CN113140217B - Voice instruction testing method, testing device and readable storage medium - Google Patents
Voice instruction testing method, testing device and readable storage medium Download PDFInfo
- Publication number
- CN113140217B CN113140217B CN202110380000.9A CN202110380000A CN113140217B CN 113140217 B CN113140217 B CN 113140217B CN 202110380000 A CN202110380000 A CN 202110380000A CN 113140217 B CN113140217 B CN 113140217B
- Authority
- CN
- China
- Prior art keywords
- voice
- test
- instruction
- wake
- module
- 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.)
- Active
Links
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
- 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
- G10L15/01—Assessment or evaluation of speech recognition systems
-
- 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
- G10L2015/223—Execution procedure of a spoken command
Abstract
The invention discloses a voice instruction testing method, a testing device and a readable storage medium, wherein the voice instruction testing method comprises the following steps: the test terminal acquires a voice instruction to be tested; and performing recognition test on the acquired voice command, wherein the recognition test is as follows: playing and executing the acquired voice command, acquiring execution result information of the voice command, comparing the execution result information with a preset execution result of the voice command, and obtaining a test result of whether the voice command is successfully identified according to the comparison result. According to the invention, the test terminal is adopted to obtain the voice instruction to be tested, the played voice instruction is executed after the voice instruction is played, whether the execution result information is matched with the preset execution result is judged according to the execution result information and the preset execution result of the voice instruction, the test result is automatically identified, and the test accuracy is improved.
Description
Technical Field
The present invention relates to the field of test systems, and in particular, to a method and an apparatus for testing a voice command and a readable storage medium.
Background
In the intelligent device through voice control, the voice recognition state of the intelligent device needs to be tested to ensure that the intelligent device can realize correct voice control. In the existing voice test, a test instruction is sent manually, the identification condition of the intelligent equipment is observed manually, and the problem of inaccurate test result is caused by the fact that the individual difference of judgment exists in the manual judgment mode.
Disclosure of Invention
The invention mainly aims to provide a voice instruction testing method, a testing device and a readable storage medium, aiming at solving the problem that the existing voice instruction testing mode is inaccurate in testing.
In order to achieve the above object, the voice instruction testing method provided by the present invention comprises the following steps:
the test terminal acquires a voice instruction to be tested; and
and carrying out recognition test on the acquired voice command, wherein the recognition test is as follows: playing and executing the acquired voice command, acquiring execution result information of the voice command, comparing the execution result information with a preset execution result of the voice command, and obtaining a test result of whether the voice command is successfully identified according to the comparison result.
Optionally, after the step of comparing the execution result information with the preset execution result of the voice instruction and obtaining a test result of whether the voice instruction is recognized successfully according to the comparison result, the voice instruction testing method further includes:
respectively executing the recognition test on a plurality of voice instructions and obtaining a plurality of test results corresponding to the plurality of voice instructions; and
and calculating the recognition rate of the voice command according to a plurality of test results.
Optionally, after the step of calculating the recognition rate of the voice command according to the plurality of test results is executed, the voice command testing method further includes:
and displaying the recognition rate of the voice command, and/or displaying the voice command with the execution result information different from the preset execution result.
Optionally, after the step of acquiring the voice command to be tested is performed, the acquired voice command is displayed.
Optionally, the obtaining, according to the comparison result, a test result of whether the voice command is successfully recognized includes:
and when the execution result information is the same as the preset execution result of the voice command, determining that the test result of the recognition test is that the voice command can be correctly recognized.
Optionally, the obtaining a test result of whether the voice command is successfully recognized according to the comparison result further includes:
when the execution result information is different from a preset execution result of the voice instruction, determining whether a voice module for storing the voice instruction is in a dormant state; and
and if the voice module for storing the voice command is not in a dormant state, determining that the voice command cannot be correctly recognized as a test result of the recognition test.
Optionally, when the execution result information is different from a preset execution result of the voice instruction, determining whether a voice module for storing the voice instruction is in a sleep state further includes:
if the voice module for storing the voice instruction is in a dormant state, performing a wake-up test on the voice module for storing the voice instruction to obtain a wake-up test result, wherein the wake-up test result comprises that the voice module for storing the voice instruction can be successfully woken up and the voice module for storing the voice instruction cannot be successfully woken up; and
and when the awakening test result is determined that the voice module for storing the voice instruction can be awakened successfully, executing the step that the test terminal acquires the voice instruction to be tested.
Optionally, if the voice module for storing the voice instruction is in a sleep state, performing a wake-up test on the voice module for storing the voice instruction to obtain a wake-up test result further includes:
and when the awakening test result is judged that the voice module for storing the voice command cannot be awakened successfully, determining that the test result of the recognition test is that the voice command cannot be recognized correctly.
Optionally, the wake-up test includes:
when receiving a wake-up test instruction, the test terminal searches a voice module for storing a voice instruction corresponding to the wake-up test instruction, and sends the wake-up test instruction to the searched voice module; and
and receiving a wake-up mark fed back by the voice module, and confirming a wake-up test result for storing whether the voice module of the voice instruction is successfully wakened according to the wake-up mark fed back by the voice module.
Optionally, the test terminal stores a preset flag corresponding to the voice command, and the step of confirming, according to the wake-up flag fed back by the voice module, a wake-up test result indicating whether the voice module storing the voice command is successfully woken up includes:
and comparing whether the awakening mark is matched with a preset mark of the voice instruction, and if so, determining that the awakening test result is that the voice module for storing the voice instruction can be awakened successfully.
Optionally, after the step of performing the wake-up test on the voice module for storing the voice instruction to obtain the wake-up test result if the voice module for storing the voice instruction is in a dormant state, the wake-up test is repeatedly performed for a preset number of times to obtain a plurality of wake-up test results, and the wake-up rate of the voice module for storing the voice instruction is calculated according to the plurality of wake-up test results.
Optionally, after the step of calculating the wake-up rate of the voice module for storing the voice command according to the plurality of wake-up test results is executed, the voice command testing method further includes:
displaying the awakening rate of the voice module used for storing the voice instruction, and/or displaying the voice instruction.
The invention also provides a voice instruction testing device, which comprises:
a memory; and
a processor, said memory having stored thereon a voice instruction testing program executable on said processor, said voice instruction testing program when executed by said processor implementing the steps of the voice instruction testing method as claimed above.
The invention also proposes a readable storage medium on which a computer program is stored, which, when executed by a processor, implements the method for testing voice instructions as described above.
According to the technical scheme, the test terminal is adopted to obtain the voice instruction to be tested, the played voice instruction is executed after the voice instruction is played, whether the execution result information is matched with the preset execution result or not is judged according to the execution result information and the preset execution result of the voice instruction, when the execution result information is matched with the preset execution result of the voice instruction, the voice instruction is represented to be normally executed, and then the test result that the voice instruction is successfully recognized is obtained. In the testing process, after the voice command to be tested is automatically obtained through the testing terminal and tested, the testing result is automatically identified, and the testing accuracy is further improved.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the embodiments or technical solutions of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
FIG. 1 is a flowchart illustrating a voice command testing method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an embodiment of obtaining a voice command recognition rate according to the present invention;
FIG. 3 is a schematic flow chart illustrating a voice command wake-up test according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a hardware structure of a voice test apparatus according to an embodiment of the present invention.
The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.
The invention provides a voice instruction testing method which can be used for voice recognition testing of intelligent terminals, such as voice recognition testing of mobile phones and PCs.
Referring to fig. 1, in an embodiment, the voice command testing method includes the following steps:
s100: the test terminal obtains a voice instruction to be tested.
The test terminal may be provided with a memory for storing the voice instruction so that the test terminal may retrieve the voice instruction from the memory. The memory can be arranged on the test terminal or can be arranged independently and is connected with the test terminal.
In this embodiment, the test method is applied to a test terminal, and the test terminal includes, but is not limited to, a terminal device such as a PC or a portable computer. The testing terminal is preset with a corresponding testing key, when a tester starts the testing key, the testing terminal executes the step of acquiring the voice instruction to be tested, optionally, a display module can be arranged on the testing terminal, and after the step of acquiring the voice instruction to be tested is executed, the acquired voice instruction is displayed on the display module, so that the tester can intuitively know the voice instruction currently being tested.
S200: and carrying out recognition test on the acquired voice command, wherein the recognition test is as follows: playing and executing the obtained voice command, obtaining the execution result information of the voice command, comparing the execution result information with the preset execution result of the voice command, and obtaining the test result of whether the voice command is recognized successfully according to the comparison result.
The test terminal stores a preset execution result corresponding to the voice instruction, the test terminal can be provided with a voice playing module such as a sound card, the test terminal plays the voice instruction after acquiring the voice instruction to be tested, and executes an operation corresponding to the voice instruction according to the played voice instruction to acquire the execution result information. And comparing the execution result information with a preset execution result corresponding to the voice command.
In this embodiment, the voice instruction has a unique preset execution result corresponding thereto, and when the voice instruction is correctly executed, unique execution result information is obtained. And when the execution result information is the same as the preset execution result of the voice instruction, the voice instruction is correctly executed, and then the test result of the recognition test is determined to be that the voice instruction can be correctly recognized.
Specifically, the test terminal is provided with a voice module for storing a voice instruction, a voice playing module for playing the voice instruction, a sound collecting module for receiving the played voice instruction, an executing module for executing the voice instruction collected by the sound collecting module, a judging module for acquiring the execution result information of the executing module and the preset execution result corresponding to the voice instruction, and a display module for displaying the voice instruction to be tested and the test result. When the tester starts the voice test operation, the test terminal obtains the corresponding voice instruction to be tested from the voice module and displays the voice instruction through the display module, so that the tester knows the current voice instruction under test. The voice playing module plays the voice command, the sound collection module collects the voice command played by the voice playing module, the execution module executes the voice command according to the voice command collected by the sound collection module and generates execution result information, and the judgment module compares the execution result information with a preset execution result corresponding to the voice command after obtaining the execution result information so as to obtain a test result of whether the voice command is correctly executed or not. And the display module displays the current voice instruction and the corresponding test result.
Because the test process is automatically carried out by the test terminal, and the test result is obtained, the test result is not influenced by human factors, the problem of erroneous judgment can not occur, the problem of manual judgment errors in manual tests can be eliminated, and the accuracy of voice instruction tests is improved. Compared with manual testing, the testing method of the embodiment also improves the testing efficiency, saves labor and saves cost compared with manual testing.
In this embodiment, after the voice instruction is played, if the voice instruction to be tested is not executed, the execution result information cannot be obtained, that is, the execution result information of the voice instruction is inconsistent with a preset execution result, which indicates that the voice instruction identification fails.
Referring to fig. 2, further, after the step of comparing the execution result information with the preset execution result of the voice instruction and obtaining a test result of whether the voice instruction is recognized successfully according to the comparison result, the voice instruction testing method further includes:
s300: and respectively executing the recognition test on the plurality of voice instructions and obtaining a plurality of test results corresponding to the plurality of voice instructions.
The test terminal sequentially acquires the voice instructions, sequentially plays the acquired voice instructions, respectively executes the played voice instructions according to the played voice instructions, and obtains a test result of whether the voice instructions are successfully recognized. And recording a plurality of test results of whether the voice commands are recognized successfully.
The test terminal can display a voice instruction of failed recognition through the display module, and the test terminal can be provided with a pause key for controlling the test terminal and pausing continuous testing of the test terminal when needed. In this embodiment, when the voice command is failed to be recognized, the test terminal suspends the voice command for a first preset time, for example, for 5 seconds, and a tester may determine whether to stop the test through the suspend button within the first preset time. And a display module of the test terminal displays the voice instruction of current recognition failure. By displaying the voice command which is failed to be identified in the plurality of voice commands, the tester can identify the reason of the failure according to the display analysis.
S400: and calculating the recognition rate of the voice command according to a plurality of test results.
And after the recognition test of the voice instructions is executed, obtaining the test results of the voice instructions, and calculating the recognition rate and the error recognition rate of the voice instructions. And the display module of the test terminal can display the identification rate and the error identification rate.
Through counting the recognition rate of the voice command, the recognition condition of the voice command can be fed back visually, and the operation condition of the intelligent terminal corresponding to the voice command is determined according to the recognition condition. The misrecognition means that the execution result information of the voice command is different from the preset execution result of the voice command.
In this embodiment, the test result corresponding to each voice instruction is recorded separately, and when the voice instruction fails to be recognized, the test terminal may output information of the recognition failure, and provide a tester to select whether to continue the test or not, or whether to retest after analyzing the reason of the recognition failure.
In the embodiment, the test terminal tests the voice instructions one by one to obtain the recognition rate of the voice instructions, so that a tester can intuitively know the execution condition of the voice instructions, the problem of test errors caused by manual test judgment is avoided, and the test efficiency is improved.
In an embodiment, the obtaining, according to the comparison result, a test result of whether the voice command is successfully recognized further includes:
when the execution result information is different from a preset execution result of the voice instruction, determining whether a voice module for storing the voice instruction is in a dormant state; and if the voice module for storing the voice command is not in a dormant state, determining that the voice command cannot be correctly recognized as a test result of the recognition test.
When the voice module for storing the voice command is not in a dormant state, the test terminal can acquire the voice command to be tested, and at the moment, if the execution result information is different from the preset execution result of the voice command, the voice command is identified by mistake, so that the test result of the identification test is determined to be that the voice command cannot be identified correctly.
In another embodiment, if the voice module for storing the voice command is in a sleep state, performing a wake-up test on the voice module for storing the voice command to obtain a wake-up test result, where the wake-up test result includes that the voice module for storing the voice command can be successfully woken up and that the voice module for storing the voice command cannot be successfully woken up.
The voice module used for storing the voice instruction is subjected to awakening test, so that the test terminal can obtain the voice instruction to be tested, and further the voice instruction is subjected to recognition test.
And when the awakening test result is that the voice module for storing the voice instruction can be awakened successfully, the test terminal can acquire the voice instruction to be tested from the voice module for storing the voice instruction, and then the test terminal is executed to acquire the voice instruction to be tested, so that the voice instruction is identified and tested.
And when the awakening test result is that the voice module for storing the voice instruction cannot be awakened successfully, the test terminal cannot acquire the voice instruction to be tested from the voice module for storing the voice instruction, and cannot perform the identification test, and the test result of the identification test is determined that the voice instruction cannot be identified correctly.
Referring to fig. 3, in an embodiment, the wake-up test includes:
s500: when receiving the awakening test instruction, the test terminal searches for a voice module used for storing the voice instruction corresponding to the awakening test instruction, and sends the awakening test instruction to the searched voice module.
The voice module is used for storing voice instructions. Each voice instruction is provided with a corresponding voice module. The voice module may be a memory or a terminal for storing the voice instruction. The voice module is a storage area corresponding to the voice instruction in the memory or the terminal.
And the test terminal searches a voice module for storing the voice instruction and sends the awakening test instruction to the voice module. The wake-up test instruction may be voice or other form. And the voice module receives the awakening test instruction and feeds back an awakening mark corresponding to the awakening test instruction to the test terminal.
Optionally, in this embodiment, if the execution result information is different from the preset execution result of the voice command in step S200, the step of receiving, by the test terminal, the wake-up test command or the next voice test command is executed. The execution result information is different from the preset execution result, and the obtained feedback information is in a dormant state and is fed back to other states. If the feedback information is dormant, performing awakening test on the voice module storing the voice instruction; and if the feedback is in other states, testing the next voice instruction for the voice module storing the voice instruction.
S600: and receiving a wake-up mark fed back by the voice module, and confirming a wake-up test result for storing whether the voice module of the voice instruction is successfully wakened according to the wake-up mark fed back by the voice module.
The test terminal receives a wake-up mark fed back by the voice module, the wake-up mark can be a voice prompt or other prompts, and whether the voice module storing the voice instruction is woken up or not is determined according to the wake-up mark. The time from sending the awakening test instruction to obtaining the voice module feedback awakening mark can be preset as second preset time by the test terminal, the awakening mark is received within the second preset time, and whether the voice module is successfully awakened or not is judged according to the received awakening mark. It can be understood that, within the second preset time, if the test terminal does not receive the wake-up flag, it indicates that the voice module is not successfully woken up, and it is determined that the test result of the recognition test is that the voice command cannot be correctly recognized.
Optionally, in this embodiment, the test terminal stores a preset flag corresponding to the voice instruction, and the step of determining whether the voice module of the test terminal is successfully awakened according to the awakening flag fed back by the voice module includes: and comparing whether the awakening mark is matched with a preset mark of the voice instruction, if so, successfully awakening the voice module. The preset mark is pre-stored in the test terminal, and each voice instruction is provided with a corresponding preset mark. And when the preset mark is consistent with the awakening mark fed back by the voice module, determining that the awakening test result is that the voice module for storing the voice instruction can be awakened successfully.
Taking the awakening mark as a voice prompt as an example, the preset mark is also a voice prompt. The test terminal sends a wakeup test instruction to the voice module which stores the voice instruction and corresponds to the voice instruction, receives a wakeup mark fed back by the voice module, compares the wakeup mark with a preset mark corresponding to the voice instruction, and when the voice prompt of the wakeup mark is consistent with the voice prompt of the preset mark, the voice module which stores the voice instruction is successfully awakened.
By performing the wake-up test on the voice module in which the voice command is stored, when the voice module is in a dormant state, the voice module may be first wakened up to avoid that the voice command to be tested cannot be obtained in step S100.
In an embodiment, in order to obtain the wake-up rate of the storage module for storing the voice command, the wake-up test is repeatedly executed for a preset number of times to obtain a plurality of wake-up test results, and the wake-up rate of the voice module for storing the voice command is calculated according to the plurality of wake-up test results. And after the preset times of awakening tests are carried out, obtaining the awakening rate of the voice module for storing the voice command, and recording and displaying the awakening rate and the corresponding voice command. And when the storage module stores a plurality of voice instructions, after the wake-up test of the storage module is finished, the recognition test of the plurality of voice instructions is executed.
After the recognition test of one voice instruction is completed, the test terminal can stay for a third preset time, and in the third preset time, a tester can select whether to continue the recognition test of the next voice instruction or not through the keys on the test terminal.
By obtaining the wake-up rate of the wake-up test, the tester can intuitively know the recognition failure reason in the instruction recognition process, where the recognition failure reason may include that the storage module for storing the voice instruction is in a dormant state and cannot be woken up, and the voice instruction is woken up but cannot be correctly recognized. The tester can automatically obtain the awakening test result conveniently, so that interference factors of manual test can be eliminated, and the test precision and efficiency are improved.
The invention also provides an embodiment of the voice instruction testing device.
Referring to fig. 4, the voice command testing apparatus includes: a memory 1002; and a processor 1001, wherein the memory 1002 stores a voice instruction testing program executable on the processor 1001, and when the voice instruction testing program is executed by the processor 1001, the voice instruction testing program implements the steps of the voice instruction testing method as described in any one of the above embodiments.
The processor 1001 may be a CPU, said processor 1001 may comprise a network interface, a user interface, a communication bus 1002, etc. The communication bus 1002 is used to implement connection communication among these components. The user interface may comprise a Display screen (Display), an input unit such as keys, and the optional user interface may also comprise a standard wired interface, a wireless interface. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), a serial port, etc. The memory 1002 may be a high-speed RAM memory 1002, or may be a non-volatile memory 1002, such as a disk memory 1002. The memory 1002 may alternatively be a storage device separate from the processor 1001.
In this apparatus, the processor 1001 may be provided with a voice module 10011 for storing voice commands, and when there are multiple voice commands, each of the voice commands may have a corresponding voice module 10011. The processor 1001 can preset an execution result, when performing the recognition test, the processor 1001 reads a voice instruction test program in the memory 1002, searches for a voice instruction to be tested in the voice module 10011, can use the sound card 10012 as a voice playing module, and plays the voice instruction to be tested through the sound card 10012, the processor 1001 is provided with a voice receiving module 10013 for executing and acquiring the voice instruction, the voice receiving module 10013 receives the voice instruction played by the sound card 10012, and the processor 1001 executes the voice instruction to obtain the execution result information. The processor 1001 has a determining module 10014, where the determining module 10014 is configured to determine whether the execution result information is consistent with a preset execution result, and if so, the voice command is successfully recognized. The processor 1001 may send the recognition test result to the display module 10015 for displaying the recognition test result.
Through the processor 1001 automatically acquires the voice command, performs recognition testing to obtain a recognition testing result, can realize automatic recognition testing of the voice command, further eliminates manual testing interference, improves testing efficiency and testing precision, and enables a tester to quickly obtain a testing result.
The present invention also proposes an embodiment of a readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method for testing voice instructions as described in any of the above embodiments.
The readable storage medium may be a U-disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, etc. which can store the program codes.
Claims (10)
1. A voice instruction testing method is characterized by comprising the following steps:
the test terminal acquires a voice instruction to be tested; and
and carrying out recognition test on the acquired voice command, wherein the recognition test is as follows: playing and executing the acquired voice instruction, acquiring execution result information of the voice instruction, comparing the execution result information with a preset execution result of the voice instruction, and obtaining a test result of whether the voice instruction is successfully identified according to the comparison result;
wherein, the obtaining of the test result of whether the voice command is recognized successfully according to the comparison result comprises:
when the execution result information is the same as the preset execution result of the voice instruction, determining that the test result of the recognition test is that the voice instruction can be correctly recognized;
when the execution result information is different from a preset execution result of the voice instruction, determining whether a voice module for storing the voice instruction is in a dormant state; and
if the voice module for storing the voice command is not in a dormant state, determining that the voice command cannot be correctly recognized as a test result of the recognition test;
if the voice module for storing the voice instruction is in a dormant state, performing a wake-up test on the voice module for storing the voice instruction to obtain a wake-up test result, wherein the wake-up test result comprises that the voice module for storing the voice instruction can be successfully woken up and the voice module for storing the voice instruction cannot be successfully woken up; and
when the awakening test result is determined that the voice module for storing the voice command can be awakened successfully, executing the step that the test terminal obtains the voice command to be tested;
if the voice module for storing the voice command is in a dormant state, performing a wake-up test on the voice module for storing the voice command to obtain a wake-up test result, further comprising:
and when the awakening test result is judged to be that the voice module for storing the voice command cannot be awakened successfully, determining that the test result of the recognition test is that the voice command cannot be recognized correctly.
2. The method for testing voice commands according to claim 1, wherein the voice commands are plural, the step of comparing the execution result information with the preset execution result of the voice command is performed, and the step of obtaining the test result of whether the voice command is recognized successfully according to the comparison result further comprises:
respectively executing the recognition test on a plurality of voice instructions and obtaining a plurality of test results corresponding to the plurality of voice instructions; and
and calculating the recognition rate of the voice command according to a plurality of test results.
3. The method for testing voice commands according to claim 2, wherein after the step of calculating the recognition rate of the voice command based on the plurality of test results is performed, the method for testing voice commands further comprises:
and displaying the recognition rate of the voice command, and/or displaying the voice command with the execution result information different from the preset execution result.
4. The voice instruction testing method of claim 1, wherein after the step of acquiring a voice instruction to be tested is performed, the acquired voice instruction is displayed.
5. The voice instruction testing method of any one of claims 1 to 4, wherein the wake-up test comprises:
when receiving a wake-up test instruction, the test terminal searches a voice module for storing a voice instruction corresponding to the wake-up test instruction, and sends the wake-up test instruction to the searched voice module; and
and receiving a wake-up mark fed back by the voice module, and confirming a wake-up test result for storing whether the voice module of the voice instruction is successfully awakened or not according to the wake-up mark fed back by the voice module.
6. The method according to claim 5, wherein the test terminal stores a preset flag corresponding to the voice command, and the step of confirming the wake-up test result for storing whether the voice module of the voice command is successfully woken up according to the wake-up flag fed back by the voice module comprises:
and comparing whether the awakening mark is matched with a preset mark of the voice instruction, and if so, determining that the awakening test result is that the voice module for storing the voice instruction can be awakened successfully.
7. The method according to any one of claims 1 to 4, wherein if the voice module for storing the voice command is in a sleep state, performing a wake-up test on the voice module for storing the voice command to obtain a wake-up test result, and then repeatedly executing the wake-up test a predetermined number of times to obtain a plurality of wake-up test results, and calculating a wake-up rate of the voice module for storing the voice command according to the plurality of wake-up test results.
8. The method for testing voice commands according to claim 7, wherein after the step of calculating the wake-up rate of the voice module for storing the voice commands according to the plurality of wake-up test results is performed, the method further comprises:
and displaying the awakening rate of a voice module used for storing the voice instruction, and/or displaying the voice instruction.
9. A voice instruction testing apparatus, comprising:
a memory; and
a processor, the memory having stored thereon a voice instruction testing program executable on the processor, the voice instruction testing program when executed by the processor implementing the steps of the voice instruction testing method as claimed in any one of claims 1 to 8.
10. A readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, carries out the method of testing speech instructions according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110380000.9A CN113140217B (en) | 2021-04-08 | 2021-04-08 | Voice instruction testing method, testing device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110380000.9A CN113140217B (en) | 2021-04-08 | 2021-04-08 | Voice instruction testing method, testing device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113140217A CN113140217A (en) | 2021-07-20 |
| CN113140217B true CN113140217B (en) | 2022-11-22 |
Family
ID=76811456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110380000.9A Active CN113140217B (en) | 2021-04-08 | 2021-04-08 | Voice instruction testing method, testing device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113140217B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113782003A (en) * | 2021-09-14 | 2021-12-10 | 上汽通用五菱汽车股份有限公司 | Test method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105681920A (en) * | 2015-12-30 | 2016-06-15 | 深圳市鹰硕音频科技有限公司 | Network teaching method and system with voice recognition function |
| CN111128139A (en) * | 2019-12-18 | 2020-05-08 | 苏州思必驰信息科技有限公司 | Non-invasive voice test method and device |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9438729B2 (en) * | 2014-08-15 | 2016-09-06 | Accenture Global Services Limited | Automated testing of interactive voice response systems |
| CN108228468A (en) * | 2018-02-12 | 2018-06-29 | 腾讯科技（深圳）有限公司 | A kind of test method, device, test equipment and storage medium |
| CN109003602B (en) * | 2018-09-10 | 2020-03-24 | 百度在线网络技术（北京）有限公司 | Voice product testing method, device, equipment and computer readable medium |
| CN109326305B (en) * | 2018-09-18 | 2023-04-07 | 易诚博睿(南京)科技有限公司 | Method and system for batch testing of speech recognition and text synthesis |
| CN109493857A (en) * | 2018-09-28 | 2019-03-19 | 广州智伴人工智能科技有限公司 | A kind of auto sleep wake-up robot system |
| CN109256115A (en) * | 2018-10-22 | 2019-01-22 | 四川虹美智能科技有限公司 | A kind of speech detection system and method for intelligent appliance |
| CN111145737B (en) * | 2018-11-06 | 2022-07-01 | 中移（杭州）信息技术有限公司 | Voice test method and device and electronic equipment |
| CN111798833B (en) * | 2019-04-04 | 2023-12-01 | 北京京东尚科信息技术有限公司 | Voice test method, device, equipment and storage medium |
| CN112309430A (en) * | 2019-07-31 | 2021-02-02 | 广东美的制冷设备有限公司 | Household appliance and self-checking method and device thereof |
| CN111179907A (en) * | 2019-12-31 | 2020-05-19 | 深圳Tcl新技术有限公司 | Voice recognition test method, device, equipment and computer readable storage medium |
| CN111415684B (en) * | 2020-03-18 | 2023-12-22 | 歌尔微电子股份有限公司 | Voice module testing method and device and computer readable storage medium |
| CN111552642A (en) * | 2020-04-27 | 2020-08-18 | 重庆长安汽车股份有限公司 | Voice automatic test system and method for vehicle machine |
| CN111785268A (en) * | 2020-06-30 | 2020-10-16 | 北京声智科技有限公司 | Method and device for testing voice interaction response speed and electronic equipment |
| CN111739513B (en) * | 2020-07-22 | 2020-12-11 | 江苏清微智能科技有限公司 | Automatic voice awakening test system and test method thereof |
| CN111933137B (en) * | 2020-08-19 | 2024-04-16 | Oppo广东移动通信有限公司 | Voice wake-up test method and device, computer readable medium and electronic equipment |
| 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 |
| CN111933108B (en) * | 2020-09-25 | 2021-01-12 | 蘑菇车联信息科技有限公司 | Automatic testing method for intelligent voice interaction system of intelligent network terminal |
-
2021
- 2021-04-08 CN CN202110380000.9A patent/CN113140217B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105681920A (en) * | 2015-12-30 | 2016-06-15 | 深圳市鹰硕音频科技有限公司 | Network teaching method and system with voice recognition function |
| CN111128139A (en) * | 2019-12-18 | 2020-05-08 | 苏州思必驰信息科技有限公司 | Non-invasive voice test method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113140217A (en) | 2021-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107037352B (en) | Capacitive touch key chip detection calibration system and method | |
| CN108037444B (en) | GNSS PCBA automatic test system and application method thereof | |
| CN109326305B (en) | Method and system for batch testing of speech recognition and text synthesis | |
| US20130268218A1 (en) | Testing system and method | |
| CN106897219B (en) | Method and device for testing stability of mobile terminal system | |
| CN112526319B (en) | Chip testing method and device, processor chip and server | |
| CN109711655A (en) | Double record quality detecting methods, device, equipment and computer readable storage medium | |
| US20110057643A1 (en) | Oscillograph and signal integrity test method using the oscillograph | |
| CN113140217B (en) | Voice instruction testing method, testing device and readable storage medium | |
| CN103489444A (en) | Speech recognition method and device | |
| CN112230569B (en) | Control method and device of detection equipment | |
| CN111179907A (en) | Voice recognition test method, device, equipment and computer readable storage medium | |
| CN113359010A (en) | Core board test system and test method thereof | |
| CN111679652A (en) | Test method and device based on smart screen, smart screen and readable storage medium | |
| US8339121B2 (en) | Oscillograph and signal identifying method of a serial data bus using the oscillograph | |
| CN114964809B (en) | Vehicle instrument testing method and device and storage medium | |
| CN110996244A (en) | Microphone array performance test method, device and system | |
| CN106060615B (en) | Judgment method and device for realizing screen parameter automatic matching by using optical sensor | |
| CN114166265A (en) | Ground test method and system for satellite, storage medium and electronic equipment | |
| CN111400193B (en) | Test case generation method, device, equipment and storage medium | |
| CN111190806B (en) | Log processing method and device of voice interaction equipment | |
| CN114999457A (en) | Voice system testing method and device, storage medium and electronic equipment | |
| CN115103289A (en) | Earphone aging monitoring method and device, computer equipment and storage medium | |
| CN106405430B (en) | Lithium ion battery on-line detection conversion control equipment, system and method | |
| CN103218592B (en) | The method of bar-code identification and corresponding sample analyser is carried out in sample analyser |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |