JP5777233B1 - Movie generation apparatus and movie generation method - Google Patents

Abstract

A moving image corresponding to a character is generated in real time. A moving image generating apparatus includes: a voice receiving unit that receives input of a character's voice from a voice person in charge; a voice output unit that outputs the received voice to a terminal of a person in charge of operation; Thereafter, an operation accepting unit 143 that receives the operation of the character corresponding to the voice from the operation person in charge terminal 2, a synthesizing unit 145 that synthesizes the audio and the video corresponding to the operation to generate a character video, and the generated character A moving image output unit 146 for outputting the moving image. [Selection] Figure 2

Description

  The present invention relates to a moving image generating apparatus and a moving image generating method.

  2. Description of the Related Art Conventionally, in the production of moving images such as anime in which characters appear, voice actors blow the sound of characters appearing in moving images (see, for example, Patent Document 1). In production of such a moving image, a scenario is first created, and a moving image without sound is generated based on the scenario. Then, the voice actor blows sound based on the scenario while watching the action of the character in the video.

JP-A-5-232601

  However, in conventional video production, there is a problem that it takes time to complete a video with sound because a video without sound is created based on a scenario and then sound is blown into the video. . For this reason, for example, there has been a problem that a live broadcast in which a character such as an anime character appears or a character cannot respond in real time in response to a request from a viewer.

  Therefore, the present invention has been made in view of these points, and an object thereof is to provide a moving image generating apparatus and a moving image generating method capable of generating a moving image corresponding to a character in real time.

  The moving image generating apparatus according to the first aspect of the present invention includes a voice receiving unit that receives input of a character's voice from a voice person, a voice output part that outputs the received voice to the terminal of the person in charge, and the voice is After being output, a composition for generating a motion picture of the character by synthesizing the motion and the motion corresponding to the motion from the terminal of the person in charge of motion and the motion corresponding to the motion And a moving image output unit that outputs the generated moving image of the character.

  The moving image generating apparatus further includes an emotion receiving unit that receives emotion information indicating the emotion of the character corresponding to the voice from the voice person, and the motion receiving unit receives the emotion information received from the voice person May be displayed on the terminal of the person in charge of the action, and the action of the character corresponding to the emotion information may be received.

  The motion accepting unit may accept the motion of the character by displaying information indicating a plurality of motions of the character on the terminal of the person in charge of the motion and accepting selection of one motion from the motions. .

  The action accepting unit displays information indicating a plurality of actions of the character corresponding to the emotion on the terminal of the person in charge of the action, and accepts selection of one action from the plurality of actions, thereby moving the action of the character May be accepted.

  The moving image generating apparatus includes a storage unit that associates and stores the emotion of the character and background music, and a selection unit that selects the background music corresponding to the emotion indicated by the emotion information with reference to the storage unit The synthesizing unit may generate the character video by synthesizing the voice, the video corresponding to the motion, and the selected background music.

  The synthesizing unit may synthesize the sound and the moving image corresponding to the action by synchronizing the time when the reproduction of the sound starts and the time when the action of the character corresponding to the sound starts. .

  The moving image generation apparatus further includes a storage unit that stores audio information indicating the received audio, the synthesizing unit acquires the audio information stored in the storage unit, and reproduces the audio indicated by the audio information. The sound and the moving image corresponding to the motion may be synthesized by synchronizing the start time and the time when the character's motion starts.

  The moving image generation apparatus further includes a conversion unit that converts received speech into text, and the operation reception unit displays the text converted by the conversion unit on a terminal of the operation person, and the operation person The movement of the character may be received from the terminal.

  The moving image output unit ends the output of the moving image corresponding to the received operation and outputs the moving image of the character corresponding to the state where the sound is not input in response to the completion of the output of the received sound. May be.

  The audio output unit outputs the received audio to the terminal of the director in charge of production, and the video generation device receives information related to the production of the video from the terminal of the director in charge of production after the voice is output. An effect receiving unit may be further included, and the composition unit may add an effect corresponding to the effect to the synthesized animation of the character.

  The moving image generating method according to the second aspect of the present invention includes a step of receiving an input of a character's voice from a voice person, a step of outputting the received voice to a terminal of the person in charge, which is executed by a computer; After the voice is output, the step of receiving the motion of the character corresponding to the voice from the terminal of the person in charge of the operation, and the step of generating the video of the character by synthesizing the voice and the video corresponding to the motion And outputting the generated animation of the character.

  According to the present invention, there is an effect that a moving image corresponding to a character can be generated in real time.

It is a figure which shows the outline | summary of the moving image production | generation system which concerns on 1st Embodiment. It is a figure which shows the structure of the moving image production | generation apparatus which concerns on 1st Embodiment. It is a sequence diagram which shows the flow of a process until a moving image production | generation apparatus outputs the moving image of a character. It is a figure which shows an example of the information regarding a character's operation | movement. It is a figure which shows an example of the information regarding background music. It is a figure which shows an example of the information regarding a sound effect. It is a figure explaining a synthesis | combination with the moving image corresponding to an audio | voice and operation | movement. It is a figure which shows an example of the moving image of a character. It is a figure which shows the structure of the moving image production | generation apparatus which concerns on 2nd Embodiment. It is a figure which shows the structure of the moving image production | generation apparatus which concerns on 3rd Embodiment.

Hereinafter, embodiments of the present invention will be described.
<First Embodiment>
[Outline of Movie Generation System S]
FIG. 1 is a diagram illustrating an overview of a moving image generation system S according to the first embodiment.
The moving image generating system S includes a moving image generating device 1, an operation person in charge terminal 2, and an effect person in charge terminal 3. The moving image generating device 1, the operation person in charge terminal 2, and the production person in charge terminal 3 are computers including a storage unit and a control unit. The moving image generating apparatus 1 is connected to the operation staff terminal 2 and the rendering staff terminal 3 via a communication network such as a LAN or the Internet so as to be communicable.

  The moving image generating apparatus 1 is a computer such as a server that generates a moving image of a character appearing in an animation or the like. Specifically, the moving image generating apparatus 1 receives an input of the character's voice from a voice person in charge of the character's voice ((1) in FIG. 1). When the moving image generating apparatus 1 receives the voice of the character, the moving picture generating apparatus 1 outputs voice information indicating the voice to the operation staff terminal 2 and the production staff terminal 3 ((2) in FIG. 1).

  The moving image generating apparatus 1 receives motion information indicating the motion of the character corresponding to the voice from the motion staff terminal 2 and background music (hereinafter referred to as BGM) corresponding to the voice or lighting effect from the director staff terminal 3. Production information indicating production such as the above is received ((3), (4) in FIG. 1).

  The moving image generating apparatus 1 combines the received sound and the moving image corresponding to the motion information, and generates a moving image of the character by adding a rendering effect indicated by the rendering information to the combined moving image (FIG. 1). (5)). The moving image generating device 1 outputs the generated moving image of the character ((6) in FIG. 1).

As described above, the moving image generating apparatus 1 can output a moving image in which a character operates while speaking. Also, in the video generation device 1, even if the voice person does not follow the scenario and improvises the voice of the character, the action person determines the character's movement so as to correspond to the voice. A video can be generated. Therefore, the moving image generating device 1 can generate a moving image of a character with sound in real time in response to the sound uttered by the sound person in charge.
Hereinafter, the configuration and operation of the moving image generating apparatus 1 will be described.

[Configuration example of moving image generation apparatus 1]
FIG. 2 is a diagram illustrating a configuration of the moving image generating apparatus 1 according to the first embodiment. The moving image generating apparatus 1 includes a communication unit 11, a microphone 12, a storage unit 13, and a control unit 14.

The communication unit 11 is a communication interface for connecting to a communication network, and includes, for example, a LAN controller.
The microphone 12 receives voice input from the user of the video generation device 1 and outputs the input voice to the control unit 14. In the present embodiment, the microphone 12 receives an input of voice from a voice person in charge of the voice of the character.

  The storage unit 13 is configured by, for example, a ROM and a RAM. The storage unit 13 stores various programs for causing the moving image generating apparatus 1 to function. The storage unit 13 causes the control unit 14 of the video generation device 1 to function as a voice reception unit 141, a voice output unit 142, an operation reception unit 143, an effect reception unit 144, a synthesis unit 145, and a video output unit 146 to be described later. Store the generation program. The storage unit 13 may read and store a program stored in a storage medium such as an external memory, or may store a program downloaded from an external device via a communication network. In addition, the storage unit 13 stores a moving image corresponding to the character's motion, a BGM reproduced according to the character's motion, a moving image editing program for setting a lighting effect on the moving image, and the like. In addition, the storage unit 13 includes an audio buffer 131 that temporarily stores audio information indicating the audio received from the audio staff.

  The control part 14 is comprised by CPU, for example. The control unit 14 controls functions related to the moving image generating device 1 by executing various programs stored in the storage unit 13. The control unit 14 includes an audio reception unit 141, an audio output unit 142, an operation reception unit 143, an effect reception unit 144, a synthesis unit 145, and a moving image output unit 146.

  Hereinafter, functions provided in the control unit 14 will be described with reference to a sequence showing a flow of processing until the moving image generation apparatus 1 outputs a character moving image. FIG. 3 is a sequence diagram showing a flow of processing until the moving image generating apparatus 1 outputs a character moving image.

First, the voice reception unit 141 receives an input of a character's voice from the voice staff via the microphone 12 (S1), and stores voice information indicating the input voice in the voice buffer 131 (S2). The audio information is, for example, digital data generated by digitally encoding an analog audio signal. The voice reception unit 141 receives voice information indicating voice input at the voice officer terminal from a voice officer terminal (not shown) used by the voice officer, thereby inputting the character's voice. You may make it accept.
Subsequently, the voice output unit 142 outputs voice information indicating the voice of the character received by the voice reception unit 141 to the operation staff terminal 2 and the production staff terminal 3.

  Subsequently, after the voice output unit 142 outputs the voice of the character to the action staff terminal 2, the action accepting section 143 receives action information indicating the action of the character corresponding to the voice of the character from the action staff terminal 2. The operation is accepted by receiving (S3). Specifically, the motion accepting unit 143 displays information indicating a plurality of motions of the character on the motion staff terminal 2, and accepts the motion of the character by accepting selection of one motion from the plurality of motions.

  More specifically, for example, as shown in FIG. 4, in the storage unit 13, as information indicating a plurality of character actions, the character emotions, the character facial expressions corresponding to the character emotions, and the character actions are stored. And a moving image corresponding to the emotion, facial expression, and action are stored in association with each other. In the example shown in FIG. 4, emotions and facial expressions are associated one-to-one, but a plurality of facial expressions may be associated with one emotion.

  The motion reception unit 143 displays information indicating a plurality of emotions of the character and an image indicating the facial expression of the character corresponding to the emotions on the motion officer terminal 2 in advance. The motion accepting unit 143 accepts selection of the character's emotion corresponding to the character's voice from the motion staff terminal 2 in response to the voice output unit 142 outputting the character's voice.

  When the emotion of the character is selected, the motion accepting unit 143 displays a motion selection screen for accepting selection of one motion from a plurality of motions associated with the emotion on the motion officer terminal 2. When one operation is selected on the operation selection screen, the operation person-in-charge terminal 2 transmits operation information indicating the selected one operation to the moving image generating apparatus 1. The motion accepting unit 143 receives the motion information and accepts selection of one motion corresponding to the selected emotion.

  The action accepting unit 143 may display information indicating a plurality of actions of the character on the action person terminal 2 in synchronization with the timing when the voice output unit 142 outputs the voice information. For example, the motion reception unit 143 causes the motion person terminal 2 to display information indicating a plurality of motions of the character at the same time as the voice output unit 142 outputs the voice information. By doing in this way, it becomes easy for the person in charge of operation to select the character's emotion and action in accordance with the timing when the person in charge of voice inputs the sound.

  The operation receiving unit 143 receives an instruction for controlling the timing at which the audio output unit 142 outputs audio information from the operation person in charge terminal 2, and based on the received instruction, The output may be stopped, or the output audio may be output again. In this way, the audio output unit 142 can read out and output audio information corresponding to the instruction from the audio buffer 131 at a timing based on the instruction received by the operation receiving unit 143. Even if the selected operation is wrong, it can be corrected to an appropriate operation.

  A plurality of operation staff terminals 2 may be provided. For example, when two operation staff terminals 2 are provided, the operation reception unit 143 receives an emotion selection from one operation staff terminal 2 and receives an operation selection from the other operation staff terminal 2. Also good.

  Subsequently, after the voice output unit 142 outputs the voice of the character to the director-in-charge person terminal 3, the stage reception unit 144 receives the stage information related to the production of the character video from the director-in-charge terminal 3 (S4).

  Specifically, as illustrated in FIG. 5, the storage unit 13 stores a title of background music (hereinafter referred to as “BGM”) and a BGM file in association with each other. The effect receiving unit 144 displays a plurality of BGM titles in advance on the effect person in charge terminal 3. In response to the fact that the voice output unit 142 has output the voice of the character, the stage reception unit 144 receives a selection of the title of the BGM that is played along with the voice of the character from the stage person in charge of the stage 3. The effect receiving unit 144 receives information indicating the title from the effect person in charge terminal 3 as effect information in response to selection of the BGM title.

  As shown in FIG. 6, the storage unit 13 stores a sound effect category, information indicating the content of the sound effect, and a sound effect file in association with each other. The effect receiving unit 144 displays the category corresponding to each of the plurality of sound effects on the effect person in charge terminal 3. The effect receiving unit 144 receives a selection of the category in response to the voice output unit 142 outputting the voice of the character. When the category is selected, the effect receiving unit 144 displays information indicating the content of the sound effect corresponding to the category on the effect person in charge terminal 3 and receives the selection of the sound effect. In response to the selection of the sound effect, the effect receiving unit 144 receives information indicating the sound effect from the effect person in charge terminal 3 as effect information.

  In addition, the storage unit 13 stores information indicating the types of lighting effects that can be applied to a moving image of a character. The effect receiving unit 144 displays information indicating a plurality of types of lighting effects on the effect person in charge terminal 3. The effect receiving unit 144 receives a selection of the type of lighting effect in response to the voice output unit 142 outputting the voice of the character. In response to the selection of the type of lighting effect, the effect receiving unit 144 receives information indicating the type from the effect person in charge terminal 3 as effect information.

By doing in this way, the animation production | generation apparatus 1 can receive the production effect suitable for the said voice which the production person in charge using the production person in charge terminal 3 selected while listening to the voice of a character.
In the above description, the moving image generating apparatus 1 has been described as receiving the effect information indicating the effect after receiving the operation information indicating the operation. However, the operation information and the effect information may not be received in this order. For example, the moving image generating apparatus 1 may receive the operation information after receiving the production information, or may receive the production information and the operation information at the same time.

  Subsequently, the synthesizing unit 145 synthesizes the audio received by the audio receiving unit 141 and the moving image corresponding to the operation received by the operation receiving unit 143 to generate a moving image with the character audio (S5). Specifically, the synthesizing unit 145 synthesizes the sound and the moving image corresponding to the operation by synchronizing the time when the reproduction of the sound starts and the time when the action of the character corresponding to the sound starts.

FIG. 7 is a diagram for explaining synthesis of audio and a moving image corresponding to an operation.
As shown in FIG. 7, when the voice reception unit 141 receives a voice at time t1, and the voice buffer 131 starts storing voice information indicating the voice, the synthesis unit 145 has a predetermined waiting time Wt. The elapsed time t3 is set as the time when the output of the character moving image is started.

  Subsequently, the synthesizing unit 145 determines that the operation received by the operation receiving unit 143 by the time t3 is the operation corresponding to the voice. In the example illustrated in FIG. 7, the synthesis unit 145 determines that the operation received at time t2 is an operation corresponding to voice. Then, the synthesizing unit 145 sets the time when the reproduction of the moving image corresponding to the operation is started as the time t3 when the reproduction of the moving image starts.

  Subsequently, the synthesizing unit 145 acquires the audio information stored in the audio buffer 131, and synthesizes the audio indicated by the audio information and the video corresponding to the received operation to generate a video with the character audio. To do.

  The combining unit 145 also adds an effect corresponding to the effect to the combined character animation. The composition unit 145 determines the effect indicated by the effect information received by the effect receiving unit 144 by the time t3 as an effect corresponding to the voice. The synthesizing unit 145 sets the time at which the effect is started as the time t3 when the reproduction of the moving image starts, and adds an effect corresponding to the effect to the synthesized character moving image.

  The moving image output unit 146 outputs a moving image of the generated character at time t3 (S6). Here, the video corresponding to the motion accepted by the motion accepting unit 143 is continuously output even though the input of the voice corresponding to the video of the character started to be output by the video output unit 146 at time t3 is completed. Then, the person who watches the animation of the character feels uncomfortable. Therefore, the video output unit 146 outputs the video corresponding to the motion accepted by the motion accepting unit 143 in response to the completion of the output of the voice accepted by the voice accepting unit 141 during the output of the generated video of the character. Terminate output. Then, the moving image output unit 146 outputs a moving image of the character corresponding to a state where no sound is input.

  In the example illustrated in FIG. 7, since the output of the audio received by the audio reception unit 141 ends at time t4, the moving image output unit 146 displays the moving image corresponding to the operation received by the operation reception unit 143 at time t4. Terminate output. Then, the moving image output unit 146 outputs, for example, a moving image corresponding to a predetermined normal operation as a moving image corresponding to a state in which no sound is input. In this way, the moving image output unit 146 can output a moving image corresponding to the operation accepted by the operation accepting unit 143 in accordance with the output of the audio accepted by the audio accepting unit 141. Thus, the person in charge of the operation can select various operations without worrying about the start time and end time of the operation, and can increase variations of the animation of the character.

[Usage example]
Next, an example of using a character animation will be described. FIG. 8 shows an example in which a moving image of a character is displayed for a television news program. In the example shown in FIG. 8, a moving image of a character is displayed in the area A1 included in the news program screen. When the content to be broadcast is determined in advance, such as in a news program, the motion of the character is few, so the motion clerk combines simple motions according to the words that the voice clerk utters in real time. The generation device 1 can generate a moving image of a character in real time. This makes it possible to realize a live broadcast that includes a character video.

  In addition, as shown in FIG. 8, the message display area A2 may be displayed on the news screen, and the message posted by the viewer on the program may be displayed. In this case, the person in charge of responding to the message is set on the broadcast station side. Then, the moving image generating apparatus 1 accepts a message from the viewer and accepts a response message of the message from the responder. Then, on the broadcast station side, these messages received by the moving image generating apparatus 1 are displayed on the news screen. Here, the response message may be displayed as a comment of the character shown in FIG. By doing so, it is possible to make the viewer feel as if they are communicating with the character, to make the character feel intimate, and to increase the willingness of the viewer to watch the program.

  Further, in the example illustrated in FIG. 8, the example in which the moving image of the character is displayed for the news program has been described, but the present invention is not limited thereto. For example, a character animation may be displayed corresponding to each news posted on the portal site. In this case, a team for generating character animations is provided for each news category. Then, the moving image generating apparatus 1 receives voices and actions from each of the plurality of teams, and generates a character moving image corresponding to each of the plurality of categories. In this way, even if a viewer views any of a plurality of news categories, the viewer can watch a video of the same character, and the entire portal site has a sense of unity. Can be put out.

  Further, on a portal site or the like, a moving image may be generated so that a character answers a question from a viewer. In this case, for example, the moving image generating apparatus 1 accepts a question message from the viewer as text information and displays it on its own display unit. After that, the moving image generating apparatus 1 accepts an answer message corresponding to the question message from the voice person, and accepts an action corresponding to the voice from the action person. Then, the moving image generating apparatus 1 generates a moving image in which the character answers the question message by synthesizing the received sound and the moving image corresponding to the received operation. In this way, the viewer can communicate with the character in real time.

  In addition, when the moving image generating apparatus 1 receives a question message from the viewer, the moving image generating device 1 may receive the question message by voice, convert the voice into text information, and display the text information on its display unit. Further, when a question message is received from a viewer, information indicating emotion may be received. By doing in this way, the voice person in charge can make an answer suitable for the viewer's emotion and can smoothly communicate.

  In addition, the creator of the news program may generate a moving image corresponding to at least one of a plurality of characters depending on the situation. In this case, the producer of the news program has a team for generating the moving images of the plurality of characters. The news program creator, when sending an opinion on the news, selects one of a plurality of characters in accordance with the content of the opinion and generates a video in which the selected character describes the opinion. Good. For example, when there are different opinions for one news, if one announcer sends out different opinions at the same time, it may be criticized that values are blurred. On the other hand, a news program creator can flexibly transmit various opinions as opinions of individual characters by causing a plurality of characters to transmit different opinions.

[Effect in the first embodiment]
As described above, the moving image generating apparatus 1 according to the first embodiment outputs the sound received from the sound person in charge to the operation person terminal 2, and after the sound is output, from the operation person terminal 2 The motion of the character corresponding to the sound is received, and the motion video corresponding to the motion is synthesized with the sound to generate and output a character motion image.

  By doing in this way, the moving picture generation device 1 determines the movement of the character by improvising the voice of the character improvising without being based on the scenario etc. It is possible to generate a video of a character with a mark in real time.

  In the present embodiment, the moving image generating apparatus 1 accepts the sound, action, and effect corresponding to one character, but is not limited thereto. For example, the moving image generating apparatus 1 may receive sounds, actions, and effects corresponding to each of a plurality of characters, and generate a moving image that includes the plurality of characters and includes the sounds of the plurality of characters.

<Second Embodiment>
[Accept actions corresponding to the emotions presented by the voice representative]
Next, the second embodiment will be described. In the first embodiment, the person in charge of the action selected the action of the character while listening to the voice of the character output to the person-in-charge terminal 2. However, if the person in charge of the action selects the action of the character based only on the voice, there is a possibility that the person in charge of the voice will select an action different from the emotion that the voice person in charge wants to express. On the other hand, in the second embodiment, the moving image generating device 1 receives emotion information indicating emotion from the person in charge of sound, and transmits an operation corresponding to the emotion information to the operation person in charge terminal 2. A selection of an action corresponding to the emotion information is received from the person in charge. Hereinafter, a moving image generating system S according to the second embodiment will be described with reference to the drawings. In addition, about the structure similar to 1st Embodiment, the same code | symbol is attached | subjected and detailed description is abbreviate | omitted.

FIG. 9 is a diagram illustrating a configuration of the moving image generating apparatus 1 according to the second embodiment. As shown in FIG. 9, the moving image generating apparatus 1 further includes an emotion receiving unit 147 and a BGM selecting unit 148.
The emotion receiving unit 147 receives emotion information indicating the emotion of the character corresponding to the voice from the voice staff. For example, the emotion accepting unit 147 displays an emotion accepting screen for accepting a selection from a plurality of emotions on a display unit (not shown) of the moving image generating device 1, and the emotion of the character played by the voice officer from the voice officer Accept the selection.

  The motion reception unit 143 displays emotion information indicating the emotion of the character received from the voice staff on the motion staff terminal 2 and receives the motion of the character corresponding to the emotion information. Here, the motion receiving unit 143 may select information indicating a plurality of motions of the character corresponding to the emotion indicated by the received emotion information with reference to the storage unit 13. Then, the operation accepting unit 143 may display the selected information on the operation person in charge terminal 2 and accept selection of one operation from the plurality of operations. In this case, the motion reception unit 143 receives information indicating a plurality of motions of the character corresponding to the emotion indicated by the emotion information in synchronization with the timing when the voice is input after receiving the emotion information from the voice representative. It may be displayed on the terminal 2.

  In the second embodiment, the storage unit 13 stores character emotions, BGM titles, and BGM files in association with each other, and the BGM selection unit 148 refers to the storage unit 13. The BGM corresponding to the emotion indicated by the emotion information received by the emotion receiving unit 147 is selected. Note that if there are a plurality of BGMs corresponding to the emotion indicated by the emotion information, the BGM selection unit 148 may randomly select one BGM from the plurality of BGMs. When there are a plurality of BGMs corresponding to the emotion indicated by the emotion information, the effect receiving unit 144 transmits information indicating the plurality of BGMs, and receives selection of one BGM from the director-in-charge terminal 3. Also good.

  The synthesizing unit 145 synthesizes the audio received by the audio receiving unit 141, the moving image corresponding to the operation received by the operation receiving unit 143, and the BGM selected by the BGM selecting unit 148 to generate a character moving image.

  In addition, when the memory | storage part 13 has memorize | stored one operation | movement corresponding to the emotion which emotion information shows, the operation | movement reception part 143 does not receive selection of one operation | movement from the operation person in charge terminal 2, but emotion information is received. You may specify the operation | movement corresponding to the emotion to show. In this case, the synthesis unit 145 synthesizes the audio received by the audio reception unit 141, the moving image corresponding to the operation specified by the operation reception unit 143, and the BGM selected by the BGM selection unit 148, and Character animation can be automatically generated without the director in charge.

  Moreover, the emotion reception part 147 may receive the information which shows a character's operation | movement with emotion information or instead of emotion information. In this case, the synthesis unit 145 synthesizes the voice received by the voice reception unit 141, the moving image corresponding to the motion received by the emotion reception unit 147, and the BGM selected by the BGM selection unit 148, and Character animation can be automatically generated without the director in charge.

[Effects of Second Embodiment]
As described above, the moving image generating apparatus 1 according to the second embodiment displays the emotion information indicating the character's emotion received from the voice staff on the operation staff terminal 2, and the character corresponding to the emotion information. The operation of is accepted. By doing in this way, the person in charge of action can grasp the emotion of the character intended by the person in charge of voice and can select the action of the character corresponding to the emotion.

  In the second embodiment, the voice person selects the character's emotion corresponding to the voice he / she uttered. However, the present invention is not limited to this, and the character's facial expression may be selected. By doing in this way, the person in charge of operation can select the action of the character corresponding to the emotion and expression imaged by the person in charge of voice.

<Third Embodiment>
[Display text indicating the input voice on the operation staff terminal 2]
Subsequently, a third embodiment will be described. In the first embodiment, the person in charge of the operation selects the action while listening to the voice received from the person in charge of the voice. However, the action may not be selected because the voice cannot be heard. On the other hand, the third embodiment is different from the first embodiment in that the moving image generating apparatus 1 converts the voice received from the voice staff into text and displays the text on the operation staff terminal 2. Different.

FIG. 10 is a diagram illustrating a configuration of the moving image generating apparatus 1 according to the third embodiment. As shown in FIG. 10, the moving image generating apparatus 1 further includes a conversion unit 149.
The conversion unit 149 converts the voice into text information by analyzing the voice received by the voice reception unit 141.
The motion accepting unit 143 displays the text information converted by the converting unit 149 on the operation person in charge terminal 2 and receives the character's action from the operation person in charge terminal.

  When the moving image generating device 1 includes the emotion receiving unit 147 as in the moving image generating device 1 according to the second embodiment, the converting unit 149 displays text or an icon corresponding to the emotion information received by the emotion receiving unit 147. The included text information may be displayed on the operation person in charge terminal 2. In this way, the person in charge of the operation can easily select the operation.

[Effect in the third embodiment]
As described above, the moving image generating apparatus 1 according to the third embodiment displays text information on the operation person in charge terminal 2 and accepts a character action from the operation person in charge terminal. The contents can be grasped accurately.

  The voice output unit 142 may output the voice to the operation staff terminal 2 after the operation reception section 143 starts displaying the text information on the operation staff terminal 2. By doing so, the person-in-charge terminal 2 displays text information corresponding to the voice before the voice is output. Thereby, since the person in charge of operation can hear the sound after confirming the content of the sound based on the text information, the content of the sound can be grasped more accurately.

  In the above description, the case where the person in charge of voice is different from the person in charge of operation and the person in charge of directing has been described, but the person in charge of sound may be the same as at least one of the person in charge of operation and the person in charge of directing.

  As mentioned above, although this invention was demonstrated using embodiment, the technical scope of this invention is not limited to the range as described in the said embodiment. It will be apparent to those skilled in the art that various modifications or improvements can be added to the above embodiment. It is apparent from the scope of the claims that the embodiments added with such changes or improvements can be included in the technical scope of the present invention.

DESCRIPTION OF SYMBOLS 1 ... Movie production | generation apparatus, 11 ... Communication part, 12 ... Microphone, 13 ... Memory | storage part, 131 ... Audio | voice buffer, 14 ... Control part, 141 ... Audio | voice reception part, 142 ... voice output unit, 143 ... motion reception unit, 144 ... production reception unit, 145 ... synthesis unit, 146 ... video output unit, 147 ... emotion reception unit, 148 ... -BGM selection part, 149 ... conversion part, 2 ... operation person in charge terminal, 3 ... production person in charge terminal, S ... animation production system

Claims (10)

A voice reception unit that receives input of a character's voice from a voice representative;
An emotion receiving unit that receives emotion information indicating the emotion of the character corresponding to the voice from the voice person in charge;
An audio output unit that outputs the received audio to the terminal of the person in charge of operation,
Corresponding to the emotion information displayed on the operation person's terminal and the voice inputted to the operation person's terminal from the operation person's terminal after the sound output unit starts outputting the sound An action accepting unit for accepting the action of the character to be
A synthesizing unit that synthesizes the voice and the video corresponding to the motion to generate the video of the character;
A video output unit for outputting the generated video of the character;
A moving image generating apparatus comprising: The motion accepting unit displays information indicating a plurality of motions of the character on the terminal of the person in charge of the motion, and accepts the motion of the character by accepting selection of one motion from the plurality of motions.
The moving image generating apparatus according to claim 1 . The action accepting unit displays information indicating a plurality of actions of the character corresponding to the emotion on the terminal of the person in charge of the action, and accepts selection of one action from the plurality of actions, thereby moving the action of the character Accept
The moving image generating apparatus according to claim 2 . A storage unit for storing the character's emotion and background music in association with each other;
A selection unit that selects the background music corresponding to the emotion indicated by the emotion information with reference to the storage unit, and
The synthesizing unit synthesizes the voice, the video corresponding to the motion, and the selected background music to generate the video of the character.
The moving image generating apparatus according to any one of claims 1 to 3 . The synthesizing unit synchronizes the time when the reproduction of the sound starts and the time when the action of the character corresponding to the sound starts, and synthesizes the sound and the moving image corresponding to the action.
The moving image generating device according to any one of claims 1 to 4 . A storage unit for storing voice information indicating the received voice;
The synthesizing unit acquires the voice information stored in the storage unit, and synchronizes the time when the reproduction of the voice indicated by the voice information starts and the time when the action of the character starts, Combining the video corresponding to the motion,
The moving image generating apparatus according to claim 5 . A conversion unit for converting the received voice into text;
The motion accepting unit displays the text converted by the converting unit on the terminal of the person in charge of operation, and accepts the action of the character from the terminal of the person in charge of motion;
The moving image generating apparatus according to claim 6 . The moving image output unit ends the output of the moving image corresponding to the received operation and outputs the moving image of the character corresponding to the state where the sound is not input in response to the completion of the output of the received sound. To
The moving image generating apparatus according to any one of claims 1 to 7 . The voice output unit outputs the received voice to the terminal of the director in charge of production,
After the sound is output, an effect receiving unit that receives information related to the effect of the moving image from the terminal of the person in charge of the effect is further provided,
The synthesis unit adds an effect corresponding to the effect to the synthesized animation of the character.
The moving image generating apparatus according to any one of claims 1 to 8 . Executed by the computer,
Receiving a voice input of the character from the voice representative;
Receiving emotion information indicating the emotion of the character corresponding to the voice from the voice representative;
Outputting the received voice to the terminal of the person in charge of operation,
After starting the output of the voice, from the terminal of the person in charge of the operation, the emotion information displayed on the terminal of the person in charge of the operation and the action of the character corresponding to the voice input to the terminal of the person in charge of the operation A step of accepting,
Synthesizing the voice and a video corresponding to the motion to generate a video of the character;
Outputting the generated animation of the character;
A video generation method comprising:

Images