CN113920803A - Error feedback method, device, equipment and readable storage medium - Google Patents
Error feedback method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN113920803A CN113920803A CN202010663079.1A CN202010663079A CN113920803A CN 113920803 A CN113920803 A CN 113920803A CN 202010663079 A CN202010663079 A CN 202010663079A CN 113920803 A CN113920803 A CN 113920803A
- Authority
- CN
- China
- Prior art keywords
- audio data
- error
- target
- determining
- correction information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000012937 correction Methods 0.000 claims abstract description 107
- 238000004590 computer program Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 abstract description 14
- 230000008569 process Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
- G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
- G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
- G09B7/04—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student characterised by modifying the teaching programme in response to a wrong answer, e.g. repeating the question, supplying a further explanation
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/60—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for measuring the quality of voice signals
Abstract
The invention discloses an error feedback method, an error feedback device, error feedback equipment and a computer readable storage medium, wherein the method comprises the following steps: acquiring audio data corresponding to the title; determining target audio data corresponding to the target knowledge point in the title in the audio data; judging whether the target audio data is correct or not; if the target audio data is incorrect, determining the error type of the target audio data, and feeding back correction information according to the error type; the method enables the correction information to be matched with the error type, the error type is the error type of the target audio data, and the audio data corresponds to the sound made by the user, so the feedback correction information can correct the specific error condition of the user, the user can know where the difference between the user and the correct pronunciation exists, how to correct the difference, the pronunciation capability of the user is effectively improved, and the correction effect is good.
Description
Technical Field
The present invention relates to the field of error feedback technologies, and in particular, to an error feedback method, an error feedback apparatus, an error feedback device, and a computer-readable storage medium.
Background
In the language learning process, the practice of pronunciation ability is a crucial link, including pronunciation of phonemes in words, accent of words, sentence break of long sentences, continuous reading of words and other factors. In the practice process of pronunciation capability, in order to make the user know whether the pronunciation is correct or not, the related technology provides correct demonstration sound recording and the user's own sound recording for the user to compare, so that the user can find out the difference and correct. However, the user often cannot find the difference between the two or does not know how to reduce the difference after finding the difference, so that the user still cannot correct the error and improve the pronunciation capability. The related art is less effective in correcting the pronunciation of the user.
Therefore, how to solve the problem of poor effect of correcting the pronunciation of the user in the related art is a technical problem to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the present invention provides an error feedback method, an error feedback apparatus, an error feedback device, and a computer readable storage medium, which solve the problem of poor correction effect on user pronunciation in the related art.
In order to solve the above technical problem, the present invention provides an error feedback method, including:
acquiring audio data corresponding to the title;
determining target audio data corresponding to the target knowledge point in the title in the audio data;
judging whether the target audio data is correct or not;
and if the target audio data is incorrect, determining the error type of the target audio data, and feeding back correction information according to the error type.
Optionally, after determining that the target audio data is incorrect, before determining the error type of the target audio data, further comprising:
updating the state data corresponding to the title;
judging whether the state data meet a preset trigger condition or not;
and if the preset trigger condition is met, executing the step of determining the error type of the target audio data and feeding back correction information according to the error type.
Optionally, the method further comprises:
acquiring a trigger condition setting instruction;
and setting the preset trigger condition according to the trigger condition setting instruction.
Optionally, determining the error type of the target audio data includes:
acquiring at least one typical error audio data corresponding to the target knowledge point;
matching the target audio data with at least one typical error audio data, and judging whether the target typical error audio data successfully matched exists;
if the target typical error audio data exists, determining the error type as a target typical error type corresponding to the target typical error audio data;
and if the target typical error audio data does not exist, determining the error type as a general error type corresponding to the title.
Optionally, the determining whether the target audio data is correct includes:
acquiring the similarity between the target audio data and at least one standard audio data corresponding to the target knowledge point;
when the similarity is larger than a similarity threshold value, determining that the target audio data is correct;
when the similarity is less than a similarity threshold, determining that the target audio data is incorrect;
and/or the presence of a gas in the gas,
scoring the target audio data to obtain a score value;
determining that the target audio data is correct when the score value is greater than a score threshold;
determining that the target audio data is incorrect when the score value is less than a score threshold.
Optionally, the feeding back the correction information according to the error type includes:
determining a plurality of candidate correction information according to the error type;
and determining the correction information from a plurality of candidate correction information according to a selection rule, and outputting the correction information.
Optionally, after feeding back the correction information according to the error type, the method further includes:
re-acquiring the audio data corresponding to the title;
counting each accuracy rate corresponding to each candidate correction information; wherein each of the accuracy rates is an accuracy rate of the audio data obtained again after each of the candidate correction information is fed back as the correction information;
and adjusting the selection rule according to the accuracy.
The present invention also provides an error feedback apparatus, comprising:
the acquisition module is used for acquiring audio data corresponding to the title;
the target audio determining module is used for determining target audio data corresponding to the target knowledge point in the title in the audio data;
the judging module is used for judging whether the target audio data is correct or not;
and the correction information feedback module is used for determining the error type of the target audio data if the target audio data is incorrect and feeding back correction information according to the error type.
The present invention also provides an error feedback device comprising a memory and a processor, wherein:
the memory is used for storing a computer program;
the processor is configured to execute the computer program to implement the error feedback method.
The invention also provides a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the error feedback method described above.
The error feedback method provided by the invention obtains the audio data corresponding to the question; determining target audio data corresponding to the target knowledge point in the title in the audio data; judging whether the target audio data is correct or not; and if the target audio data is incorrect, determining the error type of the target audio data, and feeding back correction information according to the error type.
Therefore, the method determines the target audio data after acquiring the corresponding audio data, the target audio data corresponds to the target knowledge point, and the step of judging whether the target audio data is correct or not is equivalent to the step of detecting whether the target knowledge point in the audio data is correct or not. And if the target audio data is incorrect, indicating that the target audio data is incorrect, and the user incorrectly applies the target knowledge point, determining the error type of the target audio data in order to accurately correct the target audio data, and feeding back correction information according to the error type. Because the correction information is matched with the error type, the error type is the error type of the target audio data, and the audio data corresponds to the sound sent by the user, the feedback correction information can correct the specific error condition of the user, so that the user can know where the difference between the correction information and the correct pronunciation is, how to correct the difference, the pronunciation capability of the user is effectively improved, the correction effect is good, and the problem that the correction effect of the related technology on the pronunciation of the user is poor is solved. .
In addition, the invention also provides an error feedback device, error feedback equipment and a computer readable storage medium, and the error feedback device, the error feedback equipment and the computer readable storage medium also have the beneficial effects.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flowchart of an error feedback method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an error feedback apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an error feedback device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In a possible implementation manner, please refer to fig. 1, in which fig. 1 is a flowchart illustrating an error feedback method according to an embodiment of the present invention. The method comprises the following steps:
s101: audio data corresponding to the title is obtained.
All or part of the steps in this embodiment may be executed by an error feedback device, and the specific form of the error feedback device is not limited, and may be, for example, a smart phone, a computer, or a server. The audio data is obtained according to the sound emitted by the user, and may be audio files in various formats, or may be other data obtained by analyzing or processing the audio files, such as waveform data, or audio files subjected to noise reduction processing.
The audio data corresponds to the title, the title is the title data, and the audio data, the text data and other types can be specifically used for prompting the user to make corresponding sound. In an English teaching process, for example, a topic can be a word, a phrase, or a sentence. And the user makes corresponding sound after determining the title, and further obtains audio data. The audio data can be directly acquired by the error feedback device, for example, when the error feedback device is a smart phone, the audio data can be acquired by using a microphone array; the audio data may also be sent to the error feedback device by another device or terminal, for example, when the error feedback device is a server, the audio data sent by a smartphone used by the user may be acquired. In another embodiment, the audio data may also be obtained by using sound sent by other devices or terminals, for example, when the error feedback device is a server, sound sent by a user through a smart phone may be obtained, and the audio data may be obtained according to the sound.
S102: and determining target audio data corresponding to the target knowledge point in the title in the audio data.
It should be noted that, in order to improve the correction effect and improve the correction pertinence, only the target knowledge points in the topics are corrected in this embodiment. One topic comprises at least one knowledge point, and the specific content of the knowledge point is not limited. For example, when the title is an english word, the knowledge point may be the accent position of the word, the pronunciation of a designated phoneme in the word, etc.; when the title is an English sentence, the knowledge points can be continuous reading among words in the sentence, the tone and rhythm of the sentence, and the like. The number of the target knowledge points may be one or more, and in order to ensure the correction effect, this embodiment preferably determines one knowledge point in each topic as a target knowledge point.
After the audio data is obtained, the target audio data corresponding to the target knowledge point in the title needs to be determined. For example, when the target knowledge point is the pronunciation of a certain phoneme in a certain word, the target audio data is the part corresponding to the phoneme in the audio data; or when the target knowledge point is an accent position in a word, the target audio data is a part corresponding to the accent position in the audio data. Specifically, when the title is the sound of an applet, the correct pronunciation is
The target knowledge point may be
When the target audio data is the audio data
A portion of a location.
S103: and judging whether the target audio data is correct or not.
By judging whether the target audio data is correct or not, whether the pronunciation of the target knowledge point is correct or not when the user utters the sound corresponding to the title can be judged. The present embodiment does not limit the determination method for determining whether the audio data is correct, and in one embodiment, the audio data may be compared with the standard audio data. The S103 step may include:
step 11: and acquiring the similarity between the target audio data and at least one standard audio data corresponding to the target knowledge point.
Step 12: and when the similarity is larger than the similarity threshold value, determining that the target audio data is correct.
Step 13: when the similarity is less than the similarity threshold, the target audio data is determined to be incorrect.
In this embodiment, at least one standard audio data corresponding to the target knowledge point may be acquired, and the similarity between the target audio data and the standard audio data may be acquired. The number of similarities is only one, and it may specifically be an average similarity or a weighted similarity between the target audio data and the at least one standard audio data. The standard audio data can be obtained according to sounds for correctly pronouncing titles under different genders, ages and occasions.
The similarity threshold is used for comparing with the similarity to judge whether the target audio data is correct or not. The size of the similarity threshold may be set according to actual needs, for example, it may be set to 90% when the requirement is high, and it may be set to 70% when the requirement is low.
In another embodiment, the target audio data may be scored. The S103 step may include:
step 21: and scoring the target audio data to obtain a score value.
Step 22: when the score value is greater than the score threshold, the target audio data is determined to be correct.
Step 23: when the score value is less than the score threshold, the target audio data is determined to be incorrect.
In this embodiment, the specific method of scoring is not limited, and for example, the target audio data may be scored by using a deep learning network trained in advance to obtain a score value. The target audio data are input into the corresponding deep learning network, and the deep learning network is utilized to score the target audio data to obtain a score value. The score threshold is used for comparing with the score value and judging whether the target audio data is correct or not. The specific size of the score threshold is not limited, and for example, when the full score is one percentage, the score threshold may be 75 points.
When the target audio data is determined to be correct, the step S105 may be entered; when it is determined that the target audio data is not correct, the step S104 may be entered.
S104: and determining the error type of the target audio data, and feeding back correction information according to the error type.
If the target audio data is incorrect, the error type of the target audio data needs to be determined, so that correction information can be fed back according to the error type. Since many different types of errors may occur for a target knowledge point, for example, in applets
Some users may have a small mouth opening during pronunciation, some users may have a large mouth opening during pronunciation, and pronunciation under the two conditions is not correct, so target audio data under the two conditions is not correct. Because the two errors are completely different, in order to perform targeted correction and ensure the correction effect, corresponding correction information can be determined according to the error types, and error feedback is performed by using the correction information. The correction information may be at least one of audio, text or video, and the feedback manner of the correction information is different according to the specific content of the correction information. For example, when the correction information is audio, the feedback can be performed by playing the correction information; or when the correction information is text, the feedback can be carried out by displaying the correction information.
In one embodiment, in order to ensure the accuracy of the error type determination process, the accuracy of the correction information, and thus the correction effect, the errors may be divided into a general error and at least one typical error. A process for determining an error type of target audio data, comprising:
step 31: and acquiring at least one typical error audio data corresponding to the target knowledge point.
Step 32: and matching the target audio data with at least one typical error audio data, and judging whether the target typical error audio data which is successfully matched exists.
Step 33: and if the target typical error audio data exists, determining the error type as the target typical error type corresponding to the target typical error audio data.
Step 34: and if the target typical error audio data does not exist, determining the error type as a general error type corresponding to the title.
The typical error audio data respectively corresponds to the typical error types, the specific content of the typical errors can be set according to the actual use condition of the language and the typical errors in the language teaching process, and the specific number and content are not limited. For example in applets
The pronunciation of (a) is pronounced as/e/, which is a typical error. After the target audio data are determined to be wrong, matching is carried out on the target audio data and each typical wrong audio data, and whether the target typical wrong audio data which are successfully matched exist is judged. And if so, determining the error type as a target typical error type corresponding to the target typical error audio data. If the target typical error audio data does not exist, the target audio data is not typical error, and therefore the error type is determined to be a general error type.
Further, in a possible implementation manner, it is not necessary to feed back the correction information after each target audio data error is determined, but the correction information is fed back when a preset trigger condition is met. After determining that the target audio data is incorrect, before determining the error type of the target audio data, may further include:
step 41: and updating the state data corresponding to the title.
Step 42: and judging whether the state data meet a preset trigger condition.
Step 43: and if the preset triggering condition is met, executing the step of determining the error type of the target audio data and feeding back correction information according to the error type.
In this embodiment, each topic has corresponding state data, and the state data can be obtained by using a state machine, that is, the state machine is used to store the topic making state of the user for the topic, and is updated when the state changes. And after the target audio data are determined to be wrong, updating the state data corresponding to the question, and indicating that the question is wrong. After the updating is finished, whether the updated state data meets a preset triggering condition is judged, and the preset triggering condition is used for setting the feedback of the correction information under which conditions. The specific content of the preset trigger condition is not limited, and for example, the feedback of the correction information may be performed when two consecutive errors occur, or the feedback of the correction information may be performed when two errors occur in the last four times. When the preset trigger condition is not met, the audio data can be obtained again so as to further update the state data of the topic according to the audio data; or the title may be updated. When the preset triggering condition is met, the correction information can be fed back, namely, the step of determining the error type of the target audio data and feeding back the correction information according to the error type is executed.
Further, the preset trigger condition may be changed according to the change of the actual need, and therefore, the method may further include:
step 44: and acquiring a trigger condition setting instruction.
Step 45: and setting a preset trigger condition according to the trigger condition setting instruction.
Further, in one embodiment, each error type may correspond to a plurality of candidate correction information. Feeding back correction information according to the error types, comprising:
step 51: a plurality of candidate correction information is determined based on the error type.
Step 52: and determining correction information from the plurality of candidate correction information according to a selection rule, and outputting the correction information.
The candidate correction information may be different words used to represent the same or similar content. Specifically, different persons have different expression comprehension abilities for the same content, so that the same content is expressed by adopting different dialogs, the correction effects are possibly different, a plurality of candidate correction information can be set, and the correction information is determined to be selected according to the selection rule. The selection rule may be random selection, or may be selection according to the selection probability corresponding to each candidate correction information.
Further, in order to improve the correction effect and make it easier for the user to understand the correction information, after the step of feeding back the correction information according to the error type, the method may further include:
step 61: and re-acquiring the audio data corresponding to the title.
Step 62: counting each correct rate corresponding to each candidate correction information; wherein, each accuracy rate is the accuracy rate of the audio data obtained again after each candidate correction information is fed back as the correction information.
And step 63: and adjusting the selection rule according to the accuracy.
In this embodiment, after the feedback of the correction information, the corresponding audio data may be obtained again and the accuracy of the audio data may be counted. The accuracy of the reacquired audio data is high when the user has a better understanding of the correction information, and the accuracy of the reacquired audio data is low when the user has a poorer understanding of the correction information. The advantages and disadvantages of the candidate correction information can be reflected through the corresponding accuracy of each candidate correction information, and the selection rule is adjusted according to the accuracy, so that the probability of selecting the candidate correction information with high accuracy is increased, and the correction effect is improved.
S105: and (5) presetting operation.
When the target audio data is correct, a preset operation may be performed. The present embodiment does not limit the specific content of the preset operation, and for example, the preset operation may be an operation of updating a title, or an operation of retrieving audio data corresponding to a title, or no operation may be performed, that is, no operation is performed.
By applying the error feedback method provided by the embodiment of the invention, the target audio data in the audio data is determined after the corresponding audio data is acquired, the target audio data corresponds to the target knowledge point, and the step of judging whether the target audio data is correct or not is equivalent to the step of detecting whether the application of the target knowledge point in the audio data is correct or not. And if the target audio data is incorrect, indicating that the target audio data is incorrect, and the user incorrectly applies the target knowledge point, determining the error type of the target audio data in order to accurately correct the target audio data, and feeding back correction information according to the error type. Because the correction information is matched with the error type, the error type is the error type of the target audio data, and the audio data corresponds to the sound sent by the user, the feedback correction information can correct the specific error condition of the user, so that the user can know where the difference between the correction information and the correct pronunciation is, how to correct the difference, the pronunciation capability of the user is effectively improved, the correction effect is good, and the problem that the correction effect of the related technology on the pronunciation of the user is poor is solved.
In the following, the error feedback apparatus provided by the embodiment of the present invention is introduced, and the error feedback apparatus described below and the error feedback method described above may be referred to correspondingly.
Referring to fig. 2, fig. 2 is a schematic structural diagram of an error feedback apparatus according to an embodiment of the present invention, including:
an obtaining module 110, configured to obtain audio data corresponding to a title;
a target audio determining module 120, configured to determine, in the audio data, target audio data corresponding to a target knowledge point in the title;
a judging module 130, configured to judge whether the target audio data is correct;
and a correction information feedback module 140, configured to determine an error type of the target audio data if the target audio data is incorrect, and feed back correction information according to the error type.
Optionally, the method further comprises:
the state updating module is used for updating the state data corresponding to the title;
the condition judging module is used for judging whether the state data meet the preset triggering condition or not;
correspondingly, the correction information feedback module 140 is a module that determines the error type of the target audio data and feeds back the correction information according to the error type if the preset trigger condition is met.
Optionally, the method further comprises:
the setting instruction acquisition module is used for acquiring a triggering condition setting instruction;
and the preset trigger condition setting module is used for setting the preset trigger condition according to the trigger condition setting instruction.
Optionally, the correction information feedback module 140 includes:
the acquisition unit is used for acquiring at least one typical error audio data corresponding to the target knowledge point;
the matching unit is used for matching the target audio data with at least one typical error audio data and judging whether the target typical error audio data which is successfully matched exists or not;
the first determining unit is used for determining the error type as a target typical error type corresponding to the target typical error audio data if the target typical error audio data exists;
and the second determining unit is used for determining the error type as a general error type corresponding to the title if the target typical error audio data does not exist.
Optionally, the determining module 130 includes:
the similarity obtaining unit is used for obtaining the similarity between the target audio data and at least one standard audio data corresponding to the target knowledge point;
the first correctness determining unit is used for determining that the target audio data are correct when the similarity is greater than the similarity threshold;
a first incorrect determination unit configured to determine that the target audio data is incorrect when the similarity is smaller than a similarity threshold;
and/or the presence of a gas in the gas,
the score value acquisition unit is used for scoring the target audio data to obtain a score value;
a second correctness determining unit for determining that the target audio data is correct when the score value is greater than the score threshold value;
a second incorrect determination unit that determines that the target audio data is incorrect when the score value is less than the score threshold value.
Optionally, the correction information feedback module 140 includes:
a candidate determination unit configured to determine a plurality of candidate correction information according to the error type;
and the selecting unit is used for determining correction information from the candidate correction information according to a selecting rule and outputting the correction information.
Optionally, the method further comprises:
the reacquisition module is used for reacquiring the audio data corresponding to the title;
the accuracy rate counting module is used for counting each accuracy rate corresponding to each candidate correction information; wherein each accuracy rate is the accuracy rate of the audio data obtained again after each candidate correction information is fed back as the correction information;
and the rule adjusting module is used for adjusting the selection rule according to the accuracy.
In the following, the error feedback device provided by the embodiment of the present invention is introduced, and the error feedback device described below and the error feedback method described above may be referred to correspondingly.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an error feedback device according to an embodiment of the present invention. Wherein the error feedback device 100 may include a processor 101 and a memory 102, and may further include one or more of a multimedia component 103, an information input/information output (I/O) interface 104, and a communication component 105.
Wherein, the processor 101 is configured to control the overall operation of the error feedback apparatus 100 to complete all or part of the steps in the error feedback method; the memory 102 is used to store various types of data to support operation at the error feedback device 100, which may include, for example, instructions for any application or method operating on the error feedback device 100, as well as application-related data. The Memory 102 may be implemented by any type or combination of volatile and non-volatile Memory devices, such as one or more of Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic or optical disk.
The multimedia component 103 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 102 or transmitted through the communication component 105. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 104 provides an interface between the processor 101 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 105 is used for wired or wireless communication between the error feedback device 100 and other devices. Wireless Communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so that the corresponding Communication component 105 may include: Wi-Fi part, Bluetooth part, NFC part.
The error feedback Device 100 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components, and is configured to perform the error feedback method according to the above embodiments.
In the following, the computer-readable storage medium provided by the embodiment of the present invention is introduced, and the computer-readable storage medium described below and the error feedback method described above may be referred to correspondingly.
The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when being executed by a processor, implements the steps of the error feedback method described above.
The computer-readable storage medium may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it should also be noted that, herein, relationships such as first and second, etc., are intended only to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms include, or any other variation is intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The error feedback method, the error feedback device, the error feedback apparatus and the computer readable storage medium provided by the present invention are described in detail above, and a specific example is applied in this document to illustrate the principle and the implementation of the present invention, and the description of the above embodiment is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. An error feedback method, comprising:
acquiring audio data corresponding to the title;
determining target audio data corresponding to the target knowledge point in the title in the audio data;
judging whether the target audio data is correct or not;
and if the target audio data is incorrect, determining the error type of the target audio data, and feeding back correction information according to the error type.
2. The error feedback method according to claim 1, wherein after determining that the target audio data is incorrect, before determining the type of error of the target audio data, further comprising:
updating the state data corresponding to the title;
judging whether the state data meet a preset trigger condition or not;
and if the preset trigger condition is met, executing the step of determining the error type of the target audio data and feeding back correction information according to the error type.
3. The error feedback method of claim 2, further comprising:
acquiring a trigger condition setting instruction;
and setting the preset trigger condition according to the trigger condition setting instruction.
4. The error feedback method of claim 1, wherein determining the type of error of the target audio data comprises:
acquiring at least one typical error audio data corresponding to the target knowledge point;
matching the target audio data with at least one typical error audio data, and judging whether the target typical error audio data successfully matched exists;
if the target typical error audio data exists, determining the error type as a target typical error type corresponding to the target typical error audio data;
and if the target typical error audio data does not exist, determining the error type as a general error type corresponding to the title.
5. The error feedback method of claim 1, wherein the determining whether the target audio data is correct comprises:
acquiring the similarity between the target audio data and at least one standard audio data corresponding to the target knowledge point;
when the similarity is larger than a similarity threshold value, determining that the target audio data is correct;
when the similarity is less than a similarity threshold, determining that the target audio data is incorrect;
and/or the presence of a gas in the gas,
scoring the target audio data to obtain a score value;
determining that the target audio data is correct when the score value is greater than a score threshold;
determining that the target audio data is incorrect when the score value is less than a score threshold.
6. The error feedback method according to claim 1, wherein the feeding back the correction information according to the error type comprises:
determining a plurality of candidate correction information according to the error type;
and determining the correction information from a plurality of candidate correction information according to a selection rule, and outputting the correction information.
7. The error feedback method according to claim 6, further comprising, after feeding back correction information according to the error type:
re-acquiring the audio data corresponding to the title;
counting each accuracy rate corresponding to each candidate correction information; wherein each of the accuracy rates is an accuracy rate of the audio data obtained again after each of the candidate correction information is fed back as the correction information;
and adjusting the selection rule according to the accuracy.
8. An error feedback apparatus, comprising:
the acquisition module is used for acquiring audio data corresponding to the title;
the target audio determining module is used for determining target audio data corresponding to the target knowledge point in the title in the audio data;
the judging module is used for judging whether the target audio data is correct or not;
and the correction information feedback module is used for determining the error type of the target audio data if the target audio data is incorrect and feeding back correction information according to the error type.
9. An error feedback device comprising a memory and a processor, wherein:
the memory is used for storing a computer program;
the processor for executing the computer program to implement the error feedback method of any one of claims 1 to 7.
10. A computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the error feedback method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010663079.1A CN113920803B (en) | 2020-07-10 | Error feedback method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010663079.1A CN113920803B (en) | 2020-07-10 | Error feedback method, device, equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113920803A true CN113920803A (en) | 2022-01-11 |
| CN113920803B CN113920803B (en) | 2024-05-10 |
Family
ID=
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1197525A (en) * | 1996-07-11 | 1998-10-28 | 数字语音(以色列)有限公司 | Appts. for interactive language training |
| WO2002050798A2 (en) * | 2000-12-18 | 2002-06-27 | Digispeech Marketing Ltd. | Spoken language teaching system based on language unit segmentation |
| CN109410664A (en) * | 2018-12-12 | 2019-03-01 | 广东小天才科技有限公司 | A kind of pronunciation correction method and electronic equipment |
| CN109461436A (en) * | 2018-10-23 | 2019-03-12 | 广东小天才科技有限公司 | A kind of correcting method and system of speech recognition pronunciation mistake |
| CN110097874A (en) * | 2019-05-16 | 2019-08-06 | 上海流利说信息技术有限公司 | A kind of pronunciation correction method, apparatus, equipment and storage medium |
| CN110718210A (en) * | 2019-09-25 | 2020-01-21 | 北京字节跳动网络技术有限公司 | English mispronunciation recognition method, device, medium and electronic equipment |
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1197525A (en) * | 1996-07-11 | 1998-10-28 | 数字语音(以色列)有限公司 | Appts. for interactive language training |
| WO2002050798A2 (en) * | 2000-12-18 | 2002-06-27 | Digispeech Marketing Ltd. | Spoken language teaching system based on language unit segmentation |
| CN109461436A (en) * | 2018-10-23 | 2019-03-12 | 广东小天才科技有限公司 | A kind of correcting method and system of speech recognition pronunciation mistake |
| CN109410664A (en) * | 2018-12-12 | 2019-03-01 | 广东小天才科技有限公司 | A kind of pronunciation correction method and electronic equipment |
| CN110097874A (en) * | 2019-05-16 | 2019-08-06 | 上海流利说信息技术有限公司 | A kind of pronunciation correction method, apparatus, equipment and storage medium |
| CN110718210A (en) * | 2019-09-25 | 2020-01-21 | 北京字节跳动网络技术有限公司 | English mispronunciation recognition method, device, medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106098060B (en) | Method and device for error correction processing of voice | |
| CN110085261B (en) | Pronunciation correction method, device, equipment and computer readable storage medium | |
| US7277851B1 (en) | Automated creation of phonemic variations | |
| JP4574390B2 (en) | Speech recognition method | |
| US11682381B2 (en) | Acoustic model training using corrected terms | |
| CN109817201B (en) | Language learning method and device, electronic equipment and readable storage medium | |
| US20030195739A1 (en) | Grammar update system and method | |
| US20090228273A1 (en) | Handwriting-based user interface for correction of speech recognition errors | |
| US11024298B2 (en) | Methods and apparatus for speech recognition using a garbage model | |
| JP5824829B2 (en) | Speech recognition apparatus, speech recognition method, and speech recognition program | |
| US20110276329A1 (en) | Speech dialogue apparatus, dialogue control method, and dialogue control program | |
| JP2011002656A (en) | Device for detection of voice recognition result correction candidate, voice transcribing support device, method, and program | |
| US8326597B2 (en) | Translation apparatus, method, and computer program product for detecting language discrepancy | |
| CA3115974C (en) | Presentation assistance device for calling attention to words that are forbidden to speak | |
| US20060195318A1 (en) | System for correction of speech recognition results with confidence level indication | |
| US20170076626A1 (en) | System and Method for Dynamic Response to User Interaction | |
| CN109326284A (en) | The method, apparatus and storage medium of phonetic search | |
| JP2015087544A (en) | Voice recognition device and voice recognition program | |
| CN113920803B (en) | Error feedback method, device, equipment and readable storage medium | |
| CN113920803A (en) | Error feedback method, device, equipment and readable storage medium | |
| US20140207454A1 (en) | Text reproduction device, text reproduction method and computer program product | |
| JP6527000B2 (en) | Pronunciation error detection device, method and program | |
| CN110428668B (en) | Data extraction method and device, computer system and readable storage medium | |
| CN110148414B (en) | Voice utterance guiding method and device | |
| CN112307748A (en) | Method and device for processing text |
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 |