CN110516266A - Video caption automatic translating method, device, storage medium and computer equipment - Google Patents
Video caption automatic translating method, device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN110516266A CN110516266A CN201910894066.2A CN201910894066A CN110516266A CN 110516266 A CN110516266 A CN 110516266A CN 201910894066 A CN201910894066 A CN 201910894066A CN 110516266 A CN110516266 A CN 110516266A
- Authority
- CN
- China
- Prior art keywords
- subtitle file
- video
- file
- original
- caption
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/488—Data services, e.g. news ticker
- H04N21/4884—Data services, e.g. news ticker for displaying subtitles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/85—Assembly of content; Generation of multimedia applications
- H04N21/854—Content authoring
- H04N21/8547—Content authoring involving timestamps for synchronizing content
Abstract
The invention belongs to technical field of data processing, a kind of video caption automatic translating method, device, storage medium and computer equipment are disclosed.Device in the present invention, including data obtaining module, preprocessing module, translation module and memory module.The present invention is by translating and exporting to the subtitle of video after obtaining the caption translating request of viewer, realize the function of video caption automatic translation, avoid problem at high cost caused by human translation and limited languages, the Production Time of video caption translation is saved, it can be according to the actual demand free switching languages of viewer, the user experience of viewer is improved, there is good practical value.
Description
Technical field
The invention belongs to technical field of data processing, and in particular to a kind of video caption automatic translating method, device, storage
Medium and computer equipment.
Background technique
As a large amount of video is made, issues and is propagated using Digital Media mode, the viewings such as computer, home theater view
The equipment of frequency is also gradually popularized, and people can be contacted fast, on a large scale from country variant, different regions, different language
The propagation of video, video is more convenient and quick；But the following main problem is, for the video of different language,
Most of video viewers understand that there is also difficulties even with audio and subtitle；As propagated most wide film and electricity in video
Depending on play, viewer understands the most of dialogue of personage or monologue in video to the plot of film and TV play, therefore sees
If there are obstacles in language understanding by the person of seeing, substantially fail to understand film and TV play；Therefore, video production side is come
It says, the difficulty of language understanding means to lose potentially large number of spectators, and for viewer, then it is a large amount of to lose appreciation
The chance of outstanding video work.
In existing video production process, the caption translating production of the video of different language, which mainly relies on, to be accomplished manually,
Problem on obstacle, due to cost of labor etc., human translation word are watched caused by the languages of some subtitles although can solve
Curtain usually only translates several commonly used languages, it is difficult to meet the demand that different viewers obtains the subtitle of its suitable languages, thus
Influence the Experience Degree of viewer.
Summary of the invention
In order to solve the above problems existing in the present technology, it is an object of that present invention to provide a kind of video caption automatic translations
Method, apparatus, storage medium and computer equipment, present invention saves the Production Times of video caption translation, and can root
According to the actual demand free switching languages of viewer, there is good practical value.
The technical scheme adopted by the invention is as follows:
A kind of video caption automatic translating method, comprising the following steps:
Whether real-time detection has caption translating request, if so, then obtaining caption translating request, and is requested according to caption translating
Determine sensing word, wherein sensing word includes source languages, target language and video location；
The corresponding video file in current video position is extracted, the corresponding original subtitle text of current video file is then obtained
Part；
Currently whether the corresponding languages of original subtitle file are source languages for judgement, if so, then to current original subtitle file
It is split and generates multiple phrases, if not, output translation request error message；
The language model of target language is extracted, and multiple phrases after segmentation are sequentially input to the language model of target language
It is interior, obtain target subtitle file；
Current goal subtitle file is corresponding with original subtitle file, and current goal subtitle file is exported to working as forward sight
Information is completed in frequency file, output translation.
Preferably, caption translating request is voice request and/or text request；When caption translating request is voice request
When, determining sensing word, specific step is as follows:
Current speech is requested to carry out pretreatment operation, wherein pretreatment operation includes noise elimination and grammer segmentation；
It is converted to by pretreated voice request, obtains text request, then determined by identification text request
Sensing word.
Preferably, when obtaining the corresponding original subtitle file of current video file, the specific steps are as follows:
Judge whether to prestore the corresponding original subtitle file of current video file；
If so, then continuing the judgement currently corresponding languages of original subtitle file；
If not, obtaining the video frame of current video file, identification shape is successively then carried out to the subtitle of all video frames
At original document, all original documents are arranged according to the sequence of corresponding video frame, form original subtitle file.
Preferably, by current goal subtitle file and original subtitle file to it is corresponding when
A1. current goal subtitle file is traversed, is judged with the presence or absence of sensitive word in current goal subtitle file, if so, then
Sensitive word is replaced operation and/or delete operation, then current goal subtitle file is input to the grammer of target language
The verification of smoothness degree is carried out in model, is carried out if not, current goal subtitle file is input in the syntactic model of target language
Clear and coherent degree verification；
A2. judge whether the clear and coherent rate of smoothness degree verification is higher than threshold value, if so, final goal subtitle file is then exported, and
Final goal subtitle file is corresponding with original subtitle file, finally current final goal subtitle file is exported to current video
Target subtitle file after mark if not, the phrase by clear and coherent rate lower than threshold value is labeled, and is re-entered mesh by file
Verification object subtitle file is obtained after the language model of poster kind, and step A1 then is repeated to verification object subtitle file.
Preferably, by final goal subtitle file and original subtitle file to it is corresponding when by final goal subtitle file
Timestamp is corresponding with the timestamp of original subtitle file.
Preferably, original subtitle file includes that original captioned test and scene corresponding with each original captioned test are believed
Breath；When being split to current original subtitle file, multiple phrases are generated after dividing original captioned test, each phrase is corresponding
There is a scene information；Extract target language language model after, by after segmentation multiple phrases and corresponding scene information successively
It inputs in the language model of target language, obtains target subtitle file.
A kind of device based on above-mentioned video caption automatic translating method, including data obtaining module, preprocessing module, turn over
Translate module and memory module；
Data obtaining module, for obtaining caption translating request, video file and original subtitle corresponding with video file
File is also used to be requested to determine sensing word according to caption translating, wherein sensing word includes source languages, target language and video position
It sets；
Preprocessing module is also used to for being split processing to original subtitle file to the original subtitle text after segmentation
Part carries out languages judgement；
Memory module, for storing the language model of video file, original subtitle file and multiple languages；
Then translation module exports target subtitle text for calling the corresponding language model of the target language in sensing word
Part.
Preferably, above-mentioned video caption automatic translation device further includes correction verification module；Memory module is also used to store
The syntactic model of multiple languages；
Correction verification module, for calling the corresponding syntactic model of the target language in sensing word, then to target subtitle file
Carry out the verification of smoothness degree, and the clear and coherent rate result of output verification.
A kind of computer readable storage medium, it is characterised in that: be stored with computer program；The calculation machine program is located
When managing device execution, above-mentioned video caption automatic translating method is realized.
A kind of computer equipment, including one or more processors further include memory, further include one or more calculating
Machine program；One or more computer programs are stored in memory, and are configured as by one or more of
Processor executes；One or more computer programs are configured for executing above-mentioned video caption automatic translation side
Method.
The invention has the benefit that
By the way that the subtitle of video is translated and exported after obtaining the caption translating request of viewer, video words are realized
The function of curtain automatic translation, avoids problem at high cost caused by human translation and limited languages, has saved video caption translation
Production Time can improve the user experience of viewer according to the actual demand free switching languages of viewer, have very
Good practical value.
Other beneficial effects of the invention will be described in detail in a specific embodiment.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the flow diagram of video caption automatic translating method in embodiment 1.
Specific embodiment
With reference to the accompanying drawing and specific embodiment come the present invention is further elaborated.It should be noted that for
Although the explanation of these way of example is to be used to help understand the present invention, but and do not constitute a limitation of the invention.The present invention
Disclosed function detail is only used for description example embodiments of the present invention.However, this hair can be embodied with many alternative forms
It is bright, and be not construed as limiting the invention in the embodiment that the present invention illustrates.
It should be appreciated that terminology used in the present invention is only used for description specific embodiment, it is not intended to limit of the invention show
Example embodiment.If term " includes ", " including ", "comprising" and/or " containing " are in the present invention by use, specified institute's sound
Bright feature, integer, step, operation, unit and/or component existence, and be not excluded for one or more other features, number
Amount, step, operation, unit, component and/or their combination existence or increase.
It should be appreciated that it will be further noted that the function action occurred may go out with attached drawing in some alternative embodiments
Existing sequence is different.For example, depending on related function action, can actually substantially be executed concurrently, or sometimes
Two figures continuously shown can be executed in reverse order.
It should be appreciated that providing specific details, in the following description in order to which example embodiment is understood completely.
However, those of ordinary skill in the art are it is to be understood that implementation example embodiment without these specific details.
Such as system can be shown in block diagrams, to avoid with unnecessary details come so that example is unclear.In other instances, may be used
Or not show well-known process, structure and technology unnecessary details, to avoid making example embodiment unclear.
Embodiment 1:
As shown in Figure 1, the present embodiment provides a kind of video caption automatic translating methods, comprising the following steps:
Whether real-time detection has caption translating request, if so, then obtaining caption translating request, and is requested according to caption translating
Determine sensing word, wherein sensing word includes source languages, target language and video location；
The corresponding video file in current video position is extracted, the corresponding original subtitle text of current video file is then obtained
Part；
Currently whether the corresponding languages of original subtitle file are source languages for judgement, if so, then to current original subtitle file
It is split and generates multiple phrases, if not, output translation request error message；
The language model of target language is extracted, and multiple phrases after segmentation are sequentially input to the language model of target language
It is interior, obtain target subtitle file；
Current goal subtitle file is corresponding with original subtitle file, and current goal subtitle file is exported to working as forward sight
Information is completed in frequency file, output translation.
In the present embodiment, by the way that the subtitle of video is translated and is exported after obtaining the caption translating request of viewer,
The function of realizing video caption automatic translation avoids problem at high cost caused by human translation and limited languages, has saved view
The Production Time of frequency caption translating can improve the user of viewer according to the actual demand free switching languages of viewer
Experience Degree has good practical value.
For example, user can issue caption translating request, caption translating by oneself oral account or by man-machine interface
May include in request " English to Chinese ", " Chinese to English ", " Ying Yide ", " Ying Yi ", " Ying Yihan ", " Ying Yi Russia ", " Han Yi Russia ",
The sensing word of two languages such as " Chinese translates Korea Spro ", " Chinese translates day ", " Yi Russia " translation, thus the user convenient for different language habit exists
Independently switch the languages for oneself needing to translate when watching video, the subtitle after then translating can occur simultaneously with original subtitle
Subtitle in video pictures or after translation can substitute original subtitle and appear in video pictures, it is possible thereby to promote each languages
Information exchange and cultural exchanges.
As one of preferred embodiment, the language model of each languages is based on CNN (convolutional neural networks)
Or training forms RNN (Recognition with Recurrent Neural Network) etc. in advance, so that the data processings such as caption translating are more efficient, and then realizes
The automatic real time translation of video caption.
Embodiment 2
The present embodiment is the further improvement made on the basis of embodiment 1, and the difference of the present embodiment and embodiment 1 exists
In:
In the present embodiment, caption translating request is voice request and/or text request；When caption translating requests to ask for voice
When asking, determining sensing word, specific step is as follows:
Current speech is requested to carry out pretreatment operation, wherein pretreatment operation includes noise elimination and grammer segmentation；Its
In, grammer segmentation includes that punctuation mark prejudges, spoken language repeats screening out, segmenting for words.
It is converted to by pretreated voice request, obtains text request, then determined by identification text request
Sensing word.
It is real using Python third party library jieba when voice request is Chinese as one of preferred embodiment
Now the text request of current speech request is segmented, recognition speed is fast, so that the recognition accuracy of voice request is bright
It is aobvious to improve.
Embodiment 3
The present embodiment is the further improvement made on the basis of embodiment 1 and any embodiment 2, the present embodiment and reality
It applies example 1 and any difference of embodiment 2 is:
In the present embodiment, when obtaining the corresponding original subtitle file of current video file, the specific steps are as follows:
Judge whether to prestore the corresponding original subtitle file of current video file；
If so, then continuing the judgement currently corresponding languages of original subtitle file；
If not, obtaining the video frame of current video file, identification shape is successively then carried out to the subtitle of all video frames
At original document, all original documents are arranged according to the sequence of corresponding video frame, form original subtitle file.
As one of preferred embodiment, OCR recognizer is used when identifying to the subtitle of video frame, by
This, which can be convenient, is rapidly converted to text information for image information.
Alternatively preferred embodiment, the lower section for presetting picture in video frame is caption area, when progress word
When curtain identification, the caption area of each video frame is only identified；Thus avoid when the texts such as billboard occur in video pictures also into
Subtitle mistake caused by row identification.
Embodiment 4
The present embodiment is the further improvement made on the basis of embodiment 1-3 is any, the present embodiment and embodiment 1-3
Any difference is:
In the present embodiment, by current goal subtitle file and original subtitle file to it is corresponding when
A1. current goal subtitle file is traversed, is judged with the presence or absence of sensitive word in current goal subtitle file, if so, then
Sensitive word is replaced operation and/or delete operation, then current goal subtitle file is input to the grammer of target language
The verification of smoothness degree is carried out in model, is carried out if not, current goal subtitle file is input in the syntactic model of target language
Clear and coherent degree verification；
A2. judge whether the clear and coherent rate of smoothness degree verification is higher than threshold value, if so, final goal subtitle file is then exported, and
Final goal subtitle file is corresponding with original subtitle file, finally current final goal subtitle file is exported to current video
Target subtitle file after mark if not, the phrase by clear and coherent rate lower than threshold value is labeled, and is re-entered mesh by file
Verification object subtitle file is obtained after the language model of poster kind, and step A1 then is repeated to verification object subtitle file.
Sensitive word detection and the verification of smoothness degree make the subtitle accuracy rate after translation higher, and more adduction rule, avoid pair
Video itself causes deleterious effect.
Embodiment 5
The present embodiment is the further improvement made on the basis of embodiment 4, and the difference of the present embodiment and embodiment 4 exists
In:
In the present embodiment, by final goal subtitle file and original subtitle file to it is corresponding when by final goal subtitle file
Timestamp it is corresponding with the timestamp of original subtitle file；Thus it is watched caused by avoiding subtitle from misplacing uncomfortable.
As one of preferred embodiment, when the timestamp of original subtitle file is the broadcasting of subtitle in video
Between, during caption translating, each subtitle, which is bound, unique corresponding play time.
Embodiment 6
The present embodiment is the further improvement made on the basis of embodiment 1-5 is any, the present embodiment and embodiment 1-5
Any difference is:
In the present embodiment, original subtitle file includes original captioned test and scene corresponding with each original captioned test
Information；When being split to current original subtitle file, multiple phrases are generated after dividing original captioned test, each phrase is right
Ying Youyi scene information；Extract target language language model after, by after segmentation multiple phrases and corresponding scene information according to
In the language model of secondary input target language, target subtitle file is obtained.
In the present embodiment, by presetting scene information, so that caption translating is more accurate；Meanwhile language model is in training
Scene information training can be added in the process, so that language model can be according to current subtitle during caption
Scene translated.
Embodiment 7
The present embodiment is made on the basis of embodiment 1-6 is any, and the present embodiment provides one kind to be appointed based on embodiment 1-6
The device of the one video caption automatic translating method, including data obtaining module, preprocessing module, translation module and storage mould
Block；
Data obtaining module, for obtaining caption translating request, video file and original subtitle corresponding with video file
File is also used to be requested to determine sensing word according to caption translating, wherein sensing word includes source languages, target language and video position
It sets；
Preprocessing module is also used to for being split processing to original subtitle file to the original subtitle text after segmentation
Part carries out languages judgement；
Memory module, for storing the language model of video file, original subtitle file and multiple languages；
Then translation module exports target subtitle text for calling the corresponding language model of the target language in sensing word
Part.
Embodiment 8
The present embodiment is the further improvement made on the basis of embodiment 7, and the difference of the present embodiment and embodiment 7 exists
In:
In the present embodiment, above-mentioned video caption automatic translation device further includes correction verification module；Memory module is also used to deposit
Store up the syntactic model of multiple languages；
Correction verification module, for calling the corresponding syntactic model of the target language in sensing word, then to target subtitle file
Carry out the verification of smoothness degree, and the clear and coherent rate result of output verification.
Embodiment 9
The present embodiment is made on the basis of embodiment 1-6 is any, and the present embodiment provides a kind of computer-readable storages
Medium, it is characterised in that: be stored with computer program；When the calculation machine program is executed by processor, above-mentioned video is realized
Subtitle automatic translating method.
Wherein, computer readable storage medium described in the present embodiment includes but is not limited to that any kind of disk is (including soft
Disk, hard disk, CD, CD-ROM and magneto-optic disk), ROM (Read-Only Memory, read-only memory), RAM
(RandomAcceSS Memory, immediately memory), EPROM (EraSable Programmable Read-Only
Memory, Erarable Programmable Read only Memory), EEPROM (Electrically EraSable Programmable
Read-Only Memory, Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic card or light card.It is, storage
Equipment includes that can be by equipment (for example, computer, mobile phone) with any medium for the form storage or transmission information that can be read
Read-only memory, disk or CD etc., memory disclosed in the present embodiment are only used as citing rather than as restrictions.
Any video words of embodiment 1-7 may be implemented in computer readable storage medium provided in an embodiment of the present invention
Curtain automatic translating method, concrete function realize refer to embodiment 1-7 it is any in explanation, details are not described herein.
Embodiment 10
The present embodiment is made on the basis of embodiment any one of 1-6, and the present embodiment provides a kind of computer equipment, packets
One or more processors are included, further include memory, further include one or more computer programs；One or more meters
Calculation machine program is stored in memory, and is configured as being executed by one or more of processors；Described one or more
A computer program is configured for executing above-mentioned video caption automatic translating method.
Wherein, computer equipment described in the present embodiment can be server, personal computer and network equipment etc. and set
It is standby.It, can be with it will be understood by those skilled in the art that device structure described in the present embodiment does not constitute the restriction to all devices
Including than illustrating more or fewer components, or the certain components of combination.It includes that video caption is automatic that memory, which can be used for storing,
The computer program of interpretation method and each functional module, processor runs the computer program for being stored in memory, to hold
The various function application and data processing of row equipment.
Embodiments described above is only schematical, can if being related to unit as illustrated by the separation member
It is physically separated with being or may not be；If being related to component shown as a unit, can be or can also be with
It is not physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to actual
Need that some or all of the units may be selected to achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not
In the case where paying creative labor, it can understand and implement.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features.And these modification or
Replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
The present invention is not limited to above-mentioned optional embodiment, anyone can show that other are each under the inspiration of the present invention
The product of kind form.Above-mentioned specific embodiment should not be understood the limitation of pairs of protection scope of the present invention, protection of the invention
Range should be subject to be defined in claims, and specification can be used for interpreting the claims.
Claims (10)
1. a kind of video caption automatic translating method, it is characterised in that: the following steps are included:
Whether real-time detection has caption translating request, if so, then obtaining caption translating request, and requests to determine according to caption translating
Sensing word, wherein sensing word includes source languages, target language and video location；
The corresponding video file in current video position is extracted, the corresponding original subtitle file of current video file is then obtained；
Currently whether the corresponding languages of original subtitle file are source languages for judgement, if so, then carrying out to current original subtitle file
Segmentation generates multiple phrases, if not, output translation request error message；
The language model of target language is extracted, and multiple phrases after segmentation are sequentially input in the language model of target language,
Obtain target subtitle file；
Current goal subtitle file is corresponding with original subtitle file, and current goal subtitle file is exported to current video text
Information is completed in part, output translation.
2. video caption automatic translating method according to claim 1, it is characterised in that: caption translating request is asked for voice
It asks and/or text request；When caption translating request is voice request, determining sensing word, specific step is as follows:
Current speech is requested to carry out pretreatment operation, wherein pretreatment operation includes noise elimination and grammer segmentation；
It is converted to by pretreated voice request, obtains text request, then determined and be directed toward by identification text request
Word.
3. video caption automatic translating method according to claim 2, it is characterised in that: it is corresponding to obtain current video file
Original subtitle file when, the specific steps are as follows:
Judge whether to prestore the corresponding original subtitle file of current video file；
If so, then continuing the judgement currently corresponding languages of original subtitle file；
If not, obtaining the video frame of current video file, identification is successively then carried out to the subtitle of all video frames and is formed just
All original documents are arranged according to the sequence of corresponding video frame, form original subtitle file by beginning file.
4. video caption automatic translating method according to claim 3, it is characterised in that: by current goal subtitle file with
When original subtitle file is to corresponding to
A1. current goal subtitle file is traversed, is judged with the presence or absence of sensitive word in current goal subtitle file, if so, then will be quick
Sense word is replaced operation and/or delete operation, then current goal subtitle file is input to the syntactic model of target language
Middle progress smoothness degree verification, carries out smoothness if not, current goal subtitle file is input in the syntactic model of target language
Degree verification；
A2. judge whether the clear and coherent rate of smoothness degree verification is higher than threshold value, if so, then exporting final goal subtitle file, and will most
Whole target subtitle file is corresponding with original subtitle file, finally exports current final goal subtitle file to current video text
Target subtitle file after mark if not, the phrase by clear and coherent rate lower than threshold value is labeled, and is re-entered target by part
Verification object subtitle file is obtained after the language model of languages, and step A1 then is repeated to verification object subtitle file.
5. video caption automatic translating method according to claim 4, it is characterised in that: by final goal subtitle file with
Original subtitle file is to corresponding with the timestamp of original subtitle file by the timestamp of final goal subtitle file when corresponding to.
6. -5 any video caption automatic translating method according to claim 1, it is characterised in that: original subtitle file packet
Include original captioned test and scene information corresponding with each original captioned test；Current original subtitle file is split
When, multiple phrases are generated after dividing original captioned test, each phrase is corresponding with a scene information；Extract the language of target language
Say model after, by after segmentation multiple phrases and corresponding scene information sequentially input in the language model of target language, obtain
Target subtitle file.
7. a kind of video caption automatic translation device, it is characterised in that: including data obtaining module, preprocessing module, translation mould
Block and memory module；
Data obtaining module, for obtaining caption translating request, video file and original subtitle file corresponding with video file,
It is also used to be requested to determine sensing word according to caption translating, wherein sensing word includes source languages, target language and video location；
Preprocessing module, for being split processing to original subtitle file, be also used to the original subtitle file after segmentation into
The judgement of row languages；
Memory module, for storing the language model of video file, original subtitle file and multiple languages；
Then translation module exports target subtitle file for calling the corresponding language model of the target language in sensing word.
8. video caption automatic translation device according to claim 7, it is characterised in that: further include correction verification module；Storage
Module is also used to store the syntactic model of multiple languages；
Then correction verification module carries out target subtitle file for calling the corresponding syntactic model of the target language in sensing word
Clear and coherent degree verification, and the clear and coherent rate result of output verification.
9. a kind of computer readable storage medium, it is characterised in that: be stored with computer program；The calculation machine program is processed
When device executes, any video caption automatic translating method of claim 1 to 6 is realized.
10. a kind of computer equipment, it is characterised in that: further include memory including one or more processors, further include one
Or multiple computer programs；One or more computer programs are stored in memory, and are configured as by described
One or more processors execute；It is any that one or more computer programs are configured for perform claim requirement 1 to 6
The video caption automatic translating method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910894066.2A CN110516266A (en) | 2019-09-20 | 2019-09-20 | Video caption automatic translating method, device, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910894066.2A CN110516266A (en) | 2019-09-20 | 2019-09-20 | Video caption automatic translating method, device, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110516266A true CN110516266A (en) | 2019-11-29 |
Family
ID=68633107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910894066.2A Pending CN110516266A (en) | 2019-09-20 | 2019-09-20 | Video caption automatic translating method, device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110516266A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368557A (en) * | 2020-03-06 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Video content translation method, device, equipment and computer readable medium |
| CN111901675A (en) * | 2020-07-13 | 2020-11-06 | 腾讯科技（深圳）有限公司 | Multimedia data playing method and device, computer equipment and storage medium |
| CN112511910A (en) * | 2020-11-23 | 2021-03-16 | 浪潮天元通信信息系统有限公司 | Real-time subtitle processing method and device |
| CN112995749A (en) * | 2021-02-07 | 2021-06-18 | 北京字节跳动网络技术有限公司 | Method, device and equipment for processing video subtitles and storage medium |
| CN113038184A (en) * | 2021-03-01 | 2021-06-25 | 北京百度网讯科技有限公司 | Data processing method, device, equipment and storage medium |
| CN113438542A (en) * | 2021-05-28 | 2021-09-24 | 北京智慧星光信息技术有限公司 | Subtitle real-time translation method, system, electronic equipment and storage medium |
| CN113660432A (en) * | 2021-08-17 | 2021-11-16 | 安徽听见科技有限公司 | Translation subtitle production method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101090461A (en) * | 2006-06-13 | 2007-12-19 | 中国科学院计算技术研究所 | Automatic translation method for digital video captions |
| CN102104741A (en) * | 2009-12-16 | 2011-06-22 | 新奥特（北京）视频技术有限公司 | Method and device for arranging multi-language captions |
| CN104391839A (en) * | 2014-11-13 | 2015-03-04 | 百度在线网络技术（北京）有限公司 | Method and device for machine translation |
| CN110134973A (en) * | 2019-04-12 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Video caption real time translating method, medium and equipment based on artificial intelligence |
-
2019
- 2019-09-20 CN CN201910894066.2A patent/CN110516266A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101090461A (en) * | 2006-06-13 | 2007-12-19 | 中国科学院计算技术研究所 | Automatic translation method for digital video captions |
| CN102104741A (en) * | 2009-12-16 | 2011-06-22 | 新奥特（北京）视频技术有限公司 | Method and device for arranging multi-language captions |
| CN104391839A (en) * | 2014-11-13 | 2015-03-04 | 百度在线网络技术（北京）有限公司 | Method and device for machine translation |
| CN110134973A (en) * | 2019-04-12 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Video caption real time translating method, medium and equipment based on artificial intelligence |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368557A (en) * | 2020-03-06 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Video content translation method, device, equipment and computer readable medium |
| CN111901675A (en) * | 2020-07-13 | 2020-11-06 | 腾讯科技（深圳）有限公司 | Multimedia data playing method and device, computer equipment and storage medium |
| CN111901675B (en) * | 2020-07-13 | 2021-09-21 | 腾讯科技（深圳）有限公司 | Multimedia data playing method and device, computer equipment and storage medium |
| CN112511910A (en) * | 2020-11-23 | 2021-03-16 | 浪潮天元通信信息系统有限公司 | Real-time subtitle processing method and device |
| CN112995749A (en) * | 2021-02-07 | 2021-06-18 | 北京字节跳动网络技术有限公司 | Method, device and equipment for processing video subtitles and storage medium |
| CN112995749B (en) * | 2021-02-07 | 2023-05-26 | 北京字节跳动网络技术有限公司 | Video subtitle processing method, device, equipment and storage medium |
| CN113038184A (en) * | 2021-03-01 | 2021-06-25 | 北京百度网讯科技有限公司 | Data processing method, device, equipment and storage medium |
| CN113438542A (en) * | 2021-05-28 | 2021-09-24 | 北京智慧星光信息技术有限公司 | Subtitle real-time translation method, system, electronic equipment and storage medium |
| CN113438542B (en) * | 2021-05-28 | 2022-11-08 | 北京智慧星光信息技术有限公司 | Subtitle real-time translation method, system, electronic equipment and storage medium |
| CN113660432A (en) * | 2021-08-17 | 2021-11-16 | 安徽听见科技有限公司 | Translation subtitle production method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110516266A (en) | Video caption automatic translating method, device, storage medium and computer equipment | |
| KR101990023B1 (en) | Method for chunk-unit separation rule and display automated key word to develop foreign language studying, and system thereof | |
| CN110517689B (en) | Voice data processing method, device and storage medium | |
| EP4099709A1 (en) | Data processing method and apparatus, device, and readable storage medium | |
| CN114465737B (en) | Data processing method and device, computer equipment and storage medium | |
| CN109256133A (en) | A kind of voice interactive method, device, equipment and storage medium | |
| CN111488487B (en) | Advertisement detection method and detection system for all-media data | |
| CN112399258A (en) | Live playback video generation playing method and device, storage medium and electronic equipment | |
| CN113392273A (en) | Video playing method and device, computer equipment and storage medium | |
| CN113035199A (en) | Audio processing method, device, equipment and readable storage medium | |
| CN111526405A (en) | Media material processing method, device, equipment, server and storage medium | |
| CN113703579B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN111460094A (en) | Method and device for optimizing audio splicing based on TTS (text to speech) | |
| Ham et al. | Ksl-guide: A large-scale korean sign language dataset including interrogative sentences for guiding the deaf and hard-of-hearing | |
| WO2021169825A1 (en) | Speech synthesis method and apparatus, device and storage medium | |
| CN116567351B (en) | Video processing method, device, equipment and medium | |
| US20230326369A1 (en) | Method and apparatus for generating sign language video, computer device, and storage medium | |
| CN115690280B (en) | Three-dimensional image pronunciation mouth shape simulation method | |
| CN116366872A (en) | Live broadcast method, device and system based on man and artificial intelligence | |
| CN109905756A (en) | TV subtitling dynamic creation method and relevant device based on artificial intelligence | |
| CN113033357B (en) | Subtitle adjusting method and device based on mouth shape characteristics | |
| CN113761865A (en) | Sound and text realignment and information presentation method and device, electronic equipment and storage medium | |
| Xu et al. | Gabor based lipreading with a new audiovisual mandarin corpus | |
| Virkkunen | Automatic speech recognition for the hearing impaired in an augmented reality application | |
| CN111160051A (en) | Data processing method and device, electronic equipment and storage medium |
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 |