JP2018121181A - Edition device and edition program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To allow even members not participating in the conference to efficiently understand the content that is hard to understand for members not participating in the conference.SOLUTION: An information processing apparatus 1 includes a keyword input receiving section 103 for receiving input of keyword from a user, a text converting section 104 for converting voice indicated by voice data, based on the voice data in video voice data stored in a video voice data storage section 51, specifying section 105 for specifying the text part including the keyword received by the keyword input receiving section 103, among the text indicated by the text data, based on the text data obtained by the text converting section 104, and an editing section 106 for creating another video voice data consisting of the same time-domain part as the voice part becoming the source of the text part specified by the specifying section 105 anew.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an editing apparatus and an editing program, and more particularly, to a technique for editing video / audio obtained by shooting a meeting or the like.

  Normally, members who do not participate in a meeting will check the contents of the minutes (for example, conclusions, issues, action items) by referring to the minutes, but the minutes can be understood only from the minutes. Even so, it is difficult to feel the atmosphere of the meeting. It is also difficult to grasp the background and flow that led to the conclusions described in the minutes.

  Therefore, at present, there are cases where the content of the conference can be confirmed by video and audio by shooting the conference. If you confirm the contents of the meeting with video and audio, you can feel the atmosphere of the meeting that cannot be grasped only from the minutes. However, if the meeting is 60 minutes, it must be viewed for 60 minutes, which is not efficient.

  In the following Patent Document 1, a minutes is created by linking a video and audio of a meeting taken with a memo (a memo created by a person in charge of the minutes) so that the video and audio corresponding to the memo can be easily browsed. It is described.

JP 2008-172582 A

  In the invention described in Patent Document 1 above, if the user designates a memo, the video and audio corresponding to the designated memo are individually played back, so it is not necessary to view all the video and audio shot. The time can be shortened.

  However, in the invention described in Patent Document 1, it is troublesome for the user to check the memo and the video and audio at the same time. Also, because the user is not always able to specify the location that is spoken about the content that is the heart of the conference (eg, conclusions, issues, action items), it is possible to feel the conference atmosphere efficiently. I can not say.

  The present invention has been made in view of the above circumstances, and it is difficult for a person who has not been on the site (for example, a member who has participated in the conference) The purpose is to be able to grasp efficiently even members who are not).

  An editing apparatus according to one aspect of the present invention includes a video / audio data storage unit that stores video / audio data, a keyword input reception unit that receives a keyword input from a user, and a video / audio stored in the video / audio data storage unit. A text conversion unit that converts the voice indicated by the voice data into text based on the voice data in the data, and the text data indicated by the text data based on the text data obtained by the conversion by the text conversion unit. The text part specified by the specifying unit using the specifying unit for specifying the text part including the keyword received by the keyword input receiving unit and the video / audio data stored in the video / audio data storage unit Create another video / audio data consisting of the same time domain part as the original audio part It includes a collection unit.

  An editing program according to one aspect of the present invention is based on audio data in a video / audio data stored in a video / audio data storage unit and a video / audio data storage unit that receives a keyword input from a user. A keyword conversion unit that converts the voice indicated by the voice data into text, and the keyword input reception unit receives the text indicated by the text data based on the text data obtained by the conversion by the text conversion unit. The same time as the audio part that is the basis of the text part specified by the specifying unit using the specifying unit for specifying the text part including the keyword and the video / audio data stored in the video / audio data storage unit It functions as an editing section that creates new video and audio data consisting of areas. .

  According to the present invention, a video / audio digest organized based on keywords (words having important meanings) input by a user is generated. That is, a digest containing an important part is generated. Therefore, even if the person who was not on the spot where the video and audio were shot (for example, a member who did not participate in the meeting), by viewing the generated digest, the person who was on the spot (for example, the meeting) It is possible to efficiently grasp the content (for example, the atmosphere of the meeting) that is difficult to grasp unless the member is a member who participated in.

1 is a functional block diagram schematically showing a main internal configuration of an editing apparatus according to a first embodiment of the present invention. It is the flowchart which showed an example of the processing operation performed with the control unit in the editing apparatus which concerns on 1st Embodiment. It is the figure which showed an example of the operation screen displayed on a display part. It is the figure which showed an example of the content of the statement in a meeting. It is explanatory drawing for demonstrating the temporal relationship between the image | video which video data shows, the audio | voice which audio | voice data shows, and the text which text data shows. It is the functional block diagram which showed roughly the main internal structure of the editing apparatus which concerns on 2nd Embodiment. It is the flowchart which showed an example of the processing operation performed with the control unit in the editing apparatus which concerns on 2nd Embodiment.

  Embodiments of an editing apparatus and an editing program according to the present invention will be described below with reference to the drawings. FIG. 1 is a functional block diagram schematically showing the main internal configuration of an editing apparatus in which an editing program according to the first embodiment of the present invention is installed. The editing device 1 is an electronic device such as a personal computer (PC), for example, and includes a display unit 10, a voice output unit 20, an operation unit 30, a communication unit 40, a storage unit 50, and a control. Unit 100. Each of these components can transmit and receive data or signals with each other via a communication bus.

  The display unit 10 includes a liquid crystal display (LCD), an organic EL (OLED: Organic Light-Emitting Diode), and the like. The display unit 10 displays responses from the control unit 100, data results, and the like, and is provided with a touch panel function. The user can operate the editing apparatus 1 by touching an image displayed on the screen. .

  The audio output unit 20 is a speaker or the like and outputs audio.

  The operation unit 30 is a mouse, a keyboard, or the like, and receives various instructions from the user regarding various operations and processes that can be executed by the editing apparatus 1.

  The communication unit 40 is a communication interface including a communication module such as a LAN (Local Area Network) chip (not shown).

  For example, the editing apparatus 1 is connected to the video camera 200, and a control unit 101 described later transmits and receives data to and from the video camera 200 via the communication unit 40, and is stored in the video camera 200. Audio data (consisting of video data and audio data, and data in which these video data and audio data are synchronized) can be acquired.

  The storage unit 50 is a large-capacity storage device such as an HDD (Hard Disk Drive). The storage unit 50 stores a control program, the editing program described above, and the like, and a video / audio data storage unit 51 and an editing data storage unit 52 described later.

  The control unit 100 includes a processor, a RAM (Random Access Memory), a ROM (Read Only Memory), and a dedicated hardware circuit. The processor is, for example, a central processing unit (CPU), an application specific integrated circuit (ASIC), or a micro processing unit (MPU). The control unit 100 includes a control unit 101, an operation receiving unit 102, a text conversion unit 104, a specifying unit 105, and an editing unit 106.

  The control unit 100 functions as the control unit 101, the operation receiving unit 102, the text conversion unit 104, the specifying unit 105, and the editing unit 106 by the operation of the processor according to the control program stored in the storage unit 50. Is. However, the control unit 101 and the like can be configured by a hardware circuit regardless of the operation according to the control program by the control unit 100 or the like. The same applies to each embodiment unless otherwise specified.

  The control unit 101 governs overall operation control of the editing apparatus 1. The control unit 101 is connected to the display unit 10, the audio output unit 20, the operation unit 30, the communication unit 40, and the storage unit 50, and performs drive control of these units. For example, the control unit 101 acquires video / audio data stored in the video camera 200 via the communication unit 40, constructs a video / audio data storage unit 51 in the storage unit 50, and displays the acquired video / audio data as video. The data is stored in the audio data storage unit 51.

  The operation reception unit 102 specifies a user operation input by the user based on a detection signal output from the display unit 10 or the operation unit 30 provided with a touch panel function. Then, the operation reception unit 102 receives the specified user operation and outputs a control signal corresponding to the user operation to the control unit 101 or the like. The operation reception unit 102 includes a keyword input reception unit 103.

  Based on the audio data in the video / audio data stored in the video / audio data storage unit 51, the text conversion unit 104 converts the audio indicated by the audio data into text.

  Based on the text data obtained by the conversion by the text conversion unit 104, the specification unit 105 specifies a text portion including the keyword received by the keyword input reception unit 103 from the text indicated by the text data.

  The editing unit 106 uses the video / audio data stored in the video / audio data storage unit 51 to generate another video / audio data including the same time domain portion as the original audio portion of the text portion specified by the specifying unit 105. Create a new. For example, the editing unit 105 reads the audio / video data in the same time domain as the audio part that is the original of the text part specified by the specifying unit 105 from the audio / video data storage unit 51, and newly reads the read audio / video data. Another video / audio data.

  Next, the operation of the editing apparatus 1 having the above configuration will be described. FIG. 2 is a flowchart showing the processing operation when the editing program is executed by the control unit 100 of the editing apparatus 1. This processing operation is executed when the operation receiving unit 102 receives an editing request for video / audio data stored in the video / audio data storage unit 51.

  When the operation accepting unit 102 accepts the editing request, the keyword input accepting unit 103 accepts keyword user input by displaying an operation screen D1 as shown in FIG. 3 on the display unit 10, for example (S1). . The operation screen D1 includes a display area E1 for displaying a character string input via the operation unit 30 and a determination button B1 labeled “OK”. The keyword input reception unit 103 receives the determination button B1. When an operation is accepted, the character string input by the user is stored as a keyword.

  Subsequently, based on the audio data in the video / audio data stored in the video / audio data storage unit 51, the text conversion unit 104 converts the audio indicated by the audio data into text (S2). In addition, since a known technique is used for conversion of speech into text, detailed description thereof is omitted.

  Subsequently, the specifying unit 105 specifies a text portion including the keyword received by the keyword input receiving unit 103 from the text indicated by the text data based on the text data obtained by the conversion by the text converting unit 104. (S3).

  FIG. 4 is a diagram illustrating an example of the content of the remarks at the conference. For example, when the keyword received by the keyword input receiving unit 103 is “XXX”, the specifying unit 105 displays the underlined portions P1 to P3. Is identified as the text portion containing the keyword.

  Subsequently, the editing unit 106 starts from a predetermined time region before and after the same time region including the same time region as the original voice part of the text portion specified by the specifying unit 105 (for example, one minute before and after each). Is read from the video / audio data storage unit 51 (S4).

  FIG. 5 is an explanatory diagram for explaining the temporal relationship between the video indicated by the video data, the audio indicated by the audio data, and the text indicated by the text data. In the figure, V1 to V3 indicate the time areas of the voice parts that are the origins of the text parts P1 to P3, respectively. In the figure, V11 and V12 indicate the predetermined time areas before and after the time area V1, and V21 in the figure. , V22 indicate the predetermined time region before and after the time region V2, and V31 and V32 in the figure indicate the predetermined time region before and after the time region V3.

  In S4, the editing unit 106 reads out the video / audio data of the time regions V11, V1, V12, the time regions V21, V2, V22, and the time regions V31, V3, V32 from the video / audio data storage unit 51.

  For example, when the video / audio data has time information indicating an elapsed time from a reference time (for example, a shooting start time), the text data also has time information indicating the elapsed time. The editing unit 106 identifies a section including the designated text from the video / audio data based on the time information. Based on this time information, the audiovisual data and the text data are synchronized as described above. For this reason, the editing unit 106 converts video / audio data composed of a predetermined time region before and after the same time region including the same time region as the audio portion that is the basis of the text portion specified by the specifying unit 105 into video / audio. It is possible to read from the data storage unit 51.

  Subsequently, the editing unit 106 generates new video / audio data as editing data using the read video / audio data (S5), constructs the editing data storage unit 52 in the storage unit 50, and generates the generated editing data. The data is stored in the edit data storage unit 52 (S6).

  With respect to the edit data stored in the edit data storage unit 52, when the operation receiving unit 102 receives a reproduction request for the edit data, the control unit 101 reads the edit data from the edit data storage unit 52 and reproduces it. Thus, the video is displayed on the display unit 20 and the audio is generated from the audio output unit 20.

  According to the first embodiment, a video / audio digest organized based on keywords (words having important meanings) input by the user is generated. That is, a digest containing an important part is generated. Therefore, even if the person who was not on the spot where the video and audio were shot (for example, a member who did not participate in the meeting), by viewing the generated digest, the person who was on the spot (for example, the meeting) It is possible to efficiently grasp the content (for example, the atmosphere of the meeting) that is difficult to grasp unless the member is a member who participated in.

  FIG. 6 is a functional block diagram schematically showing the main internal configuration of the editing apparatus in which the editing program according to the second embodiment is installed. The editing apparatus 1A according to the second embodiment is different from the editing apparatus 1 shown in FIG. 1 in that the text data obtained by conversion by the text conversion unit 104 is divided into a plurality of blocks in a predetermined unit. The difference is that the control unit 100A includes the unit 107.

  Next, the operation of the editing apparatus 1A according to the second embodiment will be described. FIG. 7 is a flowchart showing the processing operation when the editing program is executed by the control unit 100A of the editing apparatus 1A. This processing operation is executed when the operation receiving unit 102 receives an editing request for video / audio data stored in the video / audio data storage unit 51.

  When the operation accepting unit 102 accepts the request, the keyword input accepting unit 103 accepts a keyword user input (S11), and the text converting unit 104 stores the audio / video data stored in the audio / video data storage unit 51. Based on the voice data in the middle, the voice indicated by the voice data is converted into text (S12). Then, the dividing unit 107 divides the text data obtained by the conversion by the text converting unit 104 into a plurality of blocks in a predetermined unit (for example, a speech unit) (S13).

  Since it is considered that the silence period continues for a certain time or more between the statements, for example, the dividing unit 107 divides the text data into a plurality of blocks based on the length of the silence period. When the silent time lasts for example 5 seconds as a predetermined time, the dividing unit 107 separates each text data portion corresponding to a portion that exists before and after the silent time and does not have the silent time. Let it be a block. In the example shown in FIG. 4, the dividing unit 107 sets, for example, “What is the merit of the AAA plan?” As one block, and “YAY is the merit of the AAA plan”. ”As a single block.

  Subsequently, the specifying unit 105 specifies a block including the keyword received by the keyword input receiving unit 103 from the text indicated by the text data based on the text data obtained by the conversion by the text converting unit 104 ( S14).

  For example, when the keyword received by the keyword input receiving unit 103 is “XXX”, the specifying unit 105 illustrated in FIG. 4 “A problem of the AAA plan is XXX”, “Can XXX be solved?”, “ The conclusion is “approved if the XXX problem can be solved” is specified as a block including a keyword.

  Subsequently, the editing unit 106 reads out the audio / video data in the same time domain as the audio part that is the source of the text part belonging to the block specified by the specifying unit 105 from the audio / video data storage unit 51 (S15). Editing data is generated by connecting the video and audio data (S16), the editing data storage unit 52 is constructed in the storage unit 50, and the generated editing data is stored in the editing data storage unit 52 (S17).

  According to the second embodiment, since a block including a keyword is specified, for example, an utterance including a keyword is taken as one lump, and video and audio data corresponding to the block can be read out.

  In another embodiment, in the same way as in the first embodiment, not only the same time region as the voice part that is the source of the text part belonging to the block specified by the specifying unit 105 but also the editing unit 106 Alternatively, the video / audio data in a predetermined time region (for example, one minute before and after each) may be read from the video / audio data storage unit 51.

  The present invention is not limited to the configuration of the above embodiment, and various modifications can be made. Moreover, although the said embodiment demonstrated using the personal computer as one Embodiment of the editing apparatus which concerns on this invention, this is only an example and may be other electronic devices, such as a smart phone and a tablet, for example.

  Moreover, in the said embodiment, the structure and process which were shown by the said embodiment using FIG. 1 thru | or FIG. 7 are only one Embodiment of this invention, and are not the meaning which limits this invention to the said structure and process.

1, 1A editing device 51 video / audio data storage unit 103 keyword input reception unit 104 text conversion unit 105 identification unit 106 editing unit 107 division unit

Claims (4)

A video / audio data storage unit for storing video / audio data;
A keyword input accepting unit that accepts keyword input from the user;
A text conversion unit that converts audio represented by the audio data into text based on audio data in the audio / video data stored in the audio / video data storage unit;
Based on the text data obtained by the conversion by the text conversion unit, from the text indicated by the text data, a specifying unit for specifying a text part including the keyword received by the keyword input receiving unit,
Using the video / audio data stored in the video / audio data storage unit, newly create another video / audio data composed of the same time domain part as the original audio part of the text part specified by the specifying unit And an editing unit. Further comprising a dividing unit that divides the text data obtained by the conversion by the text conversion unit into a plurality of blocks in a predetermined unit;
The specifying unit specifies the block including the keyword received by the keyword input receiving unit from the text indicated by the text data based on the text data obtained by the conversion by the text conversion unit,
The editing apparatus according to claim 1, wherein the editing unit newly creates another video / audio data including a time region portion that is the same as an audio portion that is a source of a text portion belonging to the block specified by the specifying unit.   The editing unit reads out the video / audio data including a predetermined time domain before and after the same time domain including the same time domain from the video / audio data storage unit, and creates the new video / audio data. The editing apparatus according to claim 1 or 2. Computer
A keyword input accepting unit that accepts keyword input from the user;
A text conversion unit that converts audio represented by the audio data into text based on audio data in the audio / video data stored in the audio / video data storage unit;
Based on the text data obtained by the conversion by the text conversion unit, from the text indicated by the text data, a specifying unit for specifying a text part including the keyword received by the keyword input receiving unit,
Using the video / audio data stored in the video / audio data storage unit, newly create another video / audio data composed of the same time domain part as the original audio part of the text part specified by the specifying unit An editing program that functions as an editing section.