CN110019667A - It is a kind of that word method and device is looked into based on voice input information - Google Patents
It is a kind of that word method and device is looked into based on voice input information Download PDFInfo
- Publication number
- CN110019667A CN110019667A CN201710983040.6A CN201710983040A CN110019667A CN 110019667 A CN110019667 A CN 110019667A CN 201710983040 A CN201710983040 A CN 201710983040A CN 110019667 A CN110019667 A CN 110019667A
- Authority
- CN
- China
- Prior art keywords
- word
- text information
- information
- letter
- target
- 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 35
- 238000012937 correction Methods 0.000 claims abstract description 55
- 241000239290 Araneae Species 0.000 claims description 3
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 2
- 238000006467 substitution reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001351 cycling effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Abstract
The application, which provides, a kind of looks into word method and device based on voice input information, wherein includes the pronunciation sequence of each letter in word to be checked in the voice messaging the described method includes: receiving the voice messaging of user's input；Pronunciation sequence in the voice messaging is identified, the text information of the word to be checked is obtained；The text information is matched with the word in word database, if not having the word to match with the text information in the word database, information correction is carried out to the text information；Matching obtains target word corresponding with the text information after information correction from the word database, and shows the target word to the user.Technical solution provided by the present application, being capable of conveniently and efficiently looking up words.
Description
Technical field
It is this application involves technical field of information processing, in particular to a kind of that word method and dress are looked into based on voice input information
It sets.
Background technique
Currently, in intelligent wearable device, smart phone and other mobile devices, each dictionary class App can be carried out
Word enquiring.In general, the mode that user inputs word can be and read out word by touchscreen keypad typing word or voice
Complete pronunciation, is inquired after transferring to speech recognition module to carry out word identification.
The method of word enquiring is likely encountered following problems when in use in the prior art:
1, very inconvenient with keyboard or hand-written operation word typing in the small screen of smartwatch；
2, user cannot be guaranteed to can be carried out contact action (such as running, cycling etc.) under any circumstance；
3, user looks into word very maximum probability and is not aware that the orthoepy of this word, therefore can not read out the complete of word
Pronunciation.
Therefore word method in the prior art of looking into has very big limitation, and word enquiring can not be effectively performed.
Summary of the invention
The application embodiment be designed to provide it is a kind of word method and device is looked into based on voice input information, can
Conveniently and efficiently looking up words.
To achieve the above object, on the one hand the application, which provides, a kind of looks into word method, the side based on voice input information
Method includes: the voice messaging for receiving user's input, includes the pronunciation sequence of each letter in word to be checked in the voice messaging；
Pronunciation sequence in the voice messaging is identified, the text information of the word to be checked is obtained；By the text information
It is matched with the word in word database, if not having the list to match with the text information in the word database
Word carries out information correction to the text information；Matching obtains and the text after information correction from the word database
The corresponding target word of this information, and the target word is shown to the user.
Further, the method also includes: match if having in the word database with the text information
Word shows the word to match to the user.
Further, whether carry out information correction to the text information includes: in the detection text information comprising sky
Lattice symbol, and if it exists, the space character, the text information after obtaining information correction are filtered from the text information.
Further, information correction is carried out to the text information and comprises determining that the letter of the target in the text information,
Wherein, the target letter is associated with candidate letter；The candidate letter is replaced into the target letter, and replacement is obtained
Text information as the text information after information correction；Wherein, the candidate letter and the pronunciation of the target letter have
The identical pronunciation syllable in part.
Further, when the quantity of the target letter in the text information is at least two, the method also includes:
The candidate letter of each target letter is subjected to permutation and combination, obtains several monograms being made of candidate letter；Traversal institute
Monogram is stated, and replaces corresponding target letter in the text information with current monogram, after obtaining information correction
Text information；When matching obtains target word corresponding with text information after information correction from the word database
When, stop the process of traversal.
Further, the method also includes:, can not be in the word database when traversing all monogram
When matching obtains target word corresponding with the text information after information correction, to user feedback miscue information.
Further, the word in the word database includes the field of preset quantity, wherein the field includes word
At least one of identification field, word content field, word paraphrase field；Correspondingly, by the text information and word
Word in database carry out matching include: word to be matched is selected from the word database, and read it is described to
Word content field in the word matched；By the information and text information progress in the word content field of reading
Match.
To achieve the above object, the application, which also provides, a kind of looks into word device, described device packet based on voice input information
Include: voice messaging receiving unit includes each in word to be checked for receiving the voice messaging of user's input, in the voice messaging
The pronunciation sequence of a letter；Voice recognition unit obtains described for identifying to the pronunciation sequence in the voice messaging
The text information of word to be checked；Matching unit, for the text information to be matched with the word in word database, if
Do not have the word to match with the text information in the word database, information correction is carried out to the text information；
Display unit obtains target corresponding with the text information after information correction for matching from the word database
Word, and the target word is shown to the user.
Further, the matching unit includes: target letter determining module, for determining the mesh in the text information
Marking-up is female, wherein the target letter is associated with candidate letter；Alphabetical replacement module, for replacing the candidate letter
The target letter, and the text information that replacement is obtained is as the text information after information correction；Wherein, the candidate letter
Has the identical pronunciation syllable in part with the pronunciation of the target letter.
Further, the matching unit further include: permutation and combination module, for when the target word in the text information
When female quantity is at least two, the candidate letter of each target letter is subjected to permutation and combination, obtains being made of candidate letter
Several monograms；Spider module replaces the text envelope for traversing the monogram, and with current monogram
Corresponding target letter, the text information after obtaining information correction in breath；Stopping modular, for from the word database
When matching obtains target word corresponding with the text information after information correction, stop the process of traversal.
Therefore the application, when carrying out looking into word, user can read out the pronunciation of each letter in word to be checked, this
Sample, looks into word app or mobile terminal can receive the voice messaging of the pronunciation sequence comprising each letter.By to the voice
Pronunciation sequence in information is identified, so as to obtain the text information of word to be checked.May include in text information
The each letter identified.In this application, can by text information and the word in the word database that in advance construct into
Row matching.Text information can specifically be carried out to whole word matching, part phrase therein can also be matched.If matching
Failure can carry out information correction to text information.Specifically, the space in text information can be filtered out, and replaces pronunciation
Then similar letter can inquire the text information after information correction again, look into during word so as to improve
Serious forgiveness, and the word that user may expect can be inquired.Therefore technical solution provided by the present application, it can
Conveniently and efficiently looking up words.
Referring to following description and accompanying drawings, specific implementations of the present application are disclosed in detail, specify the original of the application
Reason can be in a manner of adopted.It should be understood that presently filed embodiment is not so limited in range.In appended power
In the range of the spirit and terms that benefit requires, presently filed embodiment includes many changes, modifications and is equal.
The feature for describing and/or showing for a kind of embodiment can be in a manner of same or similar one or more
It uses in a other embodiment, is combined with the feature in other embodiment, or the feature in substitution other embodiment.
It should be emphasized that term "comprises/comprising" refers to the presence of feature, one integral piece, step or component when using herein, but simultaneously
It is not excluded for the presence or additional of one or more other features, one integral piece, step or component.
Detailed description of the invention
Included attached drawing is used to provide to be further understood from the application embodiment, and which constitute the one of specification
The principle of the application for illustrating presently filed embodiment, and with verbal description is come together to illustrate in part.It should be evident that
The accompanying drawings in the following description is only some embodiments of the application, for those of ordinary skill in the art, is not being paid
Out under the premise of creative labor, it is also possible to obtain other drawings based on these drawings.In the accompanying drawings:
Fig. 1 is to look into word method and step figure in the application embodiment；
Fig. 2 is to look into word method flow diagram in the application embodiment；
Fig. 3 is the functional block diagram that word device is looked into the application embodiment.
Specific embodiment
In order to make those skilled in the art better understand the technical solutions in the application, below in conjunction with the application reality
The attached drawing in mode is applied, the technical solution in the application embodiment is clearly and completely described, it is clear that described
Embodiment is only a part of embodiment of the application, rather than whole embodiments.Based on the embodiment party in the application
Formula, all other embodiment obtained by those of ordinary skill in the art without making creative efforts, is all answered
When the range for belonging to the application protection.
Please refer to Fig. 1 and Fig. 2, the application, which provides, a kind of looks into word method based on voice input information, which comprises
S1: receiving the voice messaging of user's input, includes the pronunciation of each letter in word to be checked in the voice messaging
Sequence.
In the present embodiment, user, can be by the microphone of mobile terminal, eventually to movement when needing looking up words
Hold input voice information.Specifically, user can successively read out each letter in word to be checked, in this way, by each letter
Pronunciation sequence may be constructed the voice messaging.
It in the present embodiment, can be by voice messaging according to preset after terminal device receives the voice messaging
Audio file formats are stored.
S2: identifying the pronunciation sequence in the voice messaging, obtains the text information of the word to be checked.
In the present embodiment, mobile terminal can be by means of third party's speech recognition module, in the voice messaging
Pronunciation sequence identified, to generate the text information of the word to be checked.It wherein, can be according to secondary in the text information
Sequence goes out each letter.It should be noted that the pause duration according to user when reading letter, can be added one between letter
A or multiple spaces.For example, user is at thought " bag ", the dead time is more long between a and g, then the text information generated
It can be " BA G ", there are a space characters between A and G.
S3: the text information is matched with the word in word database, if not having in the word database
The standby word to match with the text information carries out information correction to the text information.
In the present embodiment, after getting the text information, text information can accurately be matched.Specifically
Ground can match the text information with the word in word database.Word in the word database can be with
Field including preset quantity, please refers to table 1, and the field includes entry identification field, word content field, word paraphrase word
At least one of section.
The schematic table of each field in 1 word of table
| Entry identification field | Word content field | Word paraphrase field | It is other |
| ID | Word | Paraphrase |
In the present embodiment, when being matched the text information with the word in word database, Ke Yicong
Word to be matched is selected in the word database, and reads the word content field in the word to be matched, then
Information in the word content field of reading can be matched with the text information.
In the present embodiment, the content in text information and word content field can be subjected to complete match, only
Successful match can be just indicated when the two is completely the same.Match if having in the word database with the text information
Word, then the word to match can be shown in the user interface of mobile terminal, so as to user's exhibition
Show matching result.
It in the present embodiment, can if not having the word to match with the text information in the word database
To carry out information correction to the text information, to remove the disturbing factor in the text information.Specifically, due to text envelope
There may be part space character in breath, cause to malfunction in complete match.Therefore, information correction is carried out to the text information
When, it whether can detecte in the text information comprising space character, and if it exists, the space is filtered from the text information
Symbol, to obtain the text information after information correction.
Text information after preliminary corrections can be matched with word database again, if cannot still match
As a result, the letter that may be obscured in text information can be replaced.Specifically, the similar letter that can will pronounce into
Row is successively replaced, and text information is regenerated.The rule that different languages need to replace is different, by taking English alphabet as an example, letter b with
The pronunciation of alphabetical D is similar, and alphabetical G is similar with the letter pronunciation of J, easy letters,confusion successively can be carried out alphabetical replacement.
In the present embodiment, for different languages, the letter that can will likely be obscured constitutes a pair of alphabetical group.
Wherein, a letter can be the candidate letter of another letter.In this way, when carrying out information correction to the text information,
It can determine that the target letter in the text information, the target letter are the letter that possible obscure.Such as English words
B, D, G etc. in mother.Wherein, the target letter is associated with candidate letter, the candidate letter and the target letter
Pronunciation has the identical pronunciation syllable in part.For example, B is associated with D, G is associated with J.It is then possible to by the candidate letter
The target letter is replaced, and the text information that replacement is obtained is as the text information after information correction.For example, initial text
This information is abjust, wherein b can be changed to d, to obtain adjust.The adjust retrieved can be the letter
Text information after breath correction.In this way, the text information after information correction can be matched with word database again, from
And obtain matching result.
In practical applications, there may be the letters that multiple possibility are obscured in a text information.For example, text envelope
It ceases in abgust, b and g are the letter that possible obscure.At this point, when the quantity of the target letter in the text information is
When at least two, the candidate letter of each target letter can be subjected to permutation and combination, obtain being made of candidate letter several
Monogram.For example, candidate letter d and j can be carried out permutation and combination, " d ", " j " and " d-j " these three alphabetical groups are obtained
It closes.Then the monogram can be traversed, and replaces corresponding target word in the text information with current monogram
Mother, the text information after obtaining information correction.For example, after being replaced respectively with above-mentioned three kinds of monograms, it is available
Text information after these three corrections of adgust, abjust and adjust.Text information after generating a correction, just
It can once be matched with word java standard library, be obtained and text envelope after information correction when being matched from the word database
When the corresponding target word of manner of breathing, the process of traversal can be stopped.For example, if matching for the first time be " adjust " that is directed to this
A text information obtains corresponding as a result, can stop the process of traversal at this time so as to match from word database,
No longer matched for adgust and abjust.Certainly, in practical applications, all monograms can also be replaced
It after alternatively, is all once matched, the multiple results that may finally obtain matching are selected for user.
In the present embodiment, when traversing all monograms, it can not match and obtain in the word database
When target word corresponding with the text information after information correction, it can prompt to use to user feedback miscue information
Family re-types voice messaging.
S4: matching obtains target list corresponding with the text information after information correction from the word database
Word, and the target word is shown to the user.
In the present embodiment, when from the word database matching obtain and text information after information correction
After corresponding target word, the target word can be shown to the user.Specifically, can match described
Word is shown in the user interface of mobile terminal, so as to show matching result to the user.
Referring to Fig. 3, the application also provide it is a kind of word device is looked into based on voice input information, described device includes:
Voice messaging receiving unit 100 includes to be checked in the voice messaging for receiving the voice messaging of user's input
The pronunciation sequence of each letter in word；
Voice recognition unit 200 obtains described to verification certificate for identifying to the pronunciation sequence in the voice messaging
The text information of word；
Matching unit 300, for matching the text information with the word in word database, if the word
Do not have the word to match with the text information in database, information correction is carried out to the text information；
Display unit 400 obtains the text information with after information correction for matching from the word database
Corresponding target word, and the target word is shown to the user.
In the present embodiment, the matching unit includes:
Target letter determining module, for determine the target in the text information letter, wherein the target letter with
Candidate letter is associated；
Alphabetical replacement module, for the candidate letter to be replaced the target letter, and the text envelope that replacement is obtained
Breath is as the text information after information correction；Wherein, it is identical with the pronunciation of the target letter to have part for the candidate letter
Pronunciation syllable.
In the present embodiment, the matching unit further include:
Permutation and combination module, for when the quantity of the target letter in the text information be at least two when, will be each
The candidate letter of target letter carries out permutation and combination, obtains several monograms being made of candidate letter；
Spider module, for traversing the monogram, and replaced with current monogram it is right in the text information
The target letter answered, the text information after obtaining information correction；
Stopping modular, for when from the word database matching obtain it is corresponding with text information after information correction
Target word when, stop traversal process.
Therefore the application, when carrying out looking into word, user can read out the pronunciation of each letter in word to be checked, this
Sample, looks into word app or mobile terminal can receive the voice messaging of the pronunciation sequence comprising each letter.By to the voice
Pronunciation sequence in information is identified, so as to obtain the text information of word to be checked.May include in text information
The each letter identified.In this application, can by text information and the word in the word database that in advance construct into
Row matching.Text information can specifically be carried out to whole word matching, part phrase therein can also be matched.If matching
Failure can carry out information correction to text information.Specifically, the space in text information can be filtered out, and replaces pronunciation
Then similar letter can inquire the text information after information correction again, look into during word so as to improve
Serious forgiveness, and the word that user may expect can be inquired.Therefore technical solution provided by the present application, it can
Conveniently and efficiently looking up words.
Those skilled in the art are supplied to the purpose described to the description of the various embodiments of the application above.It is not
It is intended to exhaustion or be not intended to and limit the invention to single disclosed embodiment.As described above, the application's is various
Substitution and variation will be apparent for above-mentioned technology one of ordinary skill in the art.Therefore, although specifically begging for
Some alternative embodiments are discussed, but other embodiment will be apparent or those skilled in the art are opposite
It is easy to obtain.The application is intended to include all substitutions of the invention discussed herein, modification and variation, and falls in
Other embodiment in the spirit and scope of above-mentioned application.
Claims (10)
1. a kind of look into word method based on voice input information, which is characterized in that the described method includes:
The voice messaging of user's input is received, includes the pronunciation sequence of each letter in word to be checked in the voice messaging；
Pronunciation sequence in the voice messaging is identified, the text information of the word to be checked is obtained；
The text information is matched with the word in word database, if do not have in the word database with it is described
The word that text information matches carries out information correction to the text information；
It is matched from the word database and obtains target word corresponding with the text information after information correction, and to
The user shows the target word.
2. the method according to claim 1, wherein the method also includes:
If having the word to match with the text information in the word database, by the word to match to described
User shows.
3. the method according to claim 1, wherein including: to text information progress information correction
It whether detects in the text information comprising space character, and if it exists, filter the space character from the text information, obtain
Text information after to information correction.
4. the method according to claim 1, wherein including: to text information progress information correction
Determine the target letter in the text information, wherein the target letter is associated with candidate letter；
The candidate letter is replaced into the target letter, and the text information that replacement is obtained is as the text after information correction
Information；Wherein, the candidate letter and the pronunciation of the target letter have the identical pronunciation syllable in part.
5. according to the method described in claim 4, it is characterized in that, when the quantity of the target letter in the text information is extremely
When two few, the method also includes:
The candidate letter of each target letter is subjected to permutation and combination, obtains several monograms being made of candidate letter；
The monogram is traversed, and replaces corresponding target letter in the text information with current monogram, is obtained
Text information after information correction；
When matching obtains target word corresponding with the text information after information correction from the word database, stop
The process of traversal.
6. according to the method described in claim 5, it is characterized in that, the method also includes:
When traversing all monograms, it can not match and obtain and the text envelope after information correction in the word database
When the corresponding target word of manner of breathing, to user feedback miscue information.
7. the method according to claim 1, wherein the word in the word database includes preset quantity
Field, wherein the field includes at least one of entry identification field, word content field, word paraphrase field；
Correspondingly, the text information match with the word in word database include:
Word to be matched is selected from the word database, and reads the word content word in the word to be matched
Section；
Information in the word content field of reading is matched with the text information.
8. a kind of look into word device based on voice input information, which is characterized in that described device includes:
Voice messaging receiving unit includes in word to be checked in the voice messaging for receiving the voice messaging of user's input
The pronunciation sequence of each letter；
Voice recognition unit obtains the text of the word to be checked for identifying to the pronunciation sequence in the voice messaging
This information；
Matching unit, for matching the text information with the word in word database, if the word database
In do not have the word to match with the text information, to the text information carry out information correction；
Display unit, for from the word database matching obtain it is corresponding with the text information after information correction
Target word, and the target word is shown to the user.
9. device according to claim 8, which is characterized in that the matching unit includes:
Target letter determining module, for determining the letter of the target in the text information, wherein the target letter and candidate
Letter is associated；
Alphabetical replacement module, for the candidate letter to be replaced the target letter, and the text information that replacement is obtained is made
For the text information after information correction；Wherein, the candidate letter and the pronunciation of the target letter have the identical hair in part
Sound syllable.
10. device according to claim 9, which is characterized in that the matching unit further include:
Permutation and combination module, for when the quantity of the target letter in the text information be at least two when, by each target
The candidate letter of letter carries out permutation and combination, obtains several monograms being made of candidate letter；
Spider module for traversing the monogram, and is replaced with current monogram corresponding in the text information
Target letter, the text information after obtaining information correction；
Stopping modular, for when from the word database matching obtain mesh corresponding with text information after information correction
When marking word, stop the process of traversal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710983040.6A CN110019667A (en) | 2017-10-20 | 2017-10-20 | It is a kind of that word method and device is looked into based on voice input information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710983040.6A CN110019667A (en) | 2017-10-20 | 2017-10-20 | It is a kind of that word method and device is looked into based on voice input information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110019667A true CN110019667A (en) | 2019-07-16 |
Family
ID=67186692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710983040.6A Pending CN110019667A (en) | 2017-10-20 | 2017-10-20 | It is a kind of that word method and device is looked into based on voice input information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110019667A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113420734A (en) * | 2021-08-23 | 2021-09-21 | 东华理工大学南昌校区 | English character input method and English character input system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN88101389A (en) * | 1987-03-16 | 1988-10-05 | 日本电气株式会社 | Knowledge data base formula Chinese words processor |
| KR100330552B1 (en) * | 1997-09-24 | 2002-05-10 | 임형택 | Method and apparatus for searching and displaying data |
| US20070255570A1 (en) * | 2006-04-26 | 2007-11-01 | Annaz Fawaz Y | Multi-platform visual pronunciation dictionary |
| CN101218625A (en) * | 2005-07-07 | 2008-07-09 | 国际商业机器公司 | Dictionary lookup for mobile devices using spelling recognition |
| CN101645190A (en) * | 2009-07-22 | 2010-02-10 | 合肥讯飞数码科技有限公司 | Word inquiring system and inquiring system method thereof |
| CN102201235A (en) * | 2010-03-26 | 2011-09-28 | 三菱电机株式会社 | Method and system for constructing pronunciation dictionaries |
| CN102298577A (en) * | 2011-09-21 | 2011-12-28 | 深圳市万兴软件有限公司 | Method and device for detecting spelling of document edition |
| CN105096945A (en) * | 2015-08-31 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Voice recognition method and voice recognition device for terminal |
| CN107169067A (en) * | 2017-05-05 | 2017-09-15 | 上海明数数字出版科技有限公司 | The dictionary picking up method and system of a kind of utilization speech polling Chinese character |
-
2017
- 2017-10-20 CN CN201710983040.6A patent/CN110019667A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN88101389A (en) * | 1987-03-16 | 1988-10-05 | 日本电气株式会社 | Knowledge data base formula Chinese words processor |
| KR100330552B1 (en) * | 1997-09-24 | 2002-05-10 | 임형택 | Method and apparatus for searching and displaying data |
| CN101218625A (en) * | 2005-07-07 | 2008-07-09 | 国际商业机器公司 | Dictionary lookup for mobile devices using spelling recognition |
| US20070255570A1 (en) * | 2006-04-26 | 2007-11-01 | Annaz Fawaz Y | Multi-platform visual pronunciation dictionary |
| CN101645190A (en) * | 2009-07-22 | 2010-02-10 | 合肥讯飞数码科技有限公司 | Word inquiring system and inquiring system method thereof |
| CN102201235A (en) * | 2010-03-26 | 2011-09-28 | 三菱电机株式会社 | Method and system for constructing pronunciation dictionaries |
| CN102298577A (en) * | 2011-09-21 | 2011-12-28 | 深圳市万兴软件有限公司 | Method and device for detecting spelling of document edition |
| CN105096945A (en) * | 2015-08-31 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Voice recognition method and voice recognition device for terminal |
| CN107169067A (en) * | 2017-05-05 | 2017-09-15 | 上海明数数字出版科技有限公司 | The dictionary picking up method and system of a kind of utilization speech polling Chinese character |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113420734A (en) * | 2021-08-23 | 2021-09-21 | 东华理工大学南昌校区 | English character input method and English character input system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10528670B2 (en) | Amendment source-positioning method and apparatus, computer device and readable medium | |
| US20140244258A1 (en) | Speech recognition method of sentence having multiple instructions | |
| US20140278426A1 (en) | Data shredding for speech recognition acoustic model training under data retention restrictions | |
| CN102033879A (en) | Method and device for identifying Chinese name | |
| CN104423623B (en) | It is a kind of to select word treatment method and electronic equipment | |
| US11086913B2 (en) | Named entity recognition from short unstructured text | |
| CN104135577A (en) | Method and device for quickly finding contact persons based on user-defined voice | |
| CN112580339B (en) | Model training method and device, electronic equipment and storage medium | |
| CN104866308A (en) | Scenario image generation method and apparatus | |
| CN114556328A (en) | Data processing method and device, electronic equipment and storage medium | |
| US20120109633A1 (en) | Method and system for diacritizing arabic language text | |
| CN112541095B (en) | Video title generation method and device, electronic equipment and storage medium | |
| CN111369980A (en) | Voice detection method and device, electronic equipment and storage medium | |
| CN1359514A (en) | Multimodal data input device | |
| CN111523532A (en) | Method for correcting OCR character recognition error and terminal equipment | |
| KR102536944B1 (en) | Method and apparatus for speech signal processing | |
| CN110728156A (en) | Translation method and device, electronic equipment and readable storage medium | |
| KR102166102B1 (en) | Device and storage medium for protecting privacy information | |
| US20220139386A1 (en) | System and method for chinese punctuation restoration using sub-character information | |
| CN110019667A (en) | It is a kind of that word method and device is looked into based on voice input information | |
| CN110516125B (en) | Method, device and equipment for identifying abnormal character string and readable storage medium | |
| CN109741750A (en) | A kind of method of speech recognition, document handling method and terminal device | |
| US8116338B2 (en) | Method for reducing errors while transferring tokens to and from people | |
| CN109002454B (en) | Method and electronic equipment for determining spelling partition of target word | |
| US20130289974A1 (en) | Chinese character information processing method and chinese character information processing device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190716 |
|
| RJ01 | Rejection of invention patent application after publication |