CN101079268A - System and method for sign language synthesis and display - Google Patents
System and method for sign language synthesis and display Download PDFInfo
- Publication number
- CN101079268A CN101079268A CNA2006100645577A CN200610064557A CN101079268A CN 101079268 A CN101079268 A CN 101079268A CN A2006100645577 A CNA2006100645577 A CN A2006100645577A CN 200610064557 A CN200610064557 A CN 200610064557A CN 101079268 A CN101079268 A CN 101079268A
- Authority
- CN
- China
- Prior art keywords
- sign language
- sign
- language
- module
- natural language
- 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
Images
Landscapes
- Machine Translation (AREA)
Abstract
The invention discloses a gesture synthesizing and displaying system and method, which comprises the following parts: receiving mode, connecting receiving mode and synthetic mode of natural language vocabulary group, display mode of connecting synthetic mode, wherein the receiving mode receives the text information of natural language; the analyzing mode analyzes the text information; the transmitting mode transmits the test vocabulary into gesture code; the synthetic mode transmits the gesture code sequence into gesture moving data; the display mode is used to display the gesture movement. The invention can eliminate the difference and dispose the word for natural language text information, which is convenient to read and understand the natural language test information for valid.
Description
Technical field
The present invention relates to sign language synthetic with the system and method that shows, more particularly, relate to the system and method that text message with natural language converts sign language to and shows sign language motion.
Background technology
According to the update statistical description, China's hearing and speech deformity occupies first of the five big deformity such as with visual disabilities, that limb is residual, intelligence is residual, is 2,057 ten thousand people, accounts for 1.67% of Chinese population sum.The hearing disabilities people be owing to can't correct own pronunciation, cause speaking or the structure sound unclear, even linguistic function completely loses (hearing and speech deformity), and the obstacle of hearing and speech has influenced them and is familiar with the ability of literal, reading literal.
Sign language is a kind of human motion language, expresses the meaning by the motion of hand, is mainly used in the mutual interchange between the deaf person.The Chinese government promotes the interchange between them for being concerned about the deaf person, as far back as later stage the 1950's, has just begun the standardization work of Chinese deaf person's sign language.By 1994, " the general sign language sketch of deaf person " (4 volumes, a sign language sketch surplus in the of 2000), " Chinese sign language " (3330 entries), " Chinese sign language " sequel (2266 entries) had been published once.
Along with information-based high speed development, increasing information represents with forms such as digitized text, pictures that all increasing the interchange all undertaken by the internet.According to the data gained in " the 18 China Internet network state of development statistical report ", by on June 30th, 2006, Chinese netizen's total number of persons surpassed 1.2 hundred million; According to the data of Tentent Science company limited, by in Dec, 2006, registered user's number of Instant Messenger (IM) software QQ just reaches 5.7 hundred million.Though there is not the deaf-mute's ratio among the concrete data presentation netizen or among the Instant Messenger (IM) software user, can estimate that deaf and dumb number wherein is quite huge.How digitized natural language text information translation is become the sign language form, allow the deaf-mute understand the expressed content of text message better, help the deaf person to participate in every social activities (as watching TV), have important application and social effect.Be of great immediate significance.
The synthetic purpose of sign language is translated into deaf person's sign language automatically with the natural language text sentence exactly, and is shown realistically by the visual human of computing machine generation, is Intelligent Human-Machine Interface's a important subject.The synthetic research of sign language starts from nineteen eighty-two, and Shantz and Poizner have realized the computer program of a synthetic ASL.Afterwards, many countries such as China, the U.S., Japan, Germany have all carried out the sign language study on the synthesis of own country, and have obtained many important achievements in research.
Chinese patent 99121570.2 discloses a kind of " electronic type sign language dictionary and its sign language querying method ", and this invention can be inquired about sign language vocabulary easily.But this inquiry is based on word and speech, can't directly inquire about sentence, and certain limitation is arranged.
Summary of the invention
The technical problem to be solved in the present invention is, at the above-mentioned defective that can only carry out the sign language inquiry based on word, speech of prior art, provides a kind of system and method that sign language is synthetic and show that carries out based on sentence.
According to an aspect of the present invention, the invention provides a kind of system that sign language is synthetic and show that carries out, comprise the receiver module that is used to receive natural language text information, with natural language convert to the sign language sign indicating number modular converter, be used to show the sign language display module, also comprise:
The natural language vocabulary storehouse that is connected the analysis module between described receiver module and the described modular converter and is connected with described analysis module, described analysis module carries out analyzing and processing according to the content in described natural language vocabulary storehouse to the text message that is received;
The transformation rule storehouse that is connected with described modular converter, described modular converter convert the natural language after handling by analysis to sign language sign indicating number sequence according to transformation rule;
The sign language vocabulary storehouse that is connected the synthesis module between described modular converter and the described display module and is connected with described synthesis module, described synthesis module converts sign language sign indicating number sequence to the sign language motion data according to described sign language vocabulary storehouse;
Described display module is according to described sign language motion data generation and show complete sign language motion.
In system of the present invention, described receiver module is connected with instant communication client and receives text message from described instant communication client.
In system of the present invention, described analysis module uses maximum matching method that the text message that is received is carried out participle.
In system of the present invention, described analysis module uses forward maximum matching method and reverse maximum matching method that the text message that is received is carried out the disambiguation check.
In system of the present invention, described synthesis module also comprises carrying out the functional unit of linear interpolation between the frame of sign language motion and the frame.
In system of the present invention, described display module shows sign language motion in the mode of 3D.
In system of the present invention, described display module shows sign language motion in the mode of 2D.
According to a further aspect in the invention, provide a kind of method that sign language is synthetic and show of carrying out, may further comprise the steps:
S1, receiver module receive natural language text information;
S2, analysis module carry out analyzing and processing according to the natural language vocabulary storehouse to the text message that is received;
S3, modular converter convert the text message after the above-mentioned processing by analysis to sign language sign indicating number sequence according to transformation rule;
S4, synthesis module convert sign language sign indicating number sequence to the sign language motion data according to described sign language vocabulary storehouse;
S5, display module generate according to described sign language motion data and show complete sign language motion.
In method of the present invention, further comprise among the step S1 by the internet receiving natural language text information.
In method of the present invention, comprise among the step S2 and use maximum matching method to carry out word segmentation processing.
In method of the present invention, comprise among the step S2 and use forward maximum matching method and reverse maximum matching method that the text message that is received is carried out the disambiguation check.
In method of the present invention, further be included among the step S4 between the frame of sign language motion and the frame and carry out linear interpolation.
In method of the present invention, the mode with 3D that further comprises among the step S4 shows sign language motion.
In method of the present invention, the mode with 2D that further comprises among the step S4 shows sign language motion.
Implement of the present invention, have following beneficial effect: the present invention can carry out disambiguation, word segmentation processing to natural language text information comparatively exactly, and the corresponding sign language sign indicating number sequence of conversion shows sign language then, and the people of being convenient to hearing and speech deformity reads, understands natural language text information.
Description of drawings
The invention will be further described below in conjunction with drawings and Examples, in the accompanying drawing:
Fig. 1 carries out the system architecture synoptic diagram that sign language is synthetic and show according to the present invention;
Fig. 2 carries out the method flow diagram that sign language is synthetic and show according to the present invention.
Embodiment
The invention provides a kind of sign language is synthetic and show system and method.Below in conjunction with accompanying drawing the present invention is explained in detail.
The alleged natural language of the present invention is meant a kind of language that develops with culture naturally, for example English, Chinese, Japanese.The alleged natural language of the present invention is the main tool of human interchange and thinking.Be that example is set forth the present invention with Chinese in the following examples.But the present invention is not limited to Chinese, principle of the present invention can be applied to other natural languages such as English, Japanese in the synthetic and display environment of sign language.
Fig. 1 carries out the system architecture synoptic diagram that sign language is synthetic and show according to the present invention.As shown in Figure 1, the present invention carries out that sign language is synthetic to comprise receiver module 101, analysis module 103, modular converter 105, synthesis module 107, display module 109, natural language vocabulary storehouse 111, transformation rule storehouse 113 and sign language dictionary 115 with the system that shows.Wherein, analysis module 103 connects receiver module 101 and natural language vocabulary storehouse 111; Modular converter 105 connects analysis module 103 and transformation rule storehouse 113; Synthesis module 107 connects modular converter 105 and sign language dictionary 115; Display module 109 connects synthesis module 107.
Chinese is the notation of a pronunciation and meaning combination, and it is made up of voice, vocabulary and grammer three partial elements.China's sign language is the notation of shape justice combination, and language shape, gesture and grammer are the three elements of Chinese sign language.Bilingual all there are differences on expression phychology, basic vocabulary and sentence structure.
Natural language is exactly to replace the word of source language with the symbol of target language to the transfer process of sign language sign indicating number, and the source language tree is converted into the target language structure tree.The position that concrete conversion regime and conversion take place determines that by transformation rule transformation rule is according to the structural difference transition tree structure of source language and target language.In one embodiment, the transformation rule in the transformation rule storehouse 113 comprises:
1, sentence rule
(1) temporal representation rule
The tense of verb indicates by setting up a time reference.All discussion all remain within the time frame of being set up, till the new time is introduced into.Time reference is realized by word or any other time indication such as make a gesture " now ", " today ", " past ", " last year ", " in the future ", " next year ".
(2) various tone sentence expression rules
Written Chinese is represented the tone of sentence by punctuation mark, still, does not represent the gesture of the sentence tone in the Chinese sign language.At this problem,, represent the tone of sentence in the present embodiment with facial expression with reference to the characteristics that the deaf-mute talks.Different facial expressions followed in same sentence, and expression and significance differs widely.We are that example is illustrated with " being him " this simple sentence now.
The interrogative sentence rule
When making a gesture, do the query expression simultaneously: eyes stare at the other side, and eyes are opened wide.Represent " being him? "
The exclamative sentence rule
When making a gesture, do simultaneously and sigh with feeling expression: eye, eyebrow appear sure expression.Increase the weight of gesture motion simultaneously.Expression " is him! "
The declarative sentence rule
Do general expression when making a gesture simultaneously, expression " is him.”
(3) sequence rule of noun and modifier thereof
Noun attribute+noun → noun+noun attribute.
(4) sequence rule of predicate verb and object
Predicate verb+object → object+predicate verb.
(5) interrogative pronoun and by query object rule
Interrogative pronoun+by query object → by query object+interrogative pronoun.
2, word rule
Because the gesture word and the Chinese terms difference quantitatively of Chinese sign language, a large amount of Chinese terms do not have directly corresponding gesture word.At this situation, we have formulated a series of rule that is adapted to word.
(1) default rule
Omit the measure word in the Chinese language text.
(2) related word rule
Related word is beaten with the finger speech assembly.
(3) proper noun rule
The simple expression-form of only beating initial consonant is adopted in the expression name that is well known and the proper noun of place name such as Mao Zedong, Beijing.As use manual alphabet M, and Z, D represents the Mao Zedong, uses manual alphabet B, J represents Beijing.
(4) direct mapping ruler
For the word in the Chinese language text, if in Chinese sign language, there is the situation of direct gesture word correspondence to use this rule.
(5) synonym rule
If the word in the Chinese language text does not have directly corresponding gesture word in Chinese sign language, but the synonym of the word in the Chinese language text has the gesture word of direct correspondence in Chinese sign language, get synon gesture word so and substitute.
(6) spelling,finger alternative rule
For the word in those Chinese language texts, if both there be not directly corresponding gesture word in Chinese sign language, its synon gesture word does not exist yet, and substitutes with spelling,finger so.
(7) structure auxiliary word rule
The structure auxiliary word comprises:,, represent with spelling,finger.
(8) the gesture speech of the expression behavior act that direction of action changes is arranged
This class verb all is a transitive verb in the Chinese rule, and its heel has object.According to the object that its heel has, we are divided into three classes to this verb, and they are respectively that its heel has the first person I, our actional verb; Its heel has the second person you, your actional verb; Its heel have the third person he (she, it), he (she, it) actional verb.For first kind actional verb, the behavior act of gesture word is towards the person of talking; For the second class behavior verb, the behavior act of gesture word is towards the other side who talks with sign language; For the 3rd class behavior verb, the behavior act of gesture word towards talk with sign language both outside direction.
3, Else Rule
(1) the empty rule of book
Represent with the book sky for punctuation marks such as punctuation marks used to enclose the title, single quotation marks, double quotation marks, ellipsis, parenthesis, square bracket.
(2) pause rule
Pause mark, comma are represented with pausing naturally of different interval.
In needs, can also between the frame of the continuous same gesture of sign language motion and frame, can carry out the linear movement interpolation, thereby the action that seamlessly transits gesture changes.Between different sign words,, generally all carry out sport interpolation to seamlessly transit this two kinds of sign language motions owing to generally do not have motion relevance between first frame of the last frame of previous sign words and next sign words.In one embodiment, synthesis module 107 comprises an interpolation calculation unit, is specifically designed to and carries out interpolation processing.
In one embodiment, the viewing area of display module 109 is divided into two parts, and wherein a part shows the natural language text that receiver module 101 is received, and another part shows corresponding sign language motion.
Those skilled in the art will recognize, can make amendment to above-mentioned system to be fit to specific needs.For example, can add the gauge tap of " repetition ", " time-out ",, be convenient to study and understand sign language to repeat showing that sign language or time-out show sign language.
Fig. 2 is that the present invention carries out the method flow diagram that sign language is synthetic and show.In step S201, receiver module 101 receiver modules receive natural language text information.Described reception can be the input that directly receives the user, also can be to receive by the internet, also can be the reception TV subtitling etc. of other modes.In one embodiment, receiver module is connected with Instant Messenger (IM) software, receives the text message of natural language from Instant Messenger (IM) software.
Among the step S203, analysis module 103 carries out analyzing and processing according to the 111 pairs of text messages that received in natural language vocabulary storehouse.
For Chinese, because the minimum component unit of Chinese sentence is a word, and significant minimum unit is a speech, therefore, analysis module 103 at first carries out word segmentation processing to sentence after reading in a Chinese sentence, the word sequence after system's word segmentation processing is decided as fundamental node to be translated, if any the cutting ambiguity, then carry out corresponding disambiguation and handle.
In one embodiment, analysis module 103 uses maximum matching method (Maximum MatchingMethod abbreviates the MM method in this manual as) that sentence is carried out participle.The basic process of MM method is such:
Suppose that speech the longest in the vocabulary is made up of i word, then at every turn from word string that length is i of sentence head intercepting, make that entry mates successively in this word string and the vocabulary, if truly have a such i words in the vocabulary, then the match is successful, just with this word string as a speech cutting from the sentence go out; And then intercept another i word string from the head of sentence remaining part; Repeat said process till sentence is intact by cutting.
Can mate with current word string if in vocabulary, can not find an entry, just leave out a word, in vocabulary, search,, just equally this word string be gone out as speech cutting from sentence if the match is successful with the word string of (i-1) word length from this word string afterbody; If it fails to match, then leave out a word from this word string afterbody, use the word string of (i-2) word length in vocabulary, to inquire about again, until the match is successful.
For example, if the input sentence is " the founding of People's Republic of China ", supposing has " People's Republic of China (PRC) " this speech in the natural language vocabulary storehouse 111, and in the vocabulary the longest speech also be 7 words (promptly, i=7), then just the match is successful from beginning of the sentence 7 word strings of intercepting " People's Republic of China (PRC) " for the first time.After just " People's Republic of China (PRC) " cutting was gone out, the sentence remaining part was " establishment " three word word strings, if there are not 3 such words in the vocabulary, just removes a word of this word string afterbody, obtains " establishment ", and then the match is successful.Be left at last, " " also the match is successful.Arrive this, the participle process finishes.Note, though entries such as " China ", " Chinese ", " people ", " republicanism ", " republic ", " state " are also arranged in the natural language vocabulary storehouse 111, but the principle of MM method is " priority of long word ", therefore " People's Republic of China (PRC) " can be cut into a plurality of phrases.
For some sentence, the MM method can obtain wrong cutting result.For example for sentence " making saves food further becomes a common practice ", the MM method can be cut into sentence " envoy/pact/grain/further/formation/general mood ".In the time of this, just need carry out disambiguation and handle sentence.
The MM method is divided into forward maximum match (FMM) method and reverse maximum matching method (BMM) again.Introduce above in the MM method, being actually with FMM is example.Principle and the FMM of BMM are similar, and different places are that BMM carries out cutting to sentence from right to left, in it fails to match, are to remove a candidate character string word foremost to form new candidate character string.
By using FMM and BMM method that same sentence is carried out cutting, can play the effect of checking the cutting result.Research (Sun Maosong, Benjamin K.T ' sou according to Sun Maosong, Zou Jiayan.AmbiguityResolution in Chinese Word Segmentation, Benjamin K.T ' sou ﹠amp; TomB.Y.Lai (eds) Proceedings of PACL IC-10, Hong Kong, 27-28 Dec., 1995), analyze selecting 3680 sentences in the news language material at random, obtaining conclusion is, in the cutting of FMM and BMM comes to the same thing, has about 99% assurance to think that the cutting result is correct; When the cutting result of FMM and BMM inequality in, nearly 99% assurance thinks that it is correct having a kind of cutting result at least.
In one embodiment, FMM different with BMM cutting result in, analysis module 103 is according in conjunction with context or in conjunction with other factors such as vocabulary frequencies or select a kind of result as the cutting result randomly.
The technician will recognize in the field, and the present invention is not limited to the MM method of using.Analysis module of the present invention can use any method that natural language is analyzed and handled.
Among the step S205, modular converter 105 converts the text message after the above-mentioned processing by analysis to sign language sign indicating number sequence according to the transformation rule in the transformation rule storehouse 115.
In the step 207, synthesis module 107 converts sign language sign indicating number sequence to the sign language motion data according to described sign language vocabulary storehouse 115.In one embodiment, this step also further is included between the frame of same gesture of continuous sign language motion and the frame and can carries out the linear movement interpolation.In another embodiment, this step further is included between first frame of the last frame of previous sign words and next sign words interpolation processing to realize smooth excessiveness.
In the step 209, display module 109 is according to described sign language motion data generation and show complete sign language motion.In one embodiment, display module 109 shows sign language motion with the form of 3D.
The above only is preferred embodiment of the present invention, and is in order to restriction the present invention, within the spirit and principles in the present invention not all, any modification of being done, is equal to replacement, improvement etc.All should be included within protection scope of the present invention.
Claims (10)
1, a kind of carry out sign language synthetic with the system that shows, comprise the receiver module that is used to receive natural language text information, with natural language convert to the sign language sign indicating number modular converter, be used to show the sign language display module, it is characterized in that, also comprise:
The natural language vocabulary storehouse that is connected the analysis module between described receiver module and the described modular converter and is connected with described analysis module, described analysis module carries out analyzing and processing according to the content in described natural language vocabulary storehouse to the text message that is received;
The transformation rule storehouse that is connected with described modular converter, described modular converter convert the natural language after handling by analysis to sign language sign indicating number sequence according to transformation rule;
The sign language vocabulary storehouse that is connected the synthesis module between described modular converter and the described display module and is connected with described synthesis module, described synthesis module converts sign language sign indicating number sequence to the sign language motion data according to described sign language vocabulary storehouse;
Described display module is according to described sign language motion data generation and show complete sign language motion.
2, system according to claim 1 is characterized in that, described receiver module is connected with instant communication client and receives text message from described instant communication client.
3, system according to claim 1 is characterized in that, described analysis module uses maximum matching method that the text message that is received is carried out participle.
4, system according to claim 1 is characterized in that, described analysis module uses forward maximum matching method and reverse maximum matching method that the text message that is received is carried out the disambiguation check.
5, system according to claim 1 is characterized in that, described synthesis module also is included in the functional unit that carries out linear interpolation between the frame of sign language motion and the frame.
6, according to any described system in the claim 1 to 5, it is characterized in that described display module shows sign language motion in the mode of 3D.
7, a kind of based on the described system of claim 1 carry out sign language synthetic with the method that shows, it is characterized in that, may further comprise the steps:
S1, receiver module receive natural language text information;
S2, analysis module carry out analyzing and processing according to the natural language vocabulary storehouse to the text message that is received;
S3, modular converter convert the text message after the above-mentioned processing by analysis to sign language sign indicating number sequence according to transformation rule;
S4, synthesis module convert sign language sign indicating number sequence to the sign language motion data according to described sign language vocabulary storehouse;
S5, display module generate according to described sign language motion data and show complete sign language motion.
8, method according to claim 7 is characterized in that, comprises among the step S2 using maximum matching method to carry out word segmentation processing.
9, method according to claim 7 is characterized in that, comprises among the step S2 using forward maximum matching method and reverse maximum matching method that the text message that is received is carried out the disambiguation check.
10, according to any described method in the claim 7 to 9, it is characterized in that, further be included among the step S4 between the frame of sign language motion and the frame and carry out linear interpolation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2006100645577A CN101079268A (en) | 2006-12-28 | 2006-12-28 | System and method for sign language synthesis and display |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2006100645577A CN101079268A (en) | 2006-12-28 | 2006-12-28 | System and method for sign language synthesis and display |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101079268A true CN101079268A (en) | 2007-11-28 |
Family
ID=38906700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2006100645577A Pending CN101079268A (en) | 2006-12-28 | 2006-12-28 | System and method for sign language synthesis and display |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101079268A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682644A (en) * | 2012-03-26 | 2012-09-19 | 中山大学 | Chinese sign language synthesis system driven by markup language |
| CN102737397A (en) * | 2012-05-25 | 2012-10-17 | 北京工业大学 | Rhythmic head motion synthesis method based on motion deviation mapping |
| CN103854540A (en) * | 2012-11-30 | 2014-06-11 | 英业达科技有限公司 | System for translating texts into sign language and method thereof |
| CN109166409A (en) * | 2018-10-10 | 2019-01-08 | 长沙千博信息技术有限公司 | A kind of sign language conversion method and device |
| CN109409255A (en) * | 2018-10-10 | 2019-03-01 | 长沙千博信息技术有限公司 | A kind of sign language scene generating method and device |
| CN110457673A (en) * | 2019-06-25 | 2019-11-15 | 北京奇艺世纪科技有限公司 | A kind of natural language is converted to the method and device of sign language |
| CN111090998A (en) * | 2018-10-18 | 2020-05-01 | 北京搜狗科技发展有限公司 | Sign language conversion method and device and sign language conversion device |
| CN111369652A (en) * | 2020-02-28 | 2020-07-03 | 长沙千博信息技术有限公司 | Method for generating continuous sign language action based on multiple independent sign language actions |
| CN111414763A (en) * | 2020-02-28 | 2020-07-14 | 长沙千博信息技术有限公司 | Semantic disambiguation method, device, equipment and storage device for sign language calculation |
| CN113326746A (en) * | 2021-05-13 | 2021-08-31 | 中国工商银行股份有限公司 | Sign language broadcasting method and device for human body model |
| CN113689879A (en) * | 2020-05-18 | 2021-11-23 | 北京搜狗科技发展有限公司 | Method, device, electronic equipment and medium for driving virtual human in real time |
-
2006
- 2006-12-28 CN CNA2006100645577A patent/CN101079268A/en active Pending
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682644A (en) * | 2012-03-26 | 2012-09-19 | 中山大学 | Chinese sign language synthesis system driven by markup language |
| CN102682644B (en) * | 2012-03-26 | 2014-04-30 | 中山大学 | Chinese sign language synthesis system driven by markup language |
| CN102737397A (en) * | 2012-05-25 | 2012-10-17 | 北京工业大学 | Rhythmic head motion synthesis method based on motion deviation mapping |
| CN102737397B (en) * | 2012-05-25 | 2015-10-07 | 北京工业大学 | What map based on motion excursion has rhythm head movement synthetic method |
| CN103854540A (en) * | 2012-11-30 | 2014-06-11 | 英业达科技有限公司 | System for translating texts into sign language and method thereof |
| CN109166409A (en) * | 2018-10-10 | 2019-01-08 | 长沙千博信息技术有限公司 | A kind of sign language conversion method and device |
| CN109409255A (en) * | 2018-10-10 | 2019-03-01 | 长沙千博信息技术有限公司 | A kind of sign language scene generating method and device |
| CN111090998A (en) * | 2018-10-18 | 2020-05-01 | 北京搜狗科技发展有限公司 | Sign language conversion method and device and sign language conversion device |
| CN110457673A (en) * | 2019-06-25 | 2019-11-15 | 北京奇艺世纪科技有限公司 | A kind of natural language is converted to the method and device of sign language |
| CN110457673B (en) * | 2019-06-25 | 2023-12-19 | 北京奇艺世纪科技有限公司 | Method and device for converting natural language into sign language |
| CN111369652A (en) * | 2020-02-28 | 2020-07-03 | 长沙千博信息技术有限公司 | Method for generating continuous sign language action based on multiple independent sign language actions |
| CN111414763A (en) * | 2020-02-28 | 2020-07-14 | 长沙千博信息技术有限公司 | Semantic disambiguation method, device, equipment and storage device for sign language calculation |
| CN111369652B (en) * | 2020-02-28 | 2024-04-05 | 长沙千博信息技术有限公司 | Method for generating continuous sign language actions based on multiple independent sign language actions |
| CN113689879A (en) * | 2020-05-18 | 2021-11-23 | 北京搜狗科技发展有限公司 | Method, device, electronic equipment and medium for driving virtual human in real time |
| CN113689879B (en) * | 2020-05-18 | 2024-05-14 | 北京搜狗科技发展有限公司 | Method, device, electronic equipment and medium for driving virtual person in real time |
| CN113326746A (en) * | 2021-05-13 | 2021-08-31 | 中国工商银行股份有限公司 | Sign language broadcasting method and device for human body model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101079268A (en) | System and method for sign language synthesis and display | |
| CN1191514C (en) | System and method for processing chinese language text | |
| CN1205572C (en) | Language input architecture for converting one text form to another text form with minimized typographical errors and conversion errors | |
| CN1159661C (en) | System for Chinese tokenization and named entity recognition | |
| CN1094618C (en) | Method for self-correction of grammar in machine translation | |
| US20050216253A1 (en) | System and method for reverse transliteration using statistical alignment | |
| CN1253820C (en) | Device and method for intercrossing language information retrieval | |
| CN1384940A (en) | Language input architecture fot converting one text form to another text form with modeless entry | |
| CN1542649A (en) | Linguistically informed statistical models of constituent structure for ordering in sentence realization for a natural language generation system | |
| CN1652106A (en) | Machine translation method and apparatus based on language knowledge base | |
| CN1618064A (en) | Translating method, translated sentence inputting method, recording medium, program, and computer device | |
| JP2007087397A (en) | Morphological analysis program, correction program, morphological analyzer, correcting device, morphological analysis method, and correcting method | |
| CN1250189A (en) | Electronic dictionary with function of processing customary wording | |
| CN112633017A (en) | Translation model training method, translation processing method, translation model training device, translation processing equipment and storage medium | |
| CN1316689A (en) | Chinese character input unit and method | |
| CN1702650A (en) | Apparatus and method for translating Japanese into Chinese and computer program product | |
| Al-Barahamtoshy et al. | Arabic text-to-sign (ArTTS) model from automatic SR system | |
| CN86108582A (en) | Shorthand translation system | |
| Kang | Spoken language to sign language translation system based on HamNoSys | |
| CN1108572C (en) | Mechanical Chinese to japanese two-way translating machine | |
| Monga et al. | Speech to Indian Sign Language Translator | |
| CN111401085A (en) | Mobile device machine translation system based on hybrid strategy | |
| CN116089569A (en) | Sample construction method, device, electronic equipment and readable storage medium | |
| CN100337232C (en) | Braille-Chinese contrapositive editing/typesetting system and editing/typesetting method | |
| KR102437008B1 (en) | Apparatus and Method for Providing Translation Service |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Open date: 20071128 |