CN101005574A - Video frequency virtual humance sign language compiling system - Google Patents
Video frequency virtual humance sign language compiling system Download PDFInfo
- Publication number
- CN101005574A CN101005574A CN 200610023380 CN200610023380A CN101005574A CN 101005574 A CN101005574 A CN 101005574A CN 200610023380 CN200610023380 CN 200610023380 CN 200610023380 A CN200610023380 A CN 200610023380A CN 101005574 A CN101005574 A CN 101005574A
- Authority
- CN
- China
- Prior art keywords
- sign language
- text
- integrated circuit
- circuit board
- visual human
- 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
- Television Signal Processing For Recording (AREA)
Abstract
The system comprises: a video signal inputting device; a video signal outputting device; and a central computing device. The central computing device comprises a sign language synthesis module for in translating the inputted program text into sign language data; a virtual man synthesis module for expressing the sign language data by using the virtual man; a non-linear editing card supporting image overlapping function; a voice time length synchronous information acquiring module for recording the initial time and ending time of each sentence text; a main module for controlling the sign language synthesis module to translate the program text into the sign language data that is expressed by the virtual man synthesis module, then controlling the non linear editing card to overlap the sign language image into the program bit-stream, and then to output to the outputting device.
Description
Technical field
The present invention relates to the video program production technology, be specifically related to a kind of video frequency program virtual humance sign language compiling system.
Background technology
China's TV network development rapidly, and is very flourishing at present, only is that the TV stations at different levels that possess certain coverage and economic strength just have more than 1000.All there be news and feature program even the news channel of managing by oneself in these TV stations, deaf and dumb or the person hard of hearing that has suitable number among its spectators, consider this part crowd's rating needs, a lot of TV stations have all founded the column of news in Sign Language and so on, but the way of taking at present all is to finish the conversion of sign language with manpower, and how adding sign language and show when news is replayed, therefore, is ageing and accuracy and the normalized degree of sign language all have many deficiencies.Although some TV play and TV programme attempt to provide convenience in the understanding with the captions form for these have the dysaudia crowd in the recent period, yet, on speech habits and acceptance level, still not the best means that is fit to these special populations.Practice shows, increases virtual host a kind of effective means of can yet be regarded as in TV programme.
Virtual host of the prior art is broadly divided into virtual host of TV and network virtual host.No matter be virtual host of TV or network virtual host, its report mode roughly can be divided into real-time with non real-time two kinds.Non real-time virtual host's program can complete by the backstage, just can be used as common television program transmission afterwards.And real-time virtual host's program need be by motion tracking equipment Real Time Drive, or based on artificial intelligence technology by the text Real Time Drive.
Domestic present most of virtual host's program generally is a non real-time, extensive work need be finished by post-production, can't satisfy of the real-time requirement of broadcasting and TV system to news in Sign Language, certainly at present also have by by motion tracking equipment Real Time Drive, but require each issue program making all must have true people performing, thereby need to drop into great amount of manpower and material resources with the driving visual human.
Summary of the invention
The object of the present invention is to provide a kind of video frequency program virtual humance sign language compiling system, realize the real-time manufacturing of visual human's sign language video frequency program, make it can reach the requirement that the broadcasting and TV program broadcasts, synthesize to promote sign language and to serve the broadcasting and TV program that numerous deaf persons are purpose.
The object of the present invention is achieved like this:
Video frequency virtual humance sign language compiling system of the present invention comprises video input apparatus, picture output device, and the maincenter computing equipment comprises in this maincenter computing equipment:
The sign language synthesis module is used for the program text of input equipment input is translated into the sign language data;
Visual human's synthesis module is used for described sign language data are expressed by the visual human;
Support the non-linear editing integrated circuit board of overplay;
Voice duration synchronizing information acquisition module writes down the pairing initial sum termination time of each text;
Primary module, text sentence according to the voice duration information synchronization call correspondence of being obtained, translate into the sign language data by the sign language synthesis module, express by the visual human by visual human's synthesis module again, and by the non-linear editing integrated circuit board sign language picture frame is added in the program stream, the program stream that the language picture frame is received and distributed in stack outputs to output equipment by the non-linear editing integrated circuit board.
Above-mentioned video frequency virtual humance sign language compiling system, wherein, described input equipment can be player or VCD or DVD, and described output equipment can be television set or video tape recorder or computer monitor, and described maincenter computing equipment can be computer or industrial computer.
Wherein, input equipment can be by S terminal or the input of composite signal input mode; Output equipment also can be by S terminal or the output of the composite signal way of output.
Above-mentioned video frequency virtual humance sign language compiling system, wherein, the non-linear editing integrated circuit board of supporting overplay can be all kinds of on the market specialties video non-linear editing integrated circuit boards, supports the real-time stack of picture frame, support the input and output of S terminal, support the input and output of composite signal.
Above-mentioned video frequency virtual humance sign language compiling system, wherein, the generation true to nature of described three-dimensional human model has been based on that visual human's synthetic technology of open report realizes.[see " computer-aided design and graphics journal ", No.1,2004, " a kind of personalized virtual human body model skeleton generation method ", human body Modeling Research based on VRML, the Computer Simulation journal, 2004 1 phases and http://vh.ict.ac.cn etc.], based on this series technique, we make visual human's model with 3D MAX D modeling tool, be output as the vrml file of standard then, adopt the OpenGL technology to read this document then, and in other scene, carry out the synthetic of visual human and show.
Above-mentioned video frequency virtual humance sign language compiling system, wherein, described visual human's sign language is true to nature synthetic. and be based on the open Chinese sign language synthetic technology of reporting and [see " software journal ", Vol.13, No.10, " based on the Chinese sign language synthetic method of visual human's synthetic technology ", http://sy.jdl.ac.cn etc.], this technology has realized text translation is become the Chinese Industrial Standards (CIS) sign language.It is to set up a high-quality sign language motion database earlier, then input text is carried out the translation of word to the sign language data, then continuous sign language data is spliced, and forms smooth Chinese Industrial Standards (CIS) sign language at last and expresses by the visual human.
Above-mentioned video frequency virtual humance sign language compiling system, wherein, described voice and sign language captions synchronizing information are obtained, and are the modes by artificial " bat libretto ", obtain the pairing time span information of all text sentences of video, be convenient to the later stage according to the synthetic sign language of duration information.Detailed process is: program source is imported from input equipments such as VCD or DVD, by being positioned at the non-volume integrated circuit board of computer, deliver to the software primary module, through after the processing of software, be sent to the delivery outlet of non-volume integrated circuit board again, received and play back by output equipments such as television sets.The staff watches program by output equipments such as television sets on one side, in the place of needs pat a lower keyboard on one side, make software records get off pairing zero-time of each text (drama) and termination time.Whole program finishes, and the pairing initial sum termination time of the text of all programs has also just obtained, and just the synchronous duration information of voice and sign language has obtained.This kind mode is also referred to as " bat libretto " mode.
Above-mentioned video frequency virtual humance sign language compiling system, wherein, primary module plays unified scheduling effect, be on the basis of and nonlinear editing system synthetic in existing visual human's sign language, standard and every technical requirement according to video, the video of realizing visual human's sign language true to nature shows, makes visual human's sign language video display image can reach real-time generation, and the sign language picture is synthesized in the video frequency program.Its flow process is: according to the text sentence of the voice duration information synchronization call correspondence of being obtained, translate into the sign language data by the sign language synthesis module, express by the visual human by visual human's synthesis module again, and the sign language picture frame is added in the program stream by the non-linear editing integrated circuit board.
The present invention also provides a kind of method of utilizing described video frequency virtual humance sign language compiling system to carry out video visual human sign language editor, may further comprise the steps:
1) video input apparatus input program text, voice synchronous information acquisition module writes down the pairing initial sum termination time of each text;
2) primary module has access to program stream by the non-linear editing integrated circuit board, and according to the text sentence of the duration information synchronization call correspondence of being obtained;
3) the sign language synthesis module becomes the sign language data with text sentence translation;
4) visual human's synthesis module is expressed the sign language data of translating into by the visual human;
5) by the non-linear editing integrated circuit board sign language picture frame is added in the program stream;
6) stack receive and distribute the language picture frame program stream output to output equipment by the non-linear editing integrated circuit board.
Video frequency virtual humance sign language compiling system of the present invention and method can be used for the making of TV programme or Internet video program.
Video frequency virtual humance sign language compiling system of the present invention makes it compared with prior art owing to adopted above-mentioned technical scheme, has following advantage and good effect:
System and method of the present invention can more synthetic in video frequency program, stack sign language.The sign language teacher employs in the present TV station that compares, and has the efficient height, less investment, and cost is low, uses characteristics such as risk is little.Not only can save spendings such as engaging the needed human and material resources of sign language teacher for TV station, can also save the program making time of a large amount of preciousnesses, and easy to use, possess Real Time Drive, real-time rendering, automation modeling, strong sense of reality, characteristics such as the property understood height.
Description of drawings
By the description of following embodiment to video frequency virtual humance sign language compiling system of the present invention, can further understand purpose, specific structural features and the advantage of its invention in conjunction with its accompanying drawing.Wherein, accompanying drawing is:
Fig. 1 is the structured flowchart of video frequency virtual humance sign language compiling system of the present invention;
Fig. 2 is the structural representation of a kind of operating mode of video frequency virtual humance sign language compiling system hardware device of the present invention;
Fig. 3 is the structural representation of the another kind of operating mode of video frequency virtual humance sign language compiling system hardware device of the present invention;
Fig. 4 is that the synchronous duration information of voice of the present invention, sign language extracts the workflow block diagram;
Fig. 5 is synthetic and stack workflow block diagram for sign language of the present invention.
Embodiment
The present invention is based on the technology of openly having reported before following two projects and a cover video visual human's sign language captions adding system and a method of inventing.
Wherein, one is: visual human's synthetic technology [is seen " computer-aided design and graphics journal ", No.1,2004, " a kind of personalized virtual human body model skeleton generation method " is based on the human body Modeling Research of VRML, Computer Simulation journal, 2004 1 phases and http://vh.ict.ac.cn etc.], this technology has realized visual human's synthetic and demonstration on computers.Another is: Chinese sign language synthetic technology [seeing " software journal ", Vol.13, No.10, " based on the Chinese sign language synthetic method of visual human's synthetic technology ", http://sy.jdl.ac.cn etc.], this technology has realized text translation is become the Chinese Industrial Standards (CIS) sign language.
Major function of the present invention is that the program text content is translated into sign language automatically, and in the TV programme that is added to.Deaf-mute's TV reception be can either fundamentally make things convenient for, can also a large amount of human and material resources and valuable program making time be saved for TV station.Below with the television program designing be example the invention will be further elaborated, the present invention also can be used for the making of other video frequency program certainly, such as Internet video broadcasting or the like.
(1) system configuration.Referring to system architecture diagram of the present invention shown in Figure 1, video frequency virtual humance sign language compiling system of the present invention is constituted by hardware and software two parts.
1) hardware.Comprise: input equipment, output equipment, maincenter computing equipment, non-volume integrated circuit board;
Because the standard of TV signal is unified, so its input equipment can be VCD, DVD, all kinds of players etc.Can export two kinds of standard signal PAL or NTSC.The present invention has used VCD or DVD as input equipment.
Output signal of the present invention also can be a standard television signal, supports PAL and two kinds of standards of TSC-system, so output equipment of the present invention can be television set or video tape recorder or the broadcasting and TV dedicated monitor and the computer monitor etc. of various brands.
Maincenter computing equipment of the present invention can be to be provided with embedded non-linear editing integrated circuit board in computer or industrial computer, the main frame.Because this non-volume integrated circuit board is a non-linear editing integrated circuit board general in the prior art, be respectively equipped with S input, lead-out terminal on the non-volume integrated circuit board; Also be provided with composite signal input, lead-out terminal simultaneously.Therefore, for the present invention,, can use as long as non-volume integrated circuit board can be supported overplay.Computer then adopts general purpose PC or industrial computer, and operating system can be WindowsXP series.
The continuous Fig. 1 that sees also, S terminal of the present invention and composite signaling adopt general-purpose interface, and therefore, all input equipments all can be by the input of S terminal input mode; All output equipments also can be by the output of the S terminal way of output.
As shown in Figure 2, program source from input equipment VCD1 or DVD1, by being arranged on the S terminal 11 on VCD1 or the DVD1, transfer to through lead X1 and to be embedded the input 41a on the non-volume integrated circuit board 4 in the main frame 21 of computer 2 or industrial computer 2, transfer to the input 31 of video recording, watch-dog 3 through lead X2 by being embedded in the main frame 21 of computer 2 or the industrial computer 2 output 41b on the non-volume integrated circuit board 4 again.Display 22 by the non-linear editing integrated circuit board 4 on the main frame 21 that is arranged on computer 2 or industrial computer 2 and computer 2 or industrial computer 2 and operate in software in the computer, realize the stack of sign language picture, finally by video recording, watch-dog 3 is monitored and record a video.
The continuous Fig. 1 that sees also, all input equipments also can be by the inputs of composite signal input mode; All output equipments also can be by the output of the composite signal way of output.
As shown in Figure 3, program source from input equipment VCD1 or DVD1, by being arranged on the composite signal input terminal 12 on VCD1 or the DVD1, transfer to through lead X1 and to be embedded the compound input terminal 42a on the non-volume integrated circuit board 4 in the main frame 21 of computer 2 or industrial computer 2, transfer to the compound input 32 of video recording, watch-dog 3 through lead X2 by being embedded in the main frame 21 of computer 2 or the industrial computer 2 composite signal lead-out terminal 42b on the non-volume integrated circuit board 4 again.Display 22 by the non-linear editing integrated circuit board 4 on the main frame 21 that is arranged on computer 2 or industrial computer 2 and computer 2 or industrial computer 2 and operate in software in the computer, realize the stack of sign language picture, finally by video recording, watch-dog 3 is monitored and record a video.
2) software.Comprise:
The sign language synthesis module is used for the program text of input equipment input is translated into the sign language data;
Visual human's synthesis module is used for described sign language data are expressed by the visual human;
Voice duration synchronizing information acquisition module writes down the pairing initial sum termination time of each text;
Primary module, text sentence according to the voice duration information synchronization call correspondence of being obtained, translate into the sign language data by the sign language synthesis module, express by the visual human by visual human's synthesis module again, and by the non-linear editing integrated circuit board sign language picture frame is added in the program stream, the program stream that the language picture frame is received and distributed in stack outputs to output equipment by the non-linear editing integrated circuit board.
This software is based on Windows series operating system, with the exploitation of Visual C++6.0 developing instrument.
(2) course of work of whole system of the present invention
Be divided into two stages substantially:
Phase I: voice and sign language captions synchronizing information are obtained the stage;
Voice synchronous information of the present invention is obtained, and is the mode by artificial " bat libretto ", obtains the pairing time span information of all text sentences of video frequency program, is convenient to the later stage according to the synthetic Chinese sign language of duration information.Be similar to TV station's text subtitle additive process, on one side broadcast program, on one side by manually watching program, and writing time the position.
Second stage: synthetic automatically sign language of system and stack are shown to the TV programme stage.
Visual human's sign language video superimpose of the present invention shows, be synthetic existing visual human, sign language is synthetic and the basis of nonlinear editing system on, standard and every technical requirement according to TV programme, the video of realizing visual human's sign language true to nature shows, make visual human's sign language video display image can reach real-time generation, generate to satisfy 50 (PAL) resolution 200*200 of 25 frame per seconds picture, and with in the synthetic TV programme that is added to of sign language picture.Detailed process is: realize the sign language complex functionality specially by the sign language synthesis module, input is a text, and output is the sign language picture frame.The sign language complex functionality has had corresponding open report [seeing " software journal ", Vol.13, No.10, " based on the Chinese sign language synthetic method of visual human's synthetic technology " etc.].Primary module has access to program stream by non-volume integrated circuit board, temporal information and the previous duration synchronizing information that obtains according to program stream, the moment in appointment is read corresponding text, be transported to the sign language synthesis module, the sign language synthesis module returns corresponding sign language picture frame in time, by primary module the editting function of picture frame by non-volume integrated circuit board is added to and goes in the program stream.The program stream that the language picture frame is received and distributed in stack outputs to output equipment by non-volume integrated circuit board, watches, monitors in real time and final performance recording.
When the present invention was added to the sign language picture frame in the program stream, employed function was supported by non-volume integrated circuit board, according to the exploitation operation instructions of non-volume integrated circuit board, can realize this point easily in program.Sign language frame picture can be superimposed upon the lower right corner of whole TV programme, also can be superimposed upon other suitable position.
Fig. 4 obtains the workflow block diagram for voice synchronous duration information of the present invention; At first software is transferred to the synchronizing information obtaining mode.TV programme by being positioned at the non-volume integrated circuit board of computer, is delivered to the software primary module from the input of input equipments such as VCD or DVD.The staff watches program by output equipments such as television set or video tape recorder or broadcasting and TV dedicated monitor, pat a lower keyboard in the place that voice occur, make the software records pairing zero-time of each text (drama) of getting off, by the time after this voice finish, pat the termination time that keyboard writes down this text again.Whole program finishes, and the corresponding initial sum termination time of text of all programs has also just obtained, and just the synchronous duration information of voice and sign language has obtained.
Fig. 5 is synthetic and stack workflow block diagram for sign language of the present invention, and after having obtained the synchronous duration information of voice and sign language, from the beginning the staff plays TV programme one time again, at this moment software will be transferred to sign language captions overlay model.The software primary module obtains the temporal information of program stream by non-volume integrated circuit board, patting the time that obtains with the front then compares, so just can guarantee to go out the moment of realize voice at program, software will call the corresponding text sentence, and it is delivered to the sign language synthesis module, after the sign language synthesis module returns the sign language picture frame, function by non-volume integrated circuit board is added to the sign language captions in the program stream, and output to output equipment, record, institute's recorded program has just increased the sign language captions newly on original program basis.Playing programs finishes and promptly comes to an end.So far, just realized purpose of the present invention.
The present invention can realize the voice and the sign language subtitle superposition of all kinds of video frequency programs, is particularly useful for the voice and the sign language subtitle superposition of news category TV programme.
Claims (5)
1, video frequency virtual humance sign language compiling system comprises video input apparatus, picture output device, and the maincenter computing equipment comprises in this maincenter computing equipment:
The sign language synthesis module is used for the program text of input equipment input is translated into the sign language data;
Visual human's synthesis module is used for described sign language data are expressed by the visual human;
Support the non-linear editing integrated circuit board of overplay;
It is characterized in that: also comprise in this maincenter computing equipment:
Voice duration synchronizing information acquisition module obtains and writes down the pairing initial sum termination time of each text;
Primary module, text sentence according to the voice duration information synchronization call correspondence of being obtained, translate into the sign language data by the sign language synthesis module, express by the visual human by visual human's synthesis module again, and by the non-linear editing integrated circuit board sign language picture frame is added in the program stream, the program stream that the language picture frame is received and distributed in stack outputs to output equipment by the non-linear editing integrated circuit board.
2, video frequency virtual humance sign language compiling system as claimed in claim 1 is characterized in that: described voice duration synchronizing information acquisition module is that the mode by artificial " bat libretto " obtains the pairing time span information of TV programme text sentence.
3, video frequency virtual humance sign language compiling system as claimed in claim 2, it is characterized in that: described input equipment can be player or VCD or DVD, described output equipment can be television set or video tape recorder or computer monitor, and described maincenter computing equipment can be computer or industrial computer.
4, utilize the described video frequency virtual humance sign language compiling system of claim 1 to carry out video visual human sign language editor's method, may further comprise the steps:
1) video input apparatus input program text, voice synchronous information acquisition module writes down the pairing initial sum termination time of each text;
2) primary module has access to program stream by the non-linear editing integrated circuit board, and according to the text sentence of the duration information synchronization call correspondence of being obtained;
3) the sign language synthesis module becomes the sign language data with text sentence translation;
4) visual human's synthesis module is expressed the sign language data of translating into by the visual human;
5) by the non-linear editing integrated circuit board sign language picture frame is added in the program stream;
6) stack receive and distribute the language picture frame program stream output to output equipment by the non-linear editing integrated circuit board.
5, video visual human sign language editor's as claimed in claim 4 method, described synchronizing information are to obtain by the mode of artificial " bat libretto ".
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200610023380 CN101005574A (en) | 2006-01-17 | 2006-01-17 | Video frequency virtual humance sign language compiling system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200610023380 CN101005574A (en) | 2006-01-17 | 2006-01-17 | Video frequency virtual humance sign language compiling system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101005574A true CN101005574A (en) | 2007-07-25 |
Family
ID=38704404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200610023380 Pending CN101005574A (en) | 2006-01-17 | 2006-01-17 | Video frequency virtual humance sign language compiling system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101005574A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100518253C (en) * | 2007-11-19 | 2009-07-22 | 新奥特（北京）视频技术有限公司 | A manuscript writing system |
| CN100544409C (en) * | 2007-11-19 | 2009-09-23 | 新奥特（北京）视频技术有限公司 | A kind of figure record and broadcast method of serving as theme and driving with manuscript |
| CN100558146C (en) * | 2007-11-19 | 2009-11-04 | 新奥特（北京）视频技术有限公司 | A kind of figure manufacturing-broadcasting system of serving as theme and driving with manuscript |
| CN101188023B (en) * | 2007-11-19 | 2010-06-02 | 新奥特（北京）视频技术有限公司 | A method for making drawing in writing manuscript |
| CN101588457B (en) * | 2009-03-31 | 2011-02-16 | 王峻鹏 | Distributed-storage non-linear editing network for television program design |
| CN101609618B (en) * | 2008-12-23 | 2012-05-30 | 浙江工业大学 | Real-time hand language communication system based on special codes |
| CN102497513A (en) * | 2011-11-25 | 2012-06-13 | 中山大学 | Video virtual hand language system facing digital television |
| CN101539994B (en) * | 2009-04-16 | 2012-07-04 | 西安交通大学 | Mutually translating system and method of sign language and speech |
| CN101577062B (en) * | 2008-12-30 | 2012-07-25 | 浙江工业大学 | Space encoding-based method for realizing interconversion between sign language motion information and text message |
| CN102655606A (en) * | 2012-03-30 | 2012-09-05 | 浙江大学 | Method and system for adding real-time subtitle and sign language services to live program based on P2P (Peer-to-Peer) network |
| CN103188548A (en) * | 2011-12-30 | 2013-07-03 | 乐金电子(中国)研究开发中心有限公司 | Digital television sign language dubbing method and digital television sign language dubbing device |
| CN106981237A (en) * | 2016-01-19 | 2017-07-25 | 钟世雄 | A kind of method, device and the mobile phone of the sign language input selected based on picture |
| CN110730360A (en) * | 2019-10-25 | 2020-01-24 | 北京达佳互联信息技术有限公司 | Video uploading and playing methods and devices, client equipment and storage medium |
| CN111225237A (en) * | 2020-04-23 | 2020-06-02 | 腾讯科技（深圳）有限公司 | Sound and picture matching method of video, related device and storage medium |
| 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 |
| CN115223428A (en) * | 2021-04-20 | 2022-10-21 | 美光科技公司 | Converting sign language |
| CN115497499A (en) * | 2022-08-30 | 2022-12-20 | 阿里巴巴（中国）有限公司 | Method for synchronizing voice and action time |
-
2006
- 2006-01-17 CN CN 200610023380 patent/CN101005574A/en active Pending
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100518253C (en) * | 2007-11-19 | 2009-07-22 | 新奥特（北京）视频技术有限公司 | A manuscript writing system |
| CN100544409C (en) * | 2007-11-19 | 2009-09-23 | 新奥特（北京）视频技术有限公司 | A kind of figure record and broadcast method of serving as theme and driving with manuscript |
| CN100558146C (en) * | 2007-11-19 | 2009-11-04 | 新奥特（北京）视频技术有限公司 | A kind of figure manufacturing-broadcasting system of serving as theme and driving with manuscript |
| CN101188023B (en) * | 2007-11-19 | 2010-06-02 | 新奥特（北京）视频技术有限公司 | A method for making drawing in writing manuscript |
| CN101609618B (en) * | 2008-12-23 | 2012-05-30 | 浙江工业大学 | Real-time hand language communication system based on special codes |
| CN101577062B (en) * | 2008-12-30 | 2012-07-25 | 浙江工业大学 | Space encoding-based method for realizing interconversion between sign language motion information and text message |
| CN101588457B (en) * | 2009-03-31 | 2011-02-16 | 王峻鹏 | Distributed-storage non-linear editing network for television program design |
| CN101539994B (en) * | 2009-04-16 | 2012-07-04 | 西安交通大学 | Mutually translating system and method of sign language and speech |
| CN102497513A (en) * | 2011-11-25 | 2012-06-13 | 中山大学 | Video virtual hand language system facing digital television |
| CN103188548A (en) * | 2011-12-30 | 2013-07-03 | 乐金电子(中国)研究开发中心有限公司 | Digital television sign language dubbing method and digital television sign language dubbing device |
| CN102655606A (en) * | 2012-03-30 | 2012-09-05 | 浙江大学 | Method and system for adding real-time subtitle and sign language services to live program based on P2P (Peer-to-Peer) network |
| CN106981237A (en) * | 2016-01-19 | 2017-07-25 | 钟世雄 | A kind of method, device and the mobile phone of the sign language input selected based on picture |
| CN110730360A (en) * | 2019-10-25 | 2020-01-24 | 北京达佳互联信息技术有限公司 | Video uploading and playing methods and devices, client equipment and storage medium |
| CN111225237A (en) * | 2020-04-23 | 2020-06-02 | 腾讯科技（深圳）有限公司 | Sound and picture matching method of video, related device and storage medium |
| CN111225237B (en) * | 2020-04-23 | 2020-08-21 | 腾讯科技（深圳）有限公司 | Sound and picture matching method of video, related device and storage medium |
| US11972778B2 (en) | 2020-04-23 | 2024-04-30 | Tencent Technology (Shenzhen) Company Limited | Sound-picture matching method of video, related apparatus, and storage medium |
| 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 |
| CN115223428A (en) * | 2021-04-20 | 2022-10-21 | 美光科技公司 | Converting sign language |
| CN115497499A (en) * | 2022-08-30 | 2022-12-20 | 阿里巴巴（中国）有限公司 | Method for synchronizing voice and action time |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101005574A (en) | Video frequency virtual humance sign language compiling system | |
| CN204761591U (en) | Teaching is with interactive recorded broadcast system of full -automatic high definition | |
| CN103325400B (en) | A kind of surgical operation images recorded broadcast teaching system and method | |
| CN102129346B (en) | Video interaction method and device | |
| WO2018227761A1 (en) | Correction device for recorded and broadcasted data for teaching | |
| CN103179437A (en) | System and method for recording and playing virtual character videos | |
| CN106060343A (en) | Micro class assistant implementation system and method used for assisting teaching process | |
| CN101902580A (en) | Network multimedia tracking system for teaching | |
| CN103384253B (en) | The play system and its construction method of multimedia interaction function are presented in video | |
| CN104301657B (en) | A kind of video conference terminal and its secondary flow data cut-in method | |
| CN104581346A (en) | Micro video course making system and method | |
| CN201063755Y (en) | Recording system for teaching and assembly room | |
| CN102262888A (en) | Video file splitting method | |
| CN105491396A (en) | Multimedia information processing method and server | |
| CN106303288A (en) | The method of video, Apparatus and system are sung in synthesis | |
| CN205961300U (en) | Intelligence is mutual dull and stereotyped | |
| CN108766074A (en) | Remote audio-video interaction is given lessons implementation method, equipment and terminal | |
| CN110806844A (en) | Multi-subject and multi-theme display method based on multimedia exhibition hall | |
| CN112565847A (en) | Large-screen display control method and device | |
| CN202929567U (en) | Virtual character animation performance system | |
| CN103428441A (en) | Course recording method and course recording device used for on-line teaching | |
| CN210042017U (en) | Recorded broadcast remote teaching equipment | |
| CN106331553A (en) | Video storage method and device and electronic equipment | |
| Maad | Universal access to multimodal ITV content: challenges and prospects | |
| EP1964410A1 (en) | Information intermediation system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |