CN112822487A - Method and system for detecting voice performance of display equipment - Google Patents
Method and system for detecting voice performance of display equipment Download PDFInfo
- Publication number
- CN112822487A CN112822487A CN202011642628.3A CN202011642628A CN112822487A CN 112822487 A CN112822487 A CN 112822487A CN 202011642628 A CN202011642628 A CN 202011642628A CN 112822487 A CN112822487 A CN 112822487A
- Authority
- CN
- China
- Prior art keywords
- display
- test
- detection
- display device
- test parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012360 testing method Methods 0.000 claims abstract description 194
- 238000001514 detection method Methods 0.000 claims abstract description 180
- 238000013102 re-test Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000012015 optical character recognition Methods 0.000 description 6
- 238000011056 performance test Methods 0.000 description 2
- 238000005316 response function Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/04—Diagnosis, testing or measuring for television systems or their details for receivers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- 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
- G10L15/01—Assessment or evaluation of speech recognition systems
-
- 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
- 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)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention provides a method and a system for detecting the voice performance of display equipment, wherein the method for detecting the voice performance of the display equipment comprises the following steps: obtaining test parameters, wherein the test parameters comprise: the method comprises the following steps of obtaining entry audio, relative position parameters of an instruction sending sound source and a display device to be tested, and volume size parameters of the instruction sending sound source, wherein the entry audio is used for controlling display contents of the display device to be tested; adjusting the sound source sent by the instruction according to the test parameters; starting the instruction to send out a sound source so as to play the entry audio; shooting a display interface of the display equipment to be detected to obtain a detection image; identifying the detection image to acquire display content of the display equipment; and judging whether the voice performance of the display equipment under the test parameters is normal or not according to the display content of the display equipment. The invention can automatically test the voice performance of the display equipment.
Description
Technical Field
The invention relates to the technical field of equipment performance detection, in particular to a method and a system for detecting voice performance of display equipment.
Background
With the rapid development of technology, most of the existing display devices have a voice recognition function, such as a mobile phone, a television, and the like. The detection of the voice performance of the display device is particularly important, wherein the voice performance of the display device refers to the performance of the display device in response to the recognition of the voice command.
The detection of the speech performance of existing display devices is usually performed manually. Specifically, a tester simulates silence, self-noise and external noise, and a sound source sends a voice instruction to the display device under various combined environments with different distances from the television, and then the voice performance of the television is judged by observing the response condition of the display device.
However, the manual detection method cannot realize long-time continuous detection, and the manual detection cannot unify the test standards, so that the measurement accuracy is low, and meanwhile, the manual detection is easy to cause false detection due to fatigue, so that the detection efficiency is reduced.
Disclosure of Invention
In order to solve the problems, the method and the system for detecting the voice performance of the display equipment can automatically adjust the relative position of the instruction sending sound source and the display equipment to be detected by acquiring the test parameters, so that a large amount of labor input can be saved, and the detection efficiency is improved.
In a first aspect, the present invention provides a method for detecting voice performance of a display device, including:
obtaining test parameters, wherein the test parameters comprise: the method comprises the following steps of obtaining entry audio, relative position parameters of an instruction sending sound source and a display device to be tested, and volume size parameters of the instruction sending sound source, wherein the entry audio is used for controlling display contents of the display device to be tested;
adjusting the sound source sent by the instruction according to the test parameters;
starting the instruction to send out a sound source so as to play the entry audio;
shooting a display interface of the display equipment to be detected to obtain a detection image;
identifying the detection image to acquire display content of the display equipment;
and judging whether the voice performance of the display equipment under the test parameters is normal or not according to the display content of the display equipment.
Optionally, before the obtaining the test parameters, the method further includes:
acquiring a detection item list, wherein the detection item list comprises a plurality of detection items, and each detection item corresponds to at least one group of test parameters;
the acquiring of the test parameters comprises:
determining a detection item to be tested in the detection item list;
and acquiring corresponding test parameters according to the detection items.
Optionally, the plurality of detection items include: a wake-up detection item;
the awakening detection item is used for detecting whether the display equipment to be detected can be switched from a standby state to an awakening state;
the acquiring of the test parameters comprises: acquiring test parameters corresponding to the awakening detection items;
the judging whether the voice performance of the display device under the test parameters is normal according to the display content of the display device includes: judging whether the awakening voice performance of the display equipment is normal or not according to the display content of the display equipment;
the method further comprises the following steps: and after the awakening voice performance of the display equipment is determined to be normal, determining detection items except the awakening detection item in the detection item list to test.
Optionally, the method further comprises:
if the voice performance of the display device under the test parameters is normal, judging whether all the test parameters in the test items are tested, if not, testing the test parameters which are not tested in the test items, if so, judging whether all the test items in the test item list are tested, and if not, testing the test items which are not tested in the test item list.
Optionally, if the voice performance of the display device under the test parameters is not normal, executing a retesting step;
the retesting step includes:
shooting a display interface of the display equipment to be detected to obtain a detection image;
identifying the detection image to acquire display content of the display equipment;
judging whether the voice performance of the display equipment under the test parameters is normal or not according to the display content of the display equipment;
the method further comprises the following steps: if the voice performance of the display equipment under the test parameters is normal, outputting and storing a test result;
and if the retest step is executed for the specified times under the same test parameter, stopping executing the retest step, outputting the last test result in the retest step and storing the test result.
Optionally, entry audio corresponding to multiple test parameters in the same detection item is the same, and different entry audio corresponds to different preset identifiers;
the judging whether the voice performance of the display device under the test parameters is normal according to the display content of the display device includes:
determining a display identifier in the display content according to the display content of the display equipment;
and judging whether the voice performance of the display equipment under the test parameters is normal or not according to the similarity between the display identifier and the preset identifier.
In a second aspect, the present invention provides a display device voice performance detection system, including:
a first obtaining module configured to obtain test parameters, the test parameters including: the method comprises the following steps of obtaining entry audio, relative position parameters of an instruction sending sound source and a display device to be tested, and volume size parameters of the instruction sending sound source, wherein the entry audio is used for controlling display contents of the display device to be tested;
the adjusting module is configured to adjust the instruction emitting sound source according to the test parameters;
the starting module is configured to start the instruction to send out a sound source so as to play the entry audio;
the shooting module is configured to shoot a display interface of the display device to be detected so as to obtain a detection image;
the identification module is configured to identify the detection image so as to acquire display content of the display device;
and the first judging module is configured to judge whether the voice performance of the display equipment under the test parameters is normal according to the display content of the display equipment.
Optionally, the system comprises:
a second obtaining module, configured to obtain a detection item list before obtaining the test parameters, where the detection item list includes a plurality of detection items, and each detection item corresponds to at least one set of test parameters;
the first obtaining module comprises:
a first determining submodule configured to determine a detection item to be tested in the detection item list;
and the acquisition sub-module is configured to acquire the corresponding test parameters according to the detection items.
Optionally, the plurality of detection items include: a wake-up detection item;
the awakening detection item is used for detecting whether the display equipment to be detected can be switched from a standby state to an awakening state;
the first obtaining module is further configured to obtain a test parameter corresponding to the wake-up detection item;
the first judging module is further configured to judge whether the awakening voice performance of the display device is normal according to the display content of the display device;
the system further comprises: and the determining module is configured to determine detection items except the awakening detection item in the detection item list for testing after the awakening voice performance of the display device is determined to be normal.
Optionally, the system further comprises:
the second judging module is configured to judge whether all the test parameters in the test items are tested if the voice performance of the display device under the test parameters is normal, if not, test the test parameters which are not tested in the test items, if yes, judge whether all the test items in the test item list are tested, and if not, test the test items which are not tested in the test item list.
According to the method and the system for detecting the voice performance of the display equipment, the relative position of the instruction sending sound source and the display equipment to be detected can be automatically adjusted by obtaining the test parameters, so that a large amount of labor investment can be saved, the detection efficiency is improved, meanwhile, whether the voice recognition and response program of the voice performance of the display equipment is abnormal or not can be further judged by utilizing the display function of the display equipment, and the automation degree of the voice performance detection of the display equipment is further improved.
Drawings
Fig. 1 is a schematic flow chart of a method for detecting voice performance of a display device according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a display device voice performance detection system according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms to which the present invention relates are explained as follows:
near-field speech: and sending the voice command to the television end through the remote controller by using the remote controller equipment.
Far-field speech: the voice instruction is directly obtained through a microphone of the television without using a remote controller device.
Self-noise: during the speech performance test, the sound interference from the television: such as the audio being played.
External noise: during the voice performance test, sound interference from the environment: such as the sound of other equipment in the room.
In a first aspect, the present invention provides a method for detecting voice performance of a display device, which, with reference to fig. 1, includes steps S101 to S106:
step S101: and acquiring test parameters.
Wherein the test parameters include: the method comprises the following steps of obtaining entry audio, relative position parameters of an instruction sending sound source and a display device to be tested, and volume size parameters of the instruction sending sound source; the relative position parameters of the command sending sound source and the display equipment to be tested comprise: the distance between the instruction sending sound source and the display equipment to be tested and the included angle between the instruction sending sound source and the display equipment to be tested relative to the specified straight line are determined; and the entry audio is used for controlling the display content of the display equipment to be tested.
In an optional embodiment, before the obtaining the test parameters, the method further comprises: and acquiring a detection item list, wherein the detection item list comprises a plurality of detection items, and each detection item corresponds to at least one group of test parameters.
Further, the obtaining of the test parameters includes: determining a detection item to be tested in the detection item list; and acquiring corresponding test parameters according to the detection items. The test sequence of the detection items can be determined by the arrangement sequence of the detection items in the detection item list, or by the priority of the detection items. In this embodiment, the detection items are sequentially arranged in the detection item list from top to bottom according to the priorities of the detection items, and when the detection items are tested, the detection items are sequentially arranged in the detection item list according to the order of the detection items.
Step S102: and adjusting the sound source sent by the instruction according to the test parameters.
In this embodiment, the entry audio corresponding to the multiple test parameters in the same detection item is the same, and the difference is the relative position parameter between the command-emitting sound source and the display device to be tested, and the volume parameter of the command-emitting sound source.
For example, in a process of testing a certain test item on a display device to be tested, the requirement for the distance of a sound source sending an instruction relative to the display device to be tested includes: 5, 10 and 20 meters; the command sending sound source and the included angle requirement of the display equipment to be tested on a straight line which is relatively perpendicular to the front surface of the display equipment to be tested and passes through the center of the display equipment to be tested comprise: 60 degrees, 90 degrees, and 120 degrees; the volume size parameter requirements for instructing the sound source to issue include: 30 db, 60 db and 90 db. Therefore, the detection item comprises 27 groups of test parameters, and the voice performance of the display equipment to be detected can be detected under near-field voice and far-field voice.
In addition, the test parameters further comprise the setting of an interference-free sound source, the relative position parameters of the interference sound source and the display equipment to be tested, and the volume size parameters of the interference sound source, so that one detection item can comprise hundreds or thousands of groups of test parameters, and therefore the voice performance of the display equipment to be tested can be detected under near-field voice and far-field voice respectively, and meanwhile the voice performance of the display equipment to be tested can be detected under self noise and external noise respectively.
Step S103: and starting the instruction to send out a sound source so as to play the entry audio.
At this time, if the speech recognition function and the response function of the display device to be tested are normal, the display device to be tested can display corresponding contents through the display interface according to the contents of the vocabulary entry audio. If the content of the entry audio is 'returning to the homepage', the display device to be tested can display the content of the homepage; if the content of the entry audio is 'open setting interface', the display device to be tested can display the content of the setting interface.
Step S104: and shooting the display interface of the display equipment to be detected through a camera to acquire a detection image.
Step S105: and identifying the detection image to acquire the display content of the display equipment.
Step S106: and judging whether the voice performance of the display equipment under the test parameters is normal or not according to the display content of the display equipment.
The display device voice performance detection party can automatically adjust the relative position of the instruction sending sound source and the display device to be detected by acquiring the test parameters, so that a large amount of labor investment can be saved, the detection efficiency is improved, and meanwhile, whether the voice recognition of the voice performance of the display device and the response program are abnormal or not can be further judged by utilizing the display function of the display device, so that the automation degree of the voice performance detection of the display device is further improved.
In an alternative embodiment, the plurality of detection items includes: and (5) awakening the detection item. The awakening detection item is used for detecting whether the display equipment to be detected can be switched from a standby state to an awakening state.
Further, the obtaining of the test parameters includes: and acquiring test parameters corresponding to the awakening detection items. The judging whether the voice performance of the display device under the test parameters is normal according to the display content of the display device includes: and judging whether the awakening voice performance of the display equipment is normal or not according to the display content of the display equipment.
Specifically, for example, the entry audio corresponding to the wake-up detection item is "Xiaozhuizhuan". When the command sends out a sound source playing 'Xiaoyan', if the voice recognition function and the response function of the display equipment to be tested are normal, a wake-up interface is displayed on the display interface of the display equipment to be tested, and the recording function of the display equipment to be tested is turned on. And when the interface is awakened, the semi-transparent window body is positioned at the bottom of the display interface and is provided with fixed character or picture marks.
The method further comprises the following steps: and after the awakening voice performance of the display equipment is determined to be normal, determining detection items except the awakening detection item in the detection item list to test. That is, in the detection item list, the priority of the wake-up detection item is higher than the priority of other detection items.
In this embodiment, the entry audio of the detection items other than the wake-up detection item includes the entry audio of the wake-up detection item. For example, the entry audio corresponding to the detection item for detecting that the display device to be tested returns to the homepage may be "homepage returned by research in ministry. Therefore, the awakening detection item is detected firstly, so that the detection failure caused by the awakening function of the display equipment to be detected when other voice performance detection is carried out can be avoided, and the true reason of the detection failure can not be accurately obtained; meanwhile, the microphone function and the display function of the display equipment to be detected can be judged by detecting the awakening detection item, so that when other detection items are detected, if a problem occurs, the problem can be determined to be caused by a corresponding program problem.
In an optional embodiment, the method further comprises: if the voice performance of the display device under the test parameters is normal, judging whether all the test parameters in the test items are tested, if not, testing the test parameters which are not tested in the test items, if so, judging whether all the test items in the test item list are tested, if not, testing the test items which are not tested in the test item list, if so, ending the test, and sending an ending signal to inform an operator to replace the display device to be tested.
In an alternative embodiment, the retesting step is performed if the speech performance of the display device under the test parameters is not normal. The retesting step includes: shooting a display interface of the display equipment to be detected to obtain a detection image; identifying the detection image to acquire display content of the display equipment; and judging whether the voice performance of the display equipment under the test parameters is normal or not according to the display content of the display equipment.
The method further comprises the following steps: if the voice performance of the display equipment under the test parameters is normal, outputting and storing a test result; and if the retest step is executed for the specified times under the same test parameter, stopping executing the retest step, outputting the last test result in the retest step and storing the test result. Through setting up the retest step, can avoid because of shooting the problem that the environment worsens temporarily, or external factors such as external environment to signal transmission's temporary interference take place the erroneous judgement to the test result.
In an alternative embodiment, different entry tones correspond to different preset identifiers. The judging whether the voice performance of the display device under the test parameters is normal according to the display content of the display device includes: determining a display identifier in the display content according to the display content of the display equipment; and judging whether the voice performance of the display equipment under the test parameters is normal or not according to the similarity between the display identifier and the preset identifier. After any one test parameter is executed, the display equipment to be tested returns to the standby state, so that the phenomenon that when the same detection item is tested on a plurality of test parameters, the entry audio frequency is the same and one test parameter is not responded is avoided, and the entry audio frequency is misjudged as the normal test result.
In the present embodiment, the display identifier in the display content is extracted by an OCR (Optical Character Recognition) algorithm model. The process of recognition through the OCR algorithm model is divided into two stages. The first stage is a localization stage, which screens the regions with textual features in the detected image line by line based on the single-line recognition algorithm of 1D-CTC. Specifically, firstly, a detection image is input, then text positioning detection is performed through an OCR algorithm model, and digitized information of the detection image is obtained by using differentiable binaryzation. Then, a rectangular frame in which the character text is located is divided. And then performing affine transformation on the extracted rectangular frame, namely linear transformation from two-dimensional coordinates to two-dimensional coordinates, and correcting the inclined characters, thereby facilitating the identification of the characters. And finally obtaining the text rectangular box with higher straightness. The second stage is an identification stage, which adopts a common CRNN (Convolutional Recurrent Neural Network) model as an identifier to extract character contents one by one text box by extracting character features.
Further, the method further comprises: and repeatedly detecting the display equipment to be detected for multiple times by each test parameter, and judging that the display equipment to be detected is normal under the detection item when the proportion of the normal test result exceeds a certain value.
In an alternative embodiment, before obtaining the list of detection items, the method further comprises: detecting whether the connection state of the camera and the system corresponding to the method is normal or not, detecting whether the connection state of an inspection IO card in the system corresponding to the method is normal or not, and detecting whether the connection state of the OCR algorithm model is normal or not. And acquiring a detection item list under the condition that the detection is normal. Therefore, the method for detecting the voice performance of the display equipment can be ensured to be carried out smoothly.
In an optional embodiment, different entry audios correspond to different interface response templates, the image to be tested is compared with the interface response templates, and when the similarity reaches a certain threshold, the test result can be judged to be normal.
The invention provides a set of automatic solution for testing the voice performance of the television, and the detection of the voice performance of the television can be automatically finished only by inputting the preset test parameters through the machine vision detection system based on the OCR recognition method. According to the invention, manual detection is replaced by a machine, so that the labor cost is saved, the detection is more accurate than manual detection, and the problem of fatigue false detection is solved.
In a second aspect, the present invention provides a display device voice performance detection system 200, and in conjunction with fig. 2, the display device voice performance detection system 200 includes:
a first obtaining module 201 configured to obtain test parameters, the test parameters including: the method comprises the following steps of obtaining entry audio, relative position parameters of an instruction sending sound source and a display device to be tested, and volume size parameters of the instruction sending sound source, wherein the entry audio is used for controlling display contents of the display device to be tested;
an adjusting module 202 configured to adjust the command emission sound source according to the test parameters;
the starting module 203 is configured to start the instruction to issue a sound source so as to play the entry audio;
a shooting module 204 configured to shoot a display interface of the display device to be detected to obtain a detection image;
a recognition module 205 configured to recognize the detection image to obtain display content of the display device;
a first determining module 206, configured to determine whether the voice performance of the display device under the test parameter is normal according to the display content of the display device.
In an alternative embodiment, the system displays the device voice performance detection system 200:
a second obtaining module, configured to obtain a detection item list before obtaining the test parameters, where the detection item list includes a plurality of detection items, and each detection item corresponds to at least one set of test parameters;
the first obtaining module 201 includes:
a first determining submodule configured to determine a detection item to be tested in the detection item list;
and the acquisition sub-module is configured to acquire the corresponding test parameters according to the detection items.
In an alternative embodiment, the plurality of detection items includes: and (5) awakening the detection item. The awakening detection item is used for detecting whether the display equipment to be detected can be switched from a standby state to an awakening state.
The first obtaining module 201 is further configured to obtain a test parameter corresponding to the wake-up detection item;
the first determining module 206 is further configured to determine whether the wake-up voice performance of the display device is normal according to the display content of the display device;
the display device voice performance detection system 200 further includes: and the determining module is configured to determine detection items except the awakening detection item in the detection item list for testing after the awakening voice performance of the display device is determined to be normal.
In an alternative embodiment, the display device voice performance detection system 200 further includes: the second judging module is configured to judge whether all the test parameters in the test items are tested if the voice performance of the display device under the test parameters is normal, if not, test the test parameters which are not tested in the test items, if yes, judge whether all the test items in the test item list are tested, and if not, test the test items which are not tested in the test item list.
In an alternative embodiment, the display device voice performance detection system 200 further includes: and the retest module is configured to execute the retest step if the voice performance of the display equipment under the test parameters is abnormal. Wherein, the retesting step comprises: shooting a display interface of the display equipment to be detected to obtain a detection image; identifying the detection image to acquire display content of the display equipment; and judging whether the voice performance of the display equipment under the test parameters is normal or not according to the display content of the display equipment, if so, ending the test, and sending an ending signal to inform an operator to replace the display equipment to be tested.
The display device voice performance detection system 200 further includes: and the storage module is configured to output and store the test result if the voice performance of the display device under the test parameters is normal.
And the storage module is further configured to stop executing the retesting step if the retesting step executed reaches the specified times under the same test parameter, and output and store the last test result in the retesting step.
In an alternative embodiment, the entry audio corresponding to the multiple test parameters in the same detection item is the same, and different entry audio corresponds to different preset identifiers.
The first determining module 206 includes:
a second determining submodule configured to determine a display identifier in the display content according to the display content of the display device;
and the judging submodule is configured to judge whether the voice performance of the display equipment under the test parameters is normal or not according to the similarity between the display identifier and the preset identifier.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A display device voice performance detection method is characterized by comprising the following steps:
obtaining test parameters, wherein the test parameters comprise: the method comprises the following steps of obtaining entry audio, relative position parameters of an instruction sending sound source and a display device to be tested, and volume size parameters of the instruction sending sound source, wherein the entry audio is used for controlling display contents of the display device to be tested;
adjusting the sound source sent by the instruction according to the test parameters;
starting the instruction to send out a sound source so as to play the entry audio;
shooting a display interface of the display equipment to be detected to obtain a detection image;
identifying the detection image to acquire display content of the display equipment;
and judging whether the voice performance of the display equipment under the test parameters is normal or not according to the display content of the display equipment.
2. The method for detecting the voice performance of the display device according to claim 1, wherein before the obtaining the test parameters, the method further comprises:
acquiring a detection item list, wherein the detection item list comprises a plurality of detection items, and each detection item corresponds to at least one group of test parameters;
the acquiring of the test parameters comprises:
determining a detection item to be tested in the detection item list;
and acquiring corresponding test parameters according to the detection items.
3. The method for detecting the voice performance of the display device according to claim 2, wherein the plurality of detection items comprise: a wake-up detection item;
the awakening detection item is used for detecting whether the display equipment to be detected can be switched from a standby state to an awakening state;
the acquiring of the test parameters comprises: acquiring test parameters corresponding to the awakening detection items;
the judging whether the voice performance of the display device under the test parameters is normal according to the display content of the display device includes: judging whether the awakening voice performance of the display equipment is normal or not according to the display content of the display equipment;
the method further comprises the following steps: and after the awakening voice performance of the display equipment is determined to be normal, determining detection items except the awakening detection item in the detection item list to test.
4. The method for detecting the voice performance of the display device according to claim 2, further comprising:
if the voice performance of the display device under the test parameters is normal, judging whether all the test parameters in the test items are tested, if not, testing the test parameters which are not tested in the test items, if so, judging whether all the test items in the test item list are tested, and if not, testing the test items which are not tested in the test item list.
5. The method for detecting the voice performance of the display device according to claim 2, wherein if the voice performance of the display device under the test parameters is abnormal, a retesting step is performed;
the retesting step includes:
shooting a display interface of the display equipment to be detected to obtain a detection image;
identifying the detection image to acquire display content of the display equipment;
judging whether the voice performance of the display equipment under the test parameters is normal or not according to the display content of the display equipment;
the method further comprises the following steps: if the voice performance of the display equipment under the test parameters is normal, outputting and storing a test result;
and if the retest step is executed for the specified times under the same test parameter, stopping executing the retest step, outputting the last test result in the retest step and storing the test result.
6. The method for detecting the voice performance of the display device according to claim 1, wherein entry audio corresponding to a plurality of test parameters in the same detection item is the same, and different entry audio correspond to different preset identifiers;
the judging whether the voice performance of the display device under the test parameters is normal according to the display content of the display device includes:
determining a display identifier in the display content according to the display content of the display equipment;
and judging whether the voice performance of the display equipment under the test parameters is normal or not according to the similarity between the display identifier and the preset identifier.
7. A display device voice performance detection system, comprising:
a first obtaining module configured to obtain test parameters, the test parameters including: the method comprises the following steps of obtaining entry audio, relative position parameters of an instruction sending sound source and a display device to be tested, and volume size parameters of the instruction sending sound source, wherein the entry audio is used for controlling display contents of the display device to be tested;
the adjusting module is configured to adjust the instruction emitting sound source according to the test parameters;
the starting module is configured to start the instruction to send out a sound source so as to play the entry audio;
the shooting module is configured to shoot a display interface of the display device to be detected so as to obtain a detection image;
the identification module is configured to identify the detection image so as to acquire display content of the display device;
and the first judging module is configured to judge whether the voice performance of the display equipment under the test parameters is normal according to the display content of the display equipment.
8. The display device voice performance detection system of claim 7, wherein the system comprises:
a second obtaining module, configured to obtain a detection item list before obtaining the test parameters, where the detection item list includes a plurality of detection items, and each detection item corresponds to at least one set of test parameters;
the first obtaining module comprises:
a first determining submodule configured to determine a detection item to be tested in the detection item list;
and the acquisition sub-module is configured to acquire the corresponding test parameters according to the detection items.
9. The display device voice performance detection system of claim 8, wherein the plurality of detection items comprise: a wake-up detection item;
the awakening detection item is used for detecting whether the display equipment to be detected can be switched from a standby state to an awakening state;
the first obtaining module is further configured to obtain a test parameter corresponding to the wake-up detection item;
the first judging module is further configured to judge whether the awakening voice performance of the display device is normal according to the display content of the display device;
the system further comprises: and the determining module is configured to determine detection items except the awakening detection item in the detection item list for testing after the awakening voice performance of the display device is determined to be normal.
10. The display device voice performance detection system of claim 8, further comprising:
the second judging module is configured to judge whether all the test parameters in the test items are tested if the voice performance of the display device under the test parameters is normal, if not, test the test parameters which are not tested in the test items, if yes, judge whether all the test items in the test item list are tested, and if not, test the test items which are not tested in the test item list.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011642628.3A CN112822487A (en) | 2020-12-30 | 2020-12-30 | Method and system for detecting voice performance of display equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011642628.3A CN112822487A (en) | 2020-12-30 | 2020-12-30 | Method and system for detecting voice performance of display equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112822487A true CN112822487A (en) | 2021-05-18 |
Family
ID=75856536
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011642628.3A Pending CN112822487A (en) | 2020-12-30 | 2020-12-30 | Method and system for detecting voice performance of display equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112822487A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108900959A (en) * | 2018-05-30 | 2018-11-27 | 北京百度网讯科技有限公司 | Method, apparatus, equipment and the computer-readable medium of tested speech interactive device |
| CN110139204A (en) * | 2019-05-29 | 2019-08-16 | 北京百度网讯科技有限公司 | Intelligent sound equipment acoustical behavior test method and system |
| CN111611169A (en) * | 2020-05-22 | 2020-09-01 | 深圳市亿道数码技术有限公司 | Automatic testing method and testing tool for voice assistant wake-up rate |
| CN111899740A (en) * | 2020-07-23 | 2020-11-06 | 深圳慕智科技有限公司 | Voice recognition system crowdsourcing test case generation method based on test requirements |
| CN112151029A (en) * | 2020-09-04 | 2020-12-29 | 深圳创维－Rgb电子有限公司 | Voice awakening and recognition automatic test method, storage medium and test terminal |
-
2020
- 2020-12-30 CN CN202011642628.3A patent/CN112822487A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108900959A (en) * | 2018-05-30 | 2018-11-27 | 北京百度网讯科技有限公司 | Method, apparatus, equipment and the computer-readable medium of tested speech interactive device |
| CN110139204A (en) * | 2019-05-29 | 2019-08-16 | 北京百度网讯科技有限公司 | Intelligent sound equipment acoustical behavior test method and system |
| CN111611169A (en) * | 2020-05-22 | 2020-09-01 | 深圳市亿道数码技术有限公司 | Automatic testing method and testing tool for voice assistant wake-up rate |
| CN111899740A (en) * | 2020-07-23 | 2020-11-06 | 深圳慕智科技有限公司 | Voice recognition system crowdsourcing test case generation method based on test requirements |
| CN112151029A (en) * | 2020-09-04 | 2020-12-29 | 深圳创维－Rgb电子有限公司 | Voice awakening and recognition automatic test method, storage medium and test terminal |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109003602B (en) | Voice product testing method, device, equipment and computer readable medium | |
| US10643605B2 (en) | Automatic multi-performance evaluation system for hybrid speech recognition | |
| CN111724782B (en) | Response time testing system, method and equipment of vehicle-mounted voice interaction system | |
| CN114994061B (en) | Machine vision-based steel rail intelligent detection method and system | |
| CN104810025A (en) | Audio similarity detecting method and device | |
| CN111080633A (en) | Screen defect detection method and device, terminal equipment and storage medium | |
| KR20160122452A (en) | Deep learnig framework and image recognition method for content-based visual image recognition | |
| CN107784649B (en) | Image recognition-based mandrel testing remote alarm system and method | |
| CN112151029A (en) | Voice awakening and recognition automatic test method, storage medium and test terminal | |
| CN107680613A (en) | A kind of voice-operated device speech recognition capabilities method of testing and equipment | |
| CN111127699A (en) | Method, system, equipment and medium for automatically recording automobile defect data | |
| CN113838480B (en) | Washing machine abnormal sound detection method and device and electronic equipment | |
| CN109616106A (en) | Vehicle-mounted control screen voice recognition process testing method, electronic equipment and system | |
| CN112822487A (en) | Method and system for detecting voice performance of display equipment | |
| CN112550631A (en) | Ship pre-outfitting installation method, system and equipment based on optical projection | |
| CN113379943A (en) | AR system of patrolling and examining based on 5G communication | |
| CN110441714B (en) | Method and device for detecting indicator light and computer readable storage medium | |
| CN106294109A (en) | Obtain the method and device of defect code | |
| CN110825637A (en) | Robot testing method and device | |
| CN115546918A (en) | Fire-fighting equipment inspection method, system, terminal and storage medium | |
| KR20130029635A (en) | Evaluation module for speech recognition performance and method thereof | |
| CN110401781B (en) | False call detection system, method and medium | |
| CN110221978A (en) | Method for generating test case and device | |
| CN113140217B (en) | Voice instruction testing method, testing device and readable storage medium | |
| CN112289345B (en) | Visual intelligent terminal voice diagnosis method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210518 |
|
| RJ01 | Rejection of invention patent application after publication |