CN106406807A - A method and a device for voice correction of characters - Google Patents
A method and a device for voice correction of characters Download PDFInfo
- Publication number
- CN106406807A CN106406807A CN201610833691.2A CN201610833691A CN106406807A CN 106406807 A CN106406807 A CN 106406807A CN 201610833691 A CN201610833691 A CN 201610833691A CN 106406807 A CN106406807 A CN 106406807A
- Authority
- CN
- China
- Prior art keywords
- word
- modified
- alternative
- instruction
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012986 modification Methods 0.000 claims description 90
- 230000004048 modification Effects 0.000 claims description 90
- 238000002372 labelling Methods 0.000 claims description 22
- 238000007514 turning Methods 0.000 claims description 21
- 238000012790 confirmation Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 238000010586 diagram Methods 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000011017 operating method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- 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
- 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
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
- G06F3/0236—Character input methods using selection techniques to select from displayed items
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Acoustics & Sound (AREA)
- General Health & Medical Sciences (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention provides a method and a device for voice correction of characters. Wrong characters can be corrected via voice, so that the problem that users need to spend much time and energy to correct characters manually is solved. The method comprises the steps of receiving a voice correction instruction; identifying all characters having the pronunciation the same as the pronunciation specified by the voice correction instruction from a to-be-corrected document; determining to-be-corrected characters in all the identified characters; displaying an alternative character list corresponding to the to-be-corrected characters; receiving an alternative character selecting instruction; changing the to-be-corrected characters to alternative characters specified by the alternative character selecting instruction. The method effectively increases the character correction efficiency.
Description
Technical field
The present invention relates to technical field of voice recognition, more particularly, to a kind of method and device of speech modification word.
Background technology
With the fast development of speech recognition technology, this technology is widely used in all trades and professions at present, such as household electrical appliances, work
The fields such as industry, communication, automotive electronics are so that speech recognition technology has obtained effectively applying.At present, user can pass through voice
The voice sending is converted to word by input method, and without devoting a tremendous amount of time, energy is manually entered word again, brings to user
Substantial amounts of convenience.But, during speech recognition becomes word, identification error situation often occurs, such as user wants to input
Word be " operation ", the word that result identifies be " personal letter ", now user can only devote a tremendous amount of time, energy manual
By identification mistake word modify.
Content of the invention
The present invention provides a kind of method and device of speech modification word, completes to change work to wrong word by voice
Make, solve the problems, such as that user need to take much time and energy manual modification word, and have the characteristics that simple to operate.
The present invention provides a kind of method of speech modification word, including：
Receive speech modification instruction；
In document to be modified, all words of pronunciation identical are specified in identification and described speech modification instruction；
Determine the word to be modified in all words identifying；
Show the corresponding alternative textual list of described word to be modified；Described alternative word is same with described word to be modified
Sound；
Receive alternative word and select instruction；
Described word to be modified is revised as the alternative word that instruction selected in described alternative word.
Some beneficial effects of the embodiment of the present invention can include：
The method of the speech modification word that the present invention provides says, by speech modification instruction, the text-to-speech wanting to change,
And identify the word of unisonance in document to be modified, and word to be modified in the word identifying is quoted by voice, with
After can provide the corresponding alternative textual list of word to be modified supply user select, thus user can in alternative textual list voice
Select word to replace word to be modified.The method makes user can pass through simple phonetic order, completes to wrong word
Modification, operating procedure is simple, solves the problems, such as that user need to take much time and energy manual modification word.
In one embodiment, described identification and the specified pronunciation identical of described speech modification instruction in document to be modified
All words, also include：The word that will identify that from front to back in document to be modified carries out the first kind successively and numbers and show；
Word to be modified in all words that described determination identifies, including：
Receive the first kind numbering selected；
Number corresponding word with the described selected first kind in all words that will identify that and be defined as word to be modified.
In this embodiment, the text-to-speech information to be modified said according to user, in document to be modified, identification word is simultaneously
Word for identification is numbered, and then user can reach the purpose determining word to be modified, operate pole by saying numbering
For simple.
In one embodiment, described identification and the specified pronunciation identical of described speech modification instruction in document to be modified
All words, also include：First identified in document to be modified word is added predetermined labels；
Word to be modified in all words that described determination identifies, including：
Receive predetermined labels and confirm instruction or predetermined labels move；
If receiving predetermined labels move, with all words of identifying as tagged object, according to described pre- calibration
Moving method specified by note move moves described predetermined labels, is then returned to execute described reception predetermined labels and confirms to refer to
Order or the step of predetermined labels move；
Confirm that the word of presently described predetermined labels institute labelling is defined as literary composition to be modified by instruction according to described predetermined labels
Word.
In this embodiment, the text-to-speech information to be modified said according to user, positioning unisonance literary composition in document to be modified
Word, and first word for identifying adds predetermined labels, user can say predetermined labels move with mobile pre- calibration
Remember to word to be modified, thus reaching the purpose determining word to be modified.
In one embodiment, the corresponding alternative textual list of the described word to be modified of described display, including：
Show that described word to be modified is corresponding alternative with predetermined window in preset range near described word to be modified
Textual list.
In this embodiment, after determining word to be modified, in the vicinity of this word, unisonance is shown with a predetermined window
Alternative textual list, shows and checks conveniently.
In one embodiment, finish when described alternative textual list cannot once all show in described predetermined window
When, alternative textual list described in Pagination Display in described predetermined window, and the multiple alternative word the past to display in every page
Carry out Equations of The Second Kind numbering successively backward；
Described alternative word is selected instruction and is included：The alternative word corresponding second that voice is specified in current predetermined window
Class is numbered.
In this embodiment, after determining word to be modified, the alternative word of Pagination Display unisonance near this word
List.If there being the word that user wants in current page, user says this word corresponding Equations of The Second Kind numerical digit, then by this numeral
Corresponding alternative word replaces word to be modified, realizes modification.Numerous alternative textual list can be passed through limited predetermined window
Mouth is shown, display is convenient, word modification is simple to operate.
In one embodiment, after the corresponding alternative textual list of the described word to be modified of described display, described reception
Before alternative text-to-speech selectes instruction, also include：
Receive page-turning instruction；
The alternative textual list of display in described predetermined window is carried out page turning according to described page-turning instruction assigned direction.
In this embodiment, after determining word to be modified, the alternative word of Pagination Display unisonance near this word
List.If not having the word that user wants in the alternative word in the page that shows of current predetermined window, user is it may be said that page turning etc.
Instruction, searches alternative word in other pages.Then, user says the alternative word corresponding Equations of The Second Kind numbering of needs, then should
Number corresponding alternative word and replace word to be modified, realize modification.Therefore user has simple, side in the operation selecting alternative word
Just feature.
In one embodiment, after the word to be modified in all words that described determination identifies, described reception
Before alternative text-to-speech selectes instruction, also include：
Receive specified word；
Described word to be modified is revised as described specified word, and terminates flow process.
In this embodiment, after determining word to be modified, user can directly input the specified word needing to be modified as,
For example when the word that the alternative word shown does not have user to need, user can direct treating of choosing before replacing it of specified word
Modification word, reaches the purpose that word to be modified is modified.
The present invention also provides a kind of device of speech modification word, including：Receiver module, identification module, determining module, show
Show module, the second receiver module and modified module；
Described receiver module, instructs and is sent to described identification module for receiving speech modification, is additionally operable to receive alternatively
Word is selected and is instructed and be sent to described modified module；
Described identification module, the described speech modification instruction for, in document to be modified, identifying and receiving is specified and is read
The all words of sound identical；
Described determining module, for determining the word to be modified in all words that described identification module identifies；
Described display module, for showing the corresponding alternative textual list of word to be modified that described determining module determines；
Described alternative word and word unisonance to be modified；
Described modified module, it is described alternative that the word to be modified for determining described determining module is revised as receiving
The alternative word of instruction selected in word.
In one embodiment, described identification module, is additionally operable to the literary composition that will identify that from front to back in document to be modified
Word carries out the first kind successively and numbers and show；
Described determining module includes：First kind numbering receiving unit and determining unit；
Described first kind numbering receiving unit, for receiving selected first kind numbering；
Described determining unit, for, in all words of identifying in described identification module, described first kind numbering being connect
The described selected first kind that receipts unit receives is numbered corresponding word and is defined as word to be modified.
In one embodiment, described identification module, is additionally operable to add identify in document to be modified first word
Plus predetermined labels；
Described determining module includes：Labelling receiving unit, movement indicia unit and labelling confirmation unit；
Described labelling receiving unit, for being sent to described labelling confirmation form by the predetermined labels receiving confirmation instruction
Unit；It is additionally operable to for the predetermined labels receiving move to be sent to described movement indicia unit；
Described movement indicia unit, for all words of being identified with described identification module as tagged object, according to connecing
The moving method specified by predetermined labels move receiving moves described predetermined labels；
Described labelling confirmation unit, for confirming to instruct presently described predetermined labels institute according to the predetermined labels receiving
The word of labelling is defined as word to be modified.
In one embodiment, described display module is specifically near the word to be modified that described determining module determines
In preset range, the corresponding alternative textual list of described word to be modified is shown with predetermined window.
In one embodiment, described display module includes：
Judging unit, for judge the corresponding alternative textual list of described word to be modified in described predetermined window whether
Once can all show and finish；
Pagination Display unit, for when the judged result of described judging unit is for being, by alternative textual list with one page
It is shown in predetermined window；Or the described judged result judging list for no when, the alternative textual list of Pagination Display, and to every
In page, the multiple alternative word of display carries out Equations of The Second Kind numbering from front to back successively；
The alternative word that described receiver module receives is selected instruction and is included：The alternative word specified in current predetermined window
Corresponding Equations of The Second Kind numbering.
In one embodiment, described receiver module is additionally operable to receive page-turning instruction and be sent to described Pagination Display list
Unit；
Described Pagination Display unit, is additionally operable to the alternative textual list of display in described predetermined window according to turning over of receiving
Page instruction assigned direction carries out page turning.
In one embodiment, described receiver module is additionally operable to receive specified word and be sent to described modified module；
Described modified module, the word to be modified being additionally operable to determine described determining module is revised as the specified literary composition receiving
Word.
Other features and advantages of the present invention will illustrate in the following description, and, partly become from description
Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages can be by the explanations write
In book, claims and accompanying drawing, specifically noted structure is realizing and to obtain.
Below by drawings and Examples, technical scheme is described in further detail.
Brief description
Accompanying drawing is used for providing a further understanding of the present invention, and constitutes a part for description, the reality with the present invention
Apply example and be used for explaining the present invention together, be not construed as limiting the invention.In the accompanying drawings：
Fig. 1 is a kind of flow chart of the method for speech modification word in the embodiment of the present invention；
Fig. 2 is a kind of method flow diagram of speech modification word in the embodiment of the present invention one；
Fig. 3 is a kind of method flow diagram of speech modification word in the embodiment of the present invention two；
Fig. 4 is a kind of method flow diagram of speech modification word in the embodiment of the present invention three；
Fig. 5 is a kind of structural representation of the device of speech modification word provided in an embodiment of the present invention；
Fig. 6 is the structural representation of the device of another kind speech modification word provided in an embodiment of the present invention；
Fig. 7 is the structural representation of the device of another kind speech modification word provided in an embodiment of the present invention；
Fig. 8 is the structural representation of the device of another kind speech modification word provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are illustrated it will be appreciated that preferred reality described herein
Apply example to be merely to illustrate and explain the present invention, be not intended to limit the present invention.
Fig. 1 is a kind of flow chart of the method for speech modification word in the embodiment of the present invention.As shown in figure 1, the method bag
Include following steps S101-S106：
Step S101：Receive speech modification instruction.
During word is become due to speech recognition, there is the situation of identification mistake, when identification mistake occurs, such as know
The word of not mistake is " operation ", and user can send the voice of " choosing operation " by this step, initiates the wrong word of modification
The instruction of " operation ".
Step S102：In document to be modified, all words of pronunciation identical are specified in identification and described speech modification instruction.
Wherein, described " word " can be a word or word, and for example, user have issued in modification document to be modified and " performs the operation "
The instruction of this word, but " perform the operation " in document or pronunciation be " shoushu " word may more than one it is therefore desirable to will own
Pronunciation is that the word of " shoushu " all identifies, is easy to user and subsequently chooses that word of " performing the operation " desired to modify.
Step S103：Determine the word to be modified in all words identifying.
Wherein, when multiple specified pronunciation identical word with speech modification instruction in a document, user can be led to
Cross that voice which word clear and definite needs to change, and for example, identifies that in document to be modified pronunciation is " shoushu " from front to back
Word has successively：" operation ", " longevity number ", " operation " ... etc., user currently wants will identify that second word to be repaiied
Change, then the voice that can send " second " is defined as currently word to be modified come second word that will identify that.
Step S104：Show the corresponding alternative textual list of described word to be modified；Described alternative word is to be repaired with described
Change word unisonance.
Wherein, near this word, after have selected word to be modified, show the alternative textual list of unisonance, be easy to use
The subsequently selected alternative word in family.For example：If the word " longevity number " that second in document pronounces for " shoushu " is defined as treating
Modification word, then the word " longevity number " that in this step, second in a document pronounces for " shoushu " nearby shows alternatively literary composition
Word list：1st, perform the operation；2nd, write in one's own hand；3rd, longevity number；4th, sell book ...
Step S105：Receive alternative word and select instruction.
Wherein, user can say position in alternative textual list for the alternative word by voice, completes alternative word
The work chosen.
Step S106：Described word to be modified is revised as the alternative word that instruction selected in described alternative word.
Wherein, word to be modified replaced in the alternative word with choosing, you can completes the modification work of the word to identification mistake
Make.
The method of speech modification word provided in an embodiment of the present invention, user can pass through simple phonetic order, you can
Complete the modification to wrong word, such as：Say text-to-speech to be modified, and determine word to be modified in a document, finally
Determine that alternative word is replaced, operating procedure is simple, solve user and need to take much time and energy manual modification
The problem of word.
As a preferred embodiment, in said method, after step s 103, before step S105, may also include step：
The specified word that receive user directly inputs；Described word to be modified is revised as described specified word, and terminates flow process.Example
As：After determining word to be modified, the alternative word of unisonance will be shown in the vicinity of this word, if the alternative word shown does not have
There is the word that user needs, then user can directly input to specify the word needing to use.For example, want to input " universe ", but
There is no this word, it may be said that " universe of Qianrong ", go out user by semantics recognition is to describe the universe to user, then can use in alternative word
" universe " directly replaces it, as specified word, the word to be modified that front step S103 is chosen, and reaches and word to be modified is modified
Purpose.
Method speech modification word provided in an embodiment of the present invention to be described below by specific embodiment.
Embodiment one
Fig. 2 is a kind of method flow diagram of speech modification word in the embodiment of the present invention one.As shown in Fig. 2 the method bag
Include following steps S201-S207：
Step S201：Receive speech modification instruction.
Step S202：In document to be modified, all words of pronunciation identical are specified in identification and described speech modification instruction,
And the word that will identify that from front to back in document to be modified carries out the first kind successively and numbers and show.
For example, user have issued the instruction of this word of " performing the operation " in modification document, but " performs the operation " in document or pronunciation is
The possible more than one of the word of " shoushu ", needs the word being " shoushu " by all pronunciations all to identify, Ran Hougen
According to position in document to be modified for the word identifying, it is numbered from front to back, such as 1,2,3...... etc., then 1 is just right
Answer first word identifying.
Step S203：Receive the first kind numbering selected.
Step S204：Number corresponding word with the described selected first kind in all words that will identify that to be defined as treating
Modification word.
Wherein, each first kind numbering is corresponding with the word that only one identifies, therefore user can be said by voice
Go out first kind numbering, such as " 5 " are then it represents that user have selected the 5th word identifying as word to be modified.
Step S205：Show the corresponding alternative textual list of described word to be modified.
Step S206：Receive alternative word and select instruction.
Step S207：Described word to be modified is revised as the alternative word that instruction selected in described alternative word.
In the present embodiment, the text-to-speech information to be modified said according to user, in document to be modified, identification word is simultaneously
Word for identification is numbered, and then user can reach the purpose determining word to be modified, operate pole by saying numbering
For simple.
Embodiment two
Fig. 3 is a kind of method flow diagram of speech modification word in the embodiment of the present invention two.As shown in figure 3, the method bag
Include following steps S301-S308：
Step S301：Receive speech modification instruction.
Step S302：In document to be modified, all words of pronunciation identical are specified in identification and described speech modification instruction,
And first identified in document to be modified word is added predetermined labels.
For example, user have issued the work of this word of " performing the operation " in modification document, but " performs the operation " in document or pronunciation is
The possible more than one of the word of " shoushu ", needs the word being " shoushu " by all pronunciations all to identify, then will
First pronunciation identifying is that " shoushu " word adds predetermined labels, and that is, acquiescence have selected first literary composition identifying
Word.
Step S303：Receive predetermined labels and confirm instruction or predetermined labels move.
Wherein, if the word identifying of current predetermined labels institute labelling, be the word of user's expectation modification, then user
Predetermined labels can directly be sent and confirm instruction, the voice for example sending " selecting " confirms instruction as predetermined labels, subsequently holds
Row step S305 using by the word of predetermined labels institute labelling as word to be modified.
If the word identifying of current predetermined labels institute labelling is not the word of user's expectation modification, user is permissible
Send predetermined labels move, for example, pass through phonetic entry " upper " or " next ", last execution step S304 is moving
Dynamic predetermined labels, reach the purpose selecting word to be modified in the multiple unisonance words identifying.Wherein, predetermined labels move
Contain in instruction the information such as moving direction and moving step length with specify predetermined labels moving method, can be for example：" upper one
Individual ", " next ", " moving N number of afterwards ", " reach N number of " etc..
Step S304：With all words of identifying as tagged object, according to specified by described predetermined labels move
Moving method move described predetermined labels, and return execution step S303.
Step S305：Confirm that the word of presently described predetermined labels is defined as by instruction according to described predetermined labels to be modified
Word.
Step S306：Show the corresponding alternative textual list of described word to be modified.
Step S307：Receive alternative word and select instruction.
Step S308：Described word to be modified is revised as the alternative word that instruction selected in described alternative word.
In the present embodiment, the text-to-speech information to be modified said according to user, identify word in document to be modified, and
Acquiescence chooses first word identifying, that is, first word identifying has predetermined labels, is easy to user and checks.Work as user
When saying " upper one " or " next ", predetermined labels can move according to user's instruction, thus reaching determination literary composition to be modified
The purpose of word.
Embodiment three
Fig. 4 is a kind of method flow diagram of speech modification word in the embodiment of the present invention three.As shown in figure 4, the method bag
Include following steps S401-S406：
Step S401：Receive speech modification instruction；
Step S402：In document to be modified, all words of pronunciation identical are specified in identification and described speech modification instruction.
Step S403：Determine the word to be modified in all words identifying.
Step S404：Show that described word to be modified is corresponding with predetermined window in preset range near word to be modified
Alternative textual list.
Wherein, as a preferred embodiment, when described alternative textual list cannot be once whole in described predetermined window
When display finishes, alternative textual list described in Pagination Display in described predetermined window, and multiple alternative to show in every page
Word carries out Equations of The Second Kind numbering from front to back successively.For example, if having in the corresponding alternative textual list of word to be modified 10 standby
Selection word：First alternative word, the second alternative word, the 3rd alternative word, the 4th alternative word, the 5th alternative word, the 6th
Alternative word, the 7th alternative word, the 8th alternative word, the 9th alternative word, the tenth alternative word, and in described predetermined window
4 alternative words can only be shown every time, then corresponding for word to be modified alternative textual list is divided into page 3 alternative for every page
Word obtains the alternative textual list of page 1 after carrying out Equations of The Second Kind numbering successively from front to back：1st, the first alternative word；2nd, second is standby
Selection word；3rd, the 3rd alternative word；4th, the 4th alternative word；The alternative textual list of page 2：1st, the 5th alternative word；2nd, the 6th
Alternative word；3rd, the 7th alternative word；4th, the 8th alternative word；The alternative textual list of page 3：1st, the 9th alternative word；2nd,
Ten alternative words.
Step S405：Receive the alternative word corresponding Equations of The Second Kind numbering specified in current predetermined window.
For example, if user will select the 3rd alternative word of display in current predetermined window, its corresponding Equations of The Second Kind numbering
For " 3 ", then user can alternately word be selected and is specified the 3rd alternative word by phonetic entry " 3 ".
Wherein, as a preferred embodiment, when the alternative word not having user to need in current predetermined window, Yong Huke
With by the alternative word that page turning selects other pages is carried out to the alternative textual list of paging, that is, before described step S405,
May also include the steps of (1)-(2)：
(1) receive page-turning instruction；Such as user is referred to by voice page turnings such as " page ups " or " lower one page " of phonetic entry
Order.
(2) the alternative textual list of display in described predetermined window is turned over according to described page-turning instruction assigned direction
Page.
Step S406：Word to be modified is revised as Equations of The Second Kind in current predetermined window and numbers corresponding alternative word.
In the present embodiment, after determining word to be modified, the alternative text line of Pagination Display unisonance near this word
Table.If not having the word that user wants in the alternative word in current page, user is it may be said that page turning etc. is ordered, in other pages
Search alternative word.If there being the alternative word that user wants in current page, user says that the corresponding Equations of The Second Kind of this alternative word is numbered again,
Then replace word to be modified using the corresponding alternative word of this numbering, realize modification.Therefore user is selecting the operation tool of alternative word
There is simply and easily feature.
A kind of method of the speech modification word providing corresponding to above-described embodiment, the embodiment of the present invention also provides a kind of language
Sound changes the device of word, as shown in figure 5, including：Receiver module 51, identification module 52, determining module 53, display module 54 He
Modified module 55；
Receiver module 51, instructs and is sent to identification module 52 for receiving speech modification, be additionally operable to receive alternative word
Select and instruct and be sent to modified module 55；
Identification module 52, pronunciation is specified in the described speech modification instruction for, in document to be modified, identifying and receiving
The all words of identical；
Determining module 53, for determining the word to be modified in all words that identification module 52 identifies；
Display module 54, for showing the corresponding alternative textual list of word to be modified that determining module 53 determines；Described
Alternative word and word unisonance to be modified；
Modified module 55, the word to be modified for determining determining module 53 is revised as the described alternative word receiving
The alternative word of selected instruction.
Fig. 5 shown device, can be used for executing the technical scheme of embodiment of the method shown in Fig. 1, it realizes principle and technology
Effect is similar to, and here is omitted.
Fig. 6 is the structural representation of the device of another kind speech modification word provided in an embodiment of the present invention, as Fig. 6 institute
Show, on the basis of Fig. 5 shown device, further, determining module 53 includes the device of the present embodiment：First kind numbering receives
Unit 61 and determining unit 62；Wherein：
Identification module 52, the word being additionally operable to will identify that from front to back in document to be modified carries out first kind volume successively
Number and show；
First kind numbering receiving unit 61, for receiving selected first kind numbering；
Determining unit 62, in all words of identifying in identification module 52, by first kind numbering receiving unit 61
The described selected first kind receiving is numbered corresponding word and is defined as word to be modified.
Fig. 6 shown device, can be used for executing the technical scheme of embodiment of the method shown in Fig. 2, it realizes principle and technology
Effect is similar to, and here is omitted.
Fig. 7 is the structural representation of the device of another kind speech modification word provided in an embodiment of the present invention, as Fig. 7 institute
Show, on the basis of Fig. 5 shown device, further, determining module 53 includes the device of the present embodiment：Labelling receiving unit
71, movement indicia unit 72 and labelling confirmation unit 73；
Identification module 52, is additionally operable to for first identified in document to be modified word to add predetermined labels；
Labelling receiving unit 71, for being sent to labelling confirmation unit 73 by the predetermined labels receiving confirmation instruction；Also
For the predetermined labels receiving move is sent to movement indicia unit 72；
Movement indicia unit 72, for all words of being identified with identification module 52 as tagged object, according to receiving
Moving method specified by predetermined labels move move described predetermined labels；
According to the predetermined labels receiving, labelling confirmation unit 73, for confirming that presently described predetermined labels are marked by instruction
The word of note is defined as word to be modified.
Fig. 7 shown device, can be used for executing the technical scheme of embodiment of the method shown in Fig. 3, it realizes principle and technology
Effect is similar to, and here is omitted.
In another embodiment, display module 54 is specifically for predetermined near the word to be modified that determining module 53 determines
In the range of the corresponding alternative textual list of described word to be modified is shown with predetermined window.
Fig. 8 is the structural representation of the device of another kind speech modification word provided in an embodiment of the present invention, as Fig. 8 institute
Show, on the basis of Fig. 5 shown device, further, display module 54 includes the device of the present embodiment：
Judging unit 81, for judging that the corresponding alternative textual list of word to be modified whether can one in predetermined window
Secondary whole display finishes；
Pagination Display unit 82, for judging to change the corresponding alternative word of word in predetermined window in judging unit 81
List can once all show when finishing in predetermined window, and alternative textual list is shown in predetermined window with one page；
Or judge that in predetermined window, the modification corresponding alternative textual list of word can not in predetermined window in judging unit 81
When once all display finishes, the alternative textual list of Pagination Display, and to the multiple alternative word showing in every page from front to back
Carry out Equations of The Second Kind numbering successively；
In the present embodiment, the alternative word that receiver module 51 receives is selected instruction and is included：Specify in current predetermined window
Alternative word corresponding Equations of The Second Kind numbering.
Fig. 8 shown device, can be used for executing the technical scheme of embodiment of the method shown in Fig. 4, it realizes principle and technology
Effect is similar to, and here is omitted.
Preferably, in another embodiment, the receiver module 51 in Fig. 8 is additionally operable to receive page-turning instruction and be sent to paging
Display unit 82；Pagination Display unit 82, is additionally operable to the alternative textual list of display in described predetermined window according to receiving
Page-turning instruction assigned direction carries out page turning.
Preferably, in another embodiment, to be additionally operable to the specified word that receive user directly inputs concurrent for receiver module 51
Give modified module 55；Modified module 55, the word to be modified being additionally operable to determine determining module 53 is revised as the finger receiving
Determine word.
The device of the speech modification word that the present invention provides says, by speech modification instruction, the text-to-speech wanting to change,
Identify the word of unisonance in document to be modified, and quote word to be modified in the word identifying by voice, subsequently
The corresponding alternative textual list of word to be modified can be provided to supply user to select, thus user can voice choosing in alternative textual list
Select word to replace word to be modified.This device makes user can pass through simple phonetic order, completes wrong word is repaiied
Change work, simple to operate, solve the problems, such as that user need to take much time and energy manual modification word.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the present invention can be using complete hardware embodiment, complete software embodiment or the reality combining software and hardware aspect
Apply the form of example.And, the present invention can be using in one or more computers wherein including computer usable program code
The shape of the upper computer program implemented of usable storage medium (including but not limited to disk memory and optical memory etc.)
Formula.
The present invention is the flow process with reference to method according to embodiments of the present invention, equipment (system) and computer program
Figure and/or block diagram are describing.It should be understood that can be by each stream in computer program instructions flowchart and/or block diagram
Flow process in journey and/or square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processor instructing general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device is to produce
A raw machine is so that produced for reality by the instruction of computer or the computing device of other programmable data processing device
The device of the function of specifying in present one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and can guide computer or other programmable data processing device with spy
Determine in the computer-readable memory that mode works so that the instruction generation inclusion being stored in this computer-readable memory refers to
Make the manufacture of device, this command device realize in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or
The function of specifying in multiple square frames.
These computer program instructions also can be loaded in computer or other programmable data processing device so that counting
On calculation machine or other programmable devices, execution series of operation steps to be to produce computer implemented process, thus in computer or
On other programmable devices, the instruction of execution is provided for realizing in one flow process of flow chart or multiple flow process and/or block diagram one
The step of the function of specifying in individual square frame or multiple square frame.
Obviously, those skilled in the art can carry out the various changes and modification essence without deviating from the present invention to the present invention
God and scope.So, if these modifications of the present invention and modification belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprise these changes and modification.
Claims (14)
1. a kind of method of speech modification word is it is characterised in that include：
Receive speech modification instruction；
In document to be modified, all words of pronunciation identical are specified in identification and described speech modification instruction；
Determine the word to be modified in all words identifying；
Show the corresponding alternative textual list of described word to be modified；Described alternative word and described word unisonance to be modified；
Receive alternative word and select instruction；
Described word to be modified is revised as the alternative word that instruction selected in described alternative word.
2. as claimed in claim 1 a kind of method of speech modification word it is characterised in that described in document to be modified know
Do not specify all words of pronunciation identical with described speech modification instruction, also include：Document to be modified will be known from front to back
The word not gone out carries out the first kind successively and numbers and show；
Word to be modified in all words that described determination identifies, including：
Receive the first kind numbering selected；
Number corresponding word with the described selected first kind in all words that will identify that and be defined as word to be modified.
3. as claimed in claim 1 a kind of method of speech modification word it is characterised in that described in document to be modified know
Do not specify all words of pronunciation identical with described speech modification instruction, also include：First identifying in document to be modified
Individual word adds predetermined labels；
Word to be modified in all words that described determination identifies, including：
Receive predetermined labels and confirm instruction or predetermined labels move；
If receiving predetermined labels move, with all words of identifying as tagged object, moved according to described predetermined labels
The moving method of dynamic instruction moves described predetermined labels, be then returned to execute described reception predetermined labels confirm instruction or
The step of predetermined labels move；
Confirm that the word of presently described predetermined labels institute labelling is defined as word to be modified by instruction according to described predetermined labels.
4. a kind of method of the speech modification word as any one of claim 1-3 is it is characterised in that described display institute
State the corresponding alternative textual list of word to be modified, including：
In preset range near described word to be modified, the corresponding alternative word of described word to be modified is shown with predetermined window
List.
5. as claimed in claim 4 a kind of method of speech modification word it is characterised in that when described alternative textual list exists
Cannot once all show when finishing in described predetermined window, alternative text line described in Pagination Display in described predetermined window
Table, and Equations of The Second Kind numbering is carried out from front to back successively to the multiple alternative word of display in every page；
Described alternative word is selected instruction and is included：The alternative word corresponding Equations of The Second Kind numbering specified in current predetermined window.
6. as claimed in claim 5 a kind of method of speech modification word it is characterised in that described display described to be modified
After the corresponding alternative textual list of word, before instruction selected in the alternative word of described reception, also include：
Receive page-turning instruction；
The alternative textual list of display in described predetermined window is carried out page turning according to described page-turning instruction assigned direction.
7. a kind of method of the speech modification word as any one of claim 1-3 is it is characterised in that in described determination
After word to be modified in all words identifying, before the alternative text-to-speech of described reception selectes instruction, also include：
Receive specified word；
Described word to be modified is revised as described specified word, and terminates flow process.
8. a kind of device of speech modification word is it is characterised in that include：Receiver module, identification module, determining module, display
Module and modified module；
Described receiver module, instructs and is sent to described identification module for receiving speech modification, be additionally operable to receive alternative word
Select and instruct and be sent to described modified module；
Described identification module, pronunciation phase is specified in the described speech modification instruction in document to be modified, identifying with receive
Same all words；
Described determining module, for determining the word to be modified in all words that described identification module identifies；
Described display module, for showing the corresponding alternative textual list of word to be modified that described determining module determines；Described
Alternative word and word unisonance to be modified；
Described modified module, the word to be modified for determining described determining module is revised as the described alternative word receiving
The alternative word of selected instruction.
9. a kind of device of speech modification word, it is characterised in that described identification module, is additionally operable to as claimed in claim 8
The word that will identify that from front to back in document to be modified carries out the first kind successively and numbers and show；
Described determining module includes：First kind numbering receiving unit and determining unit；
Described first kind numbering receiving unit, for receiving selected first kind numbering；
Described determining unit, for, in all words of identifying in described identification module, described first kind numbering being received single
The described selected first kind that unit receives is numbered corresponding word and is defined as word to be modified.
10. a kind of device of speech modification word, it is characterised in that described identification module, is additionally operable to as claimed in claim 8
First identified in document to be modified word is added predetermined labels；
Described determining module includes：Labelling receiving unit, movement indicia unit and labelling confirmation unit；
Described labelling receiving unit, for being sent to described labelling confirmation unit by the predetermined labels receiving confirmation instruction；Also
For the predetermined labels receiving move is sent to described movement indicia unit；
Described movement indicia unit, for all words of being identified with described identification module as tagged object, according to receiving
Moving method specified by predetermined labels move move described predetermined labels；
Described labelling confirmation unit, for confirming to instruct presently described predetermined labels institute labelling according to the predetermined labels receiving
Word be defined as word to be modified.
A kind of device of the 11. speech modification words as any one of claim 8-10 is it is characterised in that described display
Module specifically in preset range near the word to be modified that described determining module determines with predetermined window show described in treat
The modification corresponding alternative textual list of word.
12. as claimed in claim 11 a kind of device of speech modification word it is characterised in that described display module includes：
Judging unit, for judging that the corresponding alternative textual list of described word to be modified whether can in described predetermined window
Once all display finishes；
Pagination Display unit, for when the judged result of described judging unit is for being, alternative textual list being shown with one page
In predetermined window；Or the described judged result judging list for no when, the alternative textual list of Pagination Display, and in every page
The multiple alternative word of display carries out Equations of The Second Kind numbering from front to back successively；
The alternative word that described receiver module receives is selected instruction and is included：The alternative word specified in current predetermined window corresponds to
Equations of The Second Kind numbering.
13. as claimed in claim 12 a kind of device of speech modification word it is characterised in that described receiver module is additionally operable to
Receive page-turning instruction and be sent to described Pagination Display unit；
Described Pagination Display unit, is additionally operable to refer to the alternative textual list of display in described predetermined window according to the page turning receiving
Assigned direction is made to carry out page turning.
A kind of device of the 14. speech modification words as any one of claim 8-10 is it is characterised in that described reception
Module is additionally operable to receive specified word and be sent to described modified module；
Described modified module, the word to be modified being additionally operable to determine described determining module is revised as the specified word receiving.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610833691.2A CN106406807A (en) | 2016-09-19 | 2016-09-19 | A method and a device for voice correction of characters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610833691.2A CN106406807A (en) | 2016-09-19 | 2016-09-19 | A method and a device for voice correction of characters |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106406807A true CN106406807A (en) | 2017-02-15 |
Family
ID=57997950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610833691.2A Pending CN106406807A (en) | 2016-09-19 | 2016-09-19 | A method and a device for voice correction of characters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106406807A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106952655A (en) * | 2017-02-23 | 2017-07-14 | 深圳市金立通信设备有限公司 | A kind of input method and terminal |
| CN108257601A (en) * | 2017-11-06 | 2018-07-06 | 广州市动景计算机科技有限公司 | For the method for speech recognition text, equipment, client terminal device and electronic equipment |
| CN109994105A (en) * | 2017-12-29 | 2019-07-09 | 宝马股份公司 | Data inputting method, device, system, vehicle and readable storage medium storing program for executing |
| CN112530222A (en) * | 2020-12-17 | 2021-03-19 | 江苏遨信科技有限公司 | Knowledge question bank system capable of conducting voice control and using method thereof |
| CN112579035A (en) * | 2020-12-14 | 2021-03-30 | 江苏惠通集团有限责任公司 | Voice acquisition terminal input system and input method |
| CN113378530A (en) * | 2021-06-28 | 2021-09-10 | 北京七维视觉传媒科技有限公司 | Voice editing method and device, equipment and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1282072A (en) * | 1999-07-27 | 2001-01-31 | 国际商业机器公司 | Error correcting method for voice identification result and voice identification system |
| CN1918578A (en) * | 2004-02-11 | 2007-02-21 | 美国联机股份有限公司 | Handwriting and voice input with automatic correction |
| CN101369216A (en) * | 2008-09-25 | 2009-02-18 | 腾讯科技（深圳）有限公司 | Words input method and system |
| CN101593076A (en) * | 2008-05-28 | 2009-12-02 | Lg电子株式会社 | Portable terminal and the method that is used to revise its text |
| CN103106061A (en) * | 2013-03-05 | 2013-05-15 | 北京车音网科技有限公司 | Voice input method and device |
| CN103207769A (en) * | 2012-01-16 | 2013-07-17 | 联想(北京)有限公司 | Method and user equipment for voice amending |
| CN103714048A (en) * | 2012-09-29 | 2014-04-09 | 国际商业机器公司 | Method and system used for revising text |
| CN105117034A (en) * | 2015-08-31 | 2015-12-02 | 任文 | Method for inputting Chinese speeches, positioning statements and correcting errors |
-
2016
- 2016-09-19 CN CN201610833691.2A patent/CN106406807A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1282072A (en) * | 1999-07-27 | 2001-01-31 | 国际商业机器公司 | Error correcting method for voice identification result and voice identification system |
| CN1918578A (en) * | 2004-02-11 | 2007-02-21 | 美国联机股份有限公司 | Handwriting and voice input with automatic correction |
| CN101593076A (en) * | 2008-05-28 | 2009-12-02 | Lg电子株式会社 | Portable terminal and the method that is used to revise its text |
| CN101369216A (en) * | 2008-09-25 | 2009-02-18 | 腾讯科技（深圳）有限公司 | Words input method and system |
| CN103207769A (en) * | 2012-01-16 | 2013-07-17 | 联想(北京)有限公司 | Method and user equipment for voice amending |
| CN103714048A (en) * | 2012-09-29 | 2014-04-09 | 国际商业机器公司 | Method and system used for revising text |
| CN103106061A (en) * | 2013-03-05 | 2013-05-15 | 北京车音网科技有限公司 | Voice input method and device |
| CN105117034A (en) * | 2015-08-31 | 2015-12-02 | 任文 | Method for inputting Chinese speeches, positioning statements and correcting errors |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106952655A (en) * | 2017-02-23 | 2017-07-14 | 深圳市金立通信设备有限公司 | A kind of input method and terminal |
| CN108257601A (en) * | 2017-11-06 | 2018-07-06 | 广州市动景计算机科技有限公司 | For the method for speech recognition text, equipment, client terminal device and electronic equipment |
| CN109994105A (en) * | 2017-12-29 | 2019-07-09 | 宝马股份公司 | Data inputting method, device, system, vehicle and readable storage medium storing program for executing |
| CN112579035A (en) * | 2020-12-14 | 2021-03-30 | 江苏惠通集团有限责任公司 | Voice acquisition terminal input system and input method |
| CN112530222A (en) * | 2020-12-17 | 2021-03-19 | 江苏遨信科技有限公司 | Knowledge question bank system capable of conducting voice control and using method thereof |
| CN113378530A (en) * | 2021-06-28 | 2021-09-10 | 北京七维视觉传媒科技有限公司 | Voice editing method and device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106406807A (en) | A method and a device for voice correction of characters | |
| CN103714048B (en) | Method and system for correcting text | |
| US9239829B2 (en) | Speech recognition device | |
| TWI443551B (en) | Method and system for an input method editor and computer program product | |
| EP2653964A2 (en) | Methods and systems for speech-enabling a human-to-machine interface | |
| CN106126157B (en) | Pronunciation inputting method and device based on hospital information system | |
| JP2007011358A (en) | Speech recognition assisted autocompletion of composite character | |
| RU2009139274A (en) | RECOGNITION ARCHITECTURE FOR GENERATION OF ASIAN Hieroglyphs | |
| CN101681198A (en) | Providing relevant text auto-completions | |
| CN110428813B (en) | Voice understanding method and device, electronic equipment and medium | |
| Šepić et al. | BrailleEasy: one-handed braille keyboard for smartphones | |
| CN105975256A (en) | Operation guide method and system for application | |
| CN105161097A (en) | Voice interaction method and apparatus | |
| US11189283B2 (en) | Freeform conversation writing assistant | |
| CN105760356A (en) | Automatic generation method and system of English word dictating question alternative options | |
| US20150012261A1 (en) | Method for phonetizing a data list and voice-controlled user interface | |
| CN110245224A (en) | Talk with generation method and device | |
| CN110704590A (en) | Method and apparatus for augmenting training samples | |
| CN108885872A (en) | Response generating means, dialogue control system and response generation method | |
| KR20150083173A (en) | System for editing a text of a portable terminal and method thereof | |
| US10319378B2 (en) | Interaction apparatus and method | |
| KR100593589B1 (en) | Multilingual Interpretation / Learning System Using Speech Recognition | |
| CN107945802A (en) | Voice recognition result processing method and processing device | |
| CN110148413A (en) | Speech evaluating method and relevant apparatus | |
| CN105893345A (en) | Information processing method and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20170215 |