JP2015125613A - Animation generation device, data format, animation generation method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To generate animation of a character in accordance with a start time and end time, length, and content in dialogue sentences of the character.SOLUTION: The animation generation device generates animation of a character with a voice output for dialogue sentences. The device comprises a time length adjustment unit 40-6 for inputting dialogue sentence data configured by text data showing dialogue sentences, data showing a start time of the dialogue sentences, and data showing an end time of the dialogue sentences and also inputting animation data of the character, and adjusting a time length of the animation data of the character on the basis of the dialogue sentence data.

Description

  The present invention relates to a technique for generating animation of a character according to the start time and end time, length, and content of a dialogue.

  2. Description of the Related Art Conventionally, a technique for generating an electrical signal such as an image or sound generated according to a predetermined format is known. For example, in the technique disclosed in Patent Document 1, by reproducing a plurality of acoustic signals recorded on a plurality of tracks with different positional relationships, a reproduction signal in which a phase shift between the signals is eliminated is regenerated, and an acoustic signal is reproduced. Provided is a data format that can be reproduced satisfactorily.

  In the technology disclosed in Patent Document 2, a data format that can automatically generate a character generated on an information terminal based on an image signal and audio information sent in a videophone call. I will provide a.

Japanese Patent No. 5003327 JP 2007-29776 A

  However, with the technique disclosed in Patent Document 1, the synchronization shift between the acoustic signals recorded on a plurality of tracks can be eliminated, but a character using an image signal cannot be generated.

  In addition, the technique disclosed in Patent Document 2 can generate an image signal in which the character's mouth shape is changed according to the phoneme information of the input audio signal, but it is a complicated animation such as a whole body motion or a facial expression change. It is difficult to generate an image signal in accordance with an audio signal.

  The present invention has been made in view of such circumstances, and an animation generation apparatus and a data format that can generate an animation of a character according to the start time and end time, length, and content of the character's dialogue Another object is to provide an animation generation method and program.

  (1) In order to achieve the above object, the present invention takes the following measures. That is, the animation generating apparatus of the present invention is an animation generating apparatus that generates animation of a character accompanied by speech output of speech, and includes text data indicating speech, data indicating the start time of the speech, and end time of the speech. It is provided with a time length adjustment unit that inputs dialogue data composed of the data shown, inputs animation data of the character, and adjusts the duration of the animation data of the character based on the dialogue data. .

  In this way, the text data indicating the line, the line data composed of the data indicating the start time of the line and the data indicating the end time of the line are input, the animation data of the character is input, and the line data is input. Since the time length of the character's animation data is adjusted based on this, even if the character's dialogue is dynamically generated, the synchronization of the image signal and the audio signal is eliminated, and the character's animation is generated. can do.

  (2) Moreover, the animation production | generation apparatus of this invention uses the emotion data which shows the emotion of the character corresponding to the said dialog, The emotion provision part which changes the animation data of the said character into the animation data of a character with an emotion It is further provided with the feature.

  As described above, since the animation data of the character is changed to the animation data of the character with emotion using the emotion data indicating the emotion of the character corresponding to the dialogue, the emotion expression of the animation of the character is enriched. Is possible.

  (3) The animation generation apparatus of the present invention further includes a dialogue text generation unit that recognizes input voice data and generates text data indicating dialogue.

  As described above, since the input voice data is recognized and the text data indicating the dialogue is generated, it is possible to input not only the text data but also the voice directly.

  (4) Further, the animation generation apparatus of the present invention further includes a dialogue time determination unit that detects a voiced section of the input voice data and identifies the start time of the dialogue and the end time of the dialogue. To do.

  In this way, since the voiced period of the input speech data is detected and the start time of the speech and the end time of the speech are specified, it is possible to generate speech data even when speech is input. Become.

  (5) Moreover, the animation production | generation apparatus of this invention is further provided with the animation production | generation part which recognizes the meaning content of the text data which shows the said dialog, and produces | generates the animation data of the said character.

  As described above, since the meaning content of the text data indicating the dialogue is recognized and the animation data of the character is generated, the synchronization deviation between the image signal and the audio signal can be eliminated and the animation of the character can be generated.

  (6) The animation generation apparatus of the present invention further includes an emotion generation unit that analyzes emotion classification or emotion strength of the text data indicating the dialogue and generates emotion data indicating the emotion of the character corresponding to the dialogue. It is characterized by that.

  As described above, the emotion classification or emotion strength of the text data indicating the dialogue is analyzed, and the emotion data indicating the emotion of the character corresponding to the dialogue is generated, so that the emotion corresponding to the dialogue is given to the animation of the character. Is possible.

  (7) In the animation generation apparatus of the present invention, the animation data of the character is data indicating spatial coordinates of the character's bone or polygon at an arbitrary time.

  As described above, since the animation data of the character is data indicating the spatial coordinates of the character's bone or polygon at an arbitrary time, a character having a complicated animation corresponding to the dialogue is generated. be able to.

  (8) The animation generation apparatus of the present invention further includes a character reproduction unit that reproduces the animation data of the character and outputs speech of speech and animation images.

  Thus, since the animation data of the character is reproduced and the speech and animation image of the dialogue are output, the synchronization deviation between the image signal and the audio signal can be eliminated, and the animation of the character can be generated.

  (9) The data format of the present invention is a data format of animation of a character accompanied by speech output of speech, and indicates text data indicating speech, data indicating the start time of the speech, and end time of the speech. The time length of the animation data of the character is adjusted so as to match the dialogue data composed of the data.

  In this way, the text data indicating the line, the line data composed of the data indicating the start time of the line and the data indicating the end time of the line are input, the animation data of the character is input, and the line data is input. Since the time length of the character's animation data is adjusted based on this, even if the character's dialogue is dynamically generated, the synchronization of the image signal and the audio signal is eliminated, and the character's animation is generated. can do.

  (10) The data format of the present invention is characterized in that the animation data of the character is changed to animation data of a character with emotion using emotion data indicating the emotion of the character corresponding to the dialogue. To do.

  As described above, since the animation data of the character is changed to the animation data of the character with emotion using the emotion data indicating the emotion of the character corresponding to the dialogue, the emotion expression of the animation of the character is enriched. Is possible.

  (11) Further, the animation generation method of the present invention is an animation generation method for generating an animation of a character accompanied by speech output of speech, the text data indicating speech, the data indicating the start time of the speech, and the dialogue Input dialogue data composed of data indicating an end time, input animation data of the character, and adjust time length of the animation data of the character based on the dialogue data It is characterized by that.

  In this way, the text data indicating the line, the line data composed of the data indicating the start time of the line and the data indicating the end time of the line are input, the animation data of the character is input, and the line data is input. Since the time length of the character's animation data is adjusted based on this, even if the character's dialogue is dynamically generated, the synchronization of the image signal and the audio signal is eliminated, and the character's animation is generated. can do.

  (12) Further, the program of the present invention is a program of an animation generating device that generates animation of a character accompanied by speech output of speech, the text data indicating speech, the data indicating the start time of the speech, and the dialogue A series of processes of inputting dialogue data composed of data indicating end time, inputting animation data of the character, and adjusting time length of the animation data of the character based on the dialogue data The processing is executed by a computer.

  In this way, the text data indicating the line, the line data composed of the data indicating the start time of the line and the data indicating the end time of the line are input, the animation data of the character is input, and the line data is input. Since the time length of the character's animation data is adjusted based on this, even if the character's dialogue is dynamically generated, the synchronization of the image signal and the audio signal is eliminated, and the character's animation is generated. can do.

  According to the present invention, even if the dialogue of a character is dynamically generated, the animation of the character can be generated by eliminating the synchronization deviation between the image signal and the audio signal.

It is a figure which shows schematic structure of the character animation production | generation apparatus which concerns on this embodiment. It is a block diagram which shows the function of the character animation production | generation apparatus 1 which concerns on this embodiment. It is a flowchart which shows operation | movement of the character animation production | generation apparatus which concerns on this embodiment. It is a figure which shows the dialog data comprised from text data, start time, and end time. It is a figure which shows animation data. It is a figure which shows emotion data. It is a figure which shows the data format which concerns on this embodiment.

  The character animation generating apparatus according to the embodiment of the present invention inputs speech signals that are dialogues, and based on speech data in which the input speech signals are recorded in time series, speech text data and dialogue start and end times. Are generated in time series. Character animation data is generated in time series based on the generated line text data and the line start time and end time. The animation data may be accompanied by emotion data, and emotion is given to the animation data based on the generated emotion data, and the time length of the animation data is adjusted based on the start time and end time of the dialogue. An audio signal in the audio data and an image signal in the generated animation data are generated according to the start time and end time of the generated dialogue. Thereby, even when the dialogue of the character is dynamically generated, it is possible to eliminate the synchronization shift between the image signal and the audio signal and generate the character. In addition, since an image signal in which spatial coordinates of an arbitrary bone or polygon of the character is controlled is generated as animation data, a character having a complicated animation corresponding to the dialogue can be generated.

  FIG. 1 is a diagram illustrating a schematic configuration of a character animation generation apparatus according to the present embodiment. The character animation generating apparatus 1 includes a microphone 10, a speaker 20, a display 30, and a PC (Personal Computer) 40. Then, the audio data 50 is input to the PC 40 by the microphone 10. In FIG. 1, the microphone 10 is connected to the PC 40. However, the technical idea of the present invention is not limited to this, and it is sufficient if audio data is input to the PC by any means. It is.

  The PC 40 is connected to a speaker 20 and a display 30 as a character animation generation device via a cable 40a. In the PC 40, the text data of the dialogue or the start time and the end time of the dialogue are generated in the time series based on the audio data 50 in which the speech signal input as the dialogue is recorded in the time series. Further, animation data and emotion data of the character are generated in time series based on the generated text data of the dialog and the start time and end time of the dialog. Further, emotion is given to the animation data based on the generated emotion data, and the time length of the animation data is adjusted based on the start time and end time of the generated dialogue.

  And PC40 transmits the audio | voice signal in audio | voice data to the speaker 20 at any time according to the start time and end time of the produced | generated dialog. On the other hand, the PC 40 transmits an image signal in the generated animation data to the display 30 as needed. At that time, the image generated in the PC 40 is projected on the display 30 as A1. In the character animation generation device according to the embodiment of the present invention, the audio signal in the audio data or the image signal in the animation data may not be transmitted to the speaker 20 or the display 30.

  FIG. 2 is a block diagram illustrating functions of the character animation generation apparatus according to the present embodiment. The dialogue text generation unit 40-1 of the PC 40 recognizes speech data 50 in which speech signals input as speech by the microphone 10 are recorded in time series, and generates speech text data 60-1 in time series. In addition, the line time determination unit 40-2 of the PC 40 detects the voiced section of the audio data 50, and determines the start time and end time 60-2 of the line in time series. In addition, the animation generation unit 40-3 of the PC 40 analyzes the contents of the line text data 60-1, and generates the character animation data 70 in time series for each line start time and end time 60-2. .

  Also, the emotion generation unit 40-4 of the PC 40 analyzes the contents of the line text data 60-1 and generates character emotion data 80 in time series. In addition, the emotion imparting unit 40-5 of the PC 40 converts the animation data 70 according to the emotion data 80. The time length adjustment unit 40-6 of the PC 40 converts the animation data 70 based on the start time and end time 60-2 of the dialogue. Further, the character reproduction unit 40-7 of the PC 40 reproduces the audio signal in the audio data 50 and the image signal in the generated animation data 70 in accordance with the start time and end time 60-2 of the dialogue.

  FIG. 3 is a flowchart showing the operation of the character animation generation apparatus according to this embodiment. First, an audio signal is input to the PC 40 by the microphone 10, and the input audio signal is recorded in time series to form audio data 50 (step S1). Next, in the PC 40, the voice data 50 is recognized, and the text data of the dialogue is generated in time series (step S2).

  Next, in the PC 40, a voiced section of the audio data 50 is detected, and the line start time and end time 60-2 are determined in time series (step S3). In the audio data 50, when a situation where the sound pressure level is greater than the threshold value continues for a certain time or longer, the corresponding section is determined to be a sound section, the start of the section is determined as the start time of the line, and the end of the section is determined as the end time of the line. Further, the dialogue text data generated in step S2 is divided into dialogue text data 60-1 with the determined dialogue start time to end time as one unit.

  Next, the PC 40 analyzes the contents of the dialogue text data 60-1 divided in step S3, and “closes eyes” for each dialogue start time and end time 60-2 determined in step S3. Character animation data 70 such as “bow” and “raise hand” is generated in time series (step S4). In this embodiment, a pair of animation data when the character's whole body motion or expression changes and a similarity parameter in each animation data calculated using each word existing in a typical word database such as a Japanese dictionary as a parameter. Prepare a configured animation database.

  Note that the animation data referred to here describes at which spatial position coordinates all the bones or polygons of the character exist at an arbitrary time. The similarity parameter in the line text data 60-1 is calculated, the cosine similarity with the similarity parameter in all animation data in the animation database is obtained, and the animation data having the largest value is used as the character animation data 70. Generate in time series.

  Next, the PC 40 analyzes the contents of the dialogue text data 60-1 divided in step S3, and generates character emotion data 80 composed of emotion classification and intensity in time series (step S5). Here, the case where the input text data 60-1 is a word string will be described. However, the technical idea of the present invention is not limited to words, and may be a phrase or a sentence. good. In this embodiment, an emotion word database composed of emotion classifications and respective intensities is used.

The emotion word database is the emotion classification "joy", "sadness", "anger", "disgust", "fear" used for human expression formation for all words in a large number of word databases such as Japanese dictionary Specify the ratio of “Sin”, “Shame”, “Interest”, and “Surprise”, and specify the emotional intensity in the range of 0 to 1 in 10 steps in increments of 0.1. Is formed. If the input text data 60-1 is a phrase or sentence, as in the case of a word, the phrase phrase or sentence is an emotion phrase database or emotion sentence composed of emotion classifications and respective strengths as a whole. Use a database. Here, the intensity of “joy” is S ₁ , the intensity of “sadness” is S ₂ , the intensity of “anger” is S ₃ , the intensity of “hate” is S ₄ , the intensity of “fear” is S ₅ , “sin” ”Is represented as S ₆ ,“ Shame ”as S ₇ ,“ Interest ”as S ₈ , and“ Surprise ”as S ₉ . However, the following formula shall be satisfied.

  Then, a word that matches or is similar to the input dialogue text data 60-1 is searched from the emotion word database, and the emotion classification and strength in the word are extracted to generate emotion data 80. That is, the emotion classification in the dialogue text data 60-1 is represented by a 9-dimensional vector as shown in the following equation.

  Further, the overall intensity W in the input text data 60-1 is expressed by the following equation.

  For example, when “crying and laughing” is input as the text data 60-1 for the dialogue, the following expression is generated as the emotion data 80.

  Next, in the PC 30, the animation data 70 is converted according to the emotion data 80, and an emotion is imparted to the character's whole body motion or expression change (step S 6). First, a case where the spatial coordinates of an arbitrary bone in a character are recorded in the animation data 70 in time series will be described. In this embodiment, all pre-recorded emotional animation data for whole body motion or facial expression change and animation data for each emotion classification are learned, and conversion from emotionless animation data to animation data for each emotion classification is performed in advance. By defining and synthesizing the animation data 70 generated in step S4 according to the emotion data 80 generated in step S5, an emotion is imparted to the character's whole body motion or facial expression change.

  In this specification, as an example, the principal component analysis is used to give emotions to the whole body motion or facial expression change of the character. However, the technical idea of the present invention is not limited to the principal component analysis, but a nonlinear state space. Other methods such as mapping and machine learning may be used to give emotions to whole body movements or facial expression changes. First, the emotional movements and expressions of the nine emotions of emotion classification "joy", "sadness", "anger", "hate", "fear", "sin", "shame", "interest" and "surprise" A plurality of animation data in the change is prepared in advance by recording or the like and registered in the learning database. All registered emotionless animation data and animation data of each emotion classification are learned, and parameters for converting the emotionless animation data into animation data of each emotion classification are calculated by a linear regression method.

That is, if m (m = 1, 2,...) Represents a pre-prepared whole body motion or facial expression change, a differential value k ^j (m) of the j-th principal component coordinates of emotionless animation data in the whole body motion or facial expression change m. ), Linear transformation calculation is performed according to the following equation to calculate conversion parameters a ^j _i and b ^j _i .

However, q ^j _i (m) indicates the differential value of the j-th principal component coordinate of animation data of each emotion in whole body motion or facial expression change m, i = 1 indicates that the emotion classification is “joy”, i = 2 is when the emotion classification is “sadness”, i = 3 is when the emotion classification is “anger”, i = 4 is when the emotion classification is “disgust”, i = 5 is when the emotion classification is “fear” ”, I = 6 is the emotion classification“ sin ”, i = 7 is the emotion classification“ shame ”, i = 8 is the emotion classification“ interest ”, i = 9 Represents the case where the emotion classification is “surprise”. Next, using the conversion parameters a ^j _i and b ^j _i corresponding to the emotion data 80 generated in step S5, the animation data 70 generated in step S4 is synthesized and converted to change the whole body motion or facial expression of the character. Give emotions. That is, the differential value p ^j (m) of the j-th principal component coordinate of the animation data 70 to which the emotion is given is represented by the following equation.

  The same operation is performed on all of the animation data 70 recorded in time series, and the animation data 70 is regenerated.

Next, a case where the spatial coordinates of an arbitrary polygon in a character are recorded in time series in the animation data 70 will be described. In the present embodiment, the animation data 70 generated in step S4 is synthesized and converted in accordance with the emotion data 80 generated in step S5, thereby giving an emotion to the character's whole body motion or expression change. First, the emotion classification “joy”, “sadness”, “anger”, “disgust”, “fear”, “sin”, “shame”, “interest” and “surprise” used for human expression formation are animated in whole body motion or facial expression change. The amount of change from the emotionless animation data is defined in advance for the data. Here, with respect to the coordinates of a certain polygon P in the animation data, the difference from no emotion in “joy” (X ₁ , Y ₁ , Z ₁ ) and the difference from no emotion in “sadness” (X ₂ , Y ₂ , Z ₂ ), (X ₃ , Y ₃ , Z ₃ ) the difference from no emotion in “anger”, and (X ₄ , Y ₄ , Z ₄ ) the difference from no emotion in “disgust” , The difference from feelingless in “fear” (X ₅ , Y ₅ , Z ₅ ), the difference from feelings in “sin” (X ₆ , Y ₆ , Z ₆ ), Difference (X ₇ , Y ₇ , Z ₇ ), difference with no emotion in (X ₈ , Y ₈ , Z ₈ ), difference with no emotion in “surprise” (X ₉ , Y ₉ , Z ₉ ).

Then, in accordance with the emotion data 80 generated in step S5, the animation data 70 generated in step S4 is synthesized and converted to give emotion to the whole body motion or expression change of the character. That is, if the coordinates of P in the animation data 70 are (X ₀ , Y ₀ , Z ₀ ), the coordinates (X _E , Y _E , Z _E ) of the animation data 70 to which the emotion is given are Represented.

  The same operation is performed on all of the animation data 70 recorded in time series, and the animation data 70 is regenerated.

  Next, the PC 40 converts the animation data 70 generated in step S4 or step S6 based on the dialogue start time and end time 60-2 determined in step S3, and adjusts the time length of the animation data 70. (Step S7). In this embodiment, spatial coordinates of bones or polygons in animation data in a series of whole body motions or facial expression changes of characters are divided in advance according to the contents of movement such as “start part”, “main part”, “convergence part”, etc. The animation data 70 is converted using an “animation graph” in which transitions between the key frames are specified by specifying the time as a boundary between them as key frames.

  In the present specification, as an example, the time length of the animation data 70 is adjusted using an animation graph. However, the technical idea of the present invention is not limited to the animation graph, and machine learning, Hidden Markov Model, etc. The time length of the animation data 70 may be adjusted using a probability model. First, with respect to all animation data in the animation database prepared in step S4, “start part”, “main part” and “convergence part” are defined in advance to designate key frames, and the animation graph described above is prepared.

  Next, the time length of the line text data 60-1 divided in step S3 is obtained from the line start time and end time determined in step S3. Then, the time length of the “main part” in the animation data 70 is repeatedly added to the time length of the animation data 70 generated in step S4 or step S6 so that the difference from the time length of the dialogue is minimized, and the number of repetitions Hold. Finally, the animation data 70 is regenerated in such a manner that the animation data of the “main part” is inserted as many times as the number of repetitions held immediately before the “convergence part” of the animation data 70. In this specification, as an example, the “main part” in the animation data is repeated to adjust the time length, but the technical idea of the present invention is not limited to the repetition of the “main part”. The time length of the animation data 70 may be adjusted by speed control or truncation of the “starting part” and “convergence part”.

  Next, in the PC 40, an image signal in the animation data 70 generated in the audio signal step S7 in the audio data 50 is generated in accordance with the line start time and end time 60-2 determined in step S3 (step S8). ). First, reproduction of the audio data 50 is started and generation of an audio signal is started, and drawing of a character is started and generation of an image signal is started. Next, when the reproduction time of the audio data 50 reaches the start time of the line determined in step S3, drawing of the character reflecting the animation data 70 generated in step S7 is started and an image signal is generated.

  On the other hand, when the reproduction time of the audio data 50 reaches the end time of the line determined in step S3, the image signal is generated by returning to the standard character drawing in which the animation data 70 is not reflected. Similar processing is repeated for the start time and end time 60-2 of all lines recorded in time series, and an image signal in the animation data 70 is generated. When the voice data 50 input by the microphone 10 continues after the processing for the last dialogue start time and end time 60-2 is completed, the process returns to step S1 and the next voice data 50 is processed. Start processing.

  Finally, the audio data 50 is radiated from the speaker 20, and the generated image signal of the character is projected on the display 30 (step S9).

  As described above, according to the present embodiment, the text data of the dialogue and the start time and the end time of the dialogue are generated in time series based on the audio data 50 in which the speech signal input as dialogue is recorded in time series. Also, animation data and emotion data of the character are generated in time series for each start time and end time of the line based on the generated line text data. Further, emotion is given to the animation data based on the generated emotion data, and the time length of the animation data is adjusted based on the start time and end time of the generated dialogue. And PC40 transmits the audio | voice signal in audio | voice data to the speaker 20 at any time according to the start time and end time of the produced | generated dialog. On the other hand, the PC 40 transmits an image signal in the animation data to the display 30 as needed. Thereby, in this embodiment, even when the dialogue of the character is dynamically generated, the character can be generated by eliminating the synchronization shift between the image signal and the audio signal. In addition, since an image signal in which spatial coordinates of an arbitrary bone or polygon of the character is controlled is generated as animation data, a character having a complicated animation corresponding to the dialogue can be generated.

DESCRIPTION OF SYMBOLS 10 Microphone 20 Speaker 30 Display 40-1 Dialogue text generation part 40-2 Dialogue time determination part 40-3 Animation generation part 40-4 Emotion generation part 40-5 Emotion provision part 40-6 Time length adjustment part 40-7 Character reproduction | regeneration Portion 40a Cable 50 Audio data 60-1 Text data 60-2 Start time and end time 70 Animation data 80 Emotion data

Claims (12)

An animation generation device that generates animation of a character with speech output of speech,
While inputting dialogue data composed of text data indicating dialogue, data indicating the start time of the dialogue, and data indicating the end time of the dialogue, and inputting animation data of the character, based on the dialogue data, An animation generation apparatus comprising a time length adjustment unit for adjusting a time length of animation data of a character.   The animation according to claim 1, further comprising an emotion giving unit that changes the animation data of the character into animation data of a character with an emotion using emotion data indicating the emotion of the character corresponding to the dialogue. Generator.   The animation generation apparatus according to claim 1, further comprising: a dialogue text generation unit that recognizes the input voice data and generates text data indicating the dialogue.   4. The speech time determination unit for detecting a speech section of input speech data and identifying a speech start time and a speech end time, further comprising: a speech time determination unit. Animation generator.   The animation generation apparatus according to any one of claims 1 to 4, further comprising an animation generation unit that recognizes the semantic content of the text data indicating the dialogue and generates animation data of the character.   6. The apparatus according to claim 1, further comprising an emotion generation unit that analyzes emotion classification or emotion strength of the text data indicating the dialogue and generates emotion data indicating the emotion of the character corresponding to the dialogue. The animation production | generation apparatus in any one.   The animation according to any one of claims 1 to 6, wherein the animation data of the character is data indicating a spatial coordinate at an arbitrary time of the bone or polygon of the character. Generator.   The animation generation apparatus according to claim 1, further comprising a character reproduction unit that reproduces the animation data of the character and outputs speech of speech and animation images. A data format for character animation with speech output of dialogue,
The time length of the animation data of the character is adjusted so as to be matched with the text data indicating the line, the data indicating the start time of the line and the data indicating the end time of the line Data format to be used.   The data format according to claim 9, wherein animation data of the character is changed to animation data of a character with emotion using emotion data indicating the emotion of the character corresponding to the dialogue. An animation generation method for generating an animation of a character with speech output of speech,
Inputting dialogue data composed of text data indicating dialogue, data indicating the start time of the dialogue, and data indicating the end time of the dialogue, and inputting animation data of the character;
Adjusting at least the time length of the animation data of the character based on the dialogue data. A program for an animation generation device that generates an animation of a character with speech output of speech,
A process of inputting text data indicating a line, data indicating a start time of the line, and data indicating a line end time, and inputting animation data of the character;
A program for causing a computer to execute a series of processes of adjusting a time length of animation data of the character based on the dialogue data.

Images