CN109740142A - A kind of character string error correction method and device - Google Patents
A kind of character string error correction method and device Download PDFInfo
- Publication number
- CN109740142A CN109740142A CN201810360247.2A CN201810360247A CN109740142A CN 109740142 A CN109740142 A CN 109740142A CN 201810360247 A CN201810360247 A CN 201810360247A CN 109740142 A CN109740142 A CN 109740142A
- Authority
- CN
- China
- Prior art keywords
- target
- character string
- string
- user
- text
- 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
Landscapes
- Machine Translation (AREA)
- Document Processing Apparatus (AREA)
Abstract
The embodiment of the present application discloses a kind of character string error correction method and device, improves the error correction efficiency and user experience of character string.Wherein, which comprises receive choose operation of the user to the target string obtained by speech recognition conversion, show character string candidate region, the character string candidate region shows the substitution character string of the target string;The user is received to the selection operation of the substitution character string, the target string is replaced with to the substitution character string chosen by the user, realizes the error correction to the target string.
Description
Technical field
This application involves computer field more particularly to a kind of character string error correction methods and device.
Background technique
In intelligent input method field, user not only can be by 26 keys or the dummy keyboard of 9 keys, or passes through hand-written side
Formula realizes the input to character string, can also convert speech into character string, Lai Shixian by the voice of identification user's input
Input to character string.Although current speech recognition technology recognition accuracy is higher, still there can be identification mistake
Situation, especially when in the non-type situation of user pronunciation.When the character string that user's discovery identifies is mistake, Yong Huxu
The character string is deleted manually, and inputs the character string again through above-mentioned input mode, lead to the error correction of error character string
Efficiency is lower, influences user experience.
Summary of the invention
In order to solve technical problem of the existing technology, the embodiment of the present application provides a kind of character string error correction method and dress
It sets, improves the error correction efficiency and user experience of character string.
The embodiment of the present application provides a kind of character string error correction method, which comprises
Choose operation of the user to the target string obtained by speech recognition conversion is received, shows character string candidate regions
Domain, the character string candidate region show the substitution character string of the target string;
The user is received to the selection operation of the substitution character string, the target string is replaced with by the use
The substitution character string that family is chosen.
Optionally, the number of the target string is multiple, and multiple mesh are shown in the character string candidate region
Mark the corresponding substitution character string of character string;
It is described to receive the user and include: to the selection operation of the substitution character string
Receive the selection operation of user substitution character string corresponding to the multiple target string.
Optionally, the selection for receiving user substitution character string corresponding to the multiple target string
Operation includes:
Receive the user selection operation for substituting character string sequentially corresponding to the multiple target string;
Described replace with the target string include: by the substitution character string that the user chooses
Multiple target strings are replaced with into the substitution character string that the user sequentially chooses.
Optionally, the target string includes target text, and the substitution character string of the target string includes at least
Following one of which:
Text identical with the target text pronunciation, text identical with the phonetic of the target text, and with institute
The text that target text has phonetic correlativity is stated, the phonetic of the text with phonetic correlativity is right in keypad
The phonetic of the number key answered and the target text corresponding number key in keypad is identical.
Optionally, the target string includes target punctuation mark, target letter and/or target number.
The embodiment of the present application provides a kind of character string error correction device, and described device includes:
Display unit chooses operation to the target string obtained by speech recognition conversion for receiving user, shows
Show that character string candidate region, the character string candidate region show the substitution character string of the target string;
Error correction unit, for receiving the user to the selection operation of the substitution character string, by the target string
The substitution character string chosen by the user is replaced with, realizes the error correction to the target string.
Optionally, the number of the target string is multiple, and multiple mesh are shown in the character string candidate region
Mark the corresponding substitution character string of character string;
The error correction unit, is specifically used for:
The selection operation of user substitution character string corresponding to the multiple target string is received, it will be described
Target string replaces with the substitution character string chosen by the user.
Optionally, the error correction unit, is specifically used for:
The user selection operation for substituting character string sequentially corresponding to the multiple target string is received, it will
Multiple target strings replace with the substitution character string that the user sequentially chooses, and the target string is entangled in realization
It is wrong.
Optionally, the target string includes target text, and the substitution character string of the target string includes at least
Following one of which:
Text identical with the target text pronunciation, text identical with the phonetic of the target text, and with institute
The text that target text has phonetic correlativity is stated, the phonetic of the text with phonetic correlativity is right in keypad
The phonetic of the number key answered and the target text corresponding number key in keypad is identical.
Optionally, the target string includes target punctuation mark, target letter and/or target number.
The application is by receiving choose operation of the user to the target string obtained by speech recognition conversion, display packet
The character string candidate region of the substitution character string of target string is included, and receives choosing of the user to the substitution character string
Operation is selected, the target string is replaced with to the substitution character string chosen by the user, does not need to use in the whole process
Family is re-entered with the dummy keyboard of 9 keys or 26 keys again, and is available to user and is optionally substituted character string, and user is only
It needs therefrom to select, improves character string error correction efficiency and user experience.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The some embodiments recorded in application, for those of ordinary skill in the art, without creative efforts,
It can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is a kind of flow chart of character string error correction method provided by the embodiments of the present application;
Fig. 2 is the display interface schematic diagram of electronic equipment provided by the embodiments of the present application;
Fig. 3 is the schematic diagram of another display interface of the electronic equipment provided by the embodiments of the present application;
Fig. 4 is the schematic diagram of another display interface of the electronic equipment provided by the embodiments of the present application;
Fig. 5 is the schematic diagram of the last one display interface of the electronic equipment provided by the embodiments of the present application;
Fig. 6 is a kind of structural block diagram of character string error correction device provided by the embodiments of the present application.
Specific embodiment
When the character string that speech recognition obtains when the error occurs, the prior art needs user to delete the character string manually, and
And the input modes such as input, be manually entered by dummy keyboard, the voice of 26 keys or 9 keys and re-entering the character string, lead to word
The error correction efficiency for according with string is lower, and influences user experience.
In order to overcome the above technical problems, this application provides a kind of character string error correction method and device, raising is realized
Character string error correction efficiency, the purpose for improving user experience.
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only this
Apply for a part of the embodiment, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall in the protection scope of this application.
Referring to Fig. 1, which is a kind of flow chart of character string error correction method provided by the embodiments of the present application.
Error correction method provided in this embodiment includes the following steps:
S101: choose operation of the user to the target string obtained by speech recognition conversion is received, shows character string
Candidate region, character string candidate region show the substitution character string of the target string.
In the embodiment of the present application, the voice data of user's input is identified first, so that voice data be converted
It is displayed on the screen for the form of character string.Then, user can carry out the character string of identification mistake as target string
It chooses, the purpose chosen is the substitution character string in order to show the target string, so that user is easily from substitution character string
In select the replacement that correct character string carries out target string.So receiving user to passing through speech recognition conversion
Obtained target string chooses operation, shows character string candidate region, character string candidate region shows the target word
Accord with the substitution character string of string.
So-called substitution character string refers to the matched character string of voice data that may be inputted with user.In the present embodiment,
Target string may include that target text, target punctuation mark, target letter, target number etc. are one such or a variety of.
If target string is target text, then substitution character string can be text identical with the target text pronunciation
Word, text identical with the phonetic of the target text, or the text with the target text with phonetic correlativity,
The phonetic of the text with phonetic correlativity corresponding number key and phonetic of the target text in keypad exist
Corresponding number key is identical in keypad.
For example, text identical with the target text pronunciation can be, for example, if target text is " thinking "
" sound ", not only phonetic is identical for the two, is all " xiang ", and tone is also identical, is all three sound.
If target text is " thinking ", text identical with the phonetic of the target text is, for example, " to ", " sound "
" Hunan " etc..
If target text is " thinking ", because the phonetic of target text is " xiang ", the corresponding number in keypad
Keyboard is " 94264 ", wherein the corresponding letter of number key " 9 " is " w " " x " " y " and " z ", and the corresponding letter of number key " 4 " is
" g " " h " and " i ", the corresponding letter of number key " 2 " are " a " " b " and " c ", the corresponding letter of number key " 6 " for " m " " n " and
" o ", so, number key " 94264 " can also correspond to phonetic " zhang " and " chang " etc. in addition to corresponding phonetic " xiang ", that
Substitution character string " opening " " rising " etc. can be obtained according to phonetic " zhang ", and substitution character string is obtained according to phonetic " chang "
" length " " normal " etc..Therefore, the substitution character string with phonetic correlativity of target string " thinking " includes " opening " " rising " " length "
" normal " etc..
If target string includes target letter, target number and/or target punctuation mark, target letter is replaced
For 25 letters that character string may include in 26 letters in addition to target letter, the substitution character string of target number can be with
Including other numbers in addition to target number, the substitution character string of target punctuation mark can be to remove in default punctuation mark and be somebody's turn to do
Other punctuation marks except target punctuation mark.
Optionally, when target string includes target text, target letter and/or target number, character string is substituted
Can be arranged according to preset rules, for example, according to its pronunciation and user's input voice data degree of closeness from high to low
Sequence is arranged, and the voice data that the pronunciation of character string is inputted closer to user is substituted, can more indicating the substitution character string
It can be the character string that user wants, vice versa.
Such as the substitution character string of target text " thinking " may include " to " " sound " " Hunan " " opening " " rising " " length " and
" normal ", is compared to " opening " " rising " " length " and " normal ", and the pronunciation of " to " " sound " " Hunan " these three substitution character strings is closer to mesh
The pronunciation of text " thinking " is marked, so " opening " " rising " " length " and " normal " this four substitution words should be come these three substitution character strings
Before symbol string.
When target string includes target text, in addition to the degree of closeness according to pronunciation and the voice data of user's input
Except substitution character string sorting, it can also be ranked up according to the matching degree with context semanteme.With context semanteme
Matching degree is higher, more indicates that substitution character string is the character string that user wants;Vice versa.Such as the language inputted according to user
The character string that sound data conversion obtains is " I groans homesick ", and target text is " groaning ", it is assumed that corresponding substitution character string includes
" weighing apparatus " and " very ", based on context finds, " I desires to house " semantically has certain meaning, and " I weighs homesick " in language
It is then nonsensical in justice, therefore substitute the context semantic matches degree of character string " very " in this example embodiment and be higher than substitution character
It goes here and there " weighing apparatus ".
It optionally, can also be according to the matching journey with context semanteme when target string includes target punctuation mark
Degree is ranked up substitution character string.For example, be according to the character string that is converted to of voice data that user inputs " Xiao Ming, you
Where." target string be ".", substitution character string may include ", " "? " "!" etc..Since " you are where " is interrogative sentence,
So substitution character string "? " with the matching degree of context semanteme than substitution character string ", " and "!" high, so should will replace
For character string "? " come substitution character string ", " and "!" front.
Optionally, after the substitution character string to target string is ranked up, it can choose and come preceding preset number
For a substitution character string display in character string candidate region, preset number is positive integer.
It is illustrated by taking target text as an example below and how to receive user to the mesh obtained by speech recognition conversion
Mark character string chooses operation, and in character string candidate region displaying target character string substitution character string.
Referring to fig. 2, which is the display interface schematic diagram of electronic equipment, includes 10 He of dummy keyboard in the display interface
Display area 11.Dummy keyboard 10 includes voice input control 101, editing area 102 and character string candidate region 103.Voice
Input control 101, the voice for receiving user inputs operation, so that the data under voice device triggered on electronic equipment is adopted
Collect voice data.Editing area 102 is for showing the character string identified to voice data, and reception user to mesh
Mark character string chooses operation, and target string is replaced with to the substitution character string of user's selection.Character string candidate region 103,
For the substitution character string of displaying target character string, and user is received to the selection operation of substitution character string.Display area 11 is used
Character string in display editing area 10.
Assuming that the text that user is converted to by the voice data that voice input control 101 inputs be " 1, think
Head song ", which is shown in editing area 102 and display area 11.Wherein " thinking " is the text of identification mistake, i.e. target text
Word.It receives user and operation (dotted line frame in Fig. 2 indicates to be chosen by user) is chosen to target text " thinking ", in character string candidate
Substitution character string of displaying target text " thinking ", such as " sound " " as " " Hunan " " opening " " length " etc. in region 103.
S102: receive the user to it is described substitution character string selection operation, by the target string replace with by
The substitution character string that the user chooses realizes the error correction to the target string.
In the present embodiment, the substitution character string of target string can be one, be also possible to multiple.When receiving use
After family is to the selection operation of substitution character string, target string is replaced with to the substitution character string that will be chosen by user.
By taking Fig. 3 as an example, which is the schematic diagram of another display interface of electronic equipment.By receiving user in character
It, can be in editing area 102 and display area 11 by target character to the selection operation of substitution character string in candidate region 103
String replaces with the substitution character string of user's selection.Specifically, the target text " thinking " of user's selection is received due in Fig. 2,
Character string candidate region shows the substitution character string " sound " " as " " Hunan " " opening " " length " of target text " thinking ", then, work as reception
After the substitution character string " as " of user's selection, so that it may which the target text " thinking " in editing area 102 is replaced with user's choosing
The substitution character string " as " selected, and then " the thinking " in display area 11 can also be replaced with to the substitution character string of user's selection
" as ".
It can be seen that the present embodiment is by receiving user's choosing to the target string obtained by speech recognition conversion
Operation, display include the character string candidate region of the substitution character string of target string, and receive the user and replace to described
For the selection operation of character string, the target string is replaced with to the substitution character string chosen by the user, in entire mistake
User is not needed in journey to be re-entered with the dummy keyboard of 9 keys or 26 keys again, and is available to user and is optionally substituted
Character string, user only need therefrom to select, and improve character string error correction efficiency and user experience.
It should be noted that in the above example, target string is single string, and in practical applications, target word
Symbol string number be it is multiple, i.e., user can once select multiple character strings as target string.In character string candidate region
Show the corresponding substitution character string of multiple target strings, that is to say, that multiple target strings can be used as one it is whole
The corresponding substitution character string of body, can also be not as an entirety, i.e., each target string is distinguished in multiple target strings
It is corresponding with respective substitution character string.
For example, with reference to Fig. 4, if the target string of user's selection includes " background ", if target string is whole as one
Body, then substitution character string may include " Beijing " " quiet and secluded " " northern border " etc. accordingly.Referring to Fig. 5, if target string is not made
For an entirety, then the corresponding substitution character string of first object character string " back " may include " north " " quilt " " again " etc., second
The corresponding substitution character string of target string " scape " may include " capital " " well " " quiet " etc..
When each individual target string respectively corresponds respective substitution character string, can receive the user according to
The selection operation of the corresponding substitution character string of the multiple target string of ordered pair, and multiple target strings are replaced
It is changed to the substitution character string that the user sequentially chooses.
For example, user has successively selected substitution character string " north " and " capital " from character candidates region 103, then can incite somebody to action
Target string " background " replaces with substitution character string " north " and " capital ".Certainly, if user is successively from character candidates region 103
Selected substitution character string " capital " and " north ", then target string " background " can be replaced with substitution character string " capital " and
" north " (is not shown) in Fig. 5.
Based on a kind of character string error correction method that above embodiments provide, the embodiment of the present application also provides a kind of character strings
Its working principle is described in detail with reference to the accompanying drawing in error correction device.
Referring to Fig. 6, which is a kind of structural block diagram of character string error correction device provided by the embodiments of the present application.
Character string error correction device provided in this embodiment includes:
Display unit 101 chooses operation to the target string obtained by speech recognition conversion for receiving user,
Show character string candidate region, the character string candidate region shows the substitution character string of the target string;
Error correction unit 102, for receiving the user to the selection operation of the substitution character string, by the target character
String replaces with the substitution character string chosen by the user, realizes the error correction to the target string.
Optionally, the number of the target string is multiple, and multiple mesh are shown in the character string candidate region
Mark the corresponding substitution character string of character string;
The error correction unit, is specifically used for:
The selection operation of user substitution character string corresponding to the multiple target string is received, it will be described
Target string replaces with the substitution character string chosen by the user, realizes the error correction to the target string.
Optionally, the error correction unit, is specifically used for:
The user selection operation for substituting character string sequentially corresponding to the multiple target string is received, it will
Multiple target strings replace with the substitution character string that the user sequentially chooses, and the target string is entangled in realization
It is wrong.
Optionally, the target string includes target text, and the substitution character string of the target string includes at least
Following one of which:
Text identical with the target text pronunciation, text identical with the phonetic of the target text, and with institute
The text that target text has phonetic correlativity is stated, the phonetic of the text with phonetic correlativity is right in keypad
The phonetic of the number key answered and the target text corresponding number key in keypad is identical.
Optionally, the target string includes target punctuation mark, target letter and/or target number.
When introducing the element of various embodiments of the application, the article " one ", "one", " this " and " described " be intended to
Indicate one or more elements.Word "include", "comprise" and " having " are all inclusive and mean in addition to listing
Except element, there can also be other elements.
It should be noted that those of ordinary skill in the art will appreciate that realizing the whole in above method embodiment or portion
Split flow is relevant hardware can be instructed to complete by computer program, and the program can be stored in a computer
In read/write memory medium, the program is when being executed, it may include such as the process of above-mentioned each method embodiment.Wherein, the storage
Medium can be magnetic disk, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random
Access Memory, RAM) etc..
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device reality
For applying example, since it is substantially similar to the method embodiment, so describing fairly simple, related place is referring to embodiment of the method
Part explanation.The apparatus embodiments described above are merely exemplary, wherein described be used as separate part description
Unit and module may or may not be physically separated.Furthermore it is also possible to select it according to the actual needs
In some or all of unit and module achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying
In the case where creative work, it can understand and implement.
The above is only the specific embodiment of the application, it is noted that for the ordinary skill people of the art
For member, under the premise of not departing from the application principle, several improvements and modifications can also be made, these improvements and modifications are also answered
It is considered as the protection scope of the application.
Claims (10)
1. a kind of character string error correction method, which is characterized in that the described method includes:
Choose operation of the user to the target string obtained by speech recognition conversion is received, shows character string candidate region,
The character string candidate region shows the substitution character string of the target string;
The user is received to the selection operation of the substitution character string, the target string is replaced with and is selected by the user
In substitution character string.
2. the method according to claim 1, wherein the number of the target string is multiple, the character
String shows the corresponding substitution character string of multiple target strings in candidate region;
It is described to receive the user and include: to the selection operation of the substitution character string
Receive the selection operation of user substitution character string corresponding to the multiple target string.
3. according to the method described in claim 2, it is characterized in that, described receive the user to the multiple target string
It is corresponding substitution character string selection operation include:
Receive the user selection operation for substituting character string sequentially corresponding to the multiple target string;
Described replace with the target string include: by the substitution character string that the user chooses
Multiple target strings are replaced with into the substitution character string that the user sequentially chooses.
4. the method according to claim 1, wherein the target string includes target text, the target
The substitution character string of character string includes at least following one of which:
Text identical with the target text pronunciation, text identical with the phonetic of the target text, and with the mesh
The text that text has phonetic correlativity is marked, the phonetic of the text with phonetic correlativity is corresponding in keypad
The phonetic of number key and the target text corresponding number key in keypad is identical.
5. the method according to claim 1, wherein the target string includes target punctuation mark, target
Letter and/or target number.
6. a kind of character string error correction device, which is characterized in that described device includes:
Display unit shows word for receiving choose operation of the user to the target string obtained by speech recognition conversion
Symbol string candidate region, the character string candidate region shows the substitution character string of the target string;
Error correction unit replaces the target string for receiving the user to the selection operation of the substitution character string
For the substitution character string chosen by the user.
7. device according to claim 6, which is characterized in that the number of the target string is multiple, the character
String shows the corresponding substitution character string of multiple target strings in candidate region;
The error correction unit, is specifically used for:
The selection operation for receiving user substitution character string corresponding to the multiple target string, by the target
Character string replaces with the substitution character string chosen by the user, realizes the error correction to the target string.
8. device according to claim 7, which is characterized in that the error correction unit is specifically used for:
The user selection operation for substituting character string sequentially corresponding to the multiple target string is received, it will be multiple
The target string replaces with the substitution character string that the user sequentially chooses, and realizes the error correction to the target string.
9. device according to claim 6, which is characterized in that the target string includes target text, the target
The substitution character string of character string includes at least following one of which:
Text identical with the target text pronunciation, text identical with the phonetic of the target text, and with the mesh
The text that text has phonetic correlativity is marked, the phonetic of the text with phonetic correlativity is corresponding in keypad
The phonetic of number key and the target text corresponding number key in keypad is identical.
10. device according to claim 6, which is characterized in that the target string includes target punctuation mark, target
Letter and/or target number.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810360247.2A CN109740142A (en) | 2018-04-20 | 2018-04-20 | A kind of character string error correction method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810360247.2A CN109740142A (en) | 2018-04-20 | 2018-04-20 | A kind of character string error correction method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109740142A true CN109740142A (en) | 2019-05-10 |
Family
ID=66354431
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810360247.2A Pending CN109740142A (en) | 2018-04-20 | 2018-04-20 | A kind of character string error correction method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109740142A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112698739A (en) * | 2020-12-28 | 2021-04-23 | 联想(北京)有限公司 | Positioning method and device |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009187349A (en) * | 2008-02-07 | 2009-08-20 | Nec Corp | Text correction support system, text correction support method and program for supporting text correction |
CN103369122A (en) * | 2012-03-31 | 2013-10-23 | 盛乐信息技术(上海)有限公司 | Voice input method and system |
CN103473003A (en) * | 2013-09-12 | 2013-12-25 | 天津三星通信技术研究有限公司 | Character input error correction method and device |
CN103645876A (en) * | 2013-12-06 | 2014-03-19 | 百度在线网络技术(北京)有限公司 | Voice inputting method and device |
CN104007952A (en) * | 2013-02-27 | 2014-08-27 | 联想(北京)有限公司 | Input method, device and electronic device |
CN106569986A (en) * | 2015-10-12 | 2017-04-19 | 北京国双科技有限公司 | Character string replacement method and device |
US20170242832A1 (en) * | 2014-08-13 | 2017-08-24 | Alibaba Group Holding Limited | Character editing method and device for screen display device |
CN107544726A (en) * | 2017-07-04 | 2018-01-05 | 百度在线网络技术(北京)有限公司 | Method for correcting error of voice identification result, device and storage medium based on artificial intelligence |
CN107679032A (en) * | 2017-09-04 | 2018-02-09 | 百度在线网络技术(北京)有限公司 | Voice changes error correction method and device |
-
2018
- 2018-04-20 CN CN201810360247.2A patent/CN109740142A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009187349A (en) * | 2008-02-07 | 2009-08-20 | Nec Corp | Text correction support system, text correction support method and program for supporting text correction |
CN103369122A (en) * | 2012-03-31 | 2013-10-23 | 盛乐信息技术(上海)有限公司 | Voice input method and system |
CN104007952A (en) * | 2013-02-27 | 2014-08-27 | 联想(北京)有限公司 | Input method, device and electronic device |
CN103473003A (en) * | 2013-09-12 | 2013-12-25 | 天津三星通信技术研究有限公司 | Character input error correction method and device |
CN103645876A (en) * | 2013-12-06 | 2014-03-19 | 百度在线网络技术(北京)有限公司 | Voice inputting method and device |
US20170242832A1 (en) * | 2014-08-13 | 2017-08-24 | Alibaba Group Holding Limited | Character editing method and device for screen display device |
CN106569986A (en) * | 2015-10-12 | 2017-04-19 | 北京国双科技有限公司 | Character string replacement method and device |
CN107544726A (en) * | 2017-07-04 | 2018-01-05 | 百度在线网络技术(北京)有限公司 | Method for correcting error of voice identification result, device and storage medium based on artificial intelligence |
CN107679032A (en) * | 2017-09-04 | 2018-02-09 | 百度在线网络技术(北京)有限公司 | Voice changes error correction method and device |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112698739A (en) * | 2020-12-28 | 2021-04-23 | 联想(北京)有限公司 | Positioning method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5400200B2 (en) | System, computer program and method for improving text input in a short hand on keyboard interface | |
US20180060282A1 (en) | User interface for dictation application employing automatic speech recognition | |
JP2011254553A (en) | Japanese language input mechanism for small keypad | |
JP2012079252A (en) | Information terminal, character input method and character input program | |
JP2016061855A (en) | Audio learning device and control program | |
CN112966496A (en) | Chinese error correction method and system based on pinyin characteristic representation | |
JP2005078211A (en) | Chinese input program | |
JP4738847B2 (en) | Data retrieval apparatus and method | |
TWI475405B (en) | Electronic device and text-input interface displaying method thereof | |
US7197184B2 (en) | ZhuYin symbol and tone mark input method, and electronic device | |
CN109740142A (en) | A kind of character string error correction method and device | |
KR100542757B1 (en) | Automatic expansion Method and Device for Foreign language transliteration | |
JP2018066800A (en) | Japanese speech recognition model learning device and program | |
JP6641680B2 (en) | Audio output device, audio output program, and audio output method | |
WO2007105615A1 (en) | Request content identification system, request content identification method using natural language, and program | |
CN103616962B (en) | A kind of information processing method and device | |
CN100561469C (en) | Create and use the method and system of Chinese language data and user-corrected data | |
US20110109559A1 (en) | Computer input system and input method thereof | |
CN113515586A (en) | Data processing method and device | |
CN111179645A (en) | Pinyin spelling method, device, equipment and computer readable storage medium | |
CN102221985A (en) | Chinese and control command voice recognition input method and device | |
KR101243754B1 (en) | Chinese Characters Pronunciation Displaying System using Hangul Phonetic Symbols | |
JP2002297577A (en) | Apparatus, and method of input conversion processing for chinese language and program therefor | |
Anil et al. | A mapper and combiner based Marathi text to speech synthesis using English TTS Engine | |
KR101777141B1 (en) | Apparatus and method for inputting chinese and foreign languages based on hun min jeong eum using korean input keyboard |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |