CN109671309A - Wrong pronunciation identification method and electronic equipment - Google Patents
Wrong pronunciation identification method and electronic equipment Download PDFInfo
- Publication number
- CN109671309A CN109671309A CN201811522957.7A CN201811522957A CN109671309A CN 109671309 A CN109671309 A CN 109671309A CN 201811522957 A CN201811522957 A CN 201811522957A CN 109671309 A CN109671309 A CN 109671309A
- Authority
- CN
- China
- Prior art keywords
- pronunciation
- read aloud
- word
- article
- wrong
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000012552 review Methods 0.000 claims description 57
- 238000003860 storage Methods 0.000 claims description 18
- 238000013135 deep learning Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 4
- 230000015654 memory Effects 0.000 description 23
- 238000010586 diagram Methods 0.000 description 14
- 238000004590 computer program Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
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
- G09B5/00—Electrically-operated educational appliances
- G09B5/04—Electrically-operated educational appliances with audible presentation of the material to be studied
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to the technical field of electronic equipment, and discloses an error pronunciation identification method and electronic equipment, which comprise the following steps: when a reading instruction input by a user of the electronic equipment is detected, acquiring an article identifier to be read contained in the reading instruction, and acquiring reading voice of the user through a microphone of the electronic equipment; acquiring an article to be read corresponding to the article identifier to be read and standard pronunciation information of the article to be read, wherein the standard pronunciation information comprises the standard pronunciation of each word in the article to be read; and identifying the wrong pronunciation in the reading speech based on the standard pronunciation information. By implementing the embodiment of the invention, the electronic equipment can acquire the standard pronunciation of each character in the article, so that each wrong pronunciation of the user can be identified according to the standard pronunciation of each character, and the accuracy of identifying the wrong pronunciation is improved.
Description
Technical field
The present invention relates to technical field of electronic equipment, and in particular to a kind of mistake pronunciation recognition methods and electronic equipment.
Background technique
Student usually will appear the case where misreading the pronunciation of certain words during reading aloud article.Currently, for learning
The method that raw wrong pronunciation is corrected is usual are as follows: teacher or parent hear student during reading aloud by the pronunciation of certain words
When misreading, the right pronunciation of student's word is reminded, so that student corrects the wrong pronunciation of the word.However, it has been found in practice that by
Teacher Yu or parent cannot be guaranteed the right pronunciation for knowing all words, it is thus possible to which the mistake for occurring that student can not listened to misread is read
Sound, so that it cannot student each of is misread the case where wrong pronunciation is corrected.
Summary of the invention
The embodiment of the present invention discloses a kind of wrong pronunciation recognition methods and electronic equipment, can be improved and identifies wrong pronunciation
Accuracy.
First aspect of the embodiment of the present invention discloses a kind of wrong pronunciation recognition methods, which comprises
When detecting the bright reading instruction that the user of electronic equipment inputs, obtain include in the bright reading instruction wait read aloud
Article mark, and voice is read aloud by the microphone of electronic equipment acquisition user；
Obtain article to be read aloud corresponding with the article mark to be read aloud, and the standard of article to be read aloud described in acquisition
Pronunciation information, the standard pronunciation in the standard pronunciation information comprising described wait read aloud each word in article；
Using the standard pronunciation information as foundation, the wrong pronunciation in voice is read aloud described in identification.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is described with standard pronunciation letter
Breath is foundation, after the wrong pronunciation in voice is read aloud described in identification, the method also includes:
The first quantity of the wrong pronunciation is detected, and detects the second number of the standard pronunciation in the standard pronunciation information
Amount；
Calculate the percentage that first quantity accounts for second quantity；
When the percentage is greater than preset percentage, the article to be read aloud is determined as article to be reviewed, and by institute
Article to be reviewed is stated to store to wait review in database.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is described by the article to be read aloud
It is determined as article to be reviewed, and the article to be reviewed is stored to after wait review in database, the method also includes:
Obtain the corresponding wrong pronunciation word of the wrong pronunciation；
Interface is corrected by the display output display pronunciation of the electronic equipment, it includes institute in interface that the pronunciation, which is corrected,
State wrong pronunciation word；
When detecting that pronunciation correction interface is clicked, the target error pronunciation word being clicked is determined；
The corresponding standard pronunciation of the target error pronunciation word is exported by the loudspeaker of the electronic equipment.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is described to obtain the wrong pronunciation
After corresponding mistake pronunciation word, the method also includes:
The wrong pronunciation word is stored into wrong pronunciation library corresponding with the identity information of the user；
Wherein, the method also includes:
When detecting the review instruction of user's input, the body for the user for including from the review instruction
It obtains in the wrong pronunciation library of part information matches wait review wrong pronunciation word, and determines described wait review wrong pronunciation word pair
The standard pronunciation to be reviewed answered；
Output display is described wait review wrong pronunciation word, and the current speech of the user is obtained by the microphone；
When detect the current speech with it is described wait review received pronunciation it is identical when, by the erroneous words to be reviewed from institute
It states and is deleted in wrong pronunciation library.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is described with standard pronunciation letter
Breath is foundation, and the wrong pronunciation in voice is read aloud described in identification, comprising:
By deep learning algorithm identification described in read aloud include in voice read aloud word；
From it is described read aloud determined in voice described in read aloud that word is corresponding currently to read aloud pronunciation, and believe from the standard pronunciation
It is obtained in breath and reads aloud pronunciation with the corresponding standard of word of reading aloud；
Judge described currently to read aloud pronunciation whether with the standard to read aloud pronunciation identical；
If not, currently reading aloud pronunciation by described and being determined as wrong pronunciation.
Second aspect of the embodiment of the present invention discloses a kind of electronic equipment, comprising:
First acquisition unit, for when detecting the bright reading instruction that the user of the electronic equipment inputs, described in acquisition
Article the to be read aloud mark for including in bright reading instruction, and voice is read aloud by the microphone of electronic equipment acquisition user；
Second acquisition unit, for obtaining article to be read aloud corresponding with the article mark to be read aloud, and acquisition institute
The standard pronunciation information of article to be read aloud is stated, includes the mark wait read aloud each word in article in the standard pronunciation information
Quasi- pronunciation；
Recognition unit, for reading aloud the wrong pronunciation in voice described in identification using the standard pronunciation information as foundation.
As an alternative embodiment, in second aspect of the embodiment of the present invention, the electronic equipment further include:
Detection unit, for, using the standard pronunciation information as foundation, reading aloud voice described in identification in the recognition unit
In wrong pronunciation after, detect the first quantity of the wrong pronunciation, and detect the reading of the standard in the standard pronunciation information
Second quantity of sound；
Computing unit accounts for the percentage of second quantity for calculating first quantity；
First storage unit, for when the percentage is greater than preset percentage, the article to be read aloud to be determined as
Article to be reviewed, and the article to be reviewed is stored to wait review in database.
As an alternative embodiment, in second aspect of the embodiment of the present invention, the electronic equipment further include:
Third acquiring unit, for the article to be read aloud to be determined as article to be reviewed in first storage unit,
And store the article to be reviewed to after wait review in database, obtain the corresponding wrong pronunciation word of the wrong pronunciation；
First output unit corrects interface, the reading for the display output display pronunciation by the electronic equipment
Sound is corrected in interface comprising the wrong pronunciation word；
Determination unit, for determining that the target error being clicked is read when detecting that pronunciation correction interface is clicked
Sound word；
It is corresponding to export the target error pronunciation word for the loudspeaker by the electronic equipment for second output unit
Standard pronunciation.
As an alternative embodiment, in second aspect of the embodiment of the present invention, the electronic equipment further include:
Second storage unit, for the third acquiring unit obtain the corresponding wrong pronunciation word of the wrong pronunciation it
Afterwards, the wrong pronunciation word is stored into wrong pronunciation library corresponding with the identity information of the user；
Wherein, the electronic equipment further include:
4th acquiring unit, for when detecting the review instruction of user input, from instructing with reviews
The identity information for the user for including obtains in the matched wrong pronunciation library wait review wrong pronunciation word, and described in determination
Wait review the corresponding standard pronunciation to be reviewed of wrong pronunciation word；
Third output unit, for exporting, display is described to obtain institute wait review wrong pronunciation word, and by the microphone
State the current speech of user；
Delete unit, for when detect the current speech with it is described wait review received pronunciation it is identical when, will described in
Erroneous words are reviewed to delete from the wrong pronunciation library.
As an alternative embodiment, in second aspect of the embodiment of the present invention, the recognition unit includes:
Identify subelement, for by deep learning algorithm identification described in read aloud include in voice read aloud word；
Obtain subelement, for from it is described read aloud determined in voice described in read aloud that word is corresponding currently to read aloud pronunciation, and
It is obtained from the standard pronunciation information and reads aloud pronunciation with the corresponding standard of word of reading aloud；
Judgment sub-unit described currently read aloud pronunciation whether with the standard to read aloud pronunciation identical for judging；
It determines subelement, when the result for judging in first judgment sub-unit is no, currently reads aloud reading for described
Sound is determined as wrong pronunciation.
The third aspect of the embodiment of the present invention discloses another electronic equipment, comprising:
It is stored with the memory of executable program code；
The processor coupled with the memory；
The processor calls the executable program code stored in the memory, executes any of first aspect
A kind of some or all of method step.
Fourth aspect of the embodiment of the present invention discloses a kind of computer readable storage medium, the computer readable storage medium
Store program code, wherein said program code includes the part or complete for executing any one method of first aspect
The instruction of portion's step.
The 5th aspect of the embodiment of the present invention discloses a kind of computer program product, when the computer program product is calculating
When being run on machine, so that the computer executes some or all of any one method of first aspect step.
The aspect of the embodiment of the present invention the 6th disclose a kind of using distribution platform, and the application distribution platform is for publication calculating
Machine program product, wherein when the computer program product is run on computers, so that the computer executes first party
Some or all of any one method in face step.
Compared with prior art, the embodiment of the present invention has the advantages that
In the embodiment of the present invention, when detecting the bright reading instruction that the user of electronic equipment inputs, obtain in bright reading instruction
Article the to be read aloud mark for including, and voice is read aloud by the microphone of electronic equipment acquisition user；It obtains and text to be read aloud
Chapter identifies corresponding article to be read aloud, and obtains the standard pronunciation information of article to be read aloud, in standard pronunciation information comprising to
Read aloud the standard pronunciation of each word in article；Using standard pronunciation information as foundation, the wrong pronunciation in voice is read aloud in identification.It can
See, implements the embodiment of the present invention, the corresponding received pronunciation information of article that user reads aloud can be got, and according to the standard speech
Pronunciation when message breath identification user reads aloud this article whether standard, due to the available word each into this article of electronic equipment
Standard pronunciation, therefore the wrong pronunciation of each of user can be identified according to the standard pronunciation of each word, so that it is wrong to improve identification
Misread the accuracy of sound.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of flow diagram of wrong pronunciation recognition methods disclosed by the embodiments of the present invention；
Fig. 2 is the flow diagram of another wrong pronunciation recognition methods disclosed by the embodiments of the present invention；
Fig. 3 is the flow diagram of another wrong pronunciation recognition methods disclosed by the embodiments of the present invention；
Fig. 4 is the structural schematic diagram of a kind of electronic equipment disclosed by the embodiments of the present invention；
Fig. 5 is the structural schematic diagram of another electronic equipment disclosed by the embodiments of the present invention；
Fig. 6 is the structural schematic diagram of another electronic equipment disclosed by the embodiments of the present invention；
Fig. 7 is the structural schematic diagram of another electronic equipment disclosed by the embodiments of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that the described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.Based on this
Embodiment in invention, every other reality obtained by those of ordinary skill in the art without making creative efforts
Example is applied, shall fall within the protection scope of the present invention.
It should be noted that term " includes " and " having " and their any changes in the embodiment of the present invention and attached drawing
Shape, it is intended that cover and non-exclusive include.Such as contain the process, method of a series of steps or units, system, product or
Equipment is not limited to listed step or unit, but optionally further comprising the step of not listing or unit or optional
Ground further includes the other step or units intrinsic for these process, methods, product or equipment.
The embodiment of the present invention discloses a kind of wrong pronunciation recognition methods and electronic equipment, can be read according to the standard of each word
Sound identifies the wrong pronunciation of each of user, to improve the accuracy for identifying wrong pronunciation.It is described in detail separately below.
Embodiment one
Referring to Fig. 1, Fig. 1 is a kind of flow diagram of wrong pronunciation recognition methods disclosed by the embodiments of the present invention.Such as
Shown in Fig. 1, which be may comprise steps of:
101, when detecting the bright reading instruction that the user of electronic equipment inputs, electronic equipment, which obtains in bright reading instruction, includes
Article to be read aloud mark, and read aloud voice by what the microphone of electronic equipment obtained user.
In the embodiment of the present invention, electronic equipment can be private tutor's machine, study plate, smart phone etc., in this regard, the present invention is real
Apply example without limitation.
In the embodiment of the present invention, user can be defeated by pressing physical button corresponding with bright reading instruction or virtual key
Enter bright reading instruction, bright reading instruction can also be inputted by way of inputting the voice comprising keyword relevant to bright reading instruction,
In this regard, the embodiment of the present invention is also without limitation.
In the embodiment of the present invention, may include article to be read aloud mark in bright reading instruction, should article mark be read aloud can be with
Determine article uniquely to be read aloud.Article to be read aloud can be Chinese articles, english article etc., and the embodiment of the present invention is for bright
Read the voice of article without limitation.Electronic equipment opens the microphone of electronic equipment when detecting bright reading instruction immediately, so that
Microphone can timely obtain all voices of user's output.
As an alternative embodiment, following steps can also be performed after electronic equipment executes step 101:
Electronic equipment detects the signal-to-noise ratio for reading aloud voice；
Electronic equipment judges whether the signal-to-noise ratio is less than default lowest signal-to-noise；
If so, electronic equipment, which reads aloud voice to this, executes noise reduction operation, so that electronic equipment will read aloud making an uproar in voice
Sound is filtered, so that the signal-to-noise ratio for making to read aloud in voice is greater than default lowest signal-to-noise.
Wherein, implement this embodiment, can detecte the signal-to-noise ratio for reading aloud voice, if signal-to-noise ratio is minimum less than presetting
Signal-to-noise ratio, it is believed that the noise read aloud in voice is excessive, needs to voice progress noise reduction operation is read aloud, so as to read aloud in voice
The sound read aloud of user can be more clear, to improve the accuracy that electronic equipment identifies wrong pronunciation.
102, electronic equipment obtains article to be read aloud corresponding with article to be read aloud mark, and obtains article to be read aloud
Standard pronunciation information includes the standard pronunciation wait read aloud each word in article in the standard pronunciation information.
In the embodiment of the present invention, article to be read aloud may include multiple versions, wherein multiple versions can be different geographical
Different accents version, user can specify the corresponding version of any one accent be standard pronunciation information.
As an alternative embodiment, electronic equipment obtains article to be read aloud corresponding with article to be read aloud mark,
And it obtains the mode of the standard pronunciation information of article to be read aloud and may include following steps:
Electronic equipment obtains article to be read aloud corresponding with article to be read aloud mark；
Electronic equipment detects whether to be pre-stored with pronunciation information corresponding with article to be read aloud；
If so, the pronunciation information is determined as the standard pronunciation information of article to be read aloud by electronic equipment；
If not, electronic equipment obtains the article title of article to be read aloud, and pass through internet hunt and this article title
Corresponding standard pronunciation information.
Wherein, implement this embodiment, can detecte the standard reading for whether being stored with article to be read aloud in electronic equipment
Message breath, obtains the corresponding standard pronunciation information of article to be read aloud if not provided, can search for from internet, to ensure that
Electronic equipment can accurately obtain the corresponding standard pronunciation information of article to be read aloud.
103, for electronic equipment using standard pronunciation information as foundation, the wrong pronunciation in voice is read aloud in identification.
In the embodiment of the present invention, what electronic equipment can read aloud user reads aloud all different from standard pronunciation in voice
Pronunciation is determined as wrong pronunciation, or can more each read aloud the similarity of the corresponding standard pronunciation of voice, if phase
It seemingly spends small, it is believed that this reads aloud voice as wrong pronunciation.
In the method depicted in fig. 1, the wrong pronunciation of each of user can be identified according to the standard pronunciation of each word, from
And improve the accuracy for identifying wrong pronunciation.In addition, implementing method described in Fig. 1, improves electronic equipment identification mistake and read
The accuracy of sound.In addition, implementing method described in Fig. 1, it ensure that electronic equipment can accurately obtain article pair to be read aloud
The standard pronunciation information answered.
Embodiment two
Referring to Fig. 2, Fig. 2 is the flow diagram of another wrong pronunciation recognition methods disclosed by the embodiments of the present invention.
As shown in Fig. 2, the mistake pronunciation recognition methods may comprise steps of:
201, when detecting the bright reading instruction that the user of electronic equipment inputs, electronic equipment, which obtains in bright reading instruction, includes
Article to be read aloud mark, and read aloud voice by what the microphone of electronic equipment obtained user.
202, electronic equipment obtains article to be read aloud corresponding with article to be read aloud mark, and obtains article to be read aloud
Standard pronunciation information includes the standard pronunciation wait read aloud each word in article in standard pronunciation information.
203, for electronic equipment using standard pronunciation information as foundation, the wrong pronunciation in voice is read aloud in identification.
204, electronic equipment detects the first quantity of wrong pronunciation, and the of the standard pronunciation in examination criteria pronunciation information
Two quantity.
In the embodiment of the present invention, by including the pronunciation for needing to be read aloud each word in article in standard pronunciation information,
Therefore the second quantity of the standard pronunciation in standard pronunciation information is identical as wait read aloud the number of words for including in article；In addition, electronics
Equipment can be ranked up the wrong pronunciation recognized, so as to the mistake for identifying current sequence number as electronic equipment
First quantity of pronunciation, not only marked wrong pronunciation, but also can be with the quantity of mistake of statistics pronunciation.
205, electronic equipment calculates the percentage that the first quantity accounts for the second quantity.
In the embodiment of the present invention, due to the first quantity indicate be wrong pronunciation quantity, the second quantity indicate is mark
The quantity of quasi- pronunciation, therefore the first quantity is less than or equal to the second quantity, electronic equipment can be by the first quantity divided by the second number
Amount, percentage of available first quantity relative to the second quantity that is to say that the quantity of wrong pronunciation accounts for all standard pronunciations
Percentage.
206, when percentage is greater than preset percentage, article to be read aloud is determined as article to be reviewed by electronic equipment, and
Article to be reviewed is stored to wait review in database.
In the embodiment of the present invention, if the percentage being calculated is greater than preset percentage, it is believed that user is for this
Article to be read aloud not enough is familiar with, and needs repeatedly to review, therefore article to be read aloud can be determined as to the text to be reviewed for needing to review
Chapter, and the article to be reviewed is stored to wait review in database, should wait review can store in database it is all wait review
Article.
In the embodiment of the present invention, implement above-mentioned step 204~step 206, can detecte user and read aloud the text to be read aloud
Zhang Shi, the percentage of pronunciation error, if the percentage of pronunciation error is greater than preset percentage, it is believed that user waits for this
It reads aloud article to be unfamiliar with, needs to repeat to read aloud, so that user deepens the memory for the article to be read aloud.
207, electronic equipment obtains the corresponding wrong pronunciation word of wrong pronunciation.
208, electronic equipment corrects interface by the display output display pronunciation of electronic equipment, which corrects in interface
Include wrong pronunciation word.
In the embodiment of the present invention, the mode that pronunciation corrects interface display mistake pronunciation word can be for by wrong pronunciation word
It is all simultaneously displayed on the pronunciation to correct in interface, each wrong pronunciation of display can also be sequentially output to correct interface in pronunciation
Word.
For example, when the wrong pronunciation word of institute, which is all simultaneously displayed on the pronunciation, to be corrected in interface, electronic equipment can be with
It detects user and clicks the position that pronunciation corrects interface, and determine the corresponding target error pronunciation word in the position, and identify that user is
The no reading that has a good pronunciation by the mistake pronunciation word.It, can when pronunciation correction interface, which is sequentially output, shows each wrong pronunciation word
The target error pronunciation word of interface output display is corrected to detect current pronunciation whether to be read correctly by user, if user is correct
The standard pronunciation for having read the target error pronunciation word then can control pronunciation and correct the next wrong pronunciation of interface output display
Word.
209, when detecting that pronunciation correction interface is clicked, electronic equipment determines the target error pronunciation word being clicked.
As an alternative embodiment, electronic equipment determines that the mode for the target error pronunciation word being clicked can wrap
Include following steps:
Electronic equipment determines that the corresponding pronunciation of the click location corrects the coordinate at interface；
Electronic equipment detects the corresponding region of the coordinate；
Electronic equipment identifies the corresponding target error pronunciation word in the region.
Wherein, implement this embodiment, can detecte the seat that user clicks the pronunciation correction interface of display output
Mark, and the target error pronunciation word that user clicks is determined according to the coordinate, so that electronic equipment determines target error pronunciation word
Mode is more accurate.
210, electronic equipment exports the corresponding standard pronunciation of target error pronunciation word by the loudspeaker of electronic equipment.
In the embodiment of the present invention, implement above-mentioned step 207~step 210, can will be used after user reads aloud end
The corresponding word of wrong pronunciation that family is misread is exported to the display of electronic equipment, and exports the correct reading that user wants to know
Sound reads for itself to improve user so that user can immediately know that the word of pronunciation error after reading aloud end
Horizontal understanding.
211, electronic equipment stores wrong pronunciation word into wrong pronunciation library corresponding with the identity information of user.
In the embodiment of the present invention, user is needed in the wrong pronunciation identification function provided using electronic equipment in electronics
The account of preparatory login user in equipment can be previously stored with the identity information of user, the identity information of user in the account
It may include the information such as number, name, the pet name, age, identification card number, the telephone number of user, wherein the identity information of user
In the information such as number, telephone number and identification card number can uniquely determine the identity of user, therefore can according to
The identity information at family uniquely determine user identity, more further, electronic equipment can according to subscriber identity information obtain with
The corresponding unique wrong pronunciation library of user, so as to the wrong pronunciation of active user only be stored in the mistake pronunciation library, to protect
The safety of the privacy information of user is demonstrate,proved.
212, when detecting the review instruction of user's input, the body for the user that electronic equipment includes from review instruction
It is obtained in the wrong pronunciation library of part information matches wait review wrong pronunciation word, and determined corresponding to multiple wait review wrong pronunciation word
Habit standard pronunciation.
In the embodiment of the present invention, reviewing instruction can consider that user needs to review the wrong pronunciation misread in the past,
With detect user whether by the wrong pronunciation once misread correct.
213, electronic equipment output is shown wait review wrong pronunciation word, and the current speech of user is obtained by microphone.
214, when detecting that current speech is identical as wait review received pronunciation, electronic equipment will erroneous words be reviewed from mistake
It misreads in sound library and deletes.
In the embodiment of the present invention, implement above-mentioned step 211~step 214, wrong pronunciation word can be stored, when
When detecting that user needs to review the word of mispronunciation, it can detecte user and whether can correctly stay alone and mark pronunciation, if it can,
The mistake pronunciation word can then be deleted from wrong pronunciation library, so that user can more targetedly review wrong pronunciation
Word improves the relapse reason of user.
In the embodiment of the present invention, step 211~step 214 can be before the arbitrary steps in step 208~step 210
Or execute later, the embodiment of the present invention will not be had an impact.
In the method depicted in fig. 2, the wrong pronunciation of each of user can be identified according to the standard pronunciation of each word, from
And improve the accuracy for identifying wrong pronunciation.In addition, implement Fig. 2 described in method, can be used family deepen for this wait for it is bright
Read the memory of article.In addition, implementing method described in Fig. 2, electronic equipment can be made to determine the mode of target error pronunciation word
It is more accurate.In addition, implementing method described in Fig. 2, user is improved for horizontal understanding of itself reading.In addition, implementing
Method described in Fig. 2 can more targetedly review wrong pronunciation word, improve the relapse reason of user.
Embodiment three
Referring to Fig. 3, Fig. 3 is the flow diagram of another wrong pronunciation recognition methods disclosed by the embodiments of the present invention.
As shown in figure 3, the mistake pronunciation recognition methods may comprise steps of:
301, when detecting the bright reading instruction that the user of electronic equipment inputs, electronic equipment, which obtains in bright reading instruction, includes
Article to be read aloud mark, and read aloud voice by what the microphone of electronic equipment obtained user.
302, electronic equipment obtains article to be read aloud corresponding with article to be read aloud mark, and obtains article to be read aloud
Standard pronunciation information includes the standard pronunciation wait read aloud each word in article in standard pronunciation information.
303, electronic equipment by deep learning algorithm identification read aloud include in voice read aloud word.
In the embodiment of the present invention, reading aloud may include the reading wait read aloud each word in article that user reads aloud in voice
Sound, therefore electronic equipment can be identified by deep learning algorithm and read aloud voice, to identify each read aloud in voice from reading aloud
Word.
304, electronic equipment is determined in voice and reads aloud that word is corresponding currently to read aloud pronunciation from reading aloud, and is believed from standard pronunciation
Standard corresponding with word is read aloud is obtained in breath reads aloud pronunciation.
305, electronic equipment judgement currently reads aloud pronunciation whether with standard to read aloud pronunciation identical, if so, terminating this process；
If not, executing step 306.
306, electronic equipment is by currently reading aloud pronunciation is determined as wrong pronunciation.
In the embodiment of the present invention, implement above-mentioned step 303~step 306, can be identified by deep learning algorithm bright
Read voice in include user read aloud it is all read aloud word, and can successively identify each word currently read aloud whether pronunciation is marked
Standard currently reads aloud pronunciation if there is non-type, then this can currently be read aloud to pronunciation and be determined as wrong pronunciation, to improve
The identification accuracy of wrong pronunciation.
In the method depicted in fig. 3, the wrong pronunciation of each of user can be identified according to the standard pronunciation of each word, from
And improve the accuracy for identifying wrong pronunciation.In addition, method described in implementing Fig. 3, the identification for improving wrong pronunciation is accurate
Property.
Example IV
Referring to Fig. 4, Fig. 4 is the structural schematic diagram of a kind of electronic equipment disclosed by the embodiments of the present invention.As shown in figure 4,
The electronic equipment may include:
First acquisition unit 401, for when detecting the bright reading instruction that the user of electronic equipment inputs, finger to be read aloud in acquisition
Article the to be read aloud mark for including in order, and voice is read aloud by the microphone of electronic equipment acquisition user.
As an alternative embodiment, first acquisition unit 401 can be also used for:
Detect the signal-to-noise ratio for reading aloud voice；
Judge whether the signal-to-noise ratio is less than default lowest signal-to-noise；
If so, reading aloud voice to this executes noise reduction operation, so that electronic equipment carried out the noise read aloud in voice
Filter, so that the signal-to-noise ratio for making to read aloud in voice is greater than default lowest signal-to-noise.
Wherein, implement this embodiment, can detecte the signal-to-noise ratio for reading aloud voice, if signal-to-noise ratio is minimum less than presetting
Signal-to-noise ratio, it is believed that the noise read aloud in voice is excessive, needs to voice progress noise reduction operation is read aloud, so as to read aloud in voice
The sound read aloud of user can be more clear, to improve the accuracy that electronic equipment identifies wrong pronunciation.
Second acquisition unit 402, for obtain with first acquisition unit 401 obtain article to be read aloud mark it is corresponding to
Article is read aloud, and obtains the standard pronunciation information of article to be read aloud, comprising wait read aloud in article in the standard pronunciation information
The standard pronunciation of each word.
As an alternative embodiment, the acquisition of second acquisition unit 402 is corresponding to bright with article to be read aloud mark
Article is read, and obtains the mode of the standard pronunciation information of article to be read aloud and is specifically as follows:
Obtain article to be read aloud corresponding with article to be read aloud mark；
It detects whether to be pre-stored with pronunciation information corresponding with article to be read aloud；
If so, the pronunciation information to be determined as to the standard pronunciation information of article to be read aloud；
If not, obtaining the article title of article to be read aloud, and pass through internet hunt mark corresponding with this article title
Quasi- pronunciation information.
Wherein, implement this embodiment, can detecte the standard reading for whether being stored with article to be read aloud in electronic equipment
Message breath, obtains the corresponding standard pronunciation information of article to be read aloud if not provided, can search for from internet, to ensure that
Electronic equipment can accurately obtain the corresponding standard pronunciation information of article to be read aloud.
Recognition unit 403, as foundation, identification first obtains the standard pronunciation information for being obtained using second acquisition unit 402
The wrong pronunciation read aloud in voice for taking unit 401 to obtain.
As it can be seen that implementing electronic equipment described in Fig. 4, each mistake of user can be identified according to the standard pronunciation of each word
Sound is misread, to improve the accuracy for identifying wrong pronunciation.In addition, implementing electronic equipment described in Fig. 4, improves electronics and set
The standby accuracy for identifying wrong pronunciation.In addition, implementing electronic equipment described in Fig. 4, it ensure that electronic equipment can be accurate
Obtain the corresponding standard pronunciation information of article to be read aloud.
Embodiment five
Referring to Fig. 5, Fig. 5 is the structural schematic diagram of another electronic equipment disclosed by the embodiments of the present invention.Wherein, Fig. 5
Shown in electronic equipment be that electronic equipment as shown in Figure 4 optimizes.Compared with electronic equipment shown in Fig. 4, Fig. 5
Shown in electronic equipment can also include:
Detection unit 404, for, using standard pronunciation information as foundation, the mistake in voice to be read aloud in identification in recognition unit 403
After misreading sound, the first quantity of wrong pronunciation, and the second quantity of the standard pronunciation in examination criteria pronunciation information are detected.
Computing unit 405 accounts for the percentage of the second quantity for calculating the first quantity that detection unit 404 obtains.
First storage unit 406 will be to bright when the percentage for obtaining when computing unit 405 is greater than preset percentage
It reads article and is determined as article to be reviewed, and article to be reviewed is stored to wait review in database.
In the embodiment of the present invention, it can detecte user and read aloud this when reading aloud article, the percentage of pronunciation error, if read
The percentage of sound error is greater than preset percentage, it is believed that and user is unfamiliar with the article to be read aloud, and needs to repeat to read aloud,
So that user deepens the memory for the article to be read aloud.
As an alternative embodiment, electronic equipment shown in fig. 5 can also include:
Third acquiring unit 407, for article to be read aloud to be determined as article to be reviewed in the first storage unit 406, and
Article to be reviewed is stored to after wait review in database, the corresponding mistake of wrong pronunciation that recognition unit 403 identifies is obtained
Pronunciation word；
First output unit 408 corrects interface for the display output display pronunciation by electronic equipment, and pronunciation is corrected
The wrong pronunciation word obtained in interface comprising third acquiring unit 407；
Determination unit 409, for when detect the first output unit 408 output pronunciation correct interface be clicked when, really
Surely the target error pronunciation word being clicked；
Second output unit 410 exports the target error that determination unit 409 determines for the loudspeaker by electronic equipment
The corresponding standard pronunciation of pronunciation word.
Wherein, implement this embodiment, the wrong pronunciation that user can be misread after user reads aloud end is corresponding
Word export to the display of electronic equipment, and the right pronunciation that user wants to know is exported, so that user is reading aloud knot
The word that pronunciation error can be immediately known that after beam, to improve user for horizontal understanding of itself reading.
As an alternative embodiment, determination unit 409 determines that the mode for the target error pronunciation word being clicked has
Body can be with are as follows:
Determine that the corresponding pronunciation of the click location corrects the coordinate at interface；
Detect the corresponding region of the coordinate；
Identify the corresponding target error pronunciation word in the region.
Wherein, implement this embodiment, can detecte the seat that user clicks the pronunciation correction interface of display output
Mark, and the target error pronunciation word that user clicks is determined according to the coordinate, so that electronic equipment determines target error pronunciation word
Mode is more accurate.
As an alternative embodiment, electronic equipment shown in fig. 5 can also include:
Second storage unit 411, for third acquiring unit 407 obtain the corresponding wrong pronunciation word of wrong pronunciation it
Afterwards, wrong pronunciation word is stored into wrong pronunciation library corresponding with the identity information of user；
4th acquiring unit 412, for including from review instruction when detecting the review instruction of user's input
Obtained in the matched wrong pronunciation library of the identity information of user the storage of the second storage unit 411 wait review wrong pronunciation word, and
It determines wait review the corresponding standard pronunciation to be reviewed of wrong pronunciation word；
Third output unit 413, for export display the 4th acquiring unit 412 obtain wait review wrong pronunciation word, and
The current speech of user is obtained by microphone；
Unit 414 is deleted, for when the current speech and received pronunciation to be reviewed for detecting that third output unit 413 obtains
When identical, the erroneous words to be reviewed that the 4th acquiring unit 412 obtains are deleted from wrong pronunciation library.
Wherein, implement this embodiment, wrong pronunciation word can be stored, read when detecting that user needs to review
When the word of sound mistake, it can detecte user and whether can correctly stay alone and mark pronunciation, if it is then can be by the mistake pronunciation word
It is deleted from wrong pronunciation library, so that user can more targetedly review wrong pronunciation word, improves the review effect of user
Rate.
As it can be seen that implementing electronic equipment described in Fig. 5, each mistake of user can be identified according to the standard pronunciation of each word
Sound is misread, to improve the accuracy for identifying wrong pronunciation.In addition, implementing electronic equipment described in Fig. 5, family can be used and add
The deep memory for the article to be read aloud.In addition, implementing electronic equipment described in Fig. 5, electronic equipment can be made to determine target
The mode of mistake pronunciation word is more accurate.In addition, implementing electronic equipment described in Fig. 5, improves user and read for itself
Horizontal understanding.In addition, implementing electronic equipment described in Fig. 5, wrong pronunciation word can be more targetedly reviewed, is improved
The relapse reason of user.
Embodiment six
Referring to Fig. 6, Fig. 6 is the structural schematic diagram of another electronic equipment disclosed by the embodiments of the present invention.Wherein, Fig. 6
Shown in electronic equipment be that electronic equipment as shown in Figure 5 optimizes.Compared with electronic equipment shown in fig. 5, Fig. 6
Shown in the recognition unit 403 of electronic equipment may include:
It identifies subelement 4031, reads aloud voice for what is obtained by deep learning algorithm identification first acquisition unit 401
In include read aloud word.
Subelement 4032 is obtained, reads aloud determining identification subelement in voice for what is obtained from first acquisition unit 401
4031 identifications read aloud that word is corresponding currently to read aloud pronunciation, and from the standard pronunciation information that second acquisition unit 402 obtains
It obtains standard corresponding with word is read aloud and reads aloud pronunciation.
Judgment sub-unit 4033, for judging to obtain, subelement 4032 determined currently reads aloud whether pronunciation is read aloud with standard
Pronunciation is identical.
It determines subelement 4034, when the result for judging in the first judgment sub-unit 4033 is no, will currently read aloud reading
Sound is determined as wrong pronunciation.
In the embodiment of the present invention, read aloud that the user for including in voice reads aloud all can be identified by deep learning algorithm
Read aloud word, and can successively identify each word currently read aloud pronunciation whether standard, currently read aloud if there is non-type
This then can currently be read aloud pronunciation and be determined as wrong pronunciation, to improve the identification accuracy of wrong pronunciation by pronunciation.
As it can be seen that implementing electronic equipment described in Fig. 6, each mistake of user can be identified according to the standard pronunciation of each word
Sound is misread, to improve the accuracy for identifying wrong pronunciation.In addition, implementing electronic equipment described in Fig. 6, wrong reading is improved
The identification accuracy of sound.
Embodiment seven
Referring to Fig. 7, Fig. 7 is the structural schematic diagram of another electronic equipment disclosed by the embodiments of the present invention.Such as Fig. 7 institute
Show, which may include:
It is stored with the memory 701 of executable program code；
The processor 702 coupled with memory 701；
Wherein, processor 702 calls the executable program code stored in memory 701, executes the above each method and implements
Some or all of method in example step.
A kind of computer readable storage medium is also disclosed in the embodiment of the present invention, wherein computer-readable recording medium storage
Program code, wherein program code includes for executing some or all of the method in above each method embodiment step
Instruction.
A kind of computer program product is also disclosed in the embodiment of the present invention, wherein when computer program product on computers
When operation, so that computer executes some or all of the method in such as above each method embodiment step.
The embodiment of the present invention is also disclosed a kind of using distribution platform, wherein using distribution platform for issuing computer journey
Sequence product, wherein when computer program product is run on computers, so that computer executes such as the above each method embodiment
In some or all of method step.
It should be understood that " embodiment of the present invention " that specification is mentioned in the whole text mean special characteristic related with embodiment,
Structure or characteristic is included at least one embodiment of the present invention.Therefore, the whole instruction occur everywhere " in the present invention
In embodiment " not necessarily refer to identical embodiment.In addition, these a particular feature, structure, or characteristics can be with any suitable
Mode combines in one or more embodiments.Those skilled in the art should also know that embodiment described in this description
Alternative embodiment is belonged to, related actions and modules are not necessarily necessary for the present invention.
In various embodiments of the present invention, it should be appreciated that magnitude of the sequence numbers of the above procedures are not meant to execute suitable
Successively, the execution sequence of each process should be determined by its function and internal logic the certainty of sequence, without coping with the embodiment of the present invention
Implementation process constitutes any restriction.
In addition, the terms " system " and " network " are often used interchangeably herein.It should be understood that the terms
"and/or", only a kind of incidence relation for describing affiliated partner, indicates may exist three kinds of relationships, such as A and/or B, can
To indicate: individualism A exists simultaneously A and B, these three situations of individualism B.In addition, character "/" herein, typicallys represent
Forward-backward correlation object is a kind of relationship of "or".
In embodiment provided by the present invention, it should be appreciated that " B corresponding with A " indicates that B is associated with A, can be with according to A
Determine B.It is also to be understood that determine that B is not meant to determine B only according to A according to A, it can also be according to A and/or other information
Determine B.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium include read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), programmable read only memory (Programmable Read-only Memory, PROM), erasable programmable is read-only deposits
Reservoir (Erasable Programmable Read Only Memory, EPROM), disposable programmable read-only memory (One-
Time Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read-only memory
(Electrically-Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact
Disc Read-Only Memory, CD-ROM) or other disc memories, magnetic disk storage, magnetic tape storage or can
For carrying or any other computer-readable medium of storing data.
Above-mentioned unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, can be in one place, or may be distributed over multiple nets
On network unit.Some or all of units can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
In addition, each functional unit in various embodiments of the present invention can integrate in one processing unit, it is also possible to
Each unit physically exists alone, and can also be integrated in one unit with two or more units.Above-mentioned integrated unit
Both it can take the form of hardware realization, can also realize in the form of software functional units.
If above-mentioned integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product,
It can store in a retrievable memory of computer.Based on this understanding, technical solution of the present invention substantially or
Person says all or part of of the part that contributes to existing technology or the technical solution, can be in the form of software products
It embodies, which is stored in a memory, including several requests are with so that a computer is set
Standby (can be personal computer, server or network equipment etc., specifically can be the processor in computer equipment) executes
Some or all of each embodiment above method of the invention step.
A kind of wrong pronunciation recognition methods disclosed by the embodiments of the present invention and electronic equipment are described in detail above,
Used herein a specific example illustrates the principle and implementation of the invention, and the explanation of above embodiments is only used
In facilitating the understanding of the method and its core concept of the invention；At the same time, for those skilled in the art, according to the present invention
Thought, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not be construed as
Limitation of the present invention.
Claims (10)
1. a kind of mistake pronunciation recognition methods, which is characterized in that the described method includes:
When detecting the bright reading instruction that the user of electronic equipment inputs, the article to be read aloud for including in the bright reading instruction is obtained
Mark, and voice is read aloud by the microphone of electronic equipment acquisition user；
Obtain article to be read aloud corresponding with the article mark to be read aloud, and the standard pronunciation of article to be read aloud described in acquisition
Information, the standard pronunciation in the standard pronunciation information comprising described wait read aloud each word in article；
Using the standard pronunciation information as foundation, the wrong pronunciation in voice is read aloud described in identification.
2. the method according to claim 1, wherein described using the standard pronunciation information as foundation, identification institute
After stating the wrong pronunciation read aloud in voice, the method also includes:
The first quantity of the wrong pronunciation is detected, and detects the second quantity of the standard pronunciation in the standard pronunciation information；
Calculate the percentage that first quantity accounts for second quantity；
When the percentage is greater than preset percentage, the article to be read aloud is determined as article to be reviewed, and will it is described to
Article is reviewed to store to wait review in database.
3. according to the method described in claim 2, it is characterized in that, described be determined as text to be reviewed for the article to be read aloud
Chapter, and the article to be reviewed is stored to after wait review in database, the method also includes:
Obtain the corresponding wrong pronunciation word of the wrong pronunciation；
Interface is corrected by the display output display pronunciation of the electronic equipment, it includes the mistake in interface that the pronunciation, which is corrected,
Misread sound word；
When detecting that pronunciation correction interface is clicked, the target error pronunciation word being clicked is determined；
The corresponding standard pronunciation of the target error pronunciation word is exported by the loudspeaker of the electronic equipment.
4. according to the method described in claim 3, it is characterized in that, described obtain the corresponding wrong pronunciation word of the wrong pronunciation
Later, the method also includes:
The wrong pronunciation word is stored into wrong pronunciation library corresponding with the identity information of the user；
Wherein, the method also includes:
When detecting the review instruction of user's input, believe from the identity for reviewing the user for including in instruction
It ceases and obtains in the matched wrong pronunciation library wait review wrong pronunciation word, and determine described corresponding wait review wrong pronunciation word
Standard pronunciation to be reviewed；
Output display is described wait review wrong pronunciation word, and the current speech of the user is obtained by the microphone；
When detect the current speech with it is described wait review received pronunciation it is identical when, by the erroneous words to be reviewed from the mistake
It misreads in sound library and deletes.
5. method according to any one of claims 1 to 4, which is characterized in that it is described with the standard pronunciation information be according to
According to reading aloud the wrong pronunciation in voice described in identification, comprising:
By deep learning algorithm identification described in read aloud include in voice read aloud word；
From it is described read aloud determined in voice described in read aloud that word is corresponding currently to read aloud pronunciation, and from the standard pronunciation information
It obtains and reads aloud pronunciation with the corresponding standard of word of reading aloud；
Judge described currently to read aloud pronunciation whether with the standard to read aloud pronunciation identical；
If not, currently reading aloud pronunciation by described and being determined as wrong pronunciation.
6. a kind of electronic equipment characterized by comprising
First acquisition unit, for being read aloud described in acquisition when detecting the bright reading instruction that the user of the electronic equipment inputs
Article the to be read aloud mark for including in instruction, and voice is read aloud by the microphone of electronic equipment acquisition user；
Second acquisition unit, for obtaining article to be read aloud corresponding with the article mark to be read aloud, and described in acquisition to
The standard pronunciation information of article is read aloud, is read in the standard pronunciation information comprising the standard wait read aloud each word in article
Sound；
Recognition unit, for reading aloud the wrong pronunciation in voice described in identification using the standard pronunciation information as foundation.
7. electronic equipment according to claim 6, which is characterized in that the electronic equipment further include:
Detection unit, for, using the standard pronunciation information as foundation, being read aloud in voice described in identification in the recognition unit
After mistake pronunciation, the first quantity of the wrong pronunciation is detected, and detects standard pronunciation in the standard pronunciation information
Second quantity；
Computing unit accounts for the percentage of second quantity for calculating first quantity；
First storage unit, for when the percentage is greater than preset percentage, the article to be read aloud to be determined as to multiple
Article is practised, and the article to be reviewed is stored to wait review in database.
8. electronic equipment according to claim 7, which is characterized in that the electronic equipment further include:
Third acquiring unit, for the article to be read aloud to be determined as article to be reviewed in first storage unit, and will
The article to be reviewed is stored to after wait review in database, obtains the corresponding wrong pronunciation word of the wrong pronunciation；
First output unit corrects interface for the display output display pronunciation by the electronic equipment, and the pronunciation entangles
Include the wrong pronunciation word in positive interface；
Determination unit, for determining the target error pronunciation word being clicked when detecting that pronunciation correction interface is clicked；
Second output unit exports the corresponding standard of the target error pronunciation word for the loudspeaker by the electronic equipment
Pronunciation.
9. electronic equipment according to claim 8, which is characterized in that the electronic equipment further include:
Second storage unit is used for after the third acquiring unit obtains the corresponding wrong pronunciation word of the wrong pronunciation,
The wrong pronunciation word is stored into wrong pronunciation library corresponding with the identity information of the user；
Wherein, the electronic equipment further include:
4th acquiring unit, for including from review instruction when detecting the review instruction of user's input
The user the matched wrong pronunciation library of identity information in obtain wait review wrong pronunciation word, and determine described to multiple
Practise the corresponding standard pronunciation to be reviewed of wrong pronunciation word；
Third output unit, for exporting, display is described to obtain the use wait review wrong pronunciation word, and by the microphone
The current speech at family；
Delete unit, for when detect the current speech with it is described wait review received pronunciation it is identical when, by described wait review
Erroneous words are deleted from the wrong pronunciation library.
10. according to the described in any item electronic equipments of claim 6~9, which is characterized in that the recognition unit includes:
Identify subelement, for by deep learning algorithm identification described in read aloud include in voice read aloud word；
Obtain subelement, for from it is described read aloud determined in voice described in read aloud that word is corresponding currently to read aloud pronunciation, and from institute
It states to obtain in standard pronunciation information and reads aloud pronunciation with the corresponding standard of word of reading aloud；
Judgment sub-unit described currently read aloud pronunciation whether with the standard to read aloud pronunciation identical for judging；
Determine subelement, when the result for judging in first judgment sub-unit is no, to read aloud pronunciation true by described currently
It is set to mistake pronunciation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811522957.7A CN109671309A (en) | 2018-12-12 | 2018-12-12 | Wrong pronunciation identification method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811522957.7A CN109671309A (en) | 2018-12-12 | 2018-12-12 | Wrong pronunciation identification method and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109671309A true CN109671309A (en) | 2019-04-23 |
Family
ID=66144294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811522957.7A Pending CN109671309A (en) | 2018-12-12 | 2018-12-12 | Wrong pronunciation identification method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109671309A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110853426A (en) * | 2019-11-18 | 2020-02-28 | 永城职业学院 | English pronunciation learning evaluation system and method |
| CN111081080A (en) * | 2019-05-29 | 2020-04-28 | 广东小天才科技有限公司 | Voice detection method and learning device |
| CN112306449A (en) * | 2020-03-02 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Method and apparatus for outputting information |
| CN113268981A (en) * | 2021-05-27 | 2021-08-17 | 咪咕音乐有限公司 | Information processing method and device and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117618A (en) * | 2009-12-30 | 2011-07-06 | 华为技术有限公司 | Method, device and system for eliminating music noise |
| CN106448288A (en) * | 2016-11-01 | 2017-02-22 | 安阳师范学院 | Interactive English learning system and method |
| CN106531182A (en) * | 2016-12-16 | 2017-03-22 | 上海斐讯数据通信技术有限公司 | Language learning system |
| CN107680419A (en) * | 2017-10-09 | 2018-02-09 | 吉林工程技术师范学院 | A kind of Mandarin Training intelligent apparatus |
| CN108053839A (en) * | 2017-12-11 | 2018-05-18 | 广东小天才科技有限公司 | Language exercise result display method and microphone equipment |
| CN207676514U (en) * | 2017-10-07 | 2018-07-31 | 邵美景 | A kind of Language Teacher reads aloud corrector with mandarin |
| CN108389440A (en) * | 2018-03-15 | 2018-08-10 | 广东小天才科技有限公司 | Voice playing method and device based on microphone and voice playing equipment |
| CN108922289A (en) * | 2018-07-25 | 2018-11-30 | 深圳市异度信息产业有限公司 | A kind of scoring method, device and equipment for Oral English Practice |
-
2018
- 2018-12-12 CN CN201811522957.7A patent/CN109671309A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117618A (en) * | 2009-12-30 | 2011-07-06 | 华为技术有限公司 | Method, device and system for eliminating music noise |
| CN106448288A (en) * | 2016-11-01 | 2017-02-22 | 安阳师范学院 | Interactive English learning system and method |
| CN106531182A (en) * | 2016-12-16 | 2017-03-22 | 上海斐讯数据通信技术有限公司 | Language learning system |
| CN207676514U (en) * | 2017-10-07 | 2018-07-31 | 邵美景 | A kind of Language Teacher reads aloud corrector with mandarin |
| CN107680419A (en) * | 2017-10-09 | 2018-02-09 | 吉林工程技术师范学院 | A kind of Mandarin Training intelligent apparatus |
| CN108053839A (en) * | 2017-12-11 | 2018-05-18 | 广东小天才科技有限公司 | Language exercise result display method and microphone equipment |
| CN108389440A (en) * | 2018-03-15 | 2018-08-10 | 广东小天才科技有限公司 | Voice playing method and device based on microphone and voice playing equipment |
| CN108922289A (en) * | 2018-07-25 | 2018-11-30 | 深圳市异度信息产业有限公司 | A kind of scoring method, device and equipment for Oral English Practice |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111081080A (en) * | 2019-05-29 | 2020-04-28 | 广东小天才科技有限公司 | Voice detection method and learning device |
| CN110853426A (en) * | 2019-11-18 | 2020-02-28 | 永城职业学院 | English pronunciation learning evaluation system and method |
| CN112306449A (en) * | 2020-03-02 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Method and apparatus for outputting information |
| CN113268981A (en) * | 2021-05-27 | 2021-08-17 | 咪咕音乐有限公司 | Information processing method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109671309A (en) | Wrong pronunciation identification method and electronic equipment | |
| US10013972B2 (en) | System and method for identifying speakers | |
| CN109346059A (en) | Dialect voice recognition method and electronic equipment | |
| CN104143326B (en) | A kind of voice command identification method and device | |
| CN109410664A (en) | Pronunciation correction method and electronic equipment | |
| CN109635772A (en) | Dictation content correcting method and electronic equipment | |
| CN110085261A (en) | A kind of pronunciation correction method, apparatus, equipment and computer readable storage medium | |
| CN109271585B (en) | Information pushing method and family education equipment | |
| CN109599108A (en) | Dictation auxiliary method and dictation auxiliary device | |
| CN109637521A (en) | A kind of lip reading recognition methods and device based on deep learning | |
| CN108986564A (en) | Reading control method based on intelligent interaction and electronic equipment | |
| CN109545184A (en) | Recitation detection method based on voice calibration and electronic equipment | |
| CN108920450A (en) | Knowledge point reviewing method based on electronic equipment and electronic equipment | |
| CN106875939A (en) | To the Chinese dialects voice recognition processing method and intelligent robot of wide fluctuations | |
| CN109086455A (en) | Method for constructing voice recognition library and learning equipment | |
| CN109739354A (en) | A kind of multimedia interaction method and device based on sound | |
| CN105991290B (en) | Pseudorandom vocal print cryptogram generation method and system | |
| CN109658776A (en) | Recitation fluency detection method and electronic equipment | |
| CN103413078A (en) | Double-layer online identification system and identification method based on user's mark and handwriting | |
| CN111639218A (en) | Interactive method for spoken language training and terminal equipment | |
| CN109582780B (en) | Intelligent question and answer method and device based on user emotion | |
| CN109634422A (en) | Recitation monitoring method and learning equipment based on eye movement recognition | |
| CN109389493A (en) | Customized test question mesh input method, system and equipment based on speech recognition | |
| CN108922278A (en) | Man-machine interaction method and learning equipment | |
| CN108446277B (en) | Method and device for simulating learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190423 |