CN115188369A - Voice recognition rate testing method, system, chip, electronic device and storage medium - Google Patents
Voice recognition rate testing method, system, chip, electronic device and storage medium Download PDFInfo
- Publication number
- CN115188369A CN115188369A CN202211098553.6A CN202211098553A CN115188369A CN 115188369 A CN115188369 A CN 115188369A CN 202211098553 A CN202211098553 A CN 202211098553A CN 115188369 A CN115188369 A CN 115188369A
- Authority
- CN
- China
- Prior art keywords
- information
- voice
- user
- recognition rate
- command word
- 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 134
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000004590 computer program Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 18
- 238000010586 diagram Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/01—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)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Debugging And Monitoring (AREA)
Abstract
The application discloses a voice recognition rate testing method, a system, a chip, electronic equipment and a storage medium, wherein a host responds to voice recognition rate testing operation and sends a testing instruction to an off-line voice module; the off-line voice module responds to the test instruction and starts a voice recognition mode; the host sends information to be recognized to the offline voice module in the voice recognition mode; the off-line voice module carries out voice recognition on the information to be recognized; when the off-line voice module identifies the command word from the information to be identified, the off-line voice module sends the command word information to the host; the host determines and saves the recognition result based on the command word information. The method and the device can reduce the steps of manual operation and automatically store the recognition result, so that the efficiency of testing the voice recognition rate of the off-line voice module is improved.
Description
Technical Field
The application relates to the technical field of voice recognition, in particular to a voice recognition rate testing method, a voice recognition rate testing system, a voice recognition rate testing chip, electronic equipment and a storage medium.
Background
With social progress and technological development, voice interaction gradually becomes a convenient man-machine interaction mode. More and more household electrical appliances are provided with an offline voice module with a voice interaction function. Before the off-line voice module is installed in different household appliances, the voice recognition rate of the off-line voice module needs to be tested. However, the prior art off-line voice module requires a lot of manual steps to complete the voice recognition rate test, and the recognition result output by the off-line voice module also needs to be recorded manually, which results in low efficiency of the prior art voice recognition rate test method.
Disclosure of Invention
In view of this, the present application provides a method, a system, a chip, an electronic device and a storage medium for testing a speech recognition rate, which reduces the number of steps of manual operation and automatically saves a recognition result, thereby improving the efficiency of testing the speech recognition rate of an offline speech module.
The application provides a voice recognition rate testing method, which comprises the following steps:
responding to the voice recognition rate test operation, and sending a test instruction to the off-line voice module;
when the offline voice module is detected to be in a voice recognition mode, sending information to be recognized to the offline voice module;
and receiving command word information identified by the offline voice module aiming at the information to be identified, and determining and storing an identification result based on the command word information.
Optionally, the method for testing a speech recognition rate further includes:
displaying a plurality of command words according to a preset rule, and acquiring user voice information input by aiming at each command word;
and generating corresponding information to be identified based on each user voice information.
Optionally, the generating corresponding information to be recognized based on each piece of user voice information includes:
based on preset voice configuration information, adjusting the user voice information;
and acquiring analog noise, and generating the information to be identified based on the adjusted user voice information and the analog noise.
Optionally, the method for testing a speech recognition rate further includes:
acquiring personal information of a user;
and when the recording information sent by the offline voice module is received, the personal information of the user is bound with the recording information.
Optionally, the displaying a plurality of command words according to a preset rule and acquiring user voice information input for each command word includes:
displaying corresponding command words according to a preset sequence so that a user can input user voice information according to the command words;
responding to input operation, and acquiring the user voice information, or being in a state of suspending acquisition of the user voice information;
and returning to the step of displaying the corresponding command words according to the preset sequence so that the user inputs the user voice information according to the command words until the user voice information input by aiming at each command word is obtained.
Optionally, the method for testing a speech recognition rate further includes:
generating a first timestamp when the corresponding command word is displayed;
when command word information corresponding to the command words and sent by the offline voice module is received, a second timestamp is generated;
and generating time information corresponding to the identification result based on the first time stamp and the second time stamp.
Optionally, the method for testing a speech recognition rate further includes:
and after displaying each command word, starting a voice recognition stopping mode, and counting a recognition result corresponding to each piece of information to be recognized and time information corresponding to each recognition result to obtain test result information.
Optionally, the method for testing a speech recognition rate further includes:
acquiring recording information of a voice recognition process sent by the off-line voice module;
and when the voice recognition mode is stopped, transmitting the user personal information, the recording information, the test result information and the recording information to a server so that the server updates a voice recognition model based on the user personal information, the recording information, the test result information and the recording information.
The application provides a voice recognition rate testing method, which comprises the following steps:
responding to a test instruction sent by a host computer, and starting a voice recognition mode;
when information to be recognized sent by a host is received in the voice recognition mode, performing voice recognition on the information to be recognized;
and when a command word is identified from the information to be identified, sending command word information to the host computer, so that the host computer determines and stores an identification result based on the command word information.
Optionally, the method for testing a speech recognition rate further includes:
and responding to the recording instruction sent by the host, starting a recording mode, and sending recording information to the host.
Optionally, the method for testing a speech recognition rate further includes:
and when the mobile terminal is in the voice recognition mode, recording a voice recognition process to obtain recording information of the voice recognition process, and sending the recording information to the host.
The application provides a voice recognition rate testing system, which comprises a host and an off-line voice module, wherein,
the host responds to the voice recognition rate test operation and sends a test instruction to the off-line voice module;
the off-line voice module responds to the test instruction and starts a voice recognition mode;
the host sends information to be recognized to the off-line voice module in the voice recognition mode;
the off-line voice module carries out voice recognition on the information to be recognized;
when the offline voice module identifies a command word from the information to be identified, the offline voice module sends command word information to the host;
and the host determines and stores the recognition result based on the command word information.
The present application provides a chip, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the speech recognition rate testing method according to any one of the above.
The application provides an electronic device, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the voice recognition rate testing method when executing the computer program.
The present application provides a storage medium having a computer program stored thereon, which when executed by a processor implements the steps of the speech recognition rate testing method according to any one of the above.
The application provides a method, a system, a chip, an electronic device and a storage medium for testing a voice recognition rate, wherein the method comprises the following steps: responding to the voice recognition rate test operation, sending a test instruction to the off-line voice module, sending information to be recognized to the off-line voice module when the off-line voice module is detected to be in the voice recognition mode, receiving command word information recognized by the off-line voice module aiming at the information to be recognized, and determining and storing a recognition result based on the command word information. The method comprises the steps of automatically starting a voice recognition mode by responding to voice recognition rate test operation, and carrying out voice recognition on information to be recognized to obtain command word information; and determining and storing the recognition result based on the command word information, thereby reducing the steps of manually operating the voice recognition rate test and manually recording the recognition result, and being beneficial to improving the efficiency of testing the voice recognition rate of the off-line voice module.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a speech recognition rate testing system according to an embodiment of the present application;
fig. 2 is a first flowchart of a speech recognition rate testing method according to an embodiment of the present application;
fig. 3 is a schematic diagram of a second process of the speech recognition rate testing method according to the embodiment of the present application;
fig. 4 is a third flowchart of a speech recognition rate testing method according to an embodiment of the present application;
fig. 5 is an interaction diagram of an offline voice module and a host in a voice recognition rate testing system according to an embodiment of the present application.
Detailed Description
According to the existing technical scheme for testing the voice recognition rate, a user carries out oral calling on an off-line voice module to input voice to be recognized, the off-line voice module carries out voice recognition on the voice to be recognized and outputs a recognition result, and therefore the test of the recognition rate is completed. The technical scheme of the voice recognition rate test requires that a user (namely a caller) calls 1 entry per mouth according to a table of voice command words to be tested, an offline voice module performs voice recognition on the voice called by the mouth entry and outputs a recognition result, and then the user (namely the caller) performs manual recording, so that a large amount of operation of the user is required, the time and the energy of the user are occupied, the efficiency of the voice recognition rate test is reduced, and the error probability is increased. In view of the above technical problems of the prior art, the present application provides embodiments that solve the technical problems.
The technical solutions in the embodiments of the present application are clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application. The following embodiments and their technical features may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a speech recognition rate testing system according to an embodiment of the present disclosure. The voice recognition rate testing system comprises a host and an off-line voice module. The host is connected with the relay, and the host controls the conduction or disconnection of a conductive channel between the off-line voice module and the power supply by sending a relay signal to the relay, so that the off-line voice module is controlled to be switched on or off.
Please refer to fig. 2, and fig. 2 is a first flowchart of a speech recognition rate testing method according to an embodiment of the present disclosure. The voice recognition rate testing method comprises the following steps:
and S11, responding to the voice recognition rate test operation and sending a test instruction to the off-line voice module.
In step S11, when the speech recognition rate test is required, the user operates the host computer, and only needs to click the key for starting the test in the speech recognition rate test software, then the host computer sends an opening instruction to the relay, and after the relay is opened, the off-line speech module is enabled to be conducted with the conductive channel between the power supply, so that the off-line speech module is in a working state. The off-line voice module in working state receives the test instruction from the host computer and starts the voice recognition rate test.
And S12, when the offline voice module is detected to be in the voice recognition mode, sending information to be recognized to the offline voice module.
In step S12, the offline voice module is always in the voice recognition mode after receiving the test command. The host computer can send the information to be recognized to the off-line voice module in the voice recognition mode. The information to be recognized may be a pre-recorded user voice or a live voice input by the user through a sound pickup.
And S13, receiving command word information recognized by the offline voice module aiming at the information to be recognized, and determining and storing a recognition result based on the command word information.
In some embodiments, after the offline voice module identifies the information to be identified, the corresponding command word information is obtained, for example, the information to be identified is the command word "turn on light", and if the offline voice module identifies successfully, the command word information "turn on light" is fed back to the host; if the off-line voice module recognition is not successful, the command word information of "light off" may be fed back to the host. The host can determine whether the identification result is successfully identified or unsuccessfully identified according to the command word information of 'light turned on' or the command word information of 'light turned off', and stores the identification result corresponding to the information to be identified.
It can be understood that, although the existing automatic speech recognition rate testing scheme inputs the speech of the user as the information to be recognized to the offline speech module by playing the prerecorded voice corpus of the user, the voice corpus inevitably causes distortion in the corpus collection or corpus playing link, and the sound pressure cannot completely reach the level of the live speech input by the user through the sound pick-up when playing the prerecorded voice corpus. To address this issue, the present application provides other embodiments.
Optionally, in some embodiments, please refer to fig. 3, and fig. 3 is a second flowchart of the speech recognition rate testing method according to the embodiment of the present application. On the basis of the flow shown in fig. 2, the method for testing the speech recognition rate further includes:
s10, obtaining information to be identified, wherein the S10 specifically comprises:
s101, displaying a plurality of command words according to a preset rule, and acquiring user voice information input by aiming at each command word.
In step S101, the host generates a display interface containing command words, and displays a plurality of command words to the user through the screen, and the user (i.e., the caller) only needs to read the command words from the display interface, and the host picks up the voice uttered by the user through the microphone, so as to obtain the user voice information input by the user for the command words.
Optionally, in some embodiments, step S101 includes:
(1) And displaying the corresponding command words according to a preset sequence so that the user inputs the voice information of the user according to the command words.
(2) And responding to the input operation to acquire the voice information of the user or being in a state of suspending the acquisition of the voice information of the user.
(3) And returning to the step of displaying the corresponding command words according to the preset sequence so that the user inputs the user voice information according to the command words until the user voice information input aiming at each command word is obtained.
In this embodiment, the host displays a command word to the user on the display interface each time, and the interval for displaying the command word each time can be set according to the user requirement. The user can execute the suspended input operation on the host computer to continuously display the current command word, and can also execute the input operation of re-displaying the previous command word, so that the host computer responds to the input operation and is in a state of suspending the acquisition of the voice information of the user, if the user does not execute the suspended input operation or re-displays the input operation of the previous command word, the host computer displays the next command word to the user on the display interface according to the preset sequence until all the command words preset in the test are displayed to the user once. And after the last command word is displayed according to the preset sequence, prompting the user that the oral call is finished (namely, the user does not need to input the voice information of the user), and enabling the display interface to disappear after 5 seconds. And after the last command word is displayed according to the preset sequence, the host sends a closing instruction to the relay to control the off-line voice module to be powered off.
In the embodiment, when the user needs to pause or realizes that the input voice information of the user has errors, the problem can be solved by executing corresponding input operation.
And S102, generating corresponding information to be identified based on the voice information of each user.
Optionally, in some embodiments, step S102 includes:
(4) And adjusting the voice information of the user based on preset voice configuration information.
(5) And acquiring the analog noise, and generating the information to be identified based on the adjusted user voice information and the analog noise.
In some embodiments, based on preset voice configuration information, such as an input voice volume, a play speed of a voice, and the like, a user may adjust the voice configuration information such as the voice volume, the play speed, and the like according to a requirement, and the host may adjust the voice volume, the play speed, and the like of the user for the user voice information, that is, the voice input by the user, according to the voice configuration information such as the voice volume, the play speed, and the like.
In some embodiments, analog noise needs to be added to increase the difficulty of voice recognition, so in specific implementation, the host is further connected with a sound device for playing the analog noise, so as to obtain the analog noise, and generate the information to be recognized based on the user voice information and the analog noise.
Optionally, in some embodiments, the speech recognition rate testing method further includes:
and S14, acquiring the personal information of the user.
Further, acquiring personal information of the user; and when the recording information sent by the off-line voice module is received, the personal information of the user is bound with the recording information.
As shown in fig. 1, the offline audio module is connected to a julnk (emulator) for recording and acquiring the recorded information of the recognition process, and both the offline audio module and the julnk are connected to a USB splitter, which is connected to a relay, so that the relay transmits electric energy to the offline audio module and the julnk through the USB splitter, respectively. When the JLINK is conductive and in a working state, the offline voice module can realize a recording function and send recording information to the host.
In one embodiment, when the host computer obtains the personal information of the user, the personal information input interface of the user is displayed through a screen, for example, in the personal information input interface of the user, the user can input the personal information of the user such as name, gender, age and the like, and the host computer can bind the personal information of the user with the recording information, so that classification and statistics of the recording information can be favorably carried out according to the personal information of the user when the recognition result is counted.
Optionally, in some embodiments, the speech recognition rate testing method further includes:
and S15, acquiring time information.
Specifically, when a corresponding command word is presented, a first timestamp is generated; when command word information of a corresponding command word sent by the off-line voice module is received, a second timestamp is generated; and generating time information corresponding to the identification result based on the first time stamp and the second time stamp.
In this embodiment, the host sequentially displays command words to be recognized according to a preset sequence, displays one command word at a time, and generates and records a first timestamp; when command word information corresponding to the command words sent by the offline voice module is received, generating and recording a second timestamp; and generating time information corresponding to the identification result according to the first time stamp and the second time stamp. Thereby, time information corresponding to each recognition result can be recorded.
Optionally, in some embodiments, the method for testing a speech recognition rate further includes:
and S16, obtaining test result information.
Specifically, after each command word is displayed, the voice recognition stopping mode is started, and the recognition result corresponding to each piece of information to be recognized and the time information corresponding to each recognition result are counted to obtain the test result information.
It can be understood that, after each oral call of the user is finished (i.e. after the last command word is displayed according to the preset sequence), the host computer counts all the recognition results of the oral call of the user and the time information corresponding to each recognition result to obtain the test result information.
Optionally, in some embodiments, the method for testing a speech recognition rate further includes:
and S17, acquiring the recording information of the voice recognition process.
Further, acquiring recording information of a voice recognition process sent by the off-line voice module; when in the stop voice recognition mode, transmitting the user personal information, the recording information, the test result information, and the recording information to the server so that the server updates the voice recognition model based on the user personal information, the recording information, the test result information, and the recording information.
It can be understood that after the host transmits the user personal information, the recording information, the test result information and the recording information to the server, the server can set a label for the recording information, the label comprises the user personal information, the time information and the command word information, and based on the recording information of the voice recognition process, the voice recognition process of the offline voice module is completely reproduced, and whether each frame of recording information is expected or not is analyzed, so that the purpose of improving the model is achieved.
The application provides a voice recognition rate testing method, which responds to voice recognition rate testing operation, sends a testing instruction to an offline voice module, sends information to be recognized to the offline voice module when the offline voice module is detected to be in a voice recognition mode, receives command word information recognized by the offline voice module aiming at the information to be recognized, and determines and stores a recognition result based on the command word information. The method comprises the steps of automatically starting a voice recognition mode by responding to voice recognition rate test operation, and carrying out voice recognition on information to be recognized to obtain command word information; and determining and storing the recognition result based on the command word information, thereby reducing the steps of manually operating the voice recognition rate test and manually recording the recognition result, and being beneficial to improving the efficiency of testing the voice recognition rate of the off-line voice module.
Please refer to fig. 4, where fig. 4 is a third flow diagram of the speech recognition rate testing method according to the embodiment of the present application. The voice recognition rate testing method comprises the following steps:
and S21, responding to a test instruction sent by the host computer, and starting a voice recognition mode.
And S22, when the information to be recognized sent by the host is received in the voice recognition mode, performing voice recognition on the information to be recognized.
And S23, when the command word is recognized from the information to be recognized, sending the command word information to the host computer, so that the host computer determines and stores the recognition result based on the command word information.
Optionally, in some embodiments, the method for testing a speech recognition rate further includes:
and S24, responding to the recording instruction sent by the host, starting a recording mode, and sending recording information to the host.
Optionally, in some embodiments, the speech recognition rate testing method further includes:
and S25, when the mobile terminal is in the voice recognition mode, recording the voice recognition process to obtain the recording information of the voice recognition process, and sending the recording information to the host.
In one embodiment, after receiving the recording instruction, the offline voice module enables the JLINK, so that the offline voice module collects the user voice information and the recording information of the voice recognition process in the cache in real time and uploads the user voice information and the recording information to the host.
The application provides a voice recognition rate testing method, which responds to a testing instruction sent by a host computer and starts a voice recognition mode; when information to be recognized sent by a host is received in a voice recognition mode, performing voice recognition on the information to be recognized; when the command word is recognized from the information to be recognized, the command word information is sent to the host computer, so that the host computer determines and stores the recognition result based on the command word information. The method comprises the steps of automatically starting a voice recognition mode by responding to voice recognition rate test operation, and carrying out voice recognition on information to be recognized to obtain command word information; and determining and storing the recognition result based on the command word information, thereby reducing the steps of manually operating the voice recognition rate test and manually recording the recognition result, and being beneficial to improving the efficiency of testing the voice recognition rate of the off-line voice module.
Please refer to fig. 5, wherein fig. 5 is an interaction diagram illustrating an offline voice module and a host in the voice recognition rate testing system according to an embodiment of the present application. The voice recognition rate testing system comprises a host and an off-line voice module, wherein,
and S31, the host responds to the voice recognition rate test operation and sends a test instruction to the off-line voice module.
S32, the off-line voice module responds to the test instruction and starts a voice recognition mode.
S33, the host sends the information to be recognized to the offline voice module in the voice recognition mode.
And S34, performing voice recognition on the information to be recognized by the offline voice module.
And S35, when the offline voice module identifies the command word from the information to be identified, the offline voice module sends the command word information to the host.
And S36, determining and storing the recognition result by the host computer based on the command word information.
Optionally, in some embodiments, the host is further configured to:
displaying a plurality of command words according to a preset rule, and acquiring user voice information input aiming at each command word; and generating corresponding information to be identified based on the voice information of each user.
Optionally, in some embodiments, the host is further configured to:
based on preset voice configuration information, adjusting the voice information of the user; and acquiring the analog noise, and generating the information to be identified based on the adjusted user voice information and the analog noise.
Optionally, in some embodiments, the host is further configured to:
acquiring personal information of a user; and when the recording information sent by the off-line voice module is received, the personal information of the user is bound with the recording information.
Optionally, in some embodiments, the host is further configured to:
displaying corresponding command words according to a preset sequence so that a user can input user voice information according to the command words; responding to the input operation, and acquiring the user voice information, or being in a state of suspending the acquisition of the user voice information; and returning to the step of displaying the corresponding command words according to the preset sequence so that the user inputs the user voice information according to the command words until the user voice information input aiming at each command word is obtained.
Optionally, in some embodiments, the host is further configured to:
generating a first timestamp when the corresponding command word is displayed; when command word information of a corresponding command word sent by the off-line voice module is received, a second timestamp is generated; and generating time information corresponding to the identification result based on the first time stamp and the second time stamp.
Optionally, in some embodiments, the host is further configured to:
and after each command word is displayed, starting a voice recognition stopping mode, and counting a recognition result corresponding to each piece of information to be recognized and time information corresponding to each recognition result to obtain test result information.
Optionally, in some embodiments, the host is further configured to:
acquiring recording information of a voice recognition process sent by an off-line voice module; when in the stop voice recognition mode, transmitting the user personal information, the recording information, the test result information and the recording information to the server so that the server updates the voice recognition model based on the user personal information, the recording information, the test result information and the recording information.
Optionally, in some embodiments, the offline speech module is further configured to:
and responding to a recording instruction sent by the host, starting a recording mode, and sending recording information to the host.
Optionally, in some embodiments, the offline speech module is further configured to:
and when the mobile terminal is in a voice recognition mode, recording the voice recognition process to obtain the recording information of the voice recognition process, and sending the recording information to the host.
The application provides a voice recognition rate test system.A host responds to voice recognition rate test operation and sends a test instruction to an off-line voice module; the off-line voice module responds to the test instruction and starts a voice recognition mode; the host sends information to be recognized to the offline voice module in the voice recognition mode; the off-line voice module carries out voice recognition on the information to be recognized; when the off-line voice module identifies the command word from the information to be identified, the off-line voice module sends the command word information to the host; the host determines and saves the recognition result based on the command word information. The method comprises the steps of automatically starting a voice recognition mode by responding to voice recognition rate test operation, and carrying out voice recognition on information to be recognized to obtain command word information; and determining and storing the recognition result based on the command word information, thereby reducing the steps of manually operating the voice recognition rate test and manually recording the recognition result, and being beneficial to improving the efficiency of testing the voice recognition rate of the off-line voice module.
The application provides a chip, wherein the chip stores a computer program, and the computer program realizes the steps of the voice recognition rate testing method according to any one of the above items when being executed by a processor.
The chip of the embodiment can achieve the above technical effects, and details are not repeated herein.
The electronic device provided by the application comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to realize the steps of any one of the voice recognition rate testing methods.
The electronic device of the embodiment can achieve the above technical effects, and details are not repeated herein.
The storage medium provided by the present application stores thereon a computer program, and the computer program, when executed by a processor, implements the steps of any of the above-described speech recognition rate testing methods.
Wherein the readable storage medium may include: read Only Memory (ROM), random Access Memory (RAM), magnetic or optical disks, and the like.
Since the instructions stored in the readable storage medium can execute the steps in any one of the speech recognition rate testing methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the speech recognition rate testing methods provided in the embodiments of the present application can be achieved, which are detailed in the foregoing embodiments and will not be described again here.
Although the application has been shown and described with respect to one or more implementations, equivalent alterations and modifications will occur to others skilled in the art based upon a reading and understanding of this specification and the annexed drawings. The present application includes all such modifications and alterations, and is limited only by the scope of the appended claims.
That is, the above description is only an embodiment of the present application, and not intended to limit the scope of the present application, and all equivalent structures or equivalent flow transformations made by using the contents of the specification and the drawings of the present application, such as the combination of technical features between various embodiments, or the direct or indirect application to other related technical fields, are all included in the scope of the present application.
In the present application, the same or similar descriptions of terms, technical solutions and/or application scenarios will generally be described in detail only when they occur for the first time, and when they occur repeatedly later, they will not be repeated again for brevity, and in understanding the technical solutions and the like of the present application, reference may be made to the related detailed descriptions and the like before the same or similar descriptions of terms, technical solutions and/or application scenarios and the like which are not described in detail later.
In the present application, each embodiment is described with emphasis, and reference may be made to the description of other embodiments for parts that are not described or illustrated in any embodiment.
All possible combinations of the technical features in the embodiments are not described in the present application for the sake of brevity, but should be considered as the scope of the present application as long as there is no contradiction between the combinations of the technical features.
In the above embodiments, all or part of the implementation may be realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions according to the embodiments of the present application are all or partially generated when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, digital subscriber line) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, memory Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), among others.
Claims (15)
1. A method for testing a speech recognition rate is characterized by comprising the following steps:
responding to the voice recognition rate test operation, and sending a test instruction to the off-line voice module;
when the offline voice module is detected to be in a voice recognition mode, sending information to be recognized to the offline voice module;
and receiving command word information identified by the offline voice module aiming at the information to be identified, and determining and storing an identification result based on the command word information.
2. The speech recognition rate testing method according to claim 1, further comprising:
displaying a plurality of command words according to a preset rule, and acquiring user voice information input by aiming at each command word;
and generating corresponding information to be identified based on each user voice information.
3. The method for testing speech recognition rate according to claim 2, wherein the generating corresponding information to be recognized based on each user speech information comprises:
based on preset voice configuration information, adjusting the user voice information;
and acquiring analog noise, and generating the information to be identified based on the adjusted user voice information and the analog noise.
4. The speech recognition rate testing method according to claim 2, further comprising:
acquiring personal information of a user;
and when the recording information sent by the offline voice module is received, the personal information of the user is bound with the recording information.
5. The method for testing speech recognition rate according to claim 4, wherein the presenting a plurality of command words according to a preset rule and obtaining the user speech information input for each command word comprises:
displaying corresponding command words according to a preset sequence so that a user can input user voice information according to the command words;
responding to input operation, acquiring the user voice information, or being in a state of suspending acquisition of the user voice information;
and returning to the step of displaying the corresponding command words according to the preset sequence so that the user inputs the user voice information according to the command words until the user voice information input by aiming at each command word is obtained.
6. The method of claim 5, further comprising:
generating a first timestamp when the corresponding command word is displayed;
when command word information corresponding to the command words and sent by the offline voice module is received, a second timestamp is generated;
and generating time information corresponding to the identification result based on the first time stamp and the second time stamp.
7. The speech recognition rate testing method of claim 6, further comprising:
and after displaying each command word, starting a voice recognition stopping mode, and counting a recognition result corresponding to each piece of information to be recognized and time information corresponding to each recognition result to obtain test result information.
8. The speech recognition rate testing method of claim 7, further comprising:
acquiring recording information of a voice recognition process sent by the off-line voice module;
and when the voice recognition mode is stopped, transmitting the user personal information, the recording information, the test result information and the recording information to a server so that the server updates a voice recognition model based on the user personal information, the recording information, the test result information and the recording information.
9. A method for testing a speech recognition rate is characterized by comprising the following steps:
responding to a test instruction sent by a host computer, and starting a voice recognition mode;
when information to be recognized sent by a host computer is received in the voice recognition mode, performing voice recognition on the information to be recognized;
and when a command word is identified from the information to be identified, sending command word information to the host computer, so that the host computer determines and stores an identification result based on the command word information.
10. The method for testing speech recognition rate of claim 9, further comprising:
and responding to the recording instruction sent by the host, starting a recording mode, and sending recording information to the host.
11. The speech recognition rate testing method of claim 9, further comprising:
and when the mobile terminal is in the voice recognition mode, recording the voice recognition process to obtain recording information of the voice recognition process, and sending the recording information to the host.
12. A speech recognition rate testing system is characterized in that it comprises a host and an off-line speech module, wherein,
the host responds to the voice recognition rate test operation and sends a test instruction to the off-line voice module;
the off-line voice module responds to the test instruction and starts a voice recognition mode;
the host sends information to be recognized to the offline voice module in the voice recognition mode;
the off-line voice module carries out voice recognition on the information to be recognized;
when the offline voice module identifies a command word from the information to be identified, the offline voice module sends command word information to the host;
and the host determines and stores the recognition result based on the command word information.
13. A chip storing a computer program which, when executed by a processor, carries out the steps of the speech recognition rate testing method according to any one of claims 1 to 11.
14. An electronic device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program implements the steps of the speech recognition rate testing method according to any one of claims 1 to 11.
15. A storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the speech recognition rate testing method according to any one of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211098553.6A CN115188369A (en) | 2022-09-09 | 2022-09-09 | Voice recognition rate testing method, system, chip, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211098553.6A CN115188369A (en) | 2022-09-09 | 2022-09-09 | Voice recognition rate testing method, system, chip, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115188369A true CN115188369A (en) | 2022-10-14 |
Family
ID=83523623
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211098553.6A Pending CN115188369A (en) | 2022-09-09 | 2022-09-09 | Voice recognition rate testing method, system, chip, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115188369A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060224392A1 (en) * | 2005-03-31 | 2006-10-05 | Microsoft Corporation | Test harness for a speech server |
| CN108320734A (en) * | 2017-12-29 | 2018-07-24 | 安徽科大讯飞医疗信息技术有限公司 | Audio signal processing method and device, storage medium, electronic equipment |
| CN108962222A (en) * | 2018-07-12 | 2018-12-07 | 四川虹美智能科技有限公司 | A kind of speech identifying function test method and device |
| CN109102808A (en) * | 2018-10-25 | 2018-12-28 | 珠海格力电器股份有限公司 | A kind of local speech recognition system and its method based on display interaction |
| CN112071305A (en) * | 2020-11-16 | 2020-12-11 | 成都启英泰伦科技有限公司 | Local off-line intelligent voice batch recognition module and method |
| CN112151018A (en) * | 2019-06-10 | 2020-12-29 | 阿里巴巴集团控股有限公司 | Voice evaluation and voice recognition method, device, equipment and storage medium |
| CN112860582A (en) * | 2021-03-26 | 2021-05-28 | 成都启英泰伦科技有限公司 | Local voice recognition module production test method |
| CN113707129A (en) * | 2021-08-30 | 2021-11-26 | 四川虹美智能科技有限公司 | Automatic testing method for voice module in Internet of things equipment |
-
2022
- 2022-09-09 CN CN202211098553.6A patent/CN115188369A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060224392A1 (en) * | 2005-03-31 | 2006-10-05 | Microsoft Corporation | Test harness for a speech server |
| CN108320734A (en) * | 2017-12-29 | 2018-07-24 | 安徽科大讯飞医疗信息技术有限公司 | Audio signal processing method and device, storage medium, electronic equipment |
| CN108962222A (en) * | 2018-07-12 | 2018-12-07 | 四川虹美智能科技有限公司 | A kind of speech identifying function test method and device |
| CN109102808A (en) * | 2018-10-25 | 2018-12-28 | 珠海格力电器股份有限公司 | A kind of local speech recognition system and its method based on display interaction |
| CN112151018A (en) * | 2019-06-10 | 2020-12-29 | 阿里巴巴集团控股有限公司 | Voice evaluation and voice recognition method, device, equipment and storage medium |
| CN112071305A (en) * | 2020-11-16 | 2020-12-11 | 成都启英泰伦科技有限公司 | Local off-line intelligent voice batch recognition module and method |
| CN112860582A (en) * | 2021-03-26 | 2021-05-28 | 成都启英泰伦科技有限公司 | Local voice recognition module production test method |
| CN113707129A (en) * | 2021-08-30 | 2021-11-26 | 四川虹美智能科技有限公司 | Automatic testing method for voice module in Internet of things equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210266274A1 (en) | Data processing method, apparatus, and device based on instant messaging application, and storage medium | |
| CN108470034B (en) | A kind of smart machine service providing method and system | |
| CN101313482B (en) | Determination of audio device quality | |
| CN104853081B (en) | Breakpoint image pickup method, device and mobile terminal | |
| CN112272170B (en) | Voice communication method and device, electronic equipment and storage medium | |
| US11200899B2 (en) | Voice processing method, apparatus and device | |
| CN108460120A (en) | Data save method, device, terminal device and storage medium | |
| CN107682752A (en) | Method, apparatus, system, terminal device and the storage medium that video pictures are shown | |
| CN104539871A (en) | Multimedia call method and device | |
| CN111899859A (en) | Surgical instrument counting method and device | |
| CN102881309A (en) | Lyric file generating and correcting method and device | |
| CN113672748A (en) | Multimedia information playing method and device | |
| CN109495776B (en) | Audio sending and playing method and intelligent terminal | |
| CN108259653B (en) | Voice test method, device and system | |
| CN108733341A (en) | A kind of voice interactive method and device | |
| CN113726600B (en) | Transmission delay determining method, device, terminal and storage medium | |
| JP2014130180A (en) | Audio device | |
| KR20160129787A (en) | A Method Generating Transcripts Of Digital Recording File | |
| CN115188369A (en) | Voice recognition rate testing method, system, chip, electronic device and storage medium | |
| CN103873711A (en) | VOIP phone-based virtual USB (universal serial bus) sound card creation method | |
| CN111432060B (en) | Method and device for testing mobile phone audio module and storage medium | |
| WO2023087287A1 (en) | Conference content display method, conference system and conference device | |
| CN110970032A (en) | Sound box voice interaction control method and device | |
| CN111556406B (en) | Audio processing method, audio processing device and earphone | |
| CN114786116A (en) | Sound processing method of conference all-in-one machine, conference all-in-one machine and storage medium |
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: 20221014 |
|
| RJ01 | Rejection of invention patent application after publication |