CN111724782A - Response time testing system, method and equipment of vehicle-mounted voice interaction system - Google Patents
Response time testing system, method and equipment of vehicle-mounted voice interaction system Download PDFInfo
- Publication number
- CN111724782A CN111724782A CN202010560409.4A CN202010560409A CN111724782A CN 111724782 A CN111724782 A CN 111724782A CN 202010560409 A CN202010560409 A CN 202010560409A CN 111724782 A CN111724782 A CN 111724782A
- Authority
- CN
- China
- Prior art keywords
- voice interaction
- vehicle
- response
- instruction
- response time
- 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.)
- Granted
Links
- 230000004044 response Effects 0.000 title claims abstract description 231
- 230000003993 interaction Effects 0.000 title claims abstract description 191
- 238000012360 testing method Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000004458 analytical method Methods 0.000 claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 29
- 230000009471 action Effects 0.000 claims description 22
- 230000002452 interceptive effect Effects 0.000 claims description 2
- 238000009533 lab test Methods 0.000 abstract description 3
- 230000008901 benefit Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000010998 test method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000019771 cognition Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241001672694 Citrus reticulata Species 0.000 description 1
- 241000282414 Homo sapiens Species 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/60—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for measuring the quality of voice signals
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Navigation (AREA)
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
Abstract
The invention relates to the field of real vehicle voice testing, and particularly discloses a system, a method and equipment for testing response time of a vehicle-mounted voice interaction system. The system comprises a voice instruction control module, a system response acquisition module and an analysis processing module; the voice instruction control module is used for generating a preset voice interaction instruction and inputting the preset voice interaction instruction to a vehicle-mounted voice interaction system loaded in the real vehicle; the system response acquisition module is used for acquiring response information of the vehicle-mounted voice interaction system after a preset voice interaction instruction is input; the analysis processing module is used for acquiring the response information and calculating the response time of the vehicle-mounted voice interaction system under the test according to the response information. The vehicle-mounted voice interaction system loaded in the real vehicle is controlled according to the preset voice interaction instruction, the response time of the vehicle-mounted voice interaction system is calculated according to the response information of the vehicle-mounted voice interaction system, and compared with a part-level laboratory test method, the real use environment of a user can be reflected better.
Description
Technical Field
The invention relates to the field of real vehicle voice testing, in particular to a system, a method and equipment for testing response time of a vehicle-mounted voice interaction system.
Background
The voice recognition is an important way for the vehicle-mounted voice interaction system to acquire the user intention, for example, the user can speak a voice instruction to control under the condition that the vehicle-mounted voice interaction system is inconvenient to directly control. Speech recognition may include both preliminary wake-up and subsequent recognition processes. With the addition of a host factory, a science and technology company, a pioneer company and the like to a river of an intelligent vehicle-mounted voice interaction market, software and hardware performances of a vehicle-mounted voice interaction system and functions and quality of the system cannot be guaranteed, the vehicle-mounted voice interaction system needs to be tested before leaving a factory, and time for the vehicle-mounted voice interaction system to respond to a voice instruction needs to be measured, so that whether the vehicle-mounted voice interaction system is qualified or not is judged according to the response time, and the vehicle-mounted voice interaction system is graded or used for later-stage research.
At present, the response time test of the vehicle-mounted voice interaction system is basically carried out in a laboratory and is only based on a part level (not loaded in a real vehicle), but is influenced by the driving environment, the driving state and the like of the vehicle after loading, the test result is usually obviously different from that in the laboratory, and the test method can not reflect the actual performance of the vehicle-mounted voice interaction system.
Disclosure of Invention
The invention provides a response time testing system, a response time testing method and response time testing equipment of a vehicle-mounted voice interaction system, and solves the technical problems that: the response time testing method of the vehicle-mounted voice interaction system in the part-level laboratory cannot meet the requirement of an actual driving state, the testing result is different from the actual vehicle performance, and the actual performance of the vehicle-mounted voice interaction system cannot be reflected.
The basic scheme provided by the invention is as follows:
a response time test system of a vehicle-mounted voice interaction system comprises a voice instruction control module, a system response acquisition module and an analysis processing module;
the voice instruction control module is used for generating a preset voice interaction instruction and inputting the preset voice interaction instruction to a vehicle-mounted voice interaction system loaded in the real vehicle;
the system response acquisition module is used for acquiring response information of the vehicle-mounted voice interaction system after the preset voice interaction instruction is input;
and the analysis processing module is used for acquiring the response information and calculating the response time of the vehicle-mounted voice interaction system in the test according to the response information.
The basic scheme is as follows:
the vehicle-mounted voice interaction system loaded in the real vehicle is controlled according to the preset voice interaction instruction (such as starting navigation, playing music, making a call and the like), the response time of the vehicle-mounted voice interaction system is calculated according to the response information of the vehicle-mounted voice interaction system, and compared with a part-level laboratory test method, the real use environment of a user can be reflected better.
In further embodiments, the system response acquisition module comprises an image acquisition module and a sound acquisition module;
the image acquisition module is used for acquiring the picture presented by the vehicle-mounted voice interaction system and inputting the picture to the analysis processing module;
the sound collection module is used for collecting the sound emitted by the vehicle-mounted voice interaction system and inputting the sound to the analysis processing module.
The scheme is as follows:
the external expression form based on the vehicle-mounted voice interaction system responding to the preset voice interaction instruction comprises sound and pictures, and the image acquisition module and the sound acquisition module are adopted to respectively acquire the sound and the presented pictures sent by the vehicle-mounted voice interaction system.
In a further embodiment, the calculating the response time of the vehicle-mounted voice interaction system according to the response information specifically includes:
taking the acquisition starting moment of the response information as the starting point of response time;
analyzing whether an execution action characteristic point corresponding to the preset voice interaction instruction appears in the response information, if so, taking the time of the occurrence of the execution action characteristic point as the end point of response time, and if not, marking the test as no response;
and obtaining the corresponding response time by making a difference between the starting point and the ending point.
In the scheme, from the user perspective, the calculation rule of the response time is further limited to the point of settlement from the acquisition starting time of the response information (also the output ending time of the preset voice interaction instruction) to the occurrence of the corresponding execution action characteristic point, so that the cognition of the general user on the response time is met, and the actual response condition of the vehicle-mounted voice interaction system is conveniently and directly reflected from the user level.
In a further embodiment, the preset voice interaction instruction includes first-third voice instructions, which are a voice response instruction, a picture response instruction, and a comprehensive response instruction, and the corresponding execution action feature points are respectively voice ringing, picture correct switching, voice ringing, and picture correct switching.
The scheme divides the preset voice interaction instruction into three categories, namely a voice response instruction, a picture response instruction and a comprehensive response instruction, the response acting on the vehicle-mounted voice interaction system is that only voice is emitted, only pictures are presented, and the voice and the pictures appear simultaneously, and the action characteristic points of execution obtained by analysis of the analysis processing module are respectively voice ringing, picture correct switching, voice ringing and picture correct switching. Therefore, according to different preset voice interaction instructions, the analysis module adopts a corresponding analysis strategy, and the measured response time is more accurate.
In a further embodiment, the image acquisition module employs a high frame industrial camera and the sound acquisition module employs a sound pickup.
The scheme further limits the image acquisition module to adopt a high-frame industrial camera, and utilizes the shooting advantages of high frame and high resolution to reduce the time error between the actual time of the vehicle-mounted voice interaction system for generating the picture and the snapshot time of the high-frame industrial camera to be ignored, thereby ensuring the real-time property of acquiring the response picture and improving the accuracy of the measured response time;
the limited sound collection module adopts a sound pick-up, and the advantage of rapid collection and high fidelity of a professional sound collection device, namely the sound pick-up, is utilized to reduce the time error between the actual sound emitting time of the vehicle-mounted voice interaction system and the collection time of the sound pick-up to be ignored, so that the real-time performance of the collection response time is ensured, and the accuracy of the measured response time is improved.
The present invention also provides a method for testing response time of a vehicle-mounted voice interaction system, and the basic scheme is as follows:
a method for testing response time of a vehicle-mounted voice interaction system comprises the following steps:
s1, generating a preset voice interaction instruction, and inputting the preset voice interaction instruction to a vehicle-mounted voice interaction system loaded in a real vehicle;
s2, acquiring response information of the vehicle-mounted voice interaction system after the preset voice interaction instruction is input;
and S3, calculating the response time of the vehicle-mounted voice interaction system in the test according to the response information.
The basic scheme is as follows: the vehicle-mounted voice interaction system loaded in the real vehicle is controlled according to preset voice interaction instructions (such as starting navigation, playing music, making a call and the like) (S1), the response time of the vehicle-mounted voice interaction system is calculated according to the response information of the vehicle-mounted voice interaction system (S2, S3), and compared with a part-level laboratory test method, the real use environment of a user can be reflected better.
In a further embodiment, the response information includes a picture presented by the vehicle-mounted voice interaction system and a sound emitted by the vehicle-mounted voice interaction system.
The external expression form of responding the preset voice interaction instruction based on the vehicle-mounted voice interaction system comprises sound and pictures, the scheme collects the sound and the pictures sent by the vehicle-mounted voice interaction system respectively, and compared with a mode of directly detecting signal streams, the scheme can reflect the actual response condition of the vehicle-mounted voice interaction system from a user level.
In a further embodiment, the step S3 specifically includes:
s31, taking the acquisition starting moment of the response information as the starting point of response time;
s32, analyzing whether an execution action characteristic point corresponding to the preset voice interaction instruction appears in the response information, if so, taking the time of the occurrence of the execution action characteristic point as an end point of response time and entering a step S33, and if not, marking the test as no response;
and S33, making a difference between the starting point and the ending point to obtain corresponding response time.
In the scheme, from the user perspective, the calculation rule of the response time is further limited to the point of settlement from the acquisition starting time of the response information (also the output ending time of the preset voice interaction instruction) to the occurrence of the corresponding execution action characteristic point, so that the cognition of the general user on the response time is met, and the actual response condition of the vehicle-mounted voice interaction system is conveniently and directly reflected from the user level.
In a further embodiment, the preset voice interaction instruction includes first-third voice instructions, which are a voice response instruction, a picture response instruction, and a comprehensive response instruction, and the corresponding execution action feature points are respectively voice ringing, picture correct switching, voice ringing, and picture correct switching.
The scheme divides the preset voice interaction instruction into three categories, namely a voice response instruction, a picture response instruction and a comprehensive response instruction, the response acting on the vehicle-mounted voice interaction system is that only voice is emitted, only pictures are presented, and the voice and the pictures appear simultaneously, and the action characteristic points of execution obtained by analysis of the analysis processing module are respectively voice ringing, picture correct switching, voice ringing and picture correct switching. Therefore, according to different preset voice interaction instructions, the analysis module adopts a corresponding analysis strategy, and the measured response time is more accurate.
The invention also provides a test device, wherein the test system comprises at least one of a voice instruction control module, a system response acquisition module and an analysis processing module. The testing device is a device which is formed by independently combining a voice instruction control module, a system response acquisition module and an analysis processing module, or various devices which are formed by randomly combining the voice instruction control module, the system response acquisition module and the analysis processing module, and is also the specific image of the method and the system in implementation.
The invention also provides a storage medium, on which a computer program is stored, wherein the computer program is used for being loaded by the test system or the test equipment so as to realize the voice response time test method. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.
Drawings
Fig. 1 is a block diagram of a response time testing system of a vehicle-mounted voice interaction system according to embodiment 1 of the present invention;
fig. 2 is a flowchart of steps of a response time testing system of a vehicle-mounted voice interaction system according to embodiment 2 of the present invention.
Detailed Description
The following is further detailed by the specific embodiments:
example 1
In order to efficiently and accurately test and obtain the response time of the vehicle-mounted voice interaction system in the real vehicle environment, as shown in fig. 1, the embodiment provides a method for testing the response time of the vehicle-mounted voice interaction system, which includes steps S1-S5.
S1, generating a preset voice interaction instruction, and inputting the preset voice interaction instruction to a vehicle-mounted voice interaction system loaded in a real vehicle.
The method specifically comprises the following steps:
s11, creating a voice interaction instruction set, wherein the voice interaction instruction set comprises 1 st-mth preset voice interaction instructions and is divided into three categories of first-third voice instructions, namely a voice response instruction, a picture response instruction and a comprehensive response instruction;
s12, inputting the 1 st preset voice interaction instruction to the vehicle-mounted voice interaction system for the 1 st time;
s13, waiting for the completion of the subsequent steps S2 and S3;
s14, inputting the 1 st preset voice interaction instruction to the vehicle-mounted voice interaction system for the 2 nd time, executing the step S13 again until the 1 st preset voice interaction instruction is input to the vehicle-mounted voice interaction system for the nth time, and entering the next step after the step 13 is completed;
s15, finishing the output of the 2 nd to the mth preset instructions to the vehicle-mounted voice interaction system for n times according to the same processing procedures as the steps S12 to S14, wherein m is more than or equal to 5, and n is more than or equal to 100.
The voice interaction instruction set is created in the step and comprises the 1 st to the mth preset voice interaction instructions, different voice interaction functions can be tested, such as navigation, music playing, telephone making and the like, and the test is more comprehensive; for each preset voice interaction instruction, hundreds of times are tested (n is more than or equal to 100, different awakening instructions can be tested for different times), and the more the test times are, the more accurate the calculated response time is, but the more the test times are, the larger the workload is. During actual testing, the method can be determined according to a specific vehicle-mounted voice interaction system and testing requirements.
In this embodiment, the step of inputting the preset voice interaction instruction refers to broadcasting the preset voice interaction instruction to the vehicle-mounted voice interaction system in a preset direction.
S2, collecting response information of the vehicle-mounted voice interaction system after the preset voice interaction instruction is input.
In this step, the response information includes a picture presented by the vehicle-mounted voice interaction system and a sound emitted by the vehicle-mounted voice interaction system. Aiming at the voice response instruction, the picture response instruction and the comprehensive response instruction, the collected information is respectively the emitted sound, the displayed picture and the emitted sound plus the displayed picture.
The test conditions of steps S1 and S2 in this embodiment are shown in table 1 below.
TABLE 1
Preset voice interactive instruction (m ═ 6) | Instruction function | Instruction classes | Number of tests | Response message |
1 st Preset Voice interaction Instructions | Navigating to xx | Integrated response instruction | 100 | Voice prompt and navigation interface |
2 nd preset voice interaction instruction | Open radio | Picture response instruction | 100 | Radio interface |
3 rd Preset Voice interaction instruction | Playing songs xx | Integrated response instruction | 100 | Play interface + music sound |
4 th Preset Voice interaction instruction | Telephone give xx | Picture response instruction | 100 | Interface for communication |
5 th Preset Voice interaction Instructions | Weather report | Voice response instructions | 100 | Temperature broadcast sound |
6 th preset voice interaction instruction | Broadcasting news | Voice response instructions | 100 | News broadcasting sound |
And S3, calculating the response time of the vehicle-mounted voice interaction system in the test according to the response information.
The method specifically comprises the following steps:
s31, taking the acquisition starting time of the response information (which is also the output ending time of a preset voice interaction instruction) as the starting point of response time;
s32, analyzing whether an execution action characteristic point corresponding to the preset voice interaction instruction appears in the response information, if so, taking the time of the occurrence of the execution action characteristic point as an end point of response time and entering a step S33, and if not, marking the test as no response;
and S33, making a difference between the starting point and the ending point to obtain corresponding response time.
How does the end point of the response time understand in step S32? Different settings are provided for different types of voice interaction instructions.
And regarding the voice response instruction, the moment when the correct sound is collected is taken as the end point of the response time. The correct sound is a response sound matched with a preset voice response instruction. Taking the 5 th preset voice interaction instruction ("broadcast weather") as an example, the matched response sound is "good", that is, the weather today will be broadcast for you ", if the sound sent by the vehicle-mounted voice interaction system is matched with the voice, the sound is the" correct sound ", and the moment when the correct sound starts to be collected" is the moment when the word "good" is sent. It should be noted that, if the correct sound is not collected within a preset time period, for example, 5s, the test flag is not responded, and it is not necessary to determine the end point of the response time and calculate the corresponding response time.
And aiming at the picture response instruction, the moment when the correct picture starts to be acquired is taken as the end point of the response time. The correct picture is a response picture matched with a preset voice response instruction. Taking a 4 th preset voice interaction instruction (calling xx) as an example, the matched picture is a dialing interface, if the picture switched by the vehicle-mounted voice interaction system is matched with the dialing interface, the picture is a correct picture, and the moment when the correct picture starts to be acquired is the moment when the dialing interface is switched. It should be noted that, if the correct picture is not acquired within a preset time period, for example, 5s, the test flag is not responded, and it is not necessary to determine the end point of the response time and calculate the corresponding response time.
For the comprehensive response instruction (collecting sound and picture at the same time), the selection of the end point of the response time is relatively complex. According to the setting, if the time difference between the start of collecting the correct sound and the start of detecting the correct picture is in the preset range, the time before the two is taken as the end point of the response time, and conversely, if the time difference exceeds the preset range, the time after the two is taken as the end point of the response time. It should be noted that, if the correct sound and picture are not collected within a preset time period, for example, 5s, the test flag is not responded, and it is not necessary to determine the end point of the response time and calculate the corresponding response time.
In the embodiment, from the user perspective, the calculation rule of the response time is further defined as counting from the acquisition start time of the response information (also the output end time of the preset voice interaction instruction) to the occurrence of the corresponding execution action characteristic point settlement, so that the method conforms to the cognition of a general user on the response time, and is convenient for directly reflecting the actual response condition of the vehicle-mounted voice interaction system from the user level.
And S4, counting the response time of each preset voice interaction instruction.
For the 1 st to 6 th preset voice interaction instructions, the embodiment tests 100 times, and then there are corresponding 100 results, if there is a correct response within a preset time period, for example, 5s, there is a corresponding response time, and if there is no correct response, it is marked as no response.
Taking the first preset voice interaction command (navigation-going xx) as an example, the statistical response time in this step is shown in table 2 below, where "-" indicates no response.
TABLE 2
And S5, calculating a corresponding response time average value, a non-response rate and the like according to the statistical result of the step S4.
Taking the first preset voice interaction instruction (navigation-go xx) as an example, the data in table 2 above is calculated in this step, and the corresponding response time average value P and non-response rate F are obtained.
P-236.24/97 ≈ 2.44, and F-3/100 ≈ 3%. According to actual use requirements, any parameter, such as variance, can be calculated according to the data in table 2, and the fluctuation condition of the measured response time can be represented, so that the stability of the vehicle-mounted voice interaction system is reflected.
In summary, according to the method for testing the response time of the vehicle-mounted voice interaction system provided by this embodiment, the vehicle-mounted voice interaction system loaded in the real vehicle is controlled according to the preset voice interaction instruction (such as starting navigation, playing music, making a call, and the like), and the response time of the vehicle-mounted voice interaction system is calculated according to the response information of the vehicle-mounted voice interaction system.
Example 2
The reference numbers in the drawings in the present embodiment include: the system comprises a voice instruction control module 10, a system response acquisition module 20, an analysis processing module 30, a vehicle-mounted voice interaction system 40, an image acquisition module 21 and a sound acquisition module 22.
Referring to fig. 2, a response time testing system of a vehicle-mounted voice interaction system includes a voice instruction control module 10, a system response acquisition module 20, and an analysis processing module 30; the voice instruction control module 10 is configured to generate a preset voice interaction instruction and input the preset voice interaction instruction to a vehicle-mounted voice interaction system 40 loaded in the real vehicle; the system response acquisition module 20 is configured to acquire response information of the vehicle-mounted voice interaction system 40 after a preset voice interaction instruction is input; the analysis processing module 30 is configured to obtain the response information, and calculate a response time of the vehicle-mounted voice interaction system 40 according to the response information.
In the present embodiment, the system response acquisition module 20 includes an image acquisition module 21 and a sound acquisition module 22; the image acquisition module 21 is configured to acquire a picture presented by the vehicle-mounted voice interaction system 40 and input the picture to the analysis processing module 30; the sound collection module 22 is configured to collect sound emitted by the vehicle-mounted voice interaction system 40 and input the sound to the analysis processing module 30. In the embodiment, the external representation form of the vehicle-mounted voice interaction system 40 responding to the preset voice interaction instruction includes two forms, namely, sound and picture, and the image acquisition module 21 and the sound acquisition module 22 are adopted to respectively acquire the sound and the picture sent by the vehicle-mounted voice interaction system 40, so that the actual response condition of the vehicle-mounted voice interaction system 40 can be reflected from a user plane better than a mode of directly detecting a signal stream.
In this embodiment, the calculating the response time of the vehicle-mounted voice interaction system 40 according to the response information specifically includes: taking the acquisition starting moment of the response information as the starting point of response time; analyzing whether an execution action characteristic point corresponding to the preset voice interaction instruction appears in the response information, if so, taking the time of the occurrence of the execution action characteristic point as the end point of response time, and if not, marking the test as no response; and obtaining the corresponding response time by making a difference between the starting point and the ending point. These processing procedures correspond to the method described in embodiment 1, and this embodiment is not described again.
In this embodiment, the preset voice interaction instruction includes first-third types of voice instructions, which are a voice response instruction, a picture response instruction, and a comprehensive response instruction, and the corresponding execution action feature points are voice ringing, picture correct switching, voice ringing, and picture correct switching, respectively. Similarly, this embodiment is not repeated, corresponding to the method described in embodiment 1.
The voice instruction control module 10 of this embodiment divides the preset voice interaction instruction into three categories, which are a voice response instruction, a picture response instruction, and a comprehensive response instruction, and the response acting on the vehicle-mounted voice interaction system 40 is to only make a sound, only present a picture, and simultaneously present a sound and a picture, and the feature points of the execution action analyzed and obtained by the analysis processing module 30 are respectively a voice ringing, a picture correct switching, a voice ringing, and a picture correct switching. Therefore, according to different preset voice interaction instructions, the analysis module adopts a corresponding analysis strategy, and the measured response time is more accurate.
In this embodiment, the image capturing module 21 is a high frame industrial camera, and the sound capturing module 22 is a sound pickup. The high-frame industrial camera adopts CP80-25-M/C-72 of Optronics, Germany, and the sound pick-up adopts HD-18Y/V desktop sound pick-up (omnidirectional) of beacon electronics. In the embodiment, the image acquisition module 21 is further limited to adopt a high-frame industrial camera, and the time error between the actual time of the vehicle-mounted voice interaction system 40 appearing the picture and the snapshot time of the high-frame industrial camera is reduced to be ignored by utilizing the shooting advantages of high frame and high resolution, so that the real-time performance of acquiring the response picture is ensured, and the accuracy of the measured response time is improved; the sound collecting module 22 is limited to adopt a sound pick-up, and by utilizing the advantages of rapid collection and high fidelity of a professional sound collecting device, the time error between the actual time of sound emission of the vehicle-mounted voice interaction system 40 and the collecting time of the sound pick-up is reduced to be ignored, so that the real-time performance of collecting response time is ensured, and the accuracy of the measured response time is improved.
In this embodiment, the voice command control module 10 and the analysis processing module 30 are both hardware modules with software, and in this embodiment, an upper computer is adopted, and the high-frame industrial camera and the sound pickup are connected to the upper computer through respective data lines to transmit the video images and sounds respectively collected in real time.
More specifically, the upper computer is provided with voice instruction generation simulation software, so that the voice of different types of human beings such as men, women, adults and children can be simulated, the output decibel value, the speech speed, the high-low frequency and the like of the voice can be set, dialects and foreign languages around the country can be collected for learning, and dialects and foreign languages around the country except the mandarin can be simulated to meet different voice interaction test requirements. The upper computer is further provided with analysis and processing software which analyzes data collected by the high-frame industrial camera and the sound pickup, and the specific analysis and processing process is as described in embodiment 1 and is not repeated in this embodiment. It should be added that the setting of the preset time period used in the analysis process, the determination of the correct sound or the correct picture is based on the fact that the software has stored the relevant correct sound and correct picture for comparison in advance. For each vehicle-mounted voice interaction system, in the embodiment, each input voice interaction instruction has corresponding response information, and the information is a unique response. Thus, the accuracy of response time measurement can be ensured.
In summary, the response time testing system of the vehicle-mounted voice interaction system provided in this embodiment controls the vehicle-mounted voice interaction system 40 loaded in the real vehicle according to the preset voice interaction instruction (such as starting navigation, playing music, making a call, and the like), and calculates the response time according to the response information of the vehicle-mounted voice interaction system 40, so that compared with a part-level laboratory testing method, the real use environment of the user can be better reflected.
The test system provided by the embodiment adopts each module to realize each step in the test method, provides a hardware basis for the test method, and is convenient for method implementation.
Example 3
The present embodiment provides a testing apparatus, which at least includes one of the voice command control module 10, the image capturing module 21, the sound capturing module 22, and the analysis processing module 30 described in the testing system in embodiment 2. That is, these modules are individually made into devices or combined into various devices as desired, and the method is also embodied in the implementation. The difference between this embodiment and embodiment 2 is that this embodiment focuses on protecting a device in order to protect the integrity of the structure. For example, a common desktop office system includes a display module and an operation module. The display is used as a display module and the case is used as an operation module. That is, this embodiment protects the device made of any one module alone in embodiment 1, and also protects any two, three, or all four devices integrated together.
As a preferred embodiment, the test device of this embodiment is mainly built based on an upper computer, and the voice instruction control module 10 is software loaded on the computer, and can automatically generate various preset voice interaction instructions and also can broadcast the instructions; the image acquisition module 21 is connected with a high-frame industrial camera of an upper computer through a data line and performs real-time transmission of images with the upper computer; the sound acquisition module 22 is connected with a recorder of an upper computer through a data line and performs real-time sound transmission with the upper computer; the analysis processing module 30 is also analysis software loaded on the computer, and can store pictures and sounds transmitted by the high-frame industrial camera and the sound recorder in real time, compare the information with pre-stored response information, further calculate response time if the comparison is passed, and mark that the system does not respond if the comparison is failed. The analysis software also has data processing functions, including summing, averaging, calculating variance, standard deviation, calculating the unresponsive rate or the responsive rate of a certain preset voice interaction instruction, and the like, and can also generate a responsive chart, report, and the like.
Example 4
This embodiment further provides a storage medium, on which a computer program is stored, where the computer program is used to be loaded by the voice response time testing system described in embodiment 2 or the testing apparatus described in embodiment 3, so as to implement the voice response time testing method described in embodiment 1. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.
The foregoing is merely an example of the present invention, and common general knowledge in the field of known specific structures and characteristics is not described herein in any greater extent than that known in the art at the filing date or prior to the priority date of the application, so that those skilled in the art can now appreciate that all of the above-described techniques in this field and have the ability to apply routine experimentation before this date can be combined with one or more of the present teachings to complete and implement the present invention, and that certain typical known structures or known methods do not pose any impediments to the implementation of the present invention by those skilled in the art. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (10)
1. The utility model provides a response time test system of on-vehicle voice interaction system which characterized in that: the system comprises a voice instruction control module, a system response acquisition module and an analysis processing module;
the voice instruction control module is used for generating a preset voice interaction instruction and inputting the preset voice interaction instruction to a vehicle-mounted voice interaction system loaded in the real vehicle;
the system response acquisition module is used for acquiring response information of the vehicle-mounted voice interaction system after the preset voice interaction instruction is input;
and the analysis processing module is used for acquiring the response information and calculating the response time of the vehicle-mounted voice interaction system in the test according to the response information.
2. The response time testing system of the vehicle-mounted voice interaction system as claimed in claim 1, wherein: the system response acquisition module comprises an image acquisition module and a sound acquisition module;
the image acquisition module is used for acquiring the picture presented by the vehicle-mounted voice interaction system and inputting the picture to the analysis processing module;
the sound collection module is used for collecting the sound emitted by the vehicle-mounted voice interaction system and inputting the sound to the analysis processing module.
3. The system for testing the response time of the vehicle-mounted voice interaction system according to claim 2, wherein the calculating the response time for testing the vehicle-mounted voice interaction system according to the response information specifically comprises:
taking the acquisition starting moment of the response information as the starting point of response time;
analyzing whether an execution action characteristic point corresponding to the preset voice interaction instruction appears in the response information, if so, taking the time of the occurrence of the execution action characteristic point as the end point of response time, and if not, marking the test as no response;
and obtaining the corresponding response time by making a difference between the starting point and the ending point.
4. The response time testing system of the vehicle-mounted voice interaction system as claimed in claim 3, wherein: the preset voice interaction instruction comprises a first-third type voice instruction which are a voice response instruction, a picture response instruction and a comprehensive response instruction respectively, and the corresponding execution action characteristic points are voice ringing, picture correct switching, voice ringing and picture correct switching respectively.
5. The response time testing system of the vehicle-mounted voice interaction system as claimed in claim 2, wherein: the image acquisition module adopts a high-frame industrial camera, and the sound acquisition module adopts a sound pick-up.
6. A method for testing response time of a vehicle-mounted voice interaction system is characterized by comprising the following steps:
s1, generating a preset voice interaction instruction, and inputting the preset voice interaction instruction to a vehicle-mounted voice interaction system loaded in a real vehicle;
s2, acquiring response information of the vehicle-mounted voice interaction system after the preset voice interaction instruction is input;
and S3, calculating the response time of the vehicle-mounted voice interaction system in the test according to the response information.
7. The response time testing system of claim 6, wherein in said step S2, said response information includes the picture presented by said vehicle-mounted voice interactive system and the sound emitted.
8. The response time testing system of the vehicle-mounted voice interaction system according to claim 7, wherein the step S3 specifically includes:
s31, taking the acquisition starting moment of the response information as the starting point of response time;
s32, analyzing whether an execution action characteristic point corresponding to the preset voice interaction instruction appears in the response information, if so, taking the time of the occurrence of the execution action characteristic point as an end point of response time and entering a step S33, and if not, marking the test as no response;
and S33, making a difference between the starting point and the ending point to obtain corresponding response time.
9. The response time testing system of the vehicle-mounted voice interaction system according to claim 8, wherein in the step S1, the preset voice interaction command includes first-third voice commands, which are a voice response command, a picture response command, and a comprehensive response command, respectively; in step S32, the corresponding execution operation feature points are respectively a sound-off, a correct screen switching, and a sound-off and correct screen switching.
10. A test apparatus, characterized by: at least one module of the voice command control module, the system response acquisition module and the analysis processing module of any one of claims 1 to 5 is included.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010560409.4A CN111724782B (en) | 2020-06-18 | 2020-06-18 | Response time testing system, method and equipment of vehicle-mounted voice interaction system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010560409.4A CN111724782B (en) | 2020-06-18 | 2020-06-18 | Response time testing system, method and equipment of vehicle-mounted voice interaction system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111724782A true CN111724782A (en) | 2020-09-29 |
CN111724782B CN111724782B (en) | 2022-09-13 |
Family
ID=72567563
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010560409.4A Active CN111724782B (en) | 2020-06-18 | 2020-06-18 | Response time testing system, method and equipment of vehicle-mounted voice interaction system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111724782B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112405561A (en) * | 2020-11-30 | 2021-02-26 | 天津链数科技有限公司 | Testing system for intelligent level test of household appliances |
CN112908297A (en) * | 2020-12-22 | 2021-06-04 | 北京百度网讯科技有限公司 | Response speed testing method, device, equipment and storage medium for vehicle-mounted equipment |
CN112908357A (en) * | 2021-01-19 | 2021-06-04 | 广州橙行智动汽车科技有限公司 | Instrument sound testing method and device, testing equipment and storage medium |
CN113223556A (en) * | 2021-03-25 | 2021-08-06 | 惠州市德赛西威汽车电子股份有限公司 | Sentence synthesis testing method for vehicle-mounted voice system |
CN113436611A (en) * | 2021-06-11 | 2021-09-24 | 阿波罗智联(北京)科技有限公司 | Test method and device for vehicle-mounted voice equipment, electronic equipment and storage medium |
CN113567778A (en) * | 2021-06-30 | 2021-10-29 | 南京富士通南大软件技术有限公司 | Scene-based real-vehicle automatic testing method for vehicle-mounted information entertainment system |
CN113643704A (en) * | 2021-08-18 | 2021-11-12 | 中国第一汽车股份有限公司 | Test method, upper computer, system and storage medium of vehicle-mounted machine voice system |
US20210358477A1 (en) * | 2018-05-23 | 2021-11-18 | Konica Minolta, Inc. | Job record specifying device, image processing apparatus, server, job record specifying method, and recording medium |
CN113900960A (en) * | 2021-12-02 | 2022-01-07 | 中汽研软件测评(天津)有限公司 | Intelligent vehicle mechanical arm test platform system |
CN114120969A (en) * | 2022-01-29 | 2022-03-01 | 中国电子技术标准化研究院 | Method and system for testing voice recognition function of intelligent terminal and electronic equipment |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050197836A1 (en) * | 2004-01-08 | 2005-09-08 | Jordan Cohen | Automated testing of voice recognition software |
CN103077718A (en) * | 2013-01-09 | 2013-05-01 | 华为终端有限公司 | Speech processing method, system and terminal |
US20160253989A1 (en) * | 2015-02-27 | 2016-09-01 | Microsoft Technology Licensing, Llc | Speech recognition error diagnosis |
CN106548772A (en) * | 2017-01-16 | 2017-03-29 | 上海智臻智能网络科技股份有限公司 | Speech recognition test system and method |
CN108228468A (en) * | 2018-02-12 | 2018-06-29 | 腾讯科技(深圳)有限公司 | A kind of test method, device, test equipment and storage medium |
CN108388926A (en) * | 2018-03-15 | 2018-08-10 | 百度在线网络技术(北京)有限公司 | The determination method and apparatus of interactive voice satisfaction |
CN108899012A (en) * | 2018-07-27 | 2018-11-27 | 中国电子产品可靠性与环境试验研究所((工业和信息化部电子第五研究所)(中国赛宝实验室)) | Interactive voice equipment evaluating method, system, computer equipment and storage medium |
CN110335590A (en) * | 2019-07-04 | 2019-10-15 | 中国联合网络通信集团有限公司 | Speech recognition test method, apparatus and system |
CN110379410A (en) * | 2019-07-22 | 2019-10-25 | 苏州思必驰信息科技有限公司 | Voice response speed automatic analysis method and system |
CN110838285A (en) * | 2019-11-20 | 2020-02-25 | 青岛海尔科技有限公司 | System, method and device for terminal voice test |
CN111261195A (en) * | 2020-01-10 | 2020-06-09 | Oppo广东移动通信有限公司 | Audio testing method and device, storage medium and electronic equipment |
-
2020
- 2020-06-18 CN CN202010560409.4A patent/CN111724782B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050197836A1 (en) * | 2004-01-08 | 2005-09-08 | Jordan Cohen | Automated testing of voice recognition software |
CN103077718A (en) * | 2013-01-09 | 2013-05-01 | 华为终端有限公司 | Speech processing method, system and terminal |
US20160253989A1 (en) * | 2015-02-27 | 2016-09-01 | Microsoft Technology Licensing, Llc | Speech recognition error diagnosis |
CN106548772A (en) * | 2017-01-16 | 2017-03-29 | 上海智臻智能网络科技股份有限公司 | Speech recognition test system and method |
CN108228468A (en) * | 2018-02-12 | 2018-06-29 | 腾讯科技(深圳)有限公司 | A kind of test method, device, test equipment and storage medium |
CN108388926A (en) * | 2018-03-15 | 2018-08-10 | 百度在线网络技术(北京)有限公司 | The determination method and apparatus of interactive voice satisfaction |
CN108899012A (en) * | 2018-07-27 | 2018-11-27 | 中国电子产品可靠性与环境试验研究所((工业和信息化部电子第五研究所)(中国赛宝实验室)) | Interactive voice equipment evaluating method, system, computer equipment and storage medium |
CN110335590A (en) * | 2019-07-04 | 2019-10-15 | 中国联合网络通信集团有限公司 | Speech recognition test method, apparatus and system |
CN110379410A (en) * | 2019-07-22 | 2019-10-25 | 苏州思必驰信息科技有限公司 | Voice response speed automatic analysis method and system |
CN110838285A (en) * | 2019-11-20 | 2020-02-25 | 青岛海尔科技有限公司 | System, method and device for terminal voice test |
CN111261195A (en) * | 2020-01-10 | 2020-06-09 | Oppo广东移动通信有限公司 | Audio testing method and device, storage medium and electronic equipment |
Non-Patent Citations (2)
Title |
---|
BHARATH SUDHARSAN等: "AI Vision: Smart speaker design and implementation with object detection custom skill and advanced voice interaction capability", 《2019 11TH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTING (ICOAC)》 * |
程杨 等: "智能音箱语音交互性能评测探索", 《 第17届全国互联网与音视频广播发展研讨会暨第26届中国数字广播电视与网络发展年会论文集》 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11769485B2 (en) * | 2018-05-23 | 2023-09-26 | Konica Minolta, Inc. | Job record specifying device, image processing apparatus, server, job record specifying method, and recording medium |
US20210358477A1 (en) * | 2018-05-23 | 2021-11-18 | Konica Minolta, Inc. | Job record specifying device, image processing apparatus, server, job record specifying method, and recording medium |
CN112405561A (en) * | 2020-11-30 | 2021-02-26 | 天津链数科技有限公司 | Testing system for intelligent level test of household appliances |
EP3865996A3 (en) * | 2020-12-22 | 2022-01-12 | Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd. | Method and apparatus for testing response speed of on-board equipment, device and storage medium |
CN112908297A (en) * | 2020-12-22 | 2021-06-04 | 北京百度网讯科技有限公司 | Response speed testing method, device, equipment and storage medium for vehicle-mounted equipment |
US20210327427A1 (en) * | 2020-12-22 | 2021-10-21 | Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd. | Method and apparatus for testing response speed of on-board equipment, device and storage medium |
JP7346496B2 (en) | 2020-12-22 | 2023-09-19 | 阿波羅智聯(北京)科技有限公司 | Method, device, equipment and storage medium for testing response speed of in-vehicle equipment |
CN112908297B (en) * | 2020-12-22 | 2022-07-08 | 北京百度网讯科技有限公司 | Response speed testing method, device, equipment and storage medium of vehicle-mounted equipment |
JP2022003388A (en) * | 2020-12-22 | 2022-01-11 | 阿波羅智聯(北京)科技有限公司Apollo Intelligent Connectivity(Beijing) Technology Co., Ltd. | Method, device, apparatus and storage medium for testing response speed of on-vehicle apparatus |
CN112908357A (en) * | 2021-01-19 | 2021-06-04 | 广州橙行智动汽车科技有限公司 | Instrument sound testing method and device, testing equipment and storage medium |
CN113223556A (en) * | 2021-03-25 | 2021-08-06 | 惠州市德赛西威汽车电子股份有限公司 | Sentence synthesis testing method for vehicle-mounted voice system |
CN113436611A (en) * | 2021-06-11 | 2021-09-24 | 阿波罗智联(北京)科技有限公司 | Test method and device for vehicle-mounted voice equipment, electronic equipment and storage medium |
CN113567778A (en) * | 2021-06-30 | 2021-10-29 | 南京富士通南大软件技术有限公司 | Scene-based real-vehicle automatic testing method for vehicle-mounted information entertainment system |
CN113567778B (en) * | 2021-06-30 | 2023-12-29 | 南京富士通南大软件技术有限公司 | Scene-based real-vehicle automatic testing method for vehicle-mounted information entertainment system |
CN113643704A (en) * | 2021-08-18 | 2021-11-12 | 中国第一汽车股份有限公司 | Test method, upper computer, system and storage medium of vehicle-mounted machine voice system |
CN113900960A (en) * | 2021-12-02 | 2022-01-07 | 中汽研软件测评(天津)有限公司 | Intelligent vehicle mechanical arm test platform system |
CN114120969A (en) * | 2022-01-29 | 2022-03-01 | 中国电子技术标准化研究院 | Method and system for testing voice recognition function of intelligent terminal and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN111724782B (en) | 2022-09-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111724782B (en) | Response time testing system, method and equipment of vehicle-mounted voice interaction system | |
CN110415681B (en) | Voice recognition effect testing method and system | |
US10861480B2 (en) | Method and device for generating far-field speech data, computer device and computer readable storage medium | |
US10997965B2 (en) | Automated voice processing testing system and method | |
US20060235699A1 (en) | Automating input when testing voice-enabled applications | |
CN109637525B (en) | Method and apparatus for generating an on-board acoustic model | |
CN108305618B (en) | Voice acquisition and search method, intelligent pen, search terminal and storage medium | |
CN111739512A (en) | Voice wake-up rate testing method, system, device and medium based on real vehicle | |
CN112151029A (en) | Voice awakening and recognition automatic test method, storage medium and test terminal | |
CN111031463B (en) | Microphone array performance evaluation method, device, equipment and medium | |
CN109102824B (en) | Voice error correction method and device based on man-machine interaction | |
CN111261195A (en) | Audio testing method and device, storage medium and electronic equipment | |
WO2016129740A1 (en) | Embedded voice recognition treatment method and system employing error db module based on user pattern | |
CN108874665A (en) | A kind of test result method of calibration, device, equipment and medium | |
CN110837758B (en) | Keyword input method and device and electronic equipment | |
CN109616106A (en) | Vehicle-mounted control screen voice recognition process testing method, electronic equipment and system | |
CN113014844A (en) | Audio processing method and device, storage medium and electronic equipment | |
CN111968676A (en) | Pronunciation correction method and device, electronic equipment and storage medium | |
CN111868823A (en) | Sound source separation method, device and equipment | |
CN111951833A (en) | Voice test method and device, electronic equipment and storage medium | |
CN113053365B (en) | Voice separation method, device, equipment and storage medium | |
CN107197404B (en) | Automatic sound effect adjusting method and device and recording and broadcasting system | |
CN108922275B (en) | Distance education system and education method | |
CN115174818B (en) | Target tracking method based on sound positioning, electronic equipment and readable storage medium | |
CN105847689A (en) | Focusing method, focusing device and mobile terminal |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |