CN114648975A - Method for automatically cutting English film to generate dubbing materials according to knowledge points - Google Patents
Method for automatically cutting English film to generate dubbing materials according to knowledge points Download PDFInfo
- Publication number
- CN114648975A CN114648975A CN202210126140.8A CN202210126140A CN114648975A CN 114648975 A CN114648975 A CN 114648975A CN 202210126140 A CN202210126140 A CN 202210126140A CN 114648975 A CN114648975 A CN 114648975A
- Authority
- CN
- China
- Prior art keywords
- dubbing
- film
- subtitle
- video
- english
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0272—Voice signal separating
-
- 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
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/278—Subtitling
Abstract
The invention discloses a method for automatically cutting and generating dubbing materials for an English film according to knowledge points, which comprises the following steps: (1) storing the film in a warehouse and collecting the film captions through a network; (2) performing AI listening and translation on the film to obtain AI subtitles, performing similarity comparison with the acquired plurality of film subtitles to obtain more accurate subtitles, and correcting and confirming the subtitle time axis; (3) dividing the subtitle file into a plurality of small sections according to English knowledge points of primary and secondary schools; (4) cutting the film according to the divided subtitle small sections to obtain film video segments corresponding to the subtitle small sections; (5) separating audio from each video clip, and separating human voice and background voice of the audio file to obtain the background voice and original voice required by dubbing materials; (6) and synthesizing and transcoding the background sound and the subtitle of the video clip to obtain the final dubbing material.
Description
Technical Field
The invention relates to a dubbing technology, in particular to an automatic dubbing material technology.
Background
As an innovative foreign language learning method, foreign language teaching software such as dubbing and web sites provide a learner with a special video clip, which is generally taken from a classical foreign language original movie or television play, etc., and which has been previously separated from voice and background and can also provide Chinese and foreign language subtitles. The learner of the foreign language can personally dub the video clip and learn dubbed contents in this way. Compared with the passive and listening-based traditional foreign language learning mode, the active and immersive foreign language learning mode can effectively improve the participation sense of the learner and enable the learner to more effectively master foreign language materials contained in the dubbing content.
However, the preparation of such dubbing materials for teaching requires professionals who are skilled in foreign language and video processing techniques, consumes a lot of time for editing video materials, separating original voices, generating foreign language subtitles, etc., is costly, takes a long time, and is difficult to generate in large quantities. Furthermore, for students in middle and primary schools, how to automatically generate dubbing materials matching with knowledge points in english teaching in middle and primary schools is also a technology that needs to be developed by those skilled in the art.
Disclosure of Invention
In view of the above defects in the prior art, the technical problem to be solved by the present invention is to automatically cut out a required video segment and subtitle for a complete movie according to knowledge points of primary and secondary schools, separate voice and background from the video segment, and transcode the obtained video into dubbing materials.
In order to achieve the above object, the present invention firstly provides a method for automatically cutting an english movie according to knowledge points to generate dubbing materials, which comprises the following steps:
(1) warehousing the film, and collecting the film subtitles through a network;
(2) performing AI listening and translation on the film to obtain AI subtitles, performing similarity comparison with the acquired plurality of film subtitles to obtain more accurate subtitles, and correcting and confirming the subtitle time axis;
(3) dividing the subtitle file into a plurality of small sections according to English knowledge points of primary and secondary schools;
(4) cutting the film according to the divided subtitle small sections to obtain film video sections corresponding to the subtitle small sections;
(5) separating audio from each video clip, and separating human voice and background voice of the audio file to obtain the background voice and original voice required by dubbing materials;
(6) and synthesizing and transcoding the background sound and the subtitles of the video clip to obtain the final dubbing material.
Further, a step (7) of wiring the dubbing materials to the dubbing platform APP is included.
Further, in step (4), performing online visual video clip by using the ffmpeg method.
Further, in the step (5), the speeteter method is adopted to separate the background voice of the human voice.
Further, the transcoded video material comprises standard definition, high definition, blue light and super-definition multi-code rate.
The invention also provides a system for automatically cutting and generating dubbing materials for the English film according to the knowledge points, which comprises a subtitle acquisition module, a subtitle comparison and selection module, a subtitle time axis correction module, a subtitle segmentation module, a video segmentation module, an audio separation module and a video synthesis and transcoding module; the subtitle acquisition module is used for acquiring the film subtitles stored in a warehouse through a network; the caption comparison and selection module is used for carrying out AI listening and translation on the film to obtain AI captions, and carrying out similarity comparison on the AI captions and the collected multiple film captions to obtain more accurate captions; the caption time axis correction module is used for correcting and confirming a caption time axis; the subtitle segmentation module is used for segmenting the subtitle file into a plurality of small segments according to the English knowledge points of the primary and middle schools; the video segmentation module is used for cutting the film according to the segmented subtitle segments to obtain film video segments corresponding to the subtitle segments; the audio separation module is used for separating audio from each video clip, separating human voice and background voice of the audio file and obtaining the background voice and original voice required by dubbing materials; and the video synthesis transcoding module is used for synthesizing and transcoding the background sound and the subtitle of the video segment to obtain the final dubbing material.
Further, the video segmentation module performs online visual video editing by using the ffmpeg method.
Further, the audio separation module adopts a speeteter method to separate the background sound of the human voice.
Further, the system is arranged to bring the generated dubbing material online to the dubbing platform APP.
Further, the transcoded video material comprises standard definition, high definition, blue light and super-definition multi-code rate.
The invention can automatically acquire the film captions on the network, and solves the time cost of manually searching caption files; the dubbing materials can be produced in a large scale, and dubbing resources of English interest dubbing are greatly enriched; the user can visually operate on line, so that the subtitle can be simply corrected and the information is complete, and the operation is convenient; through automatic movie cutting, the production cost of company resources is greatly saved.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the present invention;
FIG. 2 is a system operation interface diagram of caption processing in a preferred embodiment of the invention;
FIG. 3 is a system interface diagram of a video clip in accordance with a preferred embodiment of the present invention;
FIG. 4 is a system operating interface diagram of audio separation in a preferred embodiment of the present invention;
FIG. 5 is a diagram of an operation interface for information supplementation of video according to a preferred embodiment of the present invention.
Detailed Description
The technical contents of the preferred embodiments of the present invention will be more clearly and easily understood by referring to the drawings attached to the specification. The present invention may be embodied in many different forms of embodiments and the scope of the invention is not limited to the embodiments set forth herein.
As shown in fig. 1, the method for generating dubbing materials by automatically cutting an english video according to a knowledge point of the present invention comprises the steps of:
(1) and warehousing the required film, and collecting subtitle files conforming to the film. The caption file can be automatically collected through a network or manually uploaded. The operational interface is shown in fig. 2.
(2) And performing AI listening and translation on the film to obtain AI subtitles, performing similarity comparison with the plurality of acquired subtitle files to obtain more accurate subtitles, and correcting the subtitle time axis. In a preferred embodiment, the present invention employs intelligent speech recognition technology based on Ali. The system operating interface is shown in figure 3.
(3) And after the subtitle is confirmed, pre-cutting the subtitle file according to the knowledge points of the primary and secondary schools to divide the subtitle file into a plurality of subtitle segments. The knowledge points of the primary and the middle schools can be determined according to the teaching outline of the textbook and can also be determined by the teacher. In a preferred embodiment, the present invention employs the ffmpeg-based online visualization video clip technique.
(4) And editing the video according to the subtitle fragments, separating the audio from the video fragments, and determining the final video fragments. In a preferred embodiment, the present invention employs a speeeter-based human voice background sound separation technique. The system operating interface is shown in fig. 4.
(5) And supplementing the video clip with information. The system operating interface is shown in fig. 5.
(6) And transcoding and watermarking each video segment to finish dubbing materials.
(7) And (5) uploading to a resource library for the app user to use dubbing.
The invention can automatically acquire the film captions on the network, and solves the time cost of manually searching caption files; the dubbing materials can be produced in a large scale, and dubbing resources of English interest dubbing are greatly enriched; the user can visually operate on line, so that the subtitle can be simply corrected and the information is complete, and the operation is convenient; through automatic movie cutting, the production cost of company resources is greatly saved.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (10)
1. A method for automatically cutting and generating dubbing materials for an English movie according to knowledge points is characterized by comprising the following steps:
(1) warehousing the film, and collecting the film subtitles through a network;
(2) performing AI listening and translation on the film to obtain AI subtitles, performing similarity comparison with the acquired plurality of film subtitles to obtain more accurate subtitles, and correcting and confirming the subtitle time axis;
(3) dividing the subtitle file into a plurality of small sections according to English knowledge points of primary and secondary schools;
(4) cutting the film according to the divided subtitle small sections to obtain film video sections corresponding to the subtitle small sections;
(5) separating audio from each video clip, and separating human voice and background voice of the audio file to obtain the background voice and original voice required by dubbing materials;
(6) and synthesizing and transcoding the background sound and the subtitle of the video clip to obtain the final dubbing material.
2. The method for generating dubbing materials for automatic cutting of english movies according to the knowledge point as claimed in claim 1, further comprising the step (7) of uploading the dubbing materials to the dubbing platform APP.
3. The method for generating dubbing material for automatic cutting of english-language movie according to the point of knowledge as claimed in claim 1, wherein the transcoded video material comprises standard definition, high definition, blue-ray and super-definition multi-rate.
4. The method for generating dubbing materials for automatic cutting of english movie according to knowledge point as claimed in claim 1, wherein in the step (4), the video clip is visualized on line by using ffmpeg method.
5. The method for generating dubbing materials for automatic cutting of english movie according to the knowledge point as claimed in claim 1, wherein in the step (5), the spelter method is used to separate the background sound of human voice.
6. A system for automatically cutting English film to generate dubbing materials according to knowledge points is characterized by comprising
The system comprises a caption acquisition module, a caption comparison and selection module, a caption time axis correction module, a caption segmentation module, a video segmentation module, an audio separation module and a video synthesis transcoding module; the subtitle acquisition module is used for acquiring the film subtitles stored in a warehouse through a network; the caption comparison and selection module is used for carrying out AI listening and translation on the film to obtain AI captions, and carrying out similarity comparison on the AI captions and the collected multiple film captions to obtain more accurate captions; the caption time axis correction module is used for correcting and confirming a caption time axis; the subtitle segmentation module is used for segmenting the subtitle file into a plurality of small segments according to the English knowledge points of the primary and middle schools; the video segmentation module is used for cutting the film according to the segmented subtitle segments to obtain film video segments corresponding to the subtitle segments; the audio separation module is used for separating audio from each video clip, separating human voice and background voice of the audio file and obtaining the background voice and original voice required by dubbing materials; and the video synthesis transcoding module is used for synthesizing and transcoding the background sound and the subtitle of the video segment to obtain the final dubbing material.
7. The system for generating dubbing materials for automatic cutting of english movies according to the knowledge point of claim 6, wherein the video segmentation module uses ffmpeg method for online visual video editing.
8. The system for automatically cutting and generating dubbing material for an english movie according to the point of knowledge as claimed in claim 6, wherein the audio separation module performs audio background sound separation by using a spleteter method.
9. The system for automatic cutting generation of dubbing materials for english cinema according to knowledge point of claim 6, wherein the system is arranged to line the generated dubbing materials to dubbing platform APP.
10. The system for generating dubbing materials for automatic cutting of english movies according to the knowledge point of claim 5, wherein the transcoded video materials include standard definition, high definition, blue light and super definition multi-rate codes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210126140.8A CN114648975A (en) | 2022-02-10 | 2022-02-10 | Method for automatically cutting English film to generate dubbing materials according to knowledge points |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210126140.8A CN114648975A (en) | 2022-02-10 | 2022-02-10 | Method for automatically cutting English film to generate dubbing materials according to knowledge points |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114648975A true CN114648975A (en) | 2022-06-21 |
Family
ID=81992760
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210126140.8A Pending CN114648975A (en) | 2022-02-10 | 2022-02-10 | Method for automatically cutting English film to generate dubbing materials according to knowledge points |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114648975A (en) |
-
2022
- 2022-02-10 CN CN202210126140.8A patent/CN114648975A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105245917B (en) | A kind of system and method for multi-media voice subtitle generation | |
Afouras et al. | LRS3-TED: a large-scale dataset for visual speech recognition | |
KR101990023B1 (en) | Method for chunk-unit separation rule and display automated key word to develop foreign language studying, and system thereof | |
CN109275046B (en) | Teaching data labeling method based on double video acquisition | |
CN106878632B (en) | Video data processing method and device | |
CN113691836B (en) | Video template generation method, video generation method and device and electronic equipment | |
US20120147264A1 (en) | Method for the semi-automatic editing of timed and annotated data | |
WO2023197979A1 (en) | Data processing method and apparatus, and computer device and storage medium | |
KR20010072936A (en) | Post-Synchronizing an information stream | |
CN103984772A (en) | Method and device for generating text retrieval subtitle library and video retrieval method and device | |
CN109657096B (en) | Auxiliary statistical report generation method based on low school age teaching audio and video | |
WO2022228235A1 (en) | Method and apparatus for generating video corpus, and related device | |
CN114268829B (en) | Video processing method, video processing device, electronic equipment and computer readable storage medium | |
US10127824B2 (en) | System and methods to create multi-faceted index instructional videos | |
CN112800263A (en) | Video synthesis system, method and medium based on artificial intelligence | |
CN112714348A (en) | Intelligent audio and video synchronization method | |
CN117596433B (en) | International Chinese teaching audiovisual courseware editing system based on time axis fine adjustment | |
KR102124828B1 (en) | System for Instructional visual content using Automatically convert images from electronic documents | |
CN114648975A (en) | Method for automatically cutting English film to generate dubbing materials according to knowledge points | |
EP3839953A1 (en) | Automatic caption synchronization and positioning | |
CN112002328A (en) | Subtitle generating method and device, computer storage medium and electronic equipment | |
CN113591491A (en) | System, method, device and equipment for correcting voice translation text | |
CN115988149A (en) | Method for generating video by AI intelligent graphics context | |
EP3252770A1 (en) | Automated identification and processing of audiovisual data | |
Tardel et al. | Post-editing job profiles for subtitlers |
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 |