CN112151029A - Voice awakening and recognition automatic test method, storage medium and test terminal - Google Patents
Voice awakening and recognition automatic test method, storage medium and test terminal Download PDFInfo
- Publication number
- CN112151029A CN112151029A CN202010922849.XA CN202010922849A CN112151029A CN 112151029 A CN112151029 A CN 112151029A CN 202010922849 A CN202010922849 A CN 202010922849A CN 112151029 A CN112151029 A CN 112151029A
- Authority
- CN
- China
- Prior art keywords
- voice
- recognition
- test
- image
- wake
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 137
- 238000010998 test method Methods 0.000 title claims description 16
- 238000012545 processing Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 7
- 230000002452 interceptive effect Effects 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 13
- 238000001514 detection method Methods 0.000 description 11
- 230000000007 visual effect Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000238558 Eucarida Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000013095 identification testing Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
Abstract
The invention provides a voice awakening and recognition automatic testing method, a storage medium and a testing terminal. Wherein the method comprises the steps of: voice awakening and identifying the equipment to be tested by utilizing the voice command; the voice instruction comprises a wake-up voice instruction and a recognition voice instruction; and acquiring the awakened voice recognition interface image of the equipment to be tested, comparing the voice recognition interface image with a preset image for testing, and outputting a test result. The television voice awakening and recognition test is automatically carried out according to the set voice instruction, and the test report is automatically recorded and output, so that the problems of low manual test efficiency and high cost are solved, and the accuracy of the test result is improved and guaranteed.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a voice awakening and recognition automatic testing method, a storage medium and a testing terminal.
Background
In the process of research, development and test, the intelligent voice of the television needs to be verified and tested through a plurality of specific noise scenes, and the far-field voice awakening and recognition rate is guaranteed.
At present, tests for television intelligent voice systems are mostly verified in a manual mode, but the problems of manual test of voice singleness, high manual test cost and low test efficiency exist in manual tests, and test results cannot be analyzed and automatically recorded.
Therefore, the prior art is subject to further improvement and advancement.
Disclosure of Invention
In view of the foregoing deficiencies of the prior art, an object of the present invention is to provide a voice wake-up and recognition automation test method, a storage medium, and a test terminal, which are used to solve the problem of low efficiency of the existing voice wake-up and recognition test for a smart television.
A voice awakening and recognition automatic test method comprises the following steps:
voice awakening and identifying the equipment to be tested by utilizing the voice command; the voice instruction comprises a wake-up voice instruction and a recognition voice instruction;
and acquiring the awakened interface image of the equipment to be tested, comparing the voice recognition interface image with a preset image for testing, and outputting a test result.
According to the voice awakening and recognition automatic testing method, the test of the voice awakening and recognition rate of the television is automatically carried out according to the set voice instruction, and the test report is automatically recorded and output, so that the problems of low manual testing efficiency and high cost are solved, and the accuracy of the test result is improved and guaranteed.
Optionally, the voice wake-up automated testing method, wherein the step of performing voice wake-up and recognition on the device to be tested by using the voice instruction specifically includes:
pre-recording the voice command and the interference audio; the interference audio comprises an external noise interference audio and an internal noise interference audio;
and in the environment of playing the interference audio, the voice instruction is utilized to carry out voice awakening and identification on the equipment to be tested.
Optionally, the voice wakeup and recognition automated test method, wherein the step of obtaining the voice recognition interface image of the device to be tested after wakeup, comparing the voice recognition interface image with a preset image for testing, and outputting a test result specifically includes:
acquiring an awakened voice recognition interface image of the equipment to be tested, which is acquired by using camera equipment;
carrying out image character analysis on the voice recognition interface image, and distinguishing voice from the image character
Recognizing a character area;
extracting the characters in the voice recognition character area to obtain a characteristic group;
and comparing the characteristic group with image character characteristic data containing voice instructions in a preset characteristic database, identifying according to the characteristic comparison to obtain a test result, and storing the test result in a test report.
Optionally, the voice wake-up and recognition automated testing method, wherein the step of performing image-text analysis on the voice recognition interface image information and distinguishing a voice recognition text region from the voice recognition interface image further includes:
and sequentially carrying out inclination correction processing, color processing and noise point elimination processing on the image on the voice recognition interface image.
Optionally, the voice wake-up and recognition automated testing method, wherein the step of performing feature extraction on the text in the voice recognition text region to obtain a feature group specifically includes:
and performing character thinning processing on the characters in the voice recognition character area to obtain stroke end points, the number of cross points and the positions of the cross points of the characters, and storing the stroke end points, the number of the cross points and the positions of the cross points as a feature group.
Optionally, the voice wake-up and recognition automated testing method, wherein the step of obtaining the voice recognition interface image of the device to be tested after wake-up, comparing the voice recognition interface image with a preset image for testing, and outputting a test result further includes:
and when the contrast test finds that the equipment to be tested is not correctly awakened and identified, storing the acquired voice recognition interface image, and annotating the test result and then outputting the test result.
Optionally, the voice wake-up and recognition automated testing method, wherein the step of performing voice wake-up and recognition on the device to be tested by using the voice instruction in the environment where the interfering audio is played specifically includes:
when the played interference audio is the external noise interference audio, setting the equipment to be tested to be in a mute state;
and adjusting the playing angle and the sound pressure of the external noise interference audio to form different testing environments, and performing voice awakening on the equipment to be tested in the different testing environments by using the voice command.
Optionally, the voice wake-up and recognition automated testing method, wherein the step of performing voice wake-up and recognition on the device to be tested by using the voice instruction in the environment where the interfering audio is played specifically includes:
and when the played interference audio is the internal noise interference audio, adjusting the playing angle and the sound pressure of the internal noise interference audio to form different testing environments, and performing voice awakening and recognition on the equipment to be tested in the different testing environments by utilizing the voice command.
Based on the same inventive concept, the present invention also provides a storage medium, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the voice wake automatic test method as described above.
Based on the same inventive concept, the invention also provides a test terminal, wherein the test terminal comprises: a processor and a memory; the memory having stored thereon a program executable by the processor; the processor executes the program to realize the steps of the voice wake-up automatic test method.
Drawings
Fig. 1 is a flowchart of an automatic testing method for voice wake-up and recognition according to an embodiment of the present invention;
fig. 2 is a schematic view of an application scenario provided in an embodiment of the present invention;
fig. 3 is a flowchart of step S100 in an automatic testing method for voice wake-up and recognition according to an embodiment of the present invention;
fig. 4 is a flowchart of step S200 in an automatic testing method for voice wake-up and recognition according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an image contrast analysis process provided by an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a test terminal according to an embodiment of the present invention.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
Currently, smart speech gradually enters people's daily life under the energization of artificial intelligence technology. The intelligent voice is the communication of human-computer language, including voice recognition and voice synthesis. The intelligent voice is divided into near-field voice and far-field voice, and when near-field recognition is performed, for example, when a voice input method is used, a user can press a voice button of siri on the mobile phone to directly speak for recognition; during far-field recognition, for example, in a smart television scene, a television far-field voice is activated through a wakeup word, and then speaking is carried out and then voice recognition is carried out. The television is used as an intelligent control center of a family, far-field voice is added in the intelligent television, and a consumer interacts with the television through the far-field voice, so that the convenience of using the television is greatly improved.
Far-field voice of the smart television has much convenience, but in daily household living environment, various kinds of noise outside life and internal noise generated by the television in the using process affect, and the noise can cause interference to the awakening and recognition of the far-field voice. Therefore, verification and test are carried out on the intelligent voice of the television in many specific noise scenes in the research, development and test processes, and the far-field voice awakening and recognition rate is guaranteed. At present, tests for television intelligent voice systems are mostly verified in a manual mode, but the problems of manual test of voice singleness, high manual test cost and low test efficiency exist in manual tests, and test results cannot be analyzed and automatically recorded.
Based on this, the present invention provides a solution to the above technical problem, and the details thereof will be explained in the following embodiments.
For example, the embodiment of the present invention may be applied to a scenario as shown in fig. 4, in which the detection terminal 10 is connected to the sound source loudspeaker 20, the interference source loudspeaker 30, the driving motor 40, the visual detection system 50, and the device under test (tv) 60, respectively. A tested voice command and external noise interference audio are introduced into the detection terminal 10. In the detection terminal 10, according to a test voice scene: and configuring test parameters of the sound source loudspeaker box, the interference source loudspeaker box and the driving motor in quiet, internal noise and external noise scenes.
The sound source sound box (sound box A, B, C) faces the television, the distance between the sound source sound box and the television is set to be 1 meter, 3 meters and 5 meters respectively, the detection terminal 10 controls the moving positions and angles of the sound source sound box and the interference source sound box on the driving motor according to the set quiet, internal noise and external noise scenes, and the sound source sound box (sound box A, B, C) plays voice commands in sequence according to the set scenes respectively. It is understood that the distance between the sound source enclosure and the television may be set to other values as desired.
The visual detection system is arranged right in front of the television, when the sound source sound box plays a group of voice awakening and identifying instructions, the visual detection system collects images awakened and identified by the equipment to be detected and then sends the images to the detection terminal 10 for image analysis and processing. And judging whether the television is awakened or not, and whether the voice instruction and the instruction text displayed on the television are correct or not.
It should be noted that the above application scenarios are only presented to facilitate understanding of the present invention, and the embodiments of the present invention are not limited in any way in this respect. Rather, embodiments of the present invention may be applied to any scenario where applicable. The equipment to be detected can be a television with intelligent voice, an intelligent projector, an intelligent laser television and the like. In the following embodiments, the present invention is explained by taking a television with smart voice as an example.
The invention will be further explained by the description of the embodiments with reference to the drawings.
Referring to fig. 1 to 5, as shown in the drawings, an embodiment of the present invention provides a voice wake-up and recognition automated testing method, including:
s100, voice awakening is carried out on the equipment to be tested by utilizing a voice instruction; the voice instruction comprises a wake-up voice instruction and a recognition voice instruction;
specifically, as shown in fig. 2, the method comprises the steps of:
s110, pre-recording the voice command and the interference audio; the interference audio comprises an external noise interference audio and an internal noise interference audio;
and S120, in the environment of playing the interference audio, performing voice awakening on the equipment to be tested by using the voice instruction.
In this embodiment, the voice command and the interfering audio may be prerecorded; for example, the voice "hello elfin" and "what good-looking art program" can be recorded in a quiet environment by a recording device. The audio of the ' hello elfin ' is used as the awakening audio, and the audio of the ' good-looking heddles is used as the identification audio. Recording a news program, wherein the recording time of the news program can be 1-3 minutes, and the audio is used as interference audio. And simulating noise in actual use by using the interference audio, and performing voice awakening on the equipment to be tested by using the voice instruction. It is easily understood that the disturbing audio includes external noise (referring to sounds other than sounds emitted by the smart tv).
For example, 100 pre-recorded voice commands (each voice command includes 1 wake-up audio and 1 recognition audio) and external noise interference audio are introduced into the test terminal, and internal noise audio is also introduced into the device under test. In an equipment control module of the test terminal, sound pressure and angle configuration parameters of a sound source sound box, an interference source sound box, a driving motor and equipment to be tested in quiet, internal noise and external noise scenes are respectively set according to test scenes 1-9 in a table 1. After the device control module of the test terminal finishes setting the test scene, the voice awakening and recognition tests of the quiet, internal noise and external noise scenes are sequentially carried out according to the test scenes 1-9 in the table 1.
Awakening and identification test in a quiet scene: the equipment control module sets an interference sound box and the equipment to be tested in a mute state, after the sound source sound box (sound box A, B, C) is set to test the angle and the sound pressure of scenes 1-3 in the table 1, the sound source sound box (sound box A, B, C) sequentially broadcasts 100 groups of voice instructions to test the scenes 1, 3 and 5 meters, and the visual detection system and the image comparison processing module are responsible for detecting and recording 3 groups of results.
Awakening test of internal noise scene: the equipment control module sets the interference sound box to be in a mute state, sets the device to be tested to broadcast and sets the sound source sound box (sound box A, B, C) to be the angle and the sound pressure of the test scene 4-6 in the table 1, and controls the device to be tested to broadcast the internal noise audio, then the sound source sound box (sound box A, B, C) sequentially broadcasts 100 groups of voice instructions to test the internal noise scene 1, 3 and 5 meters, and the visual detection system and the image comparison processing module are responsible for detecting and recording results.
Awakening and identifying test of external noise scene: the equipment control module sets the equipment to be tested to be in a mute state, sets the interference sound box and the sound source sound box (sound box A, B, C) to be angles and sound pressures of test scenes 7-9 in table 1, controls the interference sound box to play interference audio, then sequentially broadcasts 100 groups of voice instructions by the sound source sound box (sound box A, B, C) to test external noise scenes 1, 3 and 5 meters, and the visual detection system and the image comparison processing module are responsible for detecting and recording results.
The test results are shown in Table 1
S200, acquiring the awakened voice recognition interface image of the device to be tested, comparing the voice recognition interface image with a preset image for testing, and outputting a test result.
In conjunction with fig. 3 and 5, specifically, step S200 includes the steps of:
s210, acquiring awakened voice recognition interface image information of the equipment to be tested, which is acquired by using camera equipment;
s220, carrying out image character analysis on the voice recognition interface image information, and distinguishing a voice recognition character area from the voice recognition interface image;
s230, extracting characteristics of the characters in the voice recognition character area to obtain a characteristic group;
s240, comparing the feature group with image character feature data which correspondingly contain voice instructions in a preset feature database, obtaining a test result according to the feature comparison, and storing the test result in a test report.
In this embodiment, the sound source speaker plays a test voice command, and after the device to be tested responds to the wake-up and recognition voice command, the test terminal sends an acquisition command to the image acquisition module of the visual acquisition system. And after receiving the instruction, the vision acquisition system sends an acquisition signal to control a camera of the image information acquisition module, and shoots and acquires the image information of the awakening and identification picture for the television. The shot and collected image information is sent to a test terminal in a BMP file format, and an image comparison processing module of the test terminal preprocesses the collected image: firstly, performing tilt correction and color processing on an acquired image, eliminating noise points on the image and enhancing useful information of the image; secondly, analyzing the image characters: the collected image is subjected to overall analysis, the voice recognition character and the image area are distinguished, and the voice recognition character area is subjected to recognition processing; then, feature extraction: according to the preprocessing of the image and the voice recognition character processing of the image, the character thinning processing is carried out on the voice recognition character, and the number and the positions of the stroke end points and the cross points of the character are obtained and stored as the characteristic group.
And comparing the extracted feature group with image character feature data which correspondingly contain voice instructions in a preset feature database, identifying according to the comparison of the two groups of features to obtain a test result, and storing the test result in a test report of a test terminal.
In an implementation manner of this embodiment, during the test, when the vision inspection system detects that the device under test is not woken up and recognizes the voice command correctly, an image with a wake-up recognition error is saved to the test terminal, and the result is noted in the test report for reference. It is easy to understand that the fact that the terminal under test is not woken up correctly includes two cases: firstly, although a wake-up voice command is issued, the device under test does not recognize the command and does not respond correspondingly. The other is that although the device under test responds, the recognition result of the recognized voice command is wrong, for example, the character corresponding to the voice in the recognized voice command is "broadcast art program", but the recognized character is "broadcast movie".
Based on the voice wake-up automatic test method, the present invention further provides a storage medium, where one or more programs are stored, and the one or more programs can be executed by one or more processors to implement the steps in the voice wake-up automatic test method.
Based on the above voice wake-up and recognition automated testing method, the present invention further provides a testing terminal, as shown in fig. 6, which includes at least one processor (processor) 30; a display screen 31; and a memory (memory)32, which may also include a communication interface (communication interface)33 and a bus 34. The processor 30, the display 31, the memory 32 and the communication interface 33 can communicate with each other through the bus 34. The display screen 31 is configured to display a user guidance interface preset in the initial setting mode. The communication interface 33 may transmit information. The processor 30 may call logic instructions in the memory 32 to perform the methods in the embodiments described above. In addition, the logic instructions in the memory 32 may be implemented in the form of software functional units and stored in a readable storage medium when sold or used as a stand-alone product. The memory 32 is a readable storage medium and can be configured to store software programs, such as program instructions or modules corresponding to the methods in the embodiments of the present invention. The processor 30 executes the functional application and data processing by executing the software program, instructions or modules stored in the memory 32, i.e. implements the method in the above-described embodiments. The memory 32 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 32 may include high speed random access memory and may also include non-volatile memory. For example, a variety of media that can store program codes, such as a usb disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, may also be transient storage media. In addition, the specific processes loaded and executed by the instruction processors in the storage medium and the terminal are described in detail in the method, and are not stated herein.
In summary, the present invention provides a voice wake-up and recognition automated testing method, a storage medium and a testing terminal. Wherein the method comprises the steps of: voice awakening is carried out on the equipment to be tested by utilizing the voice instruction; the voice instruction comprises a wake-up voice instruction and a recognition voice instruction; and acquiring the awakened voice recognition interface image of the equipment to be tested, comparing the voice recognition interface image with a preset image for testing, and outputting a test result. The test of television voice awakening and recognition rate is automatically carried out according to the set voice instruction, and the test report is automatically recorded and output, so that the problems of low manual test efficiency and high cost are solved, and the accuracy of the test result is improved and guaranteed.
It is to be understood that the invention is not limited to the examples described above, but that modifications and variations may be effected thereto by those of ordinary skill in the art in light of the foregoing description, and that all such modifications and variations are intended to be within the scope of the invention as defined by the appended claims.
Claims (10)
1. A voice awakening and recognition automatic test method is characterized by comprising the following steps:
voice awakening and identifying the equipment to be tested by utilizing the voice command; the voice instruction comprises a wake-up voice instruction and a recognition voice instruction;
and acquiring the awakened voice recognition interface image of the equipment to be tested, comparing the voice recognition interface image with a preset image for testing, and outputting a test result.
2. The voice wake-up and recognition automated testing method of claim 1, wherein the step of performing voice wake-up on the device under test using the voice command specifically comprises:
pre-recording the voice command and the interference audio; the interference audio comprises an external noise interference audio and an internal noise interference audio;
and in the environment of playing the interference audio, the voice instruction is utilized to carry out voice awakening and identification on the equipment to be tested.
3. The voice awakening and recognition automatic test method of claim 1, wherein the step of obtaining the awakened voice recognition interface image of the device to be tested, comparing the voice recognition interface image with a preset image for testing, and outputting a test result specifically comprises:
acquiring a voice recognition interface image of the equipment to be tested after awakening, which is acquired by using camera equipment;
carrying out image character analysis on the voice recognition interface image, and distinguishing a voice recognition character area from the image characters;
extracting the characters in the voice recognition character area to obtain a characteristic group;
and comparing the characteristic group with image character characteristic data containing voice instructions in a preset characteristic database, obtaining a test result according to the characteristic comparison, and storing the test result in a test report.
4. The voice wake-up and recognition automated testing method of claim 3, wherein the step of performing image-text analysis on the voice recognition interface image and distinguishing the voice recognition text region from the image text further comprises:
and sequentially carrying out inclination correction processing, color processing and noise point elimination processing on the image on the voice recognition interface image.
5. The voice wake-up and recognition automation test method of claim 3, wherein the step of extracting the features of the text in the voice recognition text area to obtain a feature group specifically comprises:
and performing character thinning processing on the characters in the voice recognition character area to obtain stroke end points, the number of cross points and the positions of the cross points of the characters, and storing the stroke end points, the number of the cross points and the positions of the cross points as a feature group.
6. The voice wake-up and recognition automated test method according to claim 1, wherein the step of obtaining the voice recognition interface image of the device under test after wake-up and recognition, comparing the voice recognition interface image with a preset image for testing, and outputting a test result further comprises:
and when the contrast test finds that the equipment to be tested is not awakened correctly, storing the acquired voice recognition interface image, and annotating the test result and then outputting the test result.
7. The voice wake-up and recognition automated test method of claim 2, wherein the step of performing voice wake-up and recognition on the device under test using the voice command in the environment where the interfering audio is played specifically comprises:
when the played interference audio is the external noise interference audio, setting the equipment to be tested to be in a mute state;
and adjusting the playing angle and the sound pressure of the external noise interference audio to form different testing environments, and performing voice awakening and recognition on the equipment to be tested in the different testing environments by using the voice command.
8. The voice wake-up and recognition automated testing method of claim 2, wherein the step of voice wake-up of the device under test using the voice command in the environment where the interfering audio is played specifically comprises:
and when the played interference audio is the internal noise interference audio, adjusting the playing angle and the sound pressure of the internal noise interference audio to form different testing environments, and performing voice awakening on the equipment to be tested in the different testing environments by utilizing the voice command.
9. A storage medium storing one or more programs, the one or more programs being executable by one or more processors to perform the steps of the voice wake and recognition automated test method of any one of claims 1-8.
10. A test terminal, comprising: a processor and a memory; the memory having stored thereon a program executable by the processor; the processor, when executing the program, implements the steps in the voice wake up automated test method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010922849.XA CN112151029A (en) | 2020-09-04 | 2020-09-04 | Voice awakening and recognition automatic test method, storage medium and test terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010922849.XA CN112151029A (en) | 2020-09-04 | 2020-09-04 | Voice awakening and recognition automatic test method, storage medium and test terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112151029A true CN112151029A (en) | 2020-12-29 |
Family
ID=73890965
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010922849.XA Pending CN112151029A (en) | 2020-09-04 | 2020-09-04 | Voice awakening and recognition automatic test method, storage medium and test terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112151029A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112822487A (en) * | 2020-12-30 | 2021-05-18 | 深圳市前海研祥亚太电子装备技术有限公司 | Method and system for detecting voice performance of display equipment |
| CN112863545A (en) * | 2021-01-13 | 2021-05-28 | 北京字节跳动网络技术有限公司 | Performance test method and device, electronic equipment and computer readable storage medium |
| CN113140217A (en) * | 2021-04-08 | 2021-07-20 | 青岛歌尔智能传感器有限公司 | Voice instruction testing method, testing device and readable storage medium |
| CN113450767A (en) * | 2021-06-24 | 2021-09-28 | 平安国际智慧城市科技股份有限公司 | Voice recognition test method, device, test equipment and storage medium |
| CN113593549A (en) * | 2021-06-29 | 2021-11-02 | 青岛海尔科技有限公司 | Method and device for determining awakening rate of voice equipment |
| CN113593564A (en) * | 2021-09-02 | 2021-11-02 | 北京声智科技有限公司 | Processing method for device test, test system, electronic device and storage medium |
| CN113794876A (en) * | 2021-09-17 | 2021-12-14 | 天津大学 | Intelligent testing arrangement towards domestic intelligent TV |
| 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 |
| CN114639373A (en) * | 2022-03-16 | 2022-06-17 | 北京德风运科技有限公司 | Intelligent voice evaluation method, system and storage medium |
| CN113593564B (en) * | 2021-09-02 | 2024-05-14 | 北京声智科技有限公司 | Processing method of equipment test, test system, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR19980023848A (en) * | 1996-09-30 | 1998-07-06 | 배순훈 | Character switching apparatus by sound step recognition in television receiver and method thereof |
| JPH1155614A (en) * | 1997-08-04 | 1999-02-26 | Casio Comput Co Ltd | Speech recognition image processing unit |
| KR20050053236A (en) * | 2003-12-02 | 2005-06-08 | 엘지전자 주식회사 | Character recognition and voice output apparatus and method for mobile station having camera |
| CN109616106A (en) * | 2018-11-12 | 2019-04-12 | 东风汽车有限公司 | Vehicle-mounted control screen voice recognition process testing method, electronic equipment and system |
| CN110085210A (en) * | 2019-03-15 | 2019-08-02 | 平安科技（深圳）有限公司 | Interactive information test method, device, computer equipment and storage medium |
| WO2020150899A1 (en) * | 2019-01-22 | 2020-07-30 | 京东方科技集团股份有限公司 | Voice control method, voice control apparatus, and computer-executable non-volatile storage medium |
-
2020
- 2020-09-04 CN CN202010922849.XA patent/CN112151029A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR19980023848A (en) * | 1996-09-30 | 1998-07-06 | 배순훈 | Character switching apparatus by sound step recognition in television receiver and method thereof |
| JPH1155614A (en) * | 1997-08-04 | 1999-02-26 | Casio Comput Co Ltd | Speech recognition image processing unit |
| KR20050053236A (en) * | 2003-12-02 | 2005-06-08 | 엘지전자 주식회사 | Character recognition and voice output apparatus and method for mobile station having camera |
| CN109616106A (en) * | 2018-11-12 | 2019-04-12 | 东风汽车有限公司 | Vehicle-mounted control screen voice recognition process testing method, electronic equipment and system |
| WO2020150899A1 (en) * | 2019-01-22 | 2020-07-30 | 京东方科技集团股份有限公司 | Voice control method, voice control apparatus, and computer-executable non-volatile storage medium |
| CN110085210A (en) * | 2019-03-15 | 2019-08-02 | 平安科技（深圳）有限公司 | Interactive information test method, device, computer equipment and storage medium |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112822487A (en) * | 2020-12-30 | 2021-05-18 | 深圳市前海研祥亚太电子装备技术有限公司 | Method and system for detecting voice performance of display equipment |
| CN112863545A (en) * | 2021-01-13 | 2021-05-28 | 北京字节跳动网络技术有限公司 | Performance test method and device, electronic equipment and computer readable storage medium |
| CN112863545B (en) * | 2021-01-13 | 2023-10-03 | 抖音视界有限公司 | Performance test method, device, electronic equipment and computer readable storage medium |
| CN113140217A (en) * | 2021-04-08 | 2021-07-20 | 青岛歌尔智能传感器有限公司 | Voice instruction testing method, testing device and readable storage medium |
| CN113450767A (en) * | 2021-06-24 | 2021-09-28 | 平安国际智慧城市科技股份有限公司 | Voice recognition test method, device, test equipment and storage medium |
| CN113593549A (en) * | 2021-06-29 | 2021-11-02 | 青岛海尔科技有限公司 | Method and device for determining awakening rate of voice equipment |
| CN113593564A (en) * | 2021-09-02 | 2021-11-02 | 北京声智科技有限公司 | Processing method for device test, test system, electronic device and storage medium |
| CN113593564B (en) * | 2021-09-02 | 2024-05-14 | 北京声智科技有限公司 | Processing method of equipment test, test system, electronic equipment and storage medium |
| CN113794876A (en) * | 2021-09-17 | 2021-12-14 | 天津大学 | Intelligent testing arrangement towards domestic intelligent TV |
| CN113794876B (en) * | 2021-09-17 | 2024-04-05 | 天津大学 | Intelligent testing device for household intelligent television |
| 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 |
| CN114639373A (en) * | 2022-03-16 | 2022-06-17 | 北京德风运科技有限公司 | Intelligent voice evaluation method, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112151029A (en) | Voice awakening and recognition automatic test method, storage medium and test terminal | |
| JP6857699B2 (en) | Wake-up methods, equipment, equipment, storage media, and programs for voice dialogue equipment | |
| CN110517689B (en) | Voice data processing method, device and storage medium | |
| US8200061B2 (en) | Signal processing apparatus and method thereof | |
| US20210280172A1 (en) | Voice Response Method and Device, and Smart Device | |
| US20180293236A1 (en) | Fast identification method and household intelligent robot | |
| CN102385860A (en) | Information processing apparatus, information processing method, and program | |
| CN107702273B (en) | Air conditioner control method and device | |
| CN110970018A (en) | Speech recognition method and device | |
| CN111326152A (en) | Voice control method and device | |
| CN111739534B (en) | Processing method and device for assisting speech recognition, electronic equipment and storage medium | |
| CN111341350A (en) | Man-machine interaction control method and system, intelligent robot and storage medium | |
| CN112286364A (en) | Man-machine interaction method and device | |
| CN110473542B (en) | Awakening method and device for voice instruction execution function and electronic equipment | |
| US20200227069A1 (en) | Method, device and apparatus for recognizing voice signal, and storage medium | |
| CN114120969A (en) | Method and system for testing voice recognition function of intelligent terminal and electronic equipment | |
| CN108899011B (en) | Voice function testing method, device and system of air conditioner | |
| CN107197404B (en) | Automatic sound effect adjusting method and device and recording and broadcasting system | |
| CN113643704A (en) | Test method, upper computer, system and storage medium of vehicle-mounted machine voice system | |
| CN109271480B (en) | Voice question searching method and electronic equipment | |
| CN111710339A (en) | Voice recognition interaction system and method based on data visualization display technology | |
| CN111161710A (en) | Simultaneous interpretation method and device, electronic equipment and storage medium | |
| KR20200056754A (en) | Apparatus and method for generating personalization lip reading model | |
| CN110875905A (en) | Account management method and device and storage medium | |
| CN114999457A (en) | Voice system testing method and device, storage medium and electronic equipment |
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 |