JP2023137704A - Highlight moving image generation system, highlight moving image generation method, and program - Google Patents

Abstract

To generate a highlight moving image desired by a user by extracting a plurality of short moving images desired by the user from a moving image content.SOLUTION: A highlight moving image generation system 1 comprises an acquisition section which acquires an original moving image. Based on a result of performing sound recognition of the acquired original moving image, sound of the original moving image is extracted as a timestamped text holding a timestamp on word basis. On a screen for editing where the extracted timestamped text is displayed, a user is caused to select one or more continuous words from the timestamped text in such a manner that the timestamps are separated at intervals. The selection of the user is received, time ranges of the one or more selected continuous words are respectively identified based on the timestamped text, portions corresponding to the identified time ranges are segmented from the original moving image as short moving images and the segmented short moving images are combined such that a highlight moving image is generated.SELECTED DRAWING: Figure 1

Description

The present invention relates to a highlight video generation system, a highlight video generation method, and a program.

Due to the coronavirus pandemic, the use of video content such as web seminars and YouTube has increased around the world. However, video content also includes long videos. Therefore, from the perspective of the viewer, there is a problem in that there are many video contents that take too much time to play or become boring midway through, resulting in poor viewing efficiency.

In order to solve the above-mentioned problems, there is a technology that allows a user to quickly search for a specific part of a video that the user wants to view (see Patent Document 1), and a technology that allows the viewer to play back desired images and audio during playback. A technique (see Patent Document 2) has been provided that allows the user to easily and accurately reach the starting position. In addition, in order to create a highlight video, a technology that extracts a highlight portion specified from video content based on a frame evaluation value calculated based on feature quantities such as frame brightness and a specific subject (Patent Document 3) ) has been proposed.

Japanese Patent Application Publication No. 2019-66785 Japanese Patent Application Publication No. 2018-168508 Japanese Patent Application Publication No. 2019-216364

However, with the techniques described in Patent Documents 1 and 2, although it is possible for the user to easily reach the starting position that the user desires to view in the video content, they cut out and combine multiple short videos from the video content, and highlight It is not possible to generate videos. In addition, with the technology described in Patent Document 3, it is difficult to extract highlighted parts from video content such as Web seminars, where highlighted parts such as prominent parts or raised parts are difficult to understand, and the extracted highlighted parts are There is a problem in that the part is not necessarily the desired part.

In view of these problems, the present invention provides a highlight video generation system, a highlight video generation method, and a method for extracting a plurality of short videos desired by the user from video content and generating a highlight video desired by the user. and programs.

The present invention provides a highlight video generation system that generates a highlight video by cutting and combining a plurality of short videos from an original video to be edited, comprising: an acquisition unit that acquires the original video; an extraction unit that extracts the audio of the original video as time-stamped text in which a time stamp is added to each word based on the result of the audio recognition; a display unit that displays the time-stamped text on an editing screen; and a display unit that allows a user to select one or a plurality of consecutive words from the time-stamped text so that the timestamps are discontinuous on the editing screen; and , a selection unit that accepts the user's selection; a specification unit that specifies the time range of the one or more consecutive words that have been selected based on the time-stamped text; and A highlight video generation system comprising: a cutting unit that cuts out a portion corresponding to the specified time range as each short video; and a generation unit that combines each of the cut short videos to generate a highlight video. provide.

The present invention also provides a highlight video generation system in which the generation unit further combines a previously prepared video at the beginning and/or the end of the highlight video.

Further, in the present invention, the selection unit receives a selection of a combination order of the one or a plurality of consecutive selected words, and the generation unit combines each of the cut short videos according to the combination order. To provide a highlight video generation system that generates highlight videos.

Further, in the present invention, when the extracted time-stamped text includes a filler, the display section deletes the filler or displays the filler so that it can be distinguished from words other than the filler on the editing screen. We provide a highlight video generation system for

Further, in the present invention, when a filler is included in the one or a plurality of consecutive words that are selected, the cutting section is configured to cut out the filler from a portion of the original video that corresponds to each of the specified time ranges. To provide a highlight video generation system that cuts out parts excluding corresponding parts as each short video.

Further, the present invention provides a highlight video generation system including a captioning section that adds a caption to the highlight video.

Further, the present invention provides a highlight video generation system including an insertion section that adds sound data to the highlight video.

The present invention also provides a method executed by a highlight video generation system that generates a highlight video by cutting and combining a plurality of short videos from an original video to be edited, the method being executed by a highlight video generation system that obtains the original video. a step of audio recognizing the acquired original video; and a step of extracting the audio of the original video as time-stamped text with a time stamp added to each word based on the result of the audio recognition. Displaying the extracted time-stamped text on an editing screen; and having the user select one or more consecutive words from the time-stamped text on the editing screen so that the timestamps are discontinuous. At the same time, a step of accepting the selection of the user, a step of specifying the time range of the plurality of selected words or a plurality of consecutive words based on the time stamped text, and a step of specifying each of the plurality of selected words from the original video. To provide a highlight video generation system including the steps of: cutting out parts corresponding to the time ranges as respective short videos; and combining the cut short videos to generate a highlight video.

The present invention also provides a highlight video generation system that generates a highlight video by cutting and combining a plurality of short videos from an original video to be edited, including an acquisition unit that acquires the original video. a voice recognition unit that recognizes the voice of the original video; an extraction unit that extracts the voice of the source video as time-stamped text with a time stamp added to each word based on the result of the voice recognition; and the extracted time stamp. a display unit that displays the text with the timestamp on an editing screen; on the editing screen, the user selects one word or a plurality of consecutive words from the text with the timestamp so that the timestamps are discontinuous; a selection unit that receives a selection; a specification unit that specifies a time range of the one or more consecutive words selected based on the time-stamped text; To provide a program that functions as a cutting section that cuts out corresponding parts as respective short videos, and a generation section that combines the respective cut short videos to generate a highlight video.

According to the present invention, a plurality of short videos desired by a user are extracted from video content to generate a highlight video desired by the user.

1 is a diagram illustrating an overview of a highlight video generation system according to an embodiment of the present invention. 1 is a diagram showing a functional configuration of a highlight video generation system according to an embodiment of the present invention. FIG. 2 is a diagram showing a highlight video generation process flow executed by the highlight video generation system according to the embodiment of the present invention.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, modes for carrying out the present invention (hereinafter referred to as embodiments) will be described in detail with reference to the accompanying drawings. In the following figures, the same numbers or symbols are given to the same elements throughout the description of the embodiments.

[Basic concept/basic configuration]
FIG. 1 is a diagram for explaining an overview of a highlight video generation system 1 according to an embodiment of the present invention. The highlight video generation system 1 selects the part of the video that the user desires using the text generated by voice recognition of the video to be edited (hereinafter referred to as the original video), and selects the part of the video that the user desires from the original video. This is a system that generates light videos. In this embodiment, a highlight video is a video that is a collection of parts extracted from the original video that the user wants to show to the viewer, such as parts that were exciting, noticeable parts, and interesting parts in the original video. These include videos that collect important parts of the original video and summarize the contents of the original video.

The highlight video generation system 1 includes a highlight video generation device 10 and a user terminal 20. The highlight video generation device 10 is a device that is connected to a user terminal 20 via a network and generates a highlight video from an original video according to a user's instructions. The highlight video generation device 10 may be an on-premises or cloud server, but in this embodiment, it is a cloud server. Note that the highlight video generation system 1 also includes a viewer terminal (not shown) for viewing the highlight video generated by the highlight video generation device 10, a server (not shown) for uploading the highlight video, etc. , may be connected via a network.

The user terminal 20 is a user terminal that issues instructions when generating a highlight video from an original video, and is configured of, for example, a smartphone, a tablet terminal, a personal computer, or the like. Although only one device is displayed in this embodiment, a plurality of devices may be displayed.

The highlight video generation device 10 first obtains the original video from the network based on the user terminal 20 or an instruction from the user terminal 20 . Next, the highlight video generation device 10 performs voice recognition on the acquired original video and generates time-stamped text that holds a time stamp for each word (S1).

Here, the timestamp is the elapsed time from the start of the original video, and the text with timestamp is the time elapsed from the start of the original video, inserted into each word, in other words, at the part between words. This is the text that was created. In the time-stamped text generated from the original video shown in FIG. 1, the time stamp for each word is indicated by a black ▲, but to be more precise, the black ▲ is the elapsed time from the original video, as shown in the balloon. Furthermore, in the time-stamped text generated from the original video shown in FIG. 1, the time stamp of the first word of each frame of the original video is associated with the word of that frame.

The highlight video generation device 10 causes the user terminal 20 to display an editing screen for editing the time stamped text generated in S1 (S2). In the text with a time stamp on the editing screen shown in Figure 1, the time stamp is not displayed and the place where the time stamp is inserted is a space so that the user can easily select a word. or a timestamp may be displayed.

At the user terminal 20, the user selects one or more consecutive words from the time-stamped text displayed on the editing screen to include in the highlight video. The selection may be made by any means such as dragging, clicking, or tapping, and the selected portion may be displayed by any method such as enclosing it in a square as shown in FIG. 1 or highlighting it. Hereinafter, one or a plurality of consecutive words will be referred to as a sentence, and one selected word or a plurality of consecutive words will be referred to as a selected sentence.

When a plurality of selected sentences are selected, the highlight video generation device 10 controls the selected sentences so that the time stamps of the selected sentences are discontinuous, or in other words, the time stamps of the selected sentences are not consecutive. For example, in the editing screen shown in FIG. 1, if you select ``I would like to introduce you to a recent hot topic,'' you cannot select ``Hello'' as another selection sentence. However, "Hello" can be made into one choice sentence, such as "I would like to introduce you to the recently talked about orders." The selected sentence selected on the editing screen is transmitted from the user terminal 20 to the highlight video generation device 10 (S3).

The highlight video generation device 10 specifies the time range of each of the one or more selected sentences received from the user terminal 20 based on the timestamped text (S4). Here, the time range is the time range in the original video of the selected sentence. Specifically, the time range is from the timestamp of the first word of the selected sentence to the timestamp of the word after the selected sentence.

For example, if the time-stamped text in Figure 1, ``I would like to introduce you to the latest topic orders,'' is a selected sentence, the ``recent'' timestamp ``0:00:17:01'' indicates that after the selected sentence, The timestamp of the word "eh" up to "0:00:30:25", that is, "0:00:17:01 to 0:00:30:25" is the selected sentence "Introducing the recent hot topic of ordering" ” time range.

The highlight video generation device 10 cuts out a portion corresponding to the specified time range from the original video as a short video, and combines the cut short videos to generate a highlight video (S5).

According to such a highlight video system, a user selects a sentence from time-stamped text generated from an original video, identifies a desired portion of the user, and generates a highlight video. This makes it easy for the user to select a desired portion, and it is easy for the user to generate a desired highlight video. As a result, it is possible to create a highlight video that summarizes only the parts that the user wants to see, and by allowing viewers to view the generated highlight video, a high marketing effect can be expected.

[Functional configuration of highlight video generation system]
FIG. 2 is a diagram showing the functional configuration of the highlight video generation system 1 according to the embodiment of the present invention. The highlight video generation system 1 includes a highlight video generation device 10 and a user terminal 20 connected to the highlight video generation device 10 via a network.

[Functional configuration of highlight video generation device]
The highlight video generation device 10 includes a transmitting/receiving unit 11 that transmits and receives data to and from the user terminal 20, an acquiring unit 12, a voice recognition unit 13, an extracting unit 14, a display control unit 15, a selecting unit 16, and a specifying unit 15. It includes a section 17, a cutting section 18, a generating section 19, and a storage section 100.

The storage unit 100 stores an original video acquired by the acquisition unit 12, text with a time stamp extracted by the extraction unit 14, and a highlight video generated by the generation unit 19, which will be described later. Note that the original video and the time-stamped text may be deleted once the highlight video is generated. Note that in this embodiment, since the highlight video generation device 10 is a cloud server, the storage unit 100 is preferably configured with cloud storage or a distributed ledger.

The acquisition unit 12 acquires the original video and stores it in the storage unit 100. Specifically, the acquisition unit 12 acquires the original video from the user terminal 20 via the transmission/reception unit 11, or acquires the original video from the user terminal 20 via the transmission/reception unit 11 from a server or web page specified by a URL or the like. get. The acquisition unit 12 then stores the acquired original video in the storage unit 100.

The voice recognition unit 13 performs a process of recognizing the voice data of the original video acquired by the acquisition unit 12 and converting the voice into text data. For example, the speech recognition unit 13 converts speech data into text data by combining an acoustic model and a language model indicating linguistic constraints.

The extraction unit 14 extracts time-stamped text obtained by inserting a time stamp for each word into the text data obtained by the speech recognition unit 13. Specifically, the extraction unit 14 refers to the original video and acquires a time stamp for each word of the text obtained by the speech recognition unit 13. Then, the extraction unit 14 inserts the time stamp acquired for each word into the corresponding location of the text data, and extracts the time stamped text.
After inserting the timestamp obtained for each word into the corresponding location of the text data, the extraction unit 14 inserts the timestamp obtained for each word into the corresponding location of the text data, and then extracts a timestamp with the word of the frame linked to the timestamp of the first word of each frame of the original video. Text may also be extracted.

When the time-stamped text includes a filler, the extraction unit 14 may extract the time-stamped text by removing the filler, that is, by removing the filler and the time stamp of the filler. Fillers to be deleted are set in advance and held in the storage unit 100. Here, the filler is an utterance such as "ah" or "eh" that fills a gap in the conversation. Since fillers are useless words that are unrelated to the content of the uttered sentence, by deleting them from the timestamped text, the user can more easily select the desired portion.

The display control unit 15 generates editing screen data for instructing editing of the original video based on the time-stamped text extracted by the extraction unit 14, and transmits it to the user terminal 20. The editing screen data is capable of displaying a screen on the display unit (not shown) of the user terminal 20 that allows the user to select one word or a plurality of consecutive words from the time-stamped text in order to create a highlight video. This is the data.

Further, the editing screen data may be data that can display a screen that also has a function of searching for words in time-stamped text or a screen that also has a function of playing back the original video. Thereby, the user can easily search for the word he or she wants to select, and can also compare the time-stamped text and the original video on the editing screen.

In addition, if the time-stamped text includes filler, the editing screen data may be configured such that when displaying the time-stamped text on the display, the filler may be formatted differently from other characters, such as text size, color, font, etc. It may also have a function to change to . Note that the format of the filler may be selected by the user on the editing screen.

The selection section 16 is an editing screen displayed on the display section of the user terminal 20, and allows the user to select multiple sentences from the time-stamped text so that the timestamps are discontinuously arranged. Accept sentences. Specifically, in response to a plurality of sentences being selected by the user on the editing screen, the selection unit 16 determines whether or not the timestamps of the selected sentences are discontinuous with each other by referring to the timestamp-attached text. .

Then, if the timestamps of the selected sentences are not discontinuous, the selection unit 16 displays a message to that effect or outputs an error sound in order to prompt the user to reselect sentences on the editing screen. Instruct on the editing screen. On the other hand, the selection unit 16 accepts the selected sentences when the time stamps of the selected sentences are disjoint. In this way, by having the user select sentences so that the timestamps are scattered, it is possible to encourage the generation of an appropriate highlight video. This can prevent redundant highlight videos from being generated.

Further, when the user selects a plurality of sentences on the editing screen and also specifies the order in which the selected sentences are combined, the selection unit 16 receives the combination order along with the selected sentences. Further, when the user rewrites or deletes a part of the time-stamped text on the editing screen and selects the rewritten or deleted sentence, the selection unit 16 accepts the rewritten sentence.

The specifying unit 17 specifies the time range of each of the plurality of selected sentences based on the time-stamped text. Specifically, the specifying unit 17 specifies the time range of the selected sentence from the time stamp of the first word of the selected sentence to the time stamp of the word after the selected sentence from the time stamped text.

The cutting unit 18 cuts out a short video from the original video in the storage unit 100 based on each time range specified by the specifying unit 17. Specifically, the cutting unit 18 cuts out portions of the original video corresponding to each time range from the original video as short videos.

If the selected sentence contains a filler, the cutting unit 18 deletes the filler part from the part of the original video that corresponds to the time range specified by the specifying unit 17, and then extracts the filler from the original video as a short image. You can cut it out. In addition, if the user rewrites or deletes a part of the time-stamped text on the editing screen, and the selected sentence has been changed from the original video, the cutting unit 18 cuts out the cut short image into the changed selected sentence. You may edit to change it to .

The generation unit 19 combines the short videos cut out by the cutting unit 18 to generate a highlight video. Specifically, the generation unit 19 combines the short videos cut out by the cutting unit 18 in the order of timestamps or in the order of combination specified for the selected sentences received by the selection unit 16, and Generate light videos.

Furthermore, when combining short videos, the generation unit 19 adds a previously prepared video or still image before the first short video and/or after the last short video to generate a highlight image. Good too. This allows you to add titles and endings to highlight videos.

The generation unit 19 provides the generated highlight video to the user terminal 20 via the transmission/reception unit 11. Further, the generation unit 19 uploads the generated highlight video to a video site on the Internet via the transmission/reception unit 11, and provides the generated highlight video in URL format to the viewer.

Furthermore, if the generation unit 19 wants to change the file format of the highlight video from the file format of the original video, it converts the file format. The file format after conversion may be set by the user on the editing screen and accepted by the selection unit 16 together with the selection text, or may be determined depending on the video site or the like to which the highlight video is uploaded.

The functional configuration of the present system described above is just an example, and one functional block (database and functional processing unit) may be divided, or multiple functional blocks may be combined into one functional block. Each functional processing unit is stored in a storage device (storage unit) such as a ROM (Read Only Memory), flash memory, SSD (Solid State Drive), or hard disk by a CPU (Central Processing Unit) built into the device or terminal. This is realized by reading out a computer program (for example, core software or an application that causes the CPU to execute the various processes described above), and executing the computer program by the CPU. In other words, each functional processing unit reads and writes necessary data such as tables from a database (DB) stored in a storage device or a storage area in memory, and in some cases, This is realized by controlling hardware (for example, input/output devices, display devices, communication interface devices).

[Processing flow]
FIG. 3 is a diagram showing a highlight video generation process flow executed by the highlight video generation system according to the embodiment of the present invention. In this embodiment, the highlight video generation process is executed by the highlight video generation device.

First, the acquisition unit 12 acquires the original video from the network via the transmission/reception unit 11 based on the user terminal 20 or an instruction from the user terminal 20 (S11). Next, the voice recognition unit 13 performs voice recognition on the original video acquired in S11, and converts the voice into text data (S12). Next, the extraction unit 14 extracts time-stamped text by inserting a time stamp for each word into the text data obtained in S12 (S13).

Next, the display control unit 15 generates editing screen data for instructing editing of the original video based on the time-stamped text extracted in S13, and transmits it to the user terminal 20, and the display unit of the user terminal 30 An editing screen is displayed based on the editing screen data (S14). Next, the selection unit 16 allows the user to select a plurality of sentences from the time-stamped text on the editing screen displayed on the display unit of the user terminal 20 in S14, so that the timestamps are discontinuous, and selects The selected plurality of selected sentences are accepted (S15).

Next, the specifying unit 17 specifies the time range of each of the plurality of selected sentences received in S15, based on the time-stamped text (S16). Next, the cutting unit 18 cuts out a short video from the original video based on each time range specified in S16 (S17). The generation unit 19 then combines the short videos cut out in S17 to generate a highlight video (S18).

According to such a highlight video system, a user selects a sentence from time-stamped text generated from an original video, identifies a desired portion of the user, and generates a highlight video. This makes it easy for the user to select a desired portion, and it is easy for the user to generate a desired highlight video. As a result, it is possible to create a highlight video that summarizes only the parts that the user wants to see, and by allowing viewers to view the generated highlight video, a high marketing effect can be expected.

By having the user select sentences so that the timestamps are scattered, it is possible to encourage the generation of an appropriate highlight video, and it is also possible to encourage the generation of appropriate highlight videos. This can prevent the generation of highlight videos.

[Modified example]
(1) For example, the highlight video generation system may include a captioning section that adds a caption to the highlight video. The caption may be generated by the captioning unit based on the original video and/or the text with a timestamp, or the caption may be generated by the caption adding unit based on the original video and/or the text with a timestamp, or the caption may be generated by the user on the editing screen using a caption input by the user for the selected sentence or a caption selected from the selected sentence. It may also be received from the terminal 20. By adding captions to highlight videos, it is possible to clearly display what the user wants to convey or keep in mind.

(2) For example, the highlight video generation system may include an insertion unit that inserts sound data such as BGM and sound effects into the highlight video. Highlight videos can be shown more effectively to viewers, and higher marketing effects can be expected.

Although the present invention has been described above using the embodiments, it goes without saying that the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various changes or improvements can be made to the embodiments described above. Furthermore, it is clear from the claims that forms with such changes or improvements may also be included within the technical scope of the present invention. Note that in the above embodiments, the present invention is a product invention and the highlight video generation system has been described. However, in the present invention, the method executed by the highlight video generation system and the highlight video generation system functioning as various means It can also be seen as the invention of a program to do this.

1 Highlight video generation system 10 Highlight video generation device 11 Transmission/reception unit 12 Acquisition unit 13 Voice recognition unit 14 Extraction unit 15 Display control unit 16 Selection unit 17 Specification unit 18 Cutting unit 19 Generation unit 100 Storage unit 20 User terminal

The present invention provides a highlight video generation system that generates a highlight video by cutting and combining a plurality of short videos from an original video to be edited, comprising: an acquisition unit that acquires the original video; an extraction unit that extracts the audio of the original video as time-stamped text in which a time stamp is added to each word based on the result of the audio recognition; a display unit that displays the time-stamped text on an editing screen; and a display unit that allows a user to select one or a plurality of consecutive words from the time-stamped text on the editing screen; If the timestamps of the plurality of words to be selected are not consecutive , a selection unit that accepts the user's selection, and a time range of the plurality of selected words or the plurality of consecutive words, based on the time stamped text, A identifying section that specifies each, a cutting section that cuts out a portion corresponding to the specified time range from the original video as each short video, and a highlight video is generated by combining each of the cut short videos. Provided is a highlight video generation system comprising a generation unit that performs the following steps.

The present invention also provides a highlight video generation method executed by a computer , which includes the steps of acquiring the original video, audio recognizing the acquired original video, and generating the video based on the result of the audio recognition. a step of extracting the audio of the original video as time stamped text with a time stamp added to each word, a step of displaying the extracted time stamped text on an editing screen, and a step of displaying the time stamp on the editing screen. a step of allowing a user to select one or more consecutive words from the attached text , and accepting the user's selection if the timestamps of the multiple selected words or the multiple consecutive words are not consecutive; identifying the time ranges of the one or more consecutive words that have been identified based on the time-stamped text; The present invention provides a highlight video generation method including the steps of: cutting out the short videos as a short video; and combining the cut short videos to generate a highlight video.

The present invention also provides a highlight video generation system that generates a highlight video by cutting and combining a plurality of short videos from an original video to be edited, including an acquisition unit that acquires the original video. a voice recognition unit that recognizes the voice of the original video; an extraction unit that extracts the voice of the source video as time-stamped text with a time stamp added to each word based on the result of the voice recognition; and the extracted time stamp. a display unit that displays a text with a time stamp on an editing screen; a display unit that allows a user to select one or a plurality of consecutive words from the text with a timestamp on the editing screen; a selection section that accepts the user's selection when the timestamps are not consecutive , and a specification section that specifies the time range of the one or more consecutive words selected based on the timestamp text. , a cutting unit that cuts out portions corresponding to the specified time ranges from the original video as respective short videos, and a generation unit that combines the respective cut short videos to generate a highlight video. Provide programs.

Claims (9)

A highlight video generation system that generates a highlight video by cutting and combining multiple short videos from the original video to be edited,
an acquisition unit that acquires the original video;
a voice recognition unit that recognizes the voice of the acquired original video;
an extraction unit that extracts the audio of the original video as time-stamped text that holds a timestamp for each word, based on the result of the audio recognition;
a display unit that displays the extracted time-stamped text on an editing screen;
a selection unit that allows a user to select one or a plurality of consecutive words from the time stamped text on the editing screen so that the time stamps are discontinuous, and accepts the user's selection;
a specifying unit that specifies a time range of each of the plurality of selected words or a plurality of consecutive words based on the time-stamped text;
a cutting unit that cuts out portions corresponding to the respective specified time ranges from the original video as respective short videos;
a generation unit that generates a highlight video by combining each of the cut short videos;
Highlight video generation system. The highlight video generation system according to claim 1, wherein the generation unit further combines a previously prepared video at the beginning and/or the end of the highlight video. the selection unit accepts a selection of a combination order of the one or more consecutive words that are multiple selected;
3. The highlight video generation system according to claim 1, wherein the generation unit generates a highlight video by combining each of the cut short videos according to the order of combination. Claims 1 to 3, wherein the display unit deletes the filler or displays the filler on the editing screen so that the filler can be distinguished from words other than the filler when the extracted time-stamped text includes a filler. The highlight video generation system according to any one of Item 3. When the plurality of selected words or the plurality of consecutive words include a filler, the cutting portion removes a portion corresponding to the filler from among the portions corresponding to the respective specified time ranges from the original video. 5. The highlight video generation system according to claim 1, wherein each portion is cut out as a short video. The highlight video generation system according to any one of claims 1 to 5, further comprising a captioning section that adds a caption to the highlight video. The highlight video generation system according to any one of claims 1 to 6, further comprising a music insertion section that adds music to the highlight video. A method executed by a highlight video generation system that generates a highlight video by cutting and combining multiple short videos from an original video to be edited, the method comprising:
obtaining the original video;
a step of audio recognizing the acquired original video;
Based on the result of the voice recognition, extracting the voice of the original video as time-stamped text that retains a time stamp for each word;
displaying the extracted time-stamped text on an editing screen;
On the editing screen, allowing the user to select one or more consecutive words from the timestamped text so that the timestamps are discontinuous, and accepting the user's selection;
identifying a time range of each of the one or more consecutive words selected based on the time-stamped text;
cutting out portions corresponding to the respective specified time ranges from the original video as respective short videos;
combining each of the cut short videos to generate a highlight video;
Highlight video generation system including. A highlight video generation system that cuts and combines multiple short videos from the original video to be edited to create a highlight video.
an acquisition unit that acquires the original video;
a voice recognition unit that recognizes the voice of the acquired original video;
an extraction unit that extracts the audio of the original video as time-stamped text that holds a timestamp for each word, based on the result of the audio recognition;
a display unit that displays the extracted time-stamped text on an editing screen;
a selection unit that allows a user to select one or a plurality of consecutive words from the time stamped text on the editing screen so that the time stamps are discontinuous, and accepts the user's selection;
a specifying unit that specifies each of the time ranges of the one or a plurality of consecutively selected words based on the time-stamped text;
a cutting unit that cuts out portions corresponding to the respective specified time ranges from the original video as respective short videos;
a generation unit that generates a highlight video by combining each of the cut short videos;
A program that functions as

Images