CN105374248B - A kind of methods, devices and systems for correcting pronunciation - Google Patents
A kind of methods, devices and systems for correcting pronunciation Download PDFInfo
- Publication number
- CN105374248B CN105374248B CN201510867886.4A CN201510867886A CN105374248B CN 105374248 B CN105374248 B CN 105374248B CN 201510867886 A CN201510867886 A CN 201510867886A CN 105374248 B CN105374248 B CN 105374248B
- Authority
- CN
- China
- Prior art keywords
- pronunciation
- information
- scoring
- pronunciation information
- standard
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012216 screening Methods 0.000 claims abstract description 82
- 150000001875 compounds Chemical class 0.000 claims description 90
- 238000001914 filtration Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 10
- 206010013887 Dysarthria Diseases 0.000 description 7
- 238000009825 accumulation Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000001376 precipitating effect Effects 0.000 description 4
- 230000006698 induction Effects 0.000 description 3
- 230000033764 rhythmic process Effects 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000005194 fractionation Methods 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- 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
Abstract
The present invention relates to a kind of methods, devices and systems for correcting pronunciation, comprising: obtains pronunciation information, is scored according to preset rules the pronunciation information according to the pronunciation information;The screening pronunciation information that the scoring is less than or equal to default point threshold value is filtered out, push point is created according to preset strategy according to the screening pronunciation information;The preset correction pronunciation information corresponding to the push point is pushed, to correct pronunciation.As it can be seen that the methods, devices and systems of the correction pronunciation, can arrange non-standard pronunciation and propose that corresponding targetedly correct is instructed, non-standard pronunciation is corrected with realizing high efficiency smart, alleviates the pressure of teacher and parent.
Description
Technical field
The present invention relates to aided education technical field more particularly to a kind of methods, devices and systems for correcting pronunciation.
Background technique
Pinyin learning is a vital content during verbal learning, and children rises small student and faces
First study difficulty.In " compulsory education Chinese curriculum standard (version in 2011) ", to a teaching of Chinese pin yin mesh
Target clear stipulaties are: " can read quasi- initial consonant, simple or compound vowel of a Chinese syllable, tone and entirety and recognize pronunciation section.Syllable can accurately be combined into syllables, it is correct to write
Initial consonant, simple or compound vowel of a Chinese syllable and syllable.Recognize capitalization, learns " Chinese phonetic alphabet table " by heart." in actual learning process, combine sound into syllables
Section is a weight difficult point of pinyin learning, and in the study stage of this heavy difficult point, students' union criminal is a variety of different to combine mistake into syllables
Accidentally, in teaching link at this stage to the main teaching method for combining error correcting into syllables still rely on teacher or parent correction and
Guidance, such teaching method the main problems are as follows: 1, the pronunciation of student, combine study into syllables to the water of teacher, parent
Flat heavy dependence, and the level of parent is especially limited;2, student to combine problem into syllables ever-changing, various, and it is more professional
The energy of teacher is limited, it is impossible to accomplish one-to-one guidance;3, it is difficult the pronunciation occurred during systematically combining into syllables to student
Problem carries out conclusion guidance.
Summary of the invention
It is an object of the invention to propose it is a kind of correct pronunciation methods, devices and systems, can to non-standard pronunciation into
Row arrange simultaneously propose it is corresponding targetedly correct guidance, non-standard pronunciation is corrected with realizing high efficiency smart, alleviate teacher and
The pressure of parent.
To achieve this purpose, the present invention adopts the following technical scheme:
In a first aspect, providing a kind of method for correcting pronunciation, comprising:
Pronunciation information is obtained, is scored according to preset rules the pronunciation information according to the pronunciation information;
The screening pronunciation information that the scoring is less than or equal to default point threshold value is filtered out, is pressed according to the screening pronunciation information
Push point is created according to preset strategy;
The preset correction pronunciation information corresponding to the push point is pushed, to correct pronunciation.
Wherein, the pronunciation information is pinyin pronunciation of information, and the pinyin pronunciation of information includes initial consonant pronunciation information, simple or compound vowel of a Chinese syllable
Pronunciation information and tone pronunciation information;
It is described to be scored according to preset rules the pronunciation information according to the pronunciation information, comprising:
The corresponding pinyin pronunciation of information of each Chinese character is compared with standard phonetic pronunciation corresponding in presetting database
It is right, to obtain the scoring of the pinyin pronunciation of information;
The corresponding pinyin pronunciation of information of each Chinese character is divided into initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information and tone pronunciation
Information, and being compared respectively with presetting database, to obtain the scoring of the initial consonant pronunciation information, the simple or compound vowel of a Chinese syllable pronunciation information
Scoring and the tone pronunciation information scoring;
The presetting database includes one-to-one Chinese character and standard phonetic pronunciation, each standard phonetic pronunciation packet
Include standard initial consonant pronunciation, standard simple or compound vowel of a Chinese syllable pronunciation and concert pitch pronunciation.
Wherein, described to read the corresponding pinyin pronunciation of information of each Chinese character with standard phonetic corresponding in presetting database
Sound is compared, to obtain the scoring of the pinyin pronunciation of information, comprising:
The corresponding pinyin pronunciation of information of each Chinese character is compared with standard phonetic pronunciation corresponding in presetting database
It is right, according to the similarity of the pinyin pronunciation of information and the standard phonetic pronunciation, obtain the scoring of the pinyin pronunciation of information;
It is described that the corresponding pinyin pronunciation of information of each Chinese character is divided into initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information and tone
Pronunciation information, and being compared respectively with presetting database, to obtain the scoring of the initial consonant pronunciation information, the simple or compound vowel of a Chinese syllable pronunciation
The scoring of information and the scoring of the tone pronunciation information, comprising:
The initial consonant pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character is corresponding with presetting database
Standard initial consonant pronunciation is compared, according to the similarity of the initial consonant pronunciation information and the standard initial consonant pronunciation, described in acquisition
The scoring of initial consonant pronunciation information;
The simple or compound vowel of a Chinese syllable pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character is corresponding with presetting database
Standard simple or compound vowel of a Chinese syllable pronunciation is compared, according to the similarity of the simple or compound vowel of a Chinese syllable pronunciation information and the standard simple or compound vowel of a Chinese syllable pronunciation, described in acquisition
The scoring of simple or compound vowel of a Chinese syllable pronunciation information;
The tone pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character is corresponding with presetting database
Concert pitch pronunciation is compared, according to the similarity of the tone pronunciation information and the concert pitch pronunciation, described in acquisition
The scoring of tone pronunciation information.
Wherein, the screening pronunciation information for filtering out the scoring and being less than or equal to default point threshold value, according to the screening
Pronunciation information creates push point according to preset strategy, comprising:
The screening pronunciation information that the scoring is less than or equal to default point threshold value is filtered out, the scoring includes that the phonetic is read
Scoring, the scoring of the initial consonant pronunciation information, the scoring of the simple or compound vowel of a Chinese syllable pronunciation information and the tone pronunciation information of message breath
Scoring;The screening pronunciation information includes screening pinyin pronunciation of information, screening initial consonant pronunciation information, screening simple or compound vowel of a Chinese syllable pronunciation information
With screening tone pronunciation information;
The screening pronunciation information is matched with presetting database, when the screening pronunciation information and presetting database
In the similarity of any standard pronunciation be more than or equal to default similarity threshold, then establish and store the screening pronunciation information and
The corresponding relationship of any standard pronunciation;
In predetermined period, add up the storage number of the identical corresponding relationship, when accumulated result is more than default accumulative
Threshold value then creates push point.
Wherein, the preset correction pronunciation information corresponding to the push point of the push, comprising:
Display push key is in screen, when the push key receives triggering command, then plays preset corresponding to institute
State the correction pronunciation information of push point;
The pronunciation information of correcting includes the screening pronunciation information and any standard corresponding to the push point
Pronunciation.
Second aspect provides a kind of device for correcting pronunciation, comprising:
Score unit, for obtaining pronunciation information, according to the pronunciation information according to preset rules to the pronunciation information
It scores;
Creating unit, the screening pronunciation information for being less than or equal to default point threshold value for filtering out the scoring, according to described
It screens pronunciation information and creates push point according to preset strategy;
Push unit, for pushing the preset correction pronunciation information corresponding to the push point, to correct pronunciation.
Wherein, the pronunciation information is pinyin pronunciation of information, and the pinyin pronunciation of information includes initial consonant pronunciation information, simple or compound vowel of a Chinese syllable
Pronunciation information and tone pronunciation information;
It is described to be scored according to preset rules the pronunciation information according to the pronunciation information, comprising:
The corresponding pinyin pronunciation of information of each Chinese character is compared with standard phonetic pronunciation corresponding in presetting database
It is right, to obtain the scoring of the pinyin pronunciation of information;
The corresponding pinyin pronunciation of information of each Chinese character is divided into initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information and tone pronunciation
Information, and being compared respectively with presetting database, to obtain the scoring of the initial consonant pronunciation information, the simple or compound vowel of a Chinese syllable pronunciation information
Scoring and the tone pronunciation information scoring;
The presetting database includes one-to-one Chinese character and standard phonetic pronunciation, each standard phonetic pronunciation packet
Include standard initial consonant pronunciation, standard simple or compound vowel of a Chinese syllable pronunciation and concert pitch pronunciation.
Wherein, described to read the corresponding pinyin pronunciation of information of each Chinese character with standard phonetic corresponding in presetting database
Sound is compared, to obtain the scoring of the pinyin pronunciation of information, comprising:
The corresponding pinyin pronunciation of information of each Chinese character is compared with standard phonetic pronunciation corresponding in presetting database
It is right, according to the similarity of the pinyin pronunciation of information and the standard phonetic pronunciation, obtain the scoring of the pinyin pronunciation of information;
It is described that the corresponding pinyin pronunciation of information of each Chinese character is divided into initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information and tone
Pronunciation information, and being compared respectively with presetting database, to obtain the scoring of the initial consonant pronunciation information, the simple or compound vowel of a Chinese syllable pronunciation
The scoring of information and the scoring of the tone pronunciation information, comprising:
The initial consonant pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character is corresponding with presetting database
Standard initial consonant pronunciation is compared, according to the similarity of the initial consonant pronunciation information and the standard initial consonant pronunciation, described in acquisition
The scoring of initial consonant pronunciation information;
The simple or compound vowel of a Chinese syllable pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character is corresponding with presetting database
Standard simple or compound vowel of a Chinese syllable pronunciation is compared, according to the similarity of the simple or compound vowel of a Chinese syllable pronunciation information and the standard simple or compound vowel of a Chinese syllable pronunciation, described in acquisition
The scoring of simple or compound vowel of a Chinese syllable pronunciation information;
The tone pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character is corresponding with presetting database
Concert pitch pronunciation is compared, according to the similarity of the tone pronunciation information and the concert pitch pronunciation, described in acquisition
The scoring of tone pronunciation information.
Wherein, the creating unit, is specifically used for:
The screening pronunciation information that the scoring is less than or equal to default point threshold value is filtered out, the scoring includes that the phonetic is read
Scoring, the scoring of the initial consonant pronunciation information, the scoring of the simple or compound vowel of a Chinese syllable pronunciation information and the tone pronunciation information of message breath
Scoring;The screening pronunciation information includes screening pinyin pronunciation of information, screening initial consonant pronunciation information, screening simple or compound vowel of a Chinese syllable pronunciation information
With screening tone pronunciation information;
The screening pronunciation information is matched with presetting database, when the screening pronunciation information and presetting database
In the similarity of any standard pronunciation be more than or equal to default similarity threshold, then establish and store the screening pronunciation information and
The corresponding relationship of any standard pronunciation;
In predetermined period, add up the storage number of the identical corresponding relationship, when accumulated result is more than default accumulative
Threshold value then creates push point.
Wherein, the preset correction pronunciation information corresponding to the push point of the push, comprising:
Display push key is in screen, when the push key receives triggering command, then plays preset corresponding to institute
State the correction pronunciation information of push point;
The pronunciation information of correcting includes the screening pronunciation information and any standard corresponding to the push point
Pronunciation.
The third aspect provides a kind of system for correcting pronunciation, and client and system end including establishing network connection are described
System end includes the device of the correction pronunciation as described in second aspect;
The client is sent to the system by network connection for receiving pronunciation information, and by the pronunciation information
System end;
The system end for receiving the pronunciation information by network connection, and is entangled according to the pronunciation information acquisition
The correction pronunciation information is sent to the client by network connection, so as to the client terminal playing by positive pronunciation information.
The beneficial effects of the present invention are: a kind of methods, devices and systems for correcting pronunciation, comprising: pronunciation information is obtained,
It is scored according to preset rules the pronunciation information according to the pronunciation information;The scoring is filtered out to be less than or equal to preset
The screening pronunciation information for dividing threshold value creates push point according to preset strategy according to the screening pronunciation information;It is preset right to push
Correction pronunciation information a little is pushed described in Ying Yu, to correct pronunciation.As it can be seen that the methods, devices and systems of the correction pronunciation, it can
Non-standard pronunciation is arranged and proposes that corresponding targetedly correct is instructed, non-standard pronunciation entangles with realizing high efficiency smart
Just, alleviate the pressure of teacher and parent.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, institute in being described below to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also implement according to the present invention
The content of example and these attached drawings obtain other attached drawings.
Fig. 1 is the method flow diagram of method one embodiment provided by the invention for correcting pronunciation.
Fig. 2 is the method flow diagram of method second embodiment provided by the invention for correcting pronunciation.
Fig. 3 is the structural block diagram of device one embodiment provided by the invention for correcting pronunciation.
Fig. 4 is the structural block diagram of system one embodiment provided by the invention for correcting pronunciation.
Fig. 5 is the method flow diagram of system one embodiment provided by the invention for correcting pronunciation.
Specific embodiment
To keep the technical problems solved, the adopted technical scheme and the technical effect achieved by the invention clearer, below
It will the technical scheme of the embodiment of the invention will be described in further detail in conjunction with attached drawing, it is clear that described embodiment is only
It is a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those skilled in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall within the protection scope of the present invention.
Embodiment one:
Referring to FIG. 1, it is the method flow diagram of method one embodiment provided by the invention for correcting pronunciation.This hair
The method for the correction pronunciation that bright embodiment provides, can be applied to all kinds of electronic equipments for having phonetic function, such as learning machine, intelligence
Mobile phone, smartwatch etc. also can be applied to the server that network connection is established with all kinds of electronic equipments for having phonetic function.
The method of the correction pronunciation, comprising:
Step S101, pronunciation information is obtained, the pronunciation information is carried out according to preset rules according to the pronunciation information
Scoring.
Under normal circumstances, pronunciation information is acquired using microphone.Microphone is called microphone, is by voice signal
Be converted to the energy conversion device of electric signal.
It should be noted that those skilled in the art can according to common knowledge, under the technical background of the technical program,
Select different preset rules (as being configured according to the accuracy of pronunciation information, overall loudness, continuity, clarity
Preset rules) it scores the pronunciation information, no longer citing repeats herein.
Step S102, the screening pronunciation information that the scoring is less than or equal to default point threshold value is filtered out, according to the screening
Pronunciation information creates push point according to preset strategy.
In general, it is not up to standard to be less than or equal to the i.e. corresponding pronunciation of the default screening pronunciation information for dividing threshold value for the scoring
Pronunciation information, the non-standard pronunciation information in this part, i.e., wrong sound are exactly needed using the method provided by the invention for correcting pronunciation
The pronunciation information corrected.
Step S103, the preset correction pronunciation information corresponding to the push point is pushed, to correct pronunciation.
Certainly, pronunciation information is corrected other than including the standard pronunciation information corresponding to screening pronunciation information, it can be with
Including corresponding standard group word pronunciation information or standard example sentence pronunciation information, further to help student to combine semantic, context more
Good study pronunciation.
The method provided in an embodiment of the present invention for correcting pronunciation can arrange non-standard pronunciation and be proposed corresponding
Guidance is targetedly corrected, non-standard pronunciation is corrected with realizing high efficiency smart, alleviates the pressure of teacher and parent, practicability
By force, easy to use.
Embodiment two:
Referring to FIG. 2, it is the method flow diagram of method second embodiment provided by the invention for correcting pronunciation.This hair
Bright embodiment is on the basis of correcting method one embodiment of pronunciation, to the scoring of pronunciation information, creation push point and push
The process for correcting pronunciation information is illustrated respectively.
The method of the correction pronunciation, comprising:
Step S201, pronunciation information is obtained, the pronunciation information is pinyin pronunciation of information, and the pinyin pronunciation of information includes
Initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information and tone pronunciation information.
In standard Chinese, the pronunciation of a Chinese character is exactly a phonetic, is also pinyin syllable or syllable.Such as " I
It is exactly three Chinese characters that book ", which is write down, and reading is exactly three syllable w ǒ, de, sh ū.The syllable of Chinese includes initial consonant, simple or compound vowel of a Chinese syllable and sound
Adjust three parts.Initial consonant, the consonant being used in front of simple or compound vowel of a Chinese syllable constitute a complete syllable with simple or compound vowel of a Chinese syllable together.Simple or compound vowel of a Chinese syllable is common
The assembly of phoneme or phoneme in speech section behind initial consonant other than tone.Tone is a syllable in pronunciation height,
Low, ascending, descending is also called word tune.Tone is indispensable part in syllable structure, has the function of distinguishing syllable.
So pinyin pronunciation of information is divided into initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information and tone pronunciation information, Ke Yifang
Just the pinyin pronunciation of information superiority and inferiority of user is quantified, more accurately finds out non-standard pinyin pronunciation of information the problem of institute
Targetedly to carry out the correction of pinyin pronunciation of information.
Step S202, the corresponding pinyin pronunciation of information of each Chinese character is read with standard phonetic corresponding in presetting database
Sound is compared, to obtain the scoring of the pinyin pronunciation of information.
Step S203, the corresponding pinyin pronunciation of information of each Chinese character is divided into initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information
It with tone pronunciation information, and is compared respectively with presetting database, to obtain the scoring of the initial consonant pronunciation information, the rhythm
The scoring of female pronunciation information and the scoring of the tone pronunciation information.
Wherein, the presetting database includes one-to-one Chinese character and standard phonetic pronunciation, each standard phonetic
Pronunciation includes standard initial consonant pronunciation, standard simple or compound vowel of a Chinese syllable pronunciation and concert pitch pronunciation.
Preferably, described by the corresponding pinyin pronunciation of information of each Chinese character and standard phonetic corresponding in presetting database
Pronunciation is compared, to obtain the scoring of the pinyin pronunciation of information, comprising:
The corresponding pinyin pronunciation of information of each Chinese character is compared with standard phonetic pronunciation corresponding in presetting database
It is right, according to the similarity of the pinyin pronunciation of information and the standard phonetic pronunciation, obtain the scoring of the pinyin pronunciation of information;
It is described that the corresponding pinyin pronunciation of information of each Chinese character is divided into initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information and tone
Pronunciation information, and being compared respectively with presetting database, to obtain the scoring of the initial consonant pronunciation information, the simple or compound vowel of a Chinese syllable pronunciation
The scoring of information and the scoring of the tone pronunciation information, comprising:
The initial consonant pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character is corresponding with presetting database
Standard initial consonant pronunciation is compared, according to the similarity of the initial consonant pronunciation information and the standard initial consonant pronunciation, described in acquisition
The scoring of initial consonant pronunciation information;
The simple or compound vowel of a Chinese syllable pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character is corresponding with presetting database
Standard simple or compound vowel of a Chinese syllable pronunciation is compared, according to the similarity of the simple or compound vowel of a Chinese syllable pronunciation information and the standard simple or compound vowel of a Chinese syllable pronunciation, described in acquisition
The scoring of simple or compound vowel of a Chinese syllable pronunciation information;
The tone pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character is corresponding with presetting database
Concert pitch pronunciation is compared, according to the similarity of the tone pronunciation information and the concert pitch pronunciation, described in acquisition
The scoring of tone pronunciation information.
Preferably, pinyin pronunciation of information is compared with standard pronunciation corresponding in presetting database, according to similarity
It scores, specifically:
Pronunciation information is compared with standard pronunciation corresponding in presetting database, if similarity is 90%, the reading
The scoring of message breath is 90;
Pronunciation information is compared with standard pronunciation corresponding in presetting database, if similarity is 85%, the reading
The scoring of message breath is 85;
Pronunciation information is compared with standard pronunciation corresponding in presetting database, if similarity is 80%, the reading
The scoring of message breath is 80;
And so on, to the pinyin pronunciation of information, the initial consonant pronunciation information, the simple or compound vowel of a Chinese syllable pronunciation information and the sound
Pronunciation information is adjusted to score.
Certainly, those skilled in the art can select other under the technical background of the technical program according to common knowledge
Similarity score method score, herein no longer citing repeat.
Step S204, the screening pronunciation information that the scoring is less than or equal to default point threshold value is filtered out, the scoring includes
The scoring of the pinyin pronunciation of information, the scoring of the initial consonant pronunciation information, the scoring of the simple or compound vowel of a Chinese syllable pronunciation information and the sound
Adjust the scoring of pronunciation information;The screening pronunciation information includes screening pinyin pronunciation of information, screening initial consonant pronunciation information, screening rhythm
Female pronunciation information and screening tone pronunciation information.
Preferably, described preset divides threshold value to be 90,85 and 80, specifically can require be set according to the different of different user
It sets.Such as, if user is announcer, 90 are set by the default point threshold value;It, will be described default if user is general student
Point threshold value is set as 80;Divide the pronunciation information of threshold value with regard to criteria of right and wrong pronunciation information lower than described preset, that is, screen pronunciation information,
Such pronunciation information needs to be corrected using the method provided by the invention for correcting pronunciation.
Step S205, the screening pronunciation information is matched with presetting database, when the screening pronunciation information with
The similarity of any standard pronunciation in presetting database is more than or equal to default similarity threshold, then establishes and store the screening
The corresponding relationship of pronunciation information and any standard pronunciation.
When the similarity of the screening pronunciation information and any standard pronunciation in presetting database is more than or equal to default phase
Like degree threshold value, then illustrate that user should send out into the pronunciation hair of the first pronunciation information (the corresponding right pronunciation of screening pronunciation information)
At the second pronunciation information (any standard pronunciation), this is the most commonly seen situation of one kind that user mispronounces.
Step S206, in predetermined period, add up the storage number of the identical corresponding relationship, when accumulated result is more than
Default accumulative threshold value, then create push point.
When accumulated result is more than default accumulative threshold value, illustrate that being directed to the pronunciation mistake of the accumulated result is that user often violates
Pronunciation mistake, then pronunciation mistake creation push point can be corresponded to, so as to the application side provided by the invention for correcting pronunciation
Method carries out the push for targetedly correcting pronunciation information.
Step S207, display push key is in screen, when the push key receives triggering command, then plays preset
Correction pronunciation information corresponding to the push point.
Wherein, the pronunciation information of correcting includes the screening pronunciation information and described any corresponding to the push point
Standard pronunciation.
Preferably, the push key receives that triggering command is corresponding to click screen operator, click screen operator relative to
The accuracy for touching screen operator is higher, can reduce maloperation probability.
The method provided by the invention for correcting pronunciation has been started and has been identified to the Chinese phonetic alphabet by modern speech identification technology
New paragon;Articulation problems during being combined into syllables by special speech recognition technology means to user carry out professional correction, real
Now really standardize specialized education;By one-to-one Tutorial, combining into syllables for user is really efficiently corrected in time
Mistake has liberated the pressure of teacher and parent;Data precipitating is carried out by the voice input multiple to user, is formed and is directed to the use
The individuation data model at family carries out classified finishing to user's problem and provides personalized guidance scheme.
The method provided in an embodiment of the present invention for correcting pronunciation is accurately identified by modern advanced speech recognition technology
User combine into syllables during articulation problems, the pronunciation mistake of user can not only be analyzed, moreover it is possible to analyze user pronunciation mistake which,
Be exactly based on for a long time to this articulation problems of user carry out accumulation precipitating and induction and conclusion, the personalization that system could be provided refer to
Scheme is led, this one-to-one effective guidance is truly realized high efficiency career and corrects the effect that phonetic combines mistake into syllables.
The following are the embodiments of the device provided by the invention for correcting pronunciation.The embodiment of the device of the correction pronunciation with it is upper
The embodiment of the method for the correction pronunciation stated belongs to same design, corrects the thin of not detailed description in the embodiment of the device of pronunciation
Content is saved, it can be with reference to the embodiment of the method for above-mentioned correction pronunciation.
Embodiment three:
Referring to FIG. 3, it is the structural block diagram of device one embodiment provided by the invention for correcting pronunciation.
The device of the correction pronunciation, comprising:
Score unit, for obtaining pronunciation information, according to the pronunciation information according to preset rules to the pronunciation information
It scores;
Creating unit, the screening pronunciation information for being less than or equal to default point threshold value for filtering out the scoring, according to described
It screens pronunciation information and creates push point according to preset strategy;
Push unit, for pushing the preset correction pronunciation information corresponding to the push point, to correct pronunciation.
The device provided in an embodiment of the present invention for correcting pronunciation can arrange non-standard pronunciation and be proposed corresponding
Guidance is targetedly corrected, non-standard pronunciation is corrected with realizing high efficiency smart, alleviates the pressure of teacher and parent, practicability
By force, easy to use.
Example IV:
It is second embodiment of the device provided in an embodiment of the present invention for correcting pronunciation below, the embodiment of the present invention provides
Correction pronunciation device second embodiment correct pronunciation device one embodiment on the basis of, to pronunciation believe
The process that pronunciation information is corrected in breath scoring, creation push point and push is illustrated respectively.
The device of the correction pronunciation characterized by comprising
Score unit, for obtaining pronunciation information, according to the pronunciation information according to preset rules to the pronunciation information
It scores;
Creating unit, the screening pronunciation information for being less than or equal to default point threshold value for filtering out the scoring, according to described
It screens pronunciation information and creates push point according to preset strategy;
Push unit, for pushing the preset correction pronunciation information corresponding to the push point, to correct pronunciation.
Wherein, the pronunciation information is pinyin pronunciation of information, and the pinyin pronunciation of information includes initial consonant pronunciation information, simple or compound vowel of a Chinese syllable
Pronunciation information and tone pronunciation information;
It is described to be scored according to preset rules the pronunciation information according to the pronunciation information, comprising:
The corresponding pinyin pronunciation of information of each Chinese character is compared with standard phonetic pronunciation corresponding in presetting database
It is right, to obtain the scoring of the pinyin pronunciation of information;
The corresponding pinyin pronunciation of information of each Chinese character is divided into initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information and tone pronunciation
Information, and being compared respectively with presetting database, to obtain the scoring of the initial consonant pronunciation information, the simple or compound vowel of a Chinese syllable pronunciation information
Scoring and the tone pronunciation information scoring;
The presetting database includes one-to-one Chinese character and standard phonetic pronunciation, each standard phonetic pronunciation packet
Include standard initial consonant pronunciation, standard simple or compound vowel of a Chinese syllable pronunciation and concert pitch pronunciation.
Wherein, described to read the corresponding pinyin pronunciation of information of each Chinese character with standard phonetic corresponding in presetting database
Sound is compared, to obtain the scoring of the pinyin pronunciation of information, comprising:
The corresponding pinyin pronunciation of information of each Chinese character is compared with standard phonetic pronunciation corresponding in presetting database
It is right, according to the similarity of the pinyin pronunciation of information and the standard phonetic pronunciation, obtain the scoring of the pinyin pronunciation of information;
It is described that the corresponding pinyin pronunciation of information of each Chinese character is divided into initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information and tone
Pronunciation information, and being compared respectively with presetting database, to obtain the scoring of the initial consonant pronunciation information, the simple or compound vowel of a Chinese syllable pronunciation
The scoring of information and the scoring of the tone pronunciation information, comprising:
The initial consonant pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character is corresponding with presetting database
Standard initial consonant pronunciation is compared, according to the similarity of the initial consonant pronunciation information and the standard initial consonant pronunciation, described in acquisition
The scoring of initial consonant pronunciation information;
The simple or compound vowel of a Chinese syllable pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character is corresponding with presetting database
Standard simple or compound vowel of a Chinese syllable pronunciation is compared, according to the similarity of the simple or compound vowel of a Chinese syllable pronunciation information and the standard simple or compound vowel of a Chinese syllable pronunciation, described in acquisition
The scoring of simple or compound vowel of a Chinese syllable pronunciation information;
The tone pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character is corresponding with presetting database
Concert pitch pronunciation is compared, according to the similarity of the tone pronunciation information and the concert pitch pronunciation, described in acquisition
The scoring of tone pronunciation information.
Wherein, the creating unit, is specifically used for:
The screening pronunciation information that the scoring is less than or equal to default point threshold value is filtered out, the scoring includes that the phonetic is read
Scoring, the scoring of the initial consonant pronunciation information, the scoring of the simple or compound vowel of a Chinese syllable pronunciation information and the tone pronunciation information of message breath
Scoring;The screening pronunciation information includes screening pinyin pronunciation of information, screening initial consonant pronunciation information, screening simple or compound vowel of a Chinese syllable pronunciation information
With screening tone pronunciation information;
The screening pronunciation information is matched with presetting database, when the screening pronunciation information and presetting database
In the similarity of any standard pronunciation be more than or equal to default similarity threshold, then establish and store the screening pronunciation information and
The corresponding relationship of any standard pronunciation;
In predetermined period, add up the storage number of the identical corresponding relationship, when accumulated result is more than default accumulative
Threshold value then creates push point.
Wherein, the preset correction pronunciation information corresponding to the push point of the push, comprising:
Display push key is in screen, when the push key receives triggering command, then plays preset corresponding to institute
State the correction pronunciation information of push point;
The pronunciation information of correcting includes the screening pronunciation information and any standard corresponding to the push point
Pronunciation.
The device provided in an embodiment of the present invention for correcting pronunciation is accurately identified by modern advanced speech recognition technology
User combine into syllables during articulation problems, the pronunciation mistake of user can not only be analyzed, moreover it is possible to analyze user pronunciation mistake which,
Be exactly based on for a long time to this articulation problems of user carry out accumulation precipitating and induction and conclusion, the personalization that system could be provided refer to
Scheme is led, this one-to-one effective guidance is truly realized high efficiency career and corrects the effect that phonetic combines mistake into syllables.
The following are the embodiments of the system provided by the invention for correcting pronunciation.The embodiment of the system of the correction pronunciation with it is upper
The embodiment of the method for the correction pronunciation stated belongs to same design, corrects the thin of not detailed description in the embodiment of the system of pronunciation
Content is saved, it can be with reference to the embodiment of the method for above-mentioned correction pronunciation.
Embodiment five:
Referring to FIG. 4, it is the structural block diagram of system one embodiment provided by the invention for correcting pronunciation.
The system of the correction pronunciation, client and system end including establishing network connection, the system end includes above-mentioned
Correction pronunciation device;
The client is sent to the system by network connection for receiving pronunciation information, and by the pronunciation information
System end;
The system end for receiving the pronunciation information by network connection, and is entangled according to the pronunciation information acquisition
The correction pronunciation information is sent to the client by network connection, so as to the client terminal playing by positive pronunciation information.
Wherein, the preferably all kinds of electronic equipments for having phonetic function of the client, such as learning machine, smart phone, intelligence
Energy wrist-watch etc..The system end is preferably that the server of network connection is established with the client.
Referring to FIG. 5, it is the method flow diagram of system one embodiment provided by the invention for correcting pronunciation.
The overall flow of the system provided by the invention for correcting pronunciation is broadly divided into six steps, is respectively as follows:
Pronunciation: user carries out reading pronunciation by the content to known text, generates pronunciation information;
Identification: system identifies the pronunciation information of user and carries out the work of unit fractionation;
Assessment: system scores to the pronunciation information of user by being compared pronunciation information with standard pronunciation;
Compare: system will be less than the pronunciation information (i.e. screening pronunciation information, or wrong pronunciation information) of default point threshold value
It is compared with remaining standard pronunciation, provides similar score, similar score height to certain standard can illustrate that the mistake of user is read
The particular content of message breath, stores the comparison result;
Sort out: intersystem problem data accumulation can be sorted out to a certain extent, sum up the reading that user often occurs
Mail topic;
Push: user will be pushed with the solution of the associated system storage of pronunciation problem, to be directed to
Property practice.
The system provided in an embodiment of the present invention for correcting pronunciation can arrange non-standard pronunciation and be proposed corresponding
Guidance is targetedly corrected, non-standard pronunciation is corrected with realizing high efficiency smart, alleviates the pressure of teacher and parent, practicability
By force, easy to use.
The system provided in an embodiment of the present invention for correcting pronunciation is accurately identified by modern advanced speech recognition technology
User combine into syllables during articulation problems, the pronunciation mistake of user can not only be analyzed, moreover it is possible to analyze user pronunciation mistake which,
Be exactly based on for a long time to this articulation problems of user carry out accumulation precipitating and induction and conclusion, the personalization that system could be provided refer to
Scheme is led, this one-to-one effective guidance is truly realized high efficiency career and corrects the effect that phonetic combines mistake into syllables.
A kind of methods, devices and systems for correcting pronunciation, can arrange non-standard pronunciation and propose have accordingly
Guidance is targetedly corrected, non-standard pronunciation is corrected with realizing high efficiency smart, alleviates the pressure of teacher and parent.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, which can store in a computer-readable storage medium
In matter, storage medium may include memory, disk or CD etc..
The above is only a preferred embodiment of the present invention, for those of ordinary skill in the art, according to the present invention
Thought, there will be changes in the specific implementation manner and application range, and the content of the present specification should not be construed as to the present invention
Limitation.
Claims (5)
1. a kind of method for correcting pronunciation characterized by comprising
Pronunciation information is obtained, is scored according to preset rules the pronunciation information according to the pronunciation information;
The screening pronunciation information that the scoring is less than or equal to default point threshold value is filtered out, according to the screening pronunciation information according to pre-
If strategy creation push point;
The preset correction pronunciation information corresponding to the push point is pushed, to correct pronunciation;
Wherein, the pronunciation information is pinyin pronunciation of information, and the pinyin pronunciation of information includes initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation
Information and tone pronunciation information;
It is described to be scored according to preset rules the pronunciation information according to the pronunciation information, comprising:
The corresponding pinyin pronunciation of information of each Chinese character is compared with standard phonetic pronunciation corresponding in presetting database, with
Obtain the scoring of the pinyin pronunciation of information;
The corresponding pinyin pronunciation of information of each Chinese character is divided into initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information and tone pronunciation letter
Breath, and is compared with presetting database respectively, to obtain the scoring of the initial consonant pronunciation information, the simple or compound vowel of a Chinese syllable pronunciation information
The scoring of scoring and the tone pronunciation information;
The presetting database includes one-to-one Chinese character and standard phonetic pronunciation, and each standard phonetic pronunciation includes mark
Quasi- initial consonant pronunciation, standard simple or compound vowel of a Chinese syllable pronunciation and concert pitch pronunciation;
Wherein, it is described by the corresponding pinyin pronunciation of information of each Chinese character and standard phonetic pronunciation corresponding in presetting database into
Row compares, to obtain the scoring of the pinyin pronunciation of information, comprising:
The corresponding pinyin pronunciation of information of each Chinese character is compared with standard phonetic pronunciation corresponding in presetting database, root
According to the similarity of the pinyin pronunciation of information and the standard phonetic pronunciation, the scoring of the pinyin pronunciation of information is obtained, specifically
Ground: if the similarity of the pinyin pronunciation of information and the standard phonetic pronunciation is A%, the scoring of the pinyin pronunciation of information
For A, wherein 0≤A≤100;
It is described that the corresponding pinyin pronunciation of information of each Chinese character is divided into initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information and tone pronunciation
Information, and being compared respectively with presetting database, to obtain the scoring of the initial consonant pronunciation information, the simple or compound vowel of a Chinese syllable pronunciation information
Scoring and the tone pronunciation information scoring, comprising:
The initial consonant pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character and standard corresponding in presetting database
Initial consonant pronunciation is compared, and according to the similarity of the initial consonant pronunciation information and the standard initial consonant pronunciation, obtains the initial consonant
The scoring of pronunciation information, specifically: if the initial consonant pronunciation information and the similarity of the standard initial consonant pronunciation are B%, institute
The scoring for stating initial consonant pronunciation information is B, wherein 0≤B≤100;
The simple or compound vowel of a Chinese syllable pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character and standard corresponding in presetting database
Simple or compound vowel of a Chinese syllable pronunciation is compared, and according to the similarity of the simple or compound vowel of a Chinese syllable pronunciation information and the standard simple or compound vowel of a Chinese syllable pronunciation, obtains the simple or compound vowel of a Chinese syllable
The scoring of pronunciation information, specifically, if the simple or compound vowel of a Chinese syllable pronunciation information and the similarity of the standard simple or compound vowel of a Chinese syllable pronunciation are C%, institute
The scoring for stating simple or compound vowel of a Chinese syllable pronunciation information is C, wherein 0≤C≤100;
The tone pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character and standard corresponding in presetting database
Tone pronunciation is compared, and according to the similarity of the tone pronunciation information and the concert pitch pronunciation, obtains the tone
The scoring of pronunciation information, specifically, if the tone pronunciation information and the similarity of the concert pitch pronunciation are D%, institute
The scoring for stating tone pronunciation information is D, wherein 0≤D≤100;
Wherein, the preset correction pronunciation information corresponding to the push point of the push, comprising:
Display push key is in screen, when the push key receives triggering command, then plays and pushes away described in preset correspond to
Send correction pronunciation information a little;
The pronunciation information of correcting includes the screening pronunciation information and any standard pronunciation corresponding to the push point;
Wherein, the preset rules include according to accuracy, overall loudness, continuity and the clarity of the pronunciation information into
The rule of row setting;
Wherein, the pronunciation information of correcting further includes the standard phrase pronunciation information or the reading of standard example sentence corresponding to the push point
Message breath.
2. it is according to claim 1 correct pronunciation method, which is characterized in that it is described filter out it is described scoring be less than or equal to
The default screening pronunciation information for dividing threshold value creates push point according to preset strategy according to the screening pronunciation information, comprising:
The screening pronunciation information that the scoring is less than or equal to default point threshold value is filtered out, the scoring includes that the phonetic pronunciation is believed
The scoring of breath, the scoring of the initial consonant pronunciation information, the scoring of the simple or compound vowel of a Chinese syllable pronunciation information and the tone pronunciation information are commented
Point;The screening pronunciation information includes screening pinyin pronunciation of information, screening initial consonant pronunciation information, screening simple or compound vowel of a Chinese syllable pronunciation information and sieve
Select tone pronunciation information;
The screening pronunciation information is matched with presetting database, when in the screening pronunciation information and presetting database
The similarity of any standard pronunciation is more than or equal to default similarity threshold, then establish and store the screening pronunciation information with it is described
The corresponding relationship of any standard pronunciation;
In predetermined period, add up the storage number of the identical corresponding relationship, when accumulated result is more than default accumulative threshold value,
Then create push point.
3. a kind of device for correcting pronunciation characterized by comprising
Scoring unit carries out the pronunciation information according to preset rules according to the pronunciation information for obtaining pronunciation information
Scoring;
Creating unit, the screening pronunciation information for being less than or equal to default point threshold value for filtering out the scoring, according to the screening
Pronunciation information creates push point according to preset strategy;
Push unit, for pushing the preset correction pronunciation information corresponding to the push point, to correct pronunciation;
Wherein, the pronunciation information is pinyin pronunciation of information, and the pinyin pronunciation of information includes initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation
Information and tone pronunciation information;
It is described to be scored according to preset rules the pronunciation information according to the pronunciation information, comprising:
The corresponding pinyin pronunciation of information of each Chinese character is compared with standard phonetic pronunciation corresponding in presetting database, with
Obtain the scoring of the pinyin pronunciation of information;
The corresponding pinyin pronunciation of information of each Chinese character is divided into initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information and tone pronunciation letter
Breath, and is compared with presetting database respectively, to obtain the scoring of the initial consonant pronunciation information, the simple or compound vowel of a Chinese syllable pronunciation information
The scoring of scoring and the tone pronunciation information;
The presetting database includes one-to-one Chinese character and standard phonetic pronunciation, and each standard phonetic pronunciation includes mark
Quasi- initial consonant pronunciation, standard simple or compound vowel of a Chinese syllable pronunciation and concert pitch pronunciation;
Wherein, it is described by the corresponding pinyin pronunciation of information of each Chinese character and standard phonetic pronunciation corresponding in presetting database into
Row compares, to obtain the scoring of the pinyin pronunciation of information, comprising:
The corresponding pinyin pronunciation of information of each Chinese character is compared with standard phonetic pronunciation corresponding in presetting database, root
According to the similarity of the pinyin pronunciation of information and the standard phonetic pronunciation, the scoring of the pinyin pronunciation of information is obtained, specifically
Ground: if the similarity of the pinyin pronunciation of information and the standard phonetic pronunciation is A%, the scoring of the pinyin pronunciation of information
For A, wherein 0≤A≤100;
It is described that the corresponding pinyin pronunciation of information of each Chinese character is divided into initial consonant pronunciation information, simple or compound vowel of a Chinese syllable pronunciation information and tone pronunciation
Information, and being compared respectively with presetting database, to obtain the scoring of the initial consonant pronunciation information, the simple or compound vowel of a Chinese syllable pronunciation information
Scoring and the tone pronunciation information scoring, comprising:
The initial consonant pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character and standard corresponding in presetting database
Initial consonant pronunciation is compared, and according to the similarity of the initial consonant pronunciation information and the standard initial consonant pronunciation, obtains the initial consonant
The scoring of pronunciation information, specifically: if the initial consonant pronunciation information and the similarity of the standard initial consonant pronunciation are B%, institute
The scoring for stating initial consonant pronunciation information is B, wherein 0≤B≤100;
The simple or compound vowel of a Chinese syllable pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character and standard corresponding in presetting database
Simple or compound vowel of a Chinese syllable pronunciation is compared, and according to the similarity of the simple or compound vowel of a Chinese syllable pronunciation information and the standard simple or compound vowel of a Chinese syllable pronunciation, obtains the simple or compound vowel of a Chinese syllable
The scoring of pronunciation information, specifically, if the simple or compound vowel of a Chinese syllable pronunciation information and the similarity of the standard simple or compound vowel of a Chinese syllable pronunciation are C%, institute
The scoring for stating simple or compound vowel of a Chinese syllable pronunciation information is C, wherein 0≤C≤100;
The tone pronunciation information for including by the corresponding pinyin pronunciation of information of each Chinese character and standard corresponding in presetting database
Tone pronunciation is compared, and according to the similarity of the tone pronunciation information and the concert pitch pronunciation, obtains the tone
The scoring of pronunciation information, specifically, if the tone pronunciation information and the similarity of the concert pitch pronunciation are D%, institute
The scoring for stating tone pronunciation information is D, wherein 0≤D≤100;
Wherein, the preset correction pronunciation information corresponding to the push point of the push, comprising:
Display push key is in screen, when the push key receives triggering command, then plays and pushes away described in preset correspond to
Send correction pronunciation information a little;
The pronunciation information of correcting includes the screening pronunciation information and any standard pronunciation corresponding to the push point;
Wherein, the preset rules include according to accuracy, overall loudness, continuity and the clarity of the pronunciation information into
The rule of row setting;
Wherein, the pronunciation information of correcting further includes the standard phrase pronunciation information or the reading of standard example sentence corresponding to the push point
Message breath.
4. the device according to claim 3 for correcting pronunciation, which is characterized in that the creating unit is specifically used for:
The screening pronunciation information that the scoring is less than or equal to default point threshold value is filtered out, the scoring includes that the phonetic pronunciation is believed
The scoring of breath, the scoring of the initial consonant pronunciation information, the scoring of the simple or compound vowel of a Chinese syllable pronunciation information and the tone pronunciation information are commented
Point;The screening pronunciation information includes screening pinyin pronunciation of information, screening initial consonant pronunciation information, screening simple or compound vowel of a Chinese syllable pronunciation information and sieve
Select tone pronunciation information;
The screening pronunciation information is matched with presetting database, when in the screening pronunciation information and presetting database
The similarity of any standard pronunciation is more than or equal to default similarity threshold, then establish and store the screening pronunciation information with it is described
The corresponding relationship of any standard pronunciation;
In predetermined period, add up the storage number of the identical corresponding relationship, when accumulated result is more than default accumulative threshold value,
Then create push point.
5. a kind of system for correcting pronunciation, which is characterized in that client and system end including establishing network connection, the system
End includes such as claim 3 or the device as claimed in claim 4 for correcting pronunciation;
The client is sent to the system end by network connection for receiving pronunciation information, and by the pronunciation information;
The system end for receiving the pronunciation information by network connection, and is corrected according to the pronunciation information acquisition and is read
The correction pronunciation information is sent to the client by network connection, so as to the client terminal playing by message breath.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510867886.4A CN105374248B (en) | 2015-11-30 | 2015-11-30 | A kind of methods, devices and systems for correcting pronunciation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510867886.4A CN105374248B (en) | 2015-11-30 | 2015-11-30 | A kind of methods, devices and systems for correcting pronunciation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105374248A CN105374248A (en) | 2016-03-02 |
CN105374248B true CN105374248B (en) | 2018-12-04 |
Family
ID=55376397
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510867886.4A Active CN105374248B (en) | 2015-11-30 | 2015-11-30 | A kind of methods, devices and systems for correcting pronunciation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105374248B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107230396A (en) * | 2017-07-21 | 2017-10-03 | 渭南师范学院 | A kind of Chinese online teaching terminal and method |
CN107274739A (en) * | 2017-08-08 | 2017-10-20 | 渭南师范学院 | Remote teaching method |
TWI660340B (en) * | 2017-11-03 | 2019-05-21 | 財團法人資訊工業策進會 | Voice controlling method and system |
CN108089836A (en) * | 2017-12-29 | 2018-05-29 | 上海与德科技有限公司 | A kind of assisted learning method and robot based on robot |
CN108364508A (en) * | 2018-02-07 | 2018-08-03 | 成都音图拼英教育科技有限公司 | A kind of English phonogram phonetic teaching method |
CN109102824B (en) * | 2018-07-06 | 2021-04-09 | 北京比特智学科技有限公司 | Voice error correction method and device based on man-machine interaction |
CN109410657A (en) * | 2018-12-29 | 2019-03-01 | 潍坊科技学院 | A kind of hand-held Mandarin Training device for Chinese teaching |
CN111081080B (en) * | 2019-05-29 | 2022-05-03 | 广东小天才科技有限公司 | Voice detection method and learning device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1442781A (en) * | 2002-03-06 | 2003-09-17 | 吴建国 | Chines language shapeless character-simulating speech sound system |
CN1614684A (en) * | 2003-11-03 | 2005-05-11 | 微星科技股份有限公司 | Voice correcting device and method |
CN101086843A (en) * | 2006-06-07 | 2007-12-12 | 中国科学院自动化研究所 | A sentence similarity recognition method for voice answer system |
CN102522012A (en) * | 2011-12-17 | 2012-06-27 | 无敌科技(西安)有限公司 | Electronic device and method for identifying language grade |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100807307B1 (en) * | 2006-07-10 | 2008-02-28 | 한국전자통신연구원 | Spoken dialog system for human computer interface and response method therein |
JP2014164261A (en) * | 2013-02-27 | 2014-09-08 | Canon Inc | Information processor and information processing method |
-
2015
- 2015-11-30 CN CN201510867886.4A patent/CN105374248B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1442781A (en) * | 2002-03-06 | 2003-09-17 | 吴建国 | Chines language shapeless character-simulating speech sound system |
CN1614684A (en) * | 2003-11-03 | 2005-05-11 | 微星科技股份有限公司 | Voice correcting device and method |
CN101086843A (en) * | 2006-06-07 | 2007-12-12 | 中国科学院自动化研究所 | A sentence similarity recognition method for voice answer system |
CN102522012A (en) * | 2011-12-17 | 2012-06-27 | 无敌科技(西安)有限公司 | Electronic device and method for identifying language grade |
Also Published As
Publication number | Publication date |
---|---|
CN105374248A (en) | 2016-03-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105374248B (en) | A kind of methods, devices and systems for correcting pronunciation | |
RU2002127826A (en) | METHOD FOR AUTOMATIC DETERMINATION OF THE LANGUAGE OF RECOGNIZABLE TEXT WITH MULTILINGUAL RECOGNITION | |
Bollmann et al. | Manual and semi-automatic normalization of historical spelling-case studies from Early New High German. | |
Fuchs | Integrating variability in loudness and duration in a multidimensional model of speech rhythm: Evidence from Indian English and British English | |
CN109461436A (en) | A kind of correcting method and system of speech recognition pronunciation mistake | |
CN106297764A (en) | A kind of multilingual mixed Chinese language treatment method and system | |
CN108108344A (en) | A kind of method and device for combining identification and connection name entity | |
CN103903615B (en) | A kind of information processing method and electronic equipment | |
Nonaka et al. | Signed names in Japanese Sign Language: Linguistic and cultural analyses | |
CN110263334A (en) | A kind of method and readable storage medium storing program for executing assisting foreign language learning | |
KR101447556B1 (en) | English Learning System | |
CN113409791A (en) | Voice recognition processing method and device, electronic equipment and storage medium | |
CN109901727A (en) | A kind of method and apparatus obtaining text error correction information | |
CN107274886A (en) | A kind of audio recognition method and device | |
CN109002454A (en) | A kind of method and electronic equipment for combining subregion into syllables of determining target word | |
CN107203539B (en) | Speech evaluating device of complex word learning machine and evaluating and continuous speech imaging method thereof | |
CN110288977B (en) | Data processing method and device and electronic equipment | |
CN113593331A (en) | Finance english taste teaching aid | |
US20190189026A1 (en) | Systems and Methods for Automatically Integrating a Machine Learning Component to Improve a Spoken Language Skill of a Speaker | |
CN112185416A (en) | AR-based word recitation method | |
Albaqawi et al. | Compiling and Analysing a Corpus of Transcribed Spoken Gulf Pidgin Arabic Based on Length of Stay in the Gulf | |
Osifeso | An Optimality Approach to Word Stress Analysis in Yoruba-English | |
CN109582971A (en) | A kind of correcting method and correct system based on syntactic analysis | |
Torres et al. | Another look at the Phonological Features of Lectal Speakers: Re-validation of the Description of the Philippine English’s Phonology | |
Tokunaga et al. | Pic2PLex: A test for assessing free productive vocabulary |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210309 Address after: 528850 16th floor, 168 Dongmen Middle Road, Xiaobian community, Chang'an Town, Dongguan City, Guangdong Province Patentee after: Dongguan elf Education Software Co.,Ltd. Address before: 523860 Second Floor, 126 Wushabugao Avenue, Chang'an Town, Dongguan City, Guangdong Province Patentee before: Guangdong Xiaotiancai Technology Co.,Ltd. |