the vehicle, and the voice receiving unit in the rear (front) row of the vehicle receives the voice signal and transmits the signal to the voice recognition unit; the voice recognition unit converts the voice into text B, and transmits the text B to the microprocessor unit; the microprocessor unit compares the text A with the text B, and calculates the voice recognition accuracy, which comprehensively considers the voice propagation direction (i.e., forward propagation, backward propagation) and the voice type (i.e., short sentences and long sentences), and uses the voice recognition accuracy to characterize the in-vehicle voice clarity at various vehicle speeds.
[0060] Specifically, regarding the calculation of the recognition accuracy of the speech recognition unit, in this embodiment, the recognition accuracy of short sentences at any vehicle speed and any speech propagation direction can be calculated using formula (1):
[0061]
[0062] Among them, succ_ratio_short is the accuracy rate of short sentence speech recognition, expressed as a percentage; word_num_succ is the number of short sentences recognized correctly; word_num_total is the total number of short sentences. For example, a total of 20 short sentences are included to form a short sentence group A. These short sentences are played by the speech playing unit, received by the speech receiving unit, and then recognized by the speech recognition unit and converted into a short sentence group (text) B. Among them, 16 short sentences in the short sentence group (text) B are recognized correctly (the text is exactly the same as the corresponding text in the short sentence group A), then the accuracy rate of short sentence speech recognition = 16 / 20 × 100% = 80%.
[0063] The accuracy of long sentence speech recognition for any vehicle speed and any speech propagation direction can be calculated using formula (2):
[0064]
[0065] Among them, succ_ratio_long is the accuracy rate of long sentence speech recognition, expressed as a percentage; character_num_succ is the number of characters recognized correctly; character_num_total is the total number of characters.
[0066] It can be seen that by using formula (1) and formula (2), the short sentence speech recognition accuracy in the forward propagation direction, the long sentence speech recognition accuracy in the forward propagation direction, the short sentence speech recognition accuracy in the backward propagation direction, and the long sentence speech recognition accuracy in the backward propagation direction at each vehicle speed can be calculated.
[0067] Of course, in this embodiment, when performing a formal in-vehicle speech clarity test, the test unit must be calibrated first.
[0068] Specifically, taking the speech recognition rate test in the forward propagation direction as an example, Figure 3 and Figure 4 The voice playback unit and the voice receiving unit are arranged as shown, and the placement of the voice recognition unit and the microprocessor unit can be set according to the needs, which will not affect the propagation of the voice; then press Figure 2 As shown, use the data line (ie Figure 2 The dashed line in the figure) and the power line (i.e. Figure 2 The voice playback unit, the voice receiving unit, the voice recognition unit, and the microprocessor unit are connected by the solid line in the figure; and the vehicle is placed in a quiet environment, such as an anechoic chamber, and the vehicle is not started (no ignition); at this time, there are at most two people sitting in the car, namely the driver and the tester, and their sitting positions should not affect the propagation of voice.
[0069] Then, appropriate short sentences and long sentences are selected, which can be determined based on the number of speech and semantic content. For example, regarding the number of speech, for short sentences, several (such as 10-20) short sentences of different lengths can be selected, and for long sentences, a paragraph of text (the length of the text is generally greater than 300 words) can be selected; and regarding the semantic content of speech, it can be selected at will, but it must meet the following requirements: the speech playback unit plays the speech, the speech receiving unit receives the speech and transmits the data to the speech recognition unit for real-time recognition, and whether it is a short sentence or a long sentence, whether it is forward propagation or backward propagation, the recognition accuracy of the speech recognition unit must be 100%. If the semantic content of the speech meets this requirement, the calibration is completed; if it does not meet this requirement, the semantic content of the speech that is not recognized correctly is reselected and the calibration is re-performed until this requirement is met. The purpose of setting such a requirement is to prove that it is appropriate to use these texts to test the accuracy of speech recognition, and another function is to offset the difference in speech recognition performance of different speech recognition units.
[0070] After completing the above calibration, the formal speech recognition test can be carried out. Since the test principles and workflows for the short sentence speech recognition accuracy and long sentence speech recognition accuracy at any vehicle speed and any speech propagation direction are similar, this embodiment takes the collection of speech clarity data with a vehicle speed of 40km / h and forward propagation as an example: driving the vehicle to make the vehicle travel at a constant speed of 40km / h; the front row of the vehicle plays the speech, and the back row receives the speech and performs real-time recognition; the voice types played include short sentences and long sentences, and these two voice types should be performed in order (one voice type is performed after the other voice type is completed), and cannot be interspersed.
[0071] Taking the short sentence type test as an example, the data transmission process during the test is explained: the short sentence (text) group A stored in the microprocessor unit is played by the voice playback unit, received by the voice receiving unit and the signal is transmitted to the voice recognition unit, and converted into short sentence group (text) B by the voice recognition unit; the short sentence group (text) B is transmitted to the microprocessor unit through the voice recognition unit; the microprocessor unit compares the short sentence group A with the short sentence group B one by one, and can calculate the short sentence voice recognition accuracy in the forward propagation direction with a vehicle speed of 40km / h.
[0072] In this embodiment, the vehicle speed includes 40km / h, 50km / h, 60km / h, 70km / h, 80km / h, 90km / h, 100km / h, 110km / h, 120km / h, 130km / h, and 140km / h as an example, and the data collection process of the 40km / h working condition is referred to, and the short sentence speech recognition accuracy and long sentence speech recognition accuracy in the forward propagation direction and the backward propagation direction under the working conditions of 50km / h, 60km / h, 70km / h, 80km / h, 90km / h, 100km / h, 110km / h, 120km / h, 130km / h, and 140km / h are collected respectively. It should be noted that when data is collected at the above-mentioned vehicle speeds, the volume of the voice playback unit must be the same and the same as the volume during calibration.
[0073] Step S20: Calculating the in-vehicle speech clarity corresponding to each vehicle speed based on the short sentence speech recognition accuracy and the long sentence speech recognition accuracy in each speech propagation direction in the order of vehicle speed;
[0074] For example, in this embodiment, the in-vehicle speech clarity data at each vehicle speed is calculated in order of vehicle speed. The in-vehicle speech clarity at each vehicle speed can be calculated according to formula (3).
[0075]
[0076] Wherein, AI_vel is the in-vehicle speech clarity at a certain speed, expressed in percentage; forward_short is the short sentence speech recognition accuracy in the forward propagation direction at a certain speed; forward_long is the long sentence speech recognition accuracy in the forward propagation direction at a certain speed; backward_short is the short sentence speech recognition accuracy in the backward propagation direction at a certain speed; backward_long is the long sentence speech recognition accuracy in the backward propagation direction at a certain speed. Among them, the calculation of forward_short, forward_long, backward_short and backward_long can be performed according to formula (1) and formula (2). Therefore, after the test at a certain speed is completed, the microprocessor will automatically calculate the corresponding speech recognition accuracy.
[0077] According to formula (3), this embodiment uses the average of the speech recognition accuracy under four conditions at a certain vehicle speed to characterize the in-vehicle speech clarity of the vehicle at a certain vehicle speed; compared with the current in-vehicle speech clarity test and evaluation method (using various characteristics of in-vehicle noise to characterize the clarity of voice communication between people in the vehicle), the result obtained by formula (3) is more reasonable and scientific. It comprehensively considers the differences in speech propagation directions (forward propagation, backward propagation) and speech types (short sentences, long sentences), and is a more reliable indicator. It can be seen that the evaluation object of this embodiment is the speech clarity itself, rather than the environment in which the speech clarity is located - the in-vehicle noise. Therefore, the speech clarity represented by formula (3) is closer to the actual situation of in-vehicle speech clarity (which can be called the true value).
[0078] Step S30: selecting a first in-car voice clarity, a second in-car voice clarity and a third in-car voice clarity from the in-car voice clarity corresponding to each vehicle speed, wherein the first in-car voice clarity is the in-car voice clarity that is less than the first clarity threshold for the first time, the second in-car voice clarity is the in-car voice clarity that is less than the second clarity threshold for the first time, and the third in-car voice clarity is the in-car voice clarity corresponding to a preset typical vehicle speed;
[0079] For example, in this embodiment, for a vehicle, 120 km / h is generally considered to be a typical vehicle speed (generally, the speed limit on a highway is 120 km / h; on a highway, 120 km / h is a common vehicle speed), so this embodiment can preset the typical vehicle speed to 120 km / h. Of course, the typical vehicle speed can also be preset according to actual conditions, which is not limited here. Therefore, this embodiment uses the in-vehicle speech clarity at a speed of 120 km / h calculated according to formula (3) as a representative of the in-vehicle speech clarity, and records its value as AI_120.
[0080] In addition, the following rule exists for the in-car speech clarity: the in-car speech clarity decreases as the vehicle speed increases. Therefore, according to formula (3), the in-car speech clarity AI_vel at vehicle speeds of 40km / h, 50km / h, 60km / h, 70km / h, 80km / h, 90km / h, 100km / h, 110km / h, 120km / h, 130km / h, and 140km / h is calculated in sequence, and the value of AI_vel will decrease in sequence as the vehicle speed increases.
[0081] This embodiment will screen out the first AI_vel value that falls below the first clarity threshold for the first time and the second AI_vel value that falls below the second clarity threshold for the first time from the in-vehicle speech clarity corresponding to each vehicle speed, and determine the attenuation characteristics of the in-vehicle speech clarity performance according to the vehicle speed corresponding to the first AI_vel value and the vehicle speed corresponding to the second AI_vel value; wherein, the first clarity threshold is greater than the second clarity threshold, and the specific value settings of the two can be determined according to actual conditions and are not limited here.
[0082] For example, if the first clarity threshold is 90% and the second clarity threshold is 60%, V_90 is the vehicle speed at which the AI_vel value first falls below 90% (i.e., AI_vel < 90%). For example, if the AI_vel value at a speed of 50 km / h is 91% and the AI_vel value at a speed of 60 km / h is 85%, then V_90 is 60 km / h. The mathematical expression of V_90 is shown in formula (4):
[0083]
[0084] Among them, AI_vel(v) means AI_vel is a function of vehicle speed v; arg means parameter; firstv means the vehicle speed corresponding to the first time AI_vel(v) falls below 90%.
[0085] At the same time, V_60 is recorded as the vehicle speed at which the AI_vel value first falls below 60% (i.e., AI_vel<60%). The mathematical expression of V_60 is shown in formula (5):
[0086]
[0087] Among them, AI_vel(v) means AI_vel is a function of vehicle speed v; arg means parameter; firstv means the vehicle speed corresponding to the first time AI_vel(v) falls below 60%
[0088] It can be seen that V_90 and V_60 are characteristic vehicle speeds related to the intelligibility of in-vehicle speech.
[0089] Step S40: Calculate the vehicle speech clarity evaluation value according to the vehicle speed corresponding to the first in-vehicle speech clarity, the vehicle speed corresponding to the second in-vehicle speech clarity, the third in-vehicle speech clarity and a preset typical vehicle speed.
[0090] Furthermore, the calculation formula of the vehicle speech clarity evaluation value is as follows:
[0091]
[0092] In the formula, AI_score represents the speech clarity evaluation value of the whole vehicle, AI_vel(v z) represents the third in-car speech clarity, y represents the first clarity threshold, V_y represents the vehicle speed corresponding to the first in-car speech clarity, x represents the second clarity threshold, V_x represents the vehicle speed corresponding to the second in-car speech clarity, v z Indicates preset typical vehicle speeds.
[0093] Exemplarily, in this embodiment, the vehicle speed corresponding to the first in-vehicle speech clarity, the vehicle speed corresponding to the second in-vehicle speech clarity, the third in-vehicle speech clarity and the preset typical vehicle speed are substituted into formula (6) to calculate and obtain the whole vehicle speech clarity evaluation value.
[0094]
[0095] Among them, AI_score is the evaluation value of the vehicle's speech clarity, that is, the overall evaluation result of the vehicle's in-vehicle speech clarity, AI_vel(v z ) represents the third in-car speech clarity, y represents the first clarity threshold, V_y represents the vehicle speed corresponding to the first in-car speech clarity, x represents the second clarity threshold, V_x represents the vehicle speed corresponding to the second in-car speech clarity, v z represents the preset typical vehicle speed, where The denominator v in z It may also be a vehicle speed reference value other than the typical vehicle speed, and the vehicle speed reference value may be preset according to actual conditions, which is not limited here.
[0096] Similarly, the first clarity threshold y is 90%, the second clarity threshold x is 60%, and the typical vehicle speed v z Taking 120km / h as an example, the vehicle speech clarity evaluation value AI_score is:
[0097]
[0098] Wherein, AI_vel(120) is the in-car speech clarity at a speed of 120 km / h; V_90 is the speed at which AI_vel first falls below 90%, and V_60 is the speed at which AI_vel first falls below 60%.
[0099] Among them, AI_vel(120) is the representative value of the in-vehicle speech intelligibility at the typical vehicle speed; As a representative value of the attenuation of in-vehicle speech clarity with vehicle speed, it characterizes the attenuation characteristics of in-vehicle speech clarity performance. The larger V_60-V_90 is, the clearer the voice communication can be in a wider range of vehicle speeds, and the slower the attenuation of in-vehicle speech clarity performance is. Since AI_vel(120) is a dimensionless value (see formula (3)), the last term (second term) on the right side of the equal sign in formula (6) must also be dimensionless data. Therefore, V_60-V_90 (in units of vehicle speed, km / h) can be converted into dimensionless data by dividing it by 120 (in units of vehicle speed, km / h).
[0100] The overall vehicle in-car speech clarity evaluation result AI_score calculated in this embodiment is a comprehensive value. It is not the in-car speech clarity at a certain vehicle speed, but rather a characterization of the overall vehicle speech clarity level. It is a comprehensive speech clarity indicator that characterizes the in-car speech clarity at the vehicle's typical speed and the attenuation characteristics of the vehicle's in-car speech clarity performance with vehicle speed.
[0101] In summary, this embodiment comprehensively considers the direction of speech propagation and the types of long and short sentences to calculate the speech recognition accuracy, and uses the speech recognition accuracy to characterize the in-car speech clarity at various vehicle speeds, and comprehensively considers the typical value of the in-car speech clarity and the attenuation characteristics of the in-car speech clarity with the vehicle speed, and finally obtains the overall speech clarity evaluation result of the vehicle. This evaluation method is more intuitive and convenient, and because it comprehensively considers various factors affecting the in-car speech clarity, the evaluation result obtained is closer to the actual situation of the in-car speech clarity, which effectively improves the accuracy of the in-car speech clarity evaluation result.
[0102] The embodiment of the present application also provides a device for evaluating in-vehicle speech clarity, comprising:
[0103] An acquisition unit, which is used to acquire the short sentence speech recognition accuracy and the long sentence speech recognition accuracy of each speech propagation direction corresponding to different vehicle speeds;
[0104] A calculation unit, which is used to calculate the in-vehicle speech clarity corresponding to each vehicle speed based on the short sentence speech recognition accuracy and the long sentence speech recognition accuracy in each speech propagation direction in the order of vehicle speed;
[0105] a screening unit, configured to screen out a first in-vehicle voice clarity, a second in-vehicle voice clarity, and a third in-vehicle voice clarity from the in-vehicle voice clarity corresponding to each vehicle speed, wherein the first in-vehicle voice clarity is the in-vehicle voice clarity that is less than a first clarity threshold for the first time, the second in-vehicle voice clarity is the in-vehicle voice clarity that is less than a second clarity threshold for the first time, the third in-vehicle voice clarity is the in-vehicle voice clarity corresponding to a preset typical vehicle speed, and the first clarity threshold is greater than the second clarity threshold;
[0106] A processing unit is used to calculate a whole-vehicle speech clarity evaluation value according to a first vehicle speed corresponding to the in-vehicle speech clarity, a second vehicle speed corresponding to the in-vehicle speech clarity, a third in-vehicle speech clarity and a preset typical vehicle speed; wherein the acquisition unit, the calculation unit, the screening unit and the processing unit can be integrated into a microprocessor unit for in-vehicle speech clarity evaluation.
[0107] It can be seen that the test device involved in this embodiment has a simple structure, low cost and simple testing method; in addition, the evaluation method involved in this embodiment is intuitive, convenient and concise, and comprehensively considers various factors affecting the in-car speech clarity. The evaluation result is closer to the actual situation of the in-car speech clarity, and it can be applied to various types of cars, especially the evaluation of in-car speech clarity of passenger cars.
[0108] Furthermore, the speech propagation direction includes a forward propagation direction in which speech is transmitted from the front row of the vehicle to the rear row of the vehicle and a backward propagation direction in which speech is transmitted from the rear row of the vehicle to the front row of the vehicle.
[0109] Furthermore, the device also includes a voice playing unit arranged in the front row of the vehicle, a voice receiving unit and a voice recognition unit arranged in the back row of the vehicle:
[0110] When the vehicle is at a first speed, the voice playback unit provided in the front row of the vehicle is used to play the first short sentence text content and the first long sentence text content in sequence;
[0111] The voice receiving unit provided in the rear row of the vehicle is used to receive a first short sentence voice signal corresponding to the first short sentence text content and a first long sentence voice signal corresponding to the first long sentence text content, and send the first short sentence voice signal and the first long sentence voice signal to the voice recognition unit;
[0112] The speech recognition unit is used to perform speech recognition on the first short sentence speech signal and the first long sentence speech signal respectively, obtain the recognized short sentence text content corresponding to the first short sentence speech signal and the recognized long sentence text content corresponding to the first long sentence speech signal, and send them to the processing unit;
[0113] The processing unit is also used to compare the text content of the recognized short sentence with the text content of the first short sentence to obtain the short sentence speech recognition accuracy rate in the forward propagation direction corresponding to the first vehicle speed; and to compare the text content of the recognized long sentence with the text content of the first long sentence to obtain the long sentence speech recognition accuracy rate in the forward propagation direction corresponding to the first vehicle speed.
[0114] Furthermore, the calculation formula of the vehicle speech clarity evaluation value is as follows:
[0115]
[0116] In the formula, AI_score represents the speech clarity evaluation value of the whole vehicle, AI_vel(v z ) represents the third in-car speech clarity, y represents the first clarity threshold, V_y represents the vehicle speed corresponding to the first in-car speech clarity, x represents the second clarity threshold, V_x represents the vehicle speed corresponding to the second in-car speech clarity, v z Indicates preset typical vehicle speeds.
[0117] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and each unit can refer to the corresponding process in the aforementioned embodiment of the in-vehicle speech clarity evaluation method, and will not be repeated here.
[0118] The in-vehicle speech clarity evaluation device provided in the above embodiment can be implemented in the form of a computer program. The computer program can be used in Figure 5 The in-car speech intelligibility evaluation equipment shown is run on.
[0119] An embodiment of the present application also provides an in-vehicle speech clarity evaluation device, comprising: a memory, a processor, and a network interface connected via a system bus, wherein at least one instruction is stored in the memory, and the at least one instruction is loaded and executed by the processor to implement all or part of the steps of the aforementioned in-vehicle speech clarity evaluation method.
[0120] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0121] The processor may be a CPU, or other general-purpose processors, 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, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, etc. The processor is the control center of the computer device, and uses various interfaces and lines to connect various parts of the entire computer device.
[0122] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the computer device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a video playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as video data, image data, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMediacard, SMC), a secure digital (Secure digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device or other volatile solid-state storage device.
[0123] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, all or part of the steps of the aforementioned in-vehicle speech clarity evaluation method are implemented.
[0124] The embodiment of the present application implements all or part of the aforementioned process, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of each of the above methods when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.
[0125] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, servers or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program codes.
[0126] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.
[0127] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0128] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.
Claims
1. A method for evaluating in-vehicle speech clarity, characterized in that: The following steps are involved: Obtain the short sentence speech recognition accuracy and long sentence speech recognition accuracy of each speech propagation direction corresponding to different vehicle speeds; According to the order of vehicle speed, the in-vehicle speech intelligibility corresponding to each vehicle speed is calculated based on the short sentence speech recognition accuracy and the long sentence speech recognition accuracy of each speech propagation direction; A first in-vehicle voice clarity, a second in-vehicle voice clarity and a third in-vehicle voice clarity are selected from the in-vehicle voice clarity corresponding to each vehicle speed, wherein the first in-vehicle voice clarity is the in-vehicle voice clarity that is less than a first clarity threshold for the first time, the second in-vehicle voice clarity is the in-vehicle voice clarity that is less than a second clarity threshold for the first time, and the third in-vehicle voice clarity is the in-vehicle voice clarity corresponding to a preset typical vehicle speed, and the first clarity threshold is greater than the second clarity threshold; The speech clarity evaluation value of the entire vehicle is calculated according to the vehicle speed corresponding to the first in-vehicle speech clarity, the vehicle speed corresponding to the second in-vehicle speech clarity, the third in-vehicle speech clarity and a preset typical vehicle speed.
2. The in-vehicle speech intelligibility evaluation method according to claim 1, characterized in that: The speech propagation direction includes a forward propagation direction in which speech is transmitted from the front row of the vehicle to the rear row of the vehicle and a backward propagation direction in which speech is transmitted from the rear row of the vehicle to the front row of the vehicle.
3. The in-vehicle speech intelligibility evaluation method according to claim 2, characterized in that: Before the step of obtaining the short sentence speech recognition accuracy and the long sentence speech recognition accuracy of each speech propagation direction corresponding to different vehicle speeds, the method further includes: When the vehicle is at a first speed, the voice playback unit arranged at the front row of the vehicle plays the first short sentence text content and the first long sentence text content in sequence; The voice receiving unit disposed at the rear seat of the vehicle receives a first short sentence voice signal corresponding to the first short sentence text content and a first long sentence voice signal corresponding to the first long sentence text content, and sends the first short sentence voice signal and the first long sentence voice signal to the voice recognition unit; The speech recognition unit performs speech recognition on the first short sentence speech signal and the first long sentence speech signal respectively to obtain the recognized short sentence text content corresponding to the first short sentence speech signal and the recognized long sentence text content corresponding to the first long sentence speech signal; Compare the recognized short sentence text content with the first short sentence text content to obtain the short sentence speech recognition accuracy in the forward propagation direction corresponding to the first vehicle speed; The recognized long sentence text content is compared with the first long sentence text content to obtain the long sentence speech recognition accuracy in the forward propagation direction corresponding to the first vehicle speed.
4. The in-vehicle speech intelligibility evaluation method according to claim 1, characterized in that: The calculation formula of the vehicle speech clarity evaluation value is as follows: In the formula, AI_score represents the speech clarity evaluation value of the whole vehicle, AI_vel(v z ) represents the third in-car speech clarity, y represents the first clarity threshold, V_y represents the vehicle speed corresponding to the first in-car speech clarity, x represents the second clarity threshold, V_x represents the vehicle speed corresponding to the second in-car speech clarity, v z Indicates preset typical vehicle speeds.
5. A device for evaluating speech clarity in a vehicle, characterized in that: include: An acquisition unit, which is used to acquire the short sentence speech recognition accuracy and the long sentence speech recognition accuracy of each speech propagation direction corresponding to different vehicle speeds; A calculation unit, which is used to calculate the in-vehicle speech clarity corresponding to each vehicle speed based on the short sentence speech recognition accuracy and the long sentence speech recognition accuracy in each speech propagation direction in the order of vehicle speed; a screening unit, configured to screen out a first in-vehicle voice clarity, a second in-vehicle voice clarity, and a third in-vehicle voice clarity from the in-vehicle voice clarity corresponding to each vehicle speed, wherein the first in-vehicle voice clarity is the in-vehicle voice clarity that is less than a first clarity threshold for the first time, the second in-vehicle voice clarity is the in-vehicle voice clarity that is less than a second clarity threshold for the first time, the third in-vehicle voice clarity is the in-vehicle voice clarity corresponding to a preset typical vehicle speed, and the first clarity threshold is greater than the second clarity threshold; A processing unit is used to calculate a whole vehicle speech clarity evaluation value according to a vehicle speed corresponding to a first in-vehicle speech clarity, a vehicle speed corresponding to a second in-vehicle speech clarity, a third in-vehicle speech clarity and a preset typical vehicle speed.
6. The in-vehicle speech intelligibility evaluation device according to claim 5, characterized in that: The speech propagation direction includes a forward propagation direction in which speech is transmitted from the front row of the vehicle to the rear row of the vehicle and a backward propagation direction in which speech is transmitted from the rear row of the vehicle to the front row of the vehicle.
7. The in-vehicle speech intelligibility evaluation device according to claim 6, characterized in that: The device also includes a voice playing unit arranged in the front row of the vehicle, a voice receiving unit and a voice recognition unit arranged in the back row of the vehicle: When the vehicle is at a first speed, the voice playback unit provided in the front row of the vehicle is used to play the first short sentence text content and the first long sentence text content in sequence; The voice receiving unit provided in the rear row of the vehicle is used to receive a first short sentence voice signal corresponding to the first short sentence text content and a first long sentence voice signal corresponding to the first long sentence text content, and send the first short sentence voice signal and the first long sentence voice signal to the voice recognition unit; The speech recognition unit is used to perform speech recognition on the first short sentence speech signal and the first long sentence speech signal respectively, obtain the recognized short sentence text content corresponding to the first short sentence speech signal and the recognized long sentence text content corresponding to the first long sentence speech signal, and send them to the processing unit; The processing unit is also used to compare the text content of the recognized short sentence with the text content of the first short sentence to obtain the short sentence speech recognition accuracy rate in the forward propagation direction corresponding to the first vehicle speed; and to compare the text content of the recognized long sentence with the text content of the first long sentence to obtain the long sentence speech recognition accuracy rate in the forward propagation direction corresponding to the first vehicle speed.
8. The in-vehicle speech intelligibility evaluation device according to claim 5, characterized in that: The calculation formula of the vehicle speech clarity evaluation value is as follows: In the formula, AI_score represents the speech clarity evaluation value of the whole vehicle, AI_vel(v z ) represents the third in-car speech clarity, y represents the first clarity threshold, V_y represents the vehicle speed corresponding to the first in-car speech clarity, x represents the second clarity threshold, V_x represents the vehicle speed corresponding to the second in-car speech clarity, v z Indicates preset typical vehicle speeds.
9. A device for evaluating in-vehicle speech clarity, characterized in that: include: A memory and a processor, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the in-vehicle speech clarity evaluation method according to any one of claims 1 to 4.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the in-vehicle speech intelligibility evaluation method according to any one of claims 1 to 4 is implemented.
Citation Information
Patent Citations
Electric car driving system sound acquisition sounding method and device
CN106671875A
Method of automatic measurement of the clarity of speech in a motor vehicle
DE19813285A1
