JP2020027132A - Information processing device and program - Google Patents

Abstract

To make it possible, when vocalizing text data associated with a still image, to easily vocalize by setting a plurality of speakers respectively, as compared with a case where a user sets and vocalizes speakers corresponding to the text data.SOLUTION: A data communication unit 31 acquires text data associated with a presentation material etc. A specifying unit 41 specifies utterance sentences from a plurality of speakers from the text data. A setting unit 42 sets a plurality of speakers for the utterance sentence specified by the specifying unit 41, respectively. A vocalizing unit 43 vocalizes each utterance sentence according to the plurality of speakers set by the setting unit 42.SELECTED DRAWING: Figure 3

Description

  The present invention relates to an information processing device and a program.

  Japanese Patent Application Laid-Open No. H11-163,972 discloses a document speech device that displays a document described in a markup language on a screen and selectively vocalizes the displayed document, and detects tags in the document described in the markup language. Tag detecting means for performing, based on the registration information of the voiced tag in which the tag whose element is to be voiced is registered, determining means for determining whether to voice the element of the tag detected by the tag detecting means, There is disclosed a document sounding apparatus, comprising: a sounding means for sounding an element judged to be sounded by the judging means.

JP 2000-339132 A

  An object of the present invention is to easily convert a plurality of text data associated with a still image into a plurality of voices in comparison with a case where a user sets a speaker corresponding to the text data and voices the text data. It is an object of the present invention to provide an information processing apparatus and a program that can set a speaker and convert it into a voice.

[Information processing device]
The present invention according to claim 1 is
Acquiring means for acquiring text data associated with a still image;
From the text data obtained by the obtaining means, specifying means for specifying the utterance sentence by a plurality of speakers,
Setting means for setting a plurality of speakers for the utterance sentence specified by the specifying means,
Speech means for vocalizing each utterance sentence according to the plurality of speakers set by the setting means,
Information processing device provided with.

  The present invention according to claim 2 is the information processing apparatus according to claim 1, further comprising display control means for controlling to display voice qualities of a plurality of speakers set by the setting means.

  The present invention according to claim 3 is the information processing apparatus according to claim 2, further comprising setting change means for changing the settings of the plurality of speakers set by the setting means.

  The present invention according to claim 4 is the information processing apparatus according to claim 2, further comprising adjusting means for adjusting voice qualities of a plurality of speakers set by the setting means.

  The present invention according to claim 5 is the information processing apparatus according to claim 1, further comprising display control means for controlling to display utterances of a plurality of speakers set by the setting means.

  The present invention according to claim 6 is the information processing apparatus according to claim 5, further comprising utterance range changing means for changing utterance ranges of utterance sentences of a plurality of speakers set by the setting means.

  According to a seventh aspect of the present invention, when the at least one speaker name is included in the text data obtained by the obtaining unit, the specifying unit specifies an utterance sentence by a plurality of speakers. An information processing apparatus according to claim 1.

  The present invention according to claim 8, wherein the specifying means specifies an utterance sentence by a plurality of speakers when the text data acquired by the acquisition means includes a predetermined symbol. An information processing apparatus according to item 1.

  The present invention according to claim 9 is the information processing apparatus according to claim 1, wherein the specifying means specifies utterances of a plurality of speakers according to a language used in the text data acquired by the acquiring means.

  The present invention according to claim 10 is the information processing apparatus according to claim 9, wherein the setting means sets a speaker corresponding to each of the languages used in the utterance sentence specified by the specifying means. .

  The present invention according to claim 11, further comprising image data obtaining means for obtaining image data, wherein the specifying means specifies an utterance sentence from a specific image in the image data obtained by the image data obtaining means. An information processing apparatus as described in the above.

[program]
The present invention according to claim 12 is:
An obtaining step of obtaining text data associated with the still image;
From the text data obtained in the obtaining step, a specifying step of specifying utterances by a plurality of speakers,
A setting step of setting a plurality of speakers for the utterance sentence specified by the specifying step,
A voice-to-voice step of voice-to-voice utterances according to the plurality of speakers set by the setting step,
Is a program for causing a computer to execute.

  According to the first aspect of the present invention, when voice data of text data associated with a still image is compared with a case where a user sets a speaker corresponding to the text data to voice each text data, In addition, it is possible to provide an information processing apparatus that can easily set a plurality of speakers and convert them to speech.

  According to the second aspect of the present invention, it is possible to provide an information processing apparatus that allows a user to confirm the set voice quality of a speaker.

  According to the third aspect of the present invention, it is possible to provide an information processing apparatus in which the user can change the set voice quality of the speaker.

  According to the fourth aspect of the present invention, it is possible to provide an information processing apparatus that allows a user to adjust the set voice quality of a speaker.

  According to the fifth aspect of the present invention, it is possible to provide an information processing apparatus that allows a user to confirm a set utterance sentence of a speaker.

  According to the sixth aspect of the present invention, it is possible to provide an information processing apparatus in which the user can change the utterance range of the set utterance sentence of the speaker.

  According to the seventh aspect of the present invention, when converting text data associated with a still image to voice, the user sets a speaker corresponding to the text data and voices the text data. In addition, it is possible to provide an information processing apparatus that can easily set a plurality of speakers and convert them to speech.

  According to the present invention, when text data associated with a still image is vocalized, compared with a case where a user sets a speaker corresponding to the text data and vocalizes the speaker, In addition, it is possible to provide an information processing apparatus that can easily set a plurality of speakers and convert them to speech.

  According to the ninth aspect of the present invention, when the text data associated with the still image is vocalized, the text data is compared with the case where the user sets the speakers corresponding to the text data and vocalizes them. In addition, it is possible to provide an information processing apparatus that can easily set a plurality of speakers and convert them to speech.

  According to the tenth aspect of the present invention, it is possible to set each language to be spoken without setting the language of the speaker corresponding to the text data associated with the still image. A processing device can be provided.

  According to the eleventh aspect of the present invention, when voice data of text data associated with a still image is compared with a case where a user sets a speaker corresponding to the text data and voices the speaker, respectively. In addition, it is possible to provide an information processing apparatus that can easily set a plurality of speakers and convert them to speech.

  According to the twelfth aspect of the present invention, when voice data of text data associated with a still image is compared with a case where a user sets a speaker corresponding to the text data and voices the text data, Thus, it is possible to provide a program that can easily set a plurality of speakers and convert them to speech.

1 is a system diagram illustrating a configuration of a multimedia content generation system according to an embodiment of the present invention. FIG. 2 is a block diagram illustrating a hardware configuration of the editing processing server 10 according to the embodiment of the present invention. FIG. 2 is a block diagram illustrating a functional configuration of an editing processing server 10 according to the embodiment of the present invention. 6 is a flowchart illustrating an outline of processing in the editing processing server 10 according to the embodiment of the present invention. It is an example of presentation material taken into the editing processing server 10. FIG. 6 is a diagram showing an example of a display screen of the terminal device 20 when the presentation material shown in FIG. 5 is taken into the editing processing server 10. FIG. 7 is a diagram illustrating an example of a display screen of the terminal device 20 when a narration speaker is set in the presentation material captured in FIG. 6. FIG. 7 is a diagram showing an example of a display screen of the terminal device 20 in a case where the presentation material captured in FIG. 6 includes a conversation sentence. FIG. 7 is a diagram illustrating an example of a narrator setting screen of the presentation material captured in FIG. 6. It is a figure showing an example of a narrator setting screen of presentation material. FIG. 11 is a diagram illustrating an example of a narrator setting screen when a speech bubble is included in a presentation material. It is a figure showing an example of a narrator setting screen of presentation material. It is an example of presentation material taken into the editing processing server 10. FIG. 14 is a diagram illustrating an example of a narrator setting screen for presentation materials illustrated in FIG. 13. It is an example of presentation material taken into the editing processing server 10. FIG. 16 is a diagram showing an example of a narrator setting screen for presentation material shown in FIG. 15. FIG. 16 is a diagram showing an example of a narrator setting screen for presentation material shown in FIG. 15.

  Next, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a system diagram showing a configuration of a multimedia content generation system according to one embodiment of the present invention.

  As shown in FIG. 1, a multimedia content generation system according to an embodiment of the present invention includes an editing processing server 10 and a terminal device 20 such as a personal computer (hereinafter abbreviated as a personal computer) connected to each other via a network 30. It consists of.

  The multimedia content generation system according to the present embodiment generates multimedia content in which various contents such as images, sounds, and characters are combined. According to the multimedia content generation system of the present embodiment, for example, it is possible to generate multimedia content in which a plurality of speakers are set in text data such as presentation material and the voice is converted.

  Here, the text data includes text data of a note portion of the presentation material, text data obtained by performing image recognition processing on still image data of the presentation material, and the like.

  The editing processing server 10 is an information processing apparatus in which editing software for editing such various contents and generating multimedia contents is installed. Then, the terminal device 20 captures the text data and the still image data, and generates the multimedia content by using the editing software operating on the editing processing server 10.

  Instead of installing such editing software on the editing server 10, it is also possible to directly install and use the terminal device 20 such as a personal computer.

  Next, FIG. 2 shows a hardware configuration of the editing processing server 10 in the image forming system of the present embodiment.

  As shown in FIG. 2, the editing processing server 10 exchanges data with a CPU 11, a memory 12, a storage device 13 such as a hard disk drive (HDD), and an external device such as a terminal device 20 via a network 30. It has a communication interface (IF) 14 for transmitting and receiving, a user interface (UI) device 15 including a touch panel or a liquid crystal display, and a keyboard. These components are connected to each other via a control bus 16.

  The CPU 11 controls the operation of the edit processing server 10 by executing predetermined processing based on a control program stored in the memory 12 or the storage device 13. In the present embodiment, the CPU 11 is described as reading and executing a control program stored in the memory 12 or the storage device 13. However, the CPU 11 stores the program in a storage medium such as a CD-ROM and It is also possible to provide.

  FIG. 3 is a block diagram showing a functional configuration of the editing processing server 10 realized by executing the control program.

  As shown in FIG. 3, the editing processing server 10 according to the present embodiment includes a data communication unit 31, a control unit 32, and a multimedia data storage unit 33.

  The data communication unit 31 performs data communication with the terminal device 20 via the network 30. In addition, the data communication unit 31 functions as an obtaining unit that obtains text data associated with a presentation material or the like.

  The control unit 32 controls the operation of the editing processing server 10, and includes a specifying unit 41, a setting unit 42, an audio conversion unit 43, a display control unit 44, a user operation reception unit 45, and an image recognition unit 46. Have.

  The multimedia data storage unit 33 stores various content data such as text data, still image data, and audio data to be edited.

  The specifying unit 41 specifies utterances of one or more speakers from text data such as a notebook part of a presentation material, and specifies a location where there is a possibility of speaker change. In addition, when at least one speaker name is included in the text data, the specifying unit 41 specifies the utterances of a plurality of speakers.

  Here, the utterance sentence is a sentence in which a speaker is set for each sentence, such as a conversation sentence, a situation explanation sentence such as a written letter, and a sentence on the ground excluding a conversational sentence or written letter.

  Further, when the text data includes symbols such as parentheses and quotation marks that surround a specific character string and are distinguished from other character strings, the specifying unit 41 specifies the utterances of a plurality of speakers. I do. That is, the utterance sentence enclosed in parentheses or the like is determined to be a conversation sentence, and the other utterance sentences are determined to be ground sentences, and utterance sentences by a plurality of speakers are specified.

  In addition, when the text data includes a specific symbol attached to a situation description such as a dash or a hyphen in the text data, the specifying unit 41 specifies an utterance sentence by a plurality of speakers. That is, an utterance sentence with a dash or the like is written, and other utterances are determined to be ground sentences, and utterances by a plurality of speakers are specified.

  In addition, when the text data includes a specific symbol such as a question mark or an exclamation mark in the text data, the specifying unit 41 specifies that there is a possibility that a plurality of speakers may be uttered sentences. That is, the text data is identified as possibly having a conversation sentence.

  Further, the specifying unit 41 specifies utterances of a plurality of speakers according to the language of the character string of the text data. That is, when a plurality of languages are included in the text data, the text data is identified as possibly having a conversational sentence.

  The specifying unit 41 extracts a specific figure such as a balloon figure in the still image data, and specifies utterances of a plurality of speakers from attribute information of the specific figure. Then, the utterance sentence is specified based on the text data input over the specific figure.

  The setting unit 42 sets a plurality of speakers for the utterance sentence specified by the specifying unit 41, respectively. That is, a speaker is set for each of the specified conversational sentence, ground sentence, and writing. Further, the setting unit 42 sets voice quality by voice synthesis for each of the set speakers, and sets parameters for switching the speakers.

  Here, the voice quality is the voice quality set for each speaker, and is set by combining language, gender, voice pitch, voice loudness, speed, and the like.

  Further, the setting unit 42 sets a speaker corresponding to each language for the utterance sentence specified by the specifying unit 41.

  Further, the setting unit 42 sets a character string immediately before the conversation sentence in which the speaker is set as a speaker name. That is, the character string immediately before the parentheses or the like is set as the speaker name. If there is no character string immediately before the parentheses, a speaker may be set alternately for each utterance sentence enclosed in parentheses.

  The voice conversion unit 43 voices each utterance sentence according to one or a plurality of speakers set by the setting unit 42.

  The display control unit 44 controls a screen displayed on the terminal device 20.

  The display control unit 44 controls to display the voice qualities of one or a plurality of speakers set by the setting unit 42, respectively.

  The display control unit 44 controls to display the utterances of a plurality of speakers set by the setting unit 42 for each speaker.

  The user operation receiving unit 45 functions as a setting change unit that changes the setting of one or more speakers set by the setting unit 42. Further, the user operation receiving unit 45 functions as an adjusting unit that adjusts the voice quality of one or a plurality of speakers set by the setting unit 42. Further, the user operation receiving unit 45 functions as an utterance range changing unit that changes the utterance ranges of the utterance sentences of a plurality of speakers set by the setting unit 42.

  The image recognition unit 46 performs image recognition processing on the still image data and converts the still image data into text data.

  Next, the operation of the editing processing server 10 in the multimedia content generation system of the present embodiment will be described in detail with reference to the drawings.

  First, the outline of the operation in the editing processing server 10 will be described with reference to the flowchart in FIG.

  Here, a case will be described as an example where a presentation material as shown in FIG. 5 is taken into the editing processing server 10 to generate multimedia content to be converted into audio.

  As shown in FIG. 5, a note portion 50 can be created in the presentation material. In the note portion 50, the user can input text data such as writing a memo. Then, in the editing processing server 10 in the multimedia content generation system of the present embodiment, the contents written in the note portion 50 can be converted into voice and automatically read out.

  A display screen of the presentation material as shown in FIG. 6 is displayed on the display unit of the terminal device 20. Then, when the file storing the presentation material is selected and added and “Start importing” is selected, the editing processing server 10 imports the presentation material (Step S10).

  Then, the specifying unit 41 acquires the note portion 50 from the taken presentation material (step S11).

  Then, a narration speaker setting screen as shown in FIG. 7 is displayed. Then, the user selects the output language and the voice quality such as sex on the narration speaker setting screen, and the speaker setting is created by selecting “OK”, and the narration speaker is set in the note part 50. .

  If there is a possibility that the speaker can be changed from the note portion 50, a narrator setting screen as shown in FIG. 8 is displayed, and when "OK" is selected, the speaker can be changed. An utterance sentence having a possibility is specified (step S12), and speaker settings are created (step S13).

  Here, the case where there is a possibility of speaker change includes a case where the note portion 50 includes a conversational sentence. That is, when the parentheses and quotation marks are included in the text data, the specifying unit 41 determines that there is a possibility that the speaker may be changed, and determines that the utterance sentence having the possibility of changing the speaker includes the note portion. From 50, an utterance sentence (conversation sentence) enclosed in parentheses or the like is specified.

  Then, when there is another utterance sentence that may change the speaker (Yes in step S14), the process returns to step S12, and the utterance sentence having the possibility of another speaker change is returned from the note portion 50. Identify.

  If there is no other utterance sentence that may change the speaker (No in step S14), a speaker name is assigned to each utterance (step S15).

  That is, the character string immediately before the parentheses or the like is automatically extracted as the speaker name (character), and the speaker name is assigned to each of the automatically extracted utterance sentences. Then, the voice quality such as the language and gender corresponding to the speaker name is set, and a list is displayed on the narrator setting screen as shown in FIG.

  The narrator setting screen as shown in FIG. 9 is configured so that the user can change and adjust the voice quality such as language, gender, voice pitch, loudness, speed, etc. corresponding to each character. . Then, when "registration" is selected on the narrator setting screen, a character (speaker name) is set for each utterance sentence.

  Further, even when there is no utterance sentence enclosed in parentheses or the like in the note portion 50, if an utterance sentence with a question mark, an exclamation mark, or the like is included, as shown in FIG. A narrator setting screen that prompts the user to edit the note portion 50 is displayed. Then, "edit note" is selected, and the user sets the speaker in the utterance sentence (conversation sentence) enclosed in parentheses, for example, by enclosing the utterance sentence for which the speaker of the note portion 50 is to be changed in parentheses. It becomes possible.

  Next, another example in which utterances by a plurality of speakers are specified from the presentation material as shown in FIG. 5 and speakers are set to the respective utterances will be described.

  In the case of a presentation material including a specific graphic such as a balloon graphic as shown in FIG. It is determined that a conversational sentence is included in the data, and utterance sentences by a plurality of speakers are specified from attribute information such as the color and shape of these specific figures. At this time, the utterance sentence is displayed over the speech balloon figure.

  Then, when "OK" is selected on the narrator setting screen as shown in FIG. 11, for example, characters are assigned for each color of the balloon graphic, and the character is assigned on the yellow balloon graphic as shown in FIG. Is assigned to a woman, and a boy is assigned to the utterance on the blue speech balloon, and displayed on the narrator setting screen. Then, when "registration" is selected on the narrator setting screen, a character (speaker name) is set for each utterance sentence, and a voice quality such as a language and gender corresponding to the character is set.

  Next, a case will be described as an example where a presentation material as shown in FIG. 13 is taken into the editing processing server 10 to generate multimedia content to be converted into audio.

  In the note portion 50 of the presentation material of FIG. 13, English is included in the utterance sentence enclosed in parentheses.

  Here, the specifying unit 41 specifies the language of the note portion 50 of the presentation material, and automatically sets the language of the speaker. Specifically, since the utterance sentence enclosed in parentheses in the note portion 50 shown in FIG. 13 includes two languages, Japanese and English, in addition to the narration, a plurality of speakers It is specified that the utterance sentence is included. Then, the setting unit 42 assigns speakers corresponding to the respective languages to the Japanese and English utterances specified by the specifying unit 41, respectively, and sets the narrator as shown in FIG. Display a list on the screen. Then, when "register" is selected on the narrator setting screen, a character (speaker name) is set for each utterance sentence.

  Next, a case will be described as an example where a presentation material as shown in FIG. 15 is taken into the editing processing server 10 to generate multimedia content to be converted into audio.

  The note portion 50 of the presentation material in FIG. 15 includes an utterance sentence with a dash at the beginning of the sentence. That is, a note is added to the note portion 50 as a situation description.

  Here, as the utterance sentence that may be changed by the speaker, in addition to the conversation sentence from the note portion 50 of the presentation material, a letter written with a symbol such as a dash or a hyphen is specified.

  In this case, the specifying unit 41 specifies from the dash of the utterance sentence to which the dash of the note portion 50 is added to the start of the line feed code as a note, and sets the voice quality such as the language and gender of the speaker. The utterance sentence to which the hyphen and the paragraph indent are added, as well as the dash, may be specified as the transcript, and the voice quality such as the language and gender of the speaker may be set. Then, as shown in FIG. 16, in addition to the characters in the conversation sentence, the characters are listed as characters on the narrator setting screen. Then, when "register" is selected on the narrator setting screen, a character (speaker name) is set for each utterance sentence.

  Also, as shown in FIG. 17, the utterance sentences specified and extracted by the specifying unit 41 from the text data are displayed in a list, and the characters estimated by analogy from the extracted utterance sentences are respectively assigned and set. You may make it. The extracted utterance sentence and characters may be modified and changed by the user on a display screen as shown in FIG. Then, when "register" is selected on the narrator setting screen, a character (speaker name) is set for each utterance sentence.

10 edit processing server 11 CPU
12 memory 13 storage device 14 communication interface (IF)
Reference Signs List 15 user interface (UI) device 16 control bus 20 terminal device 30 network 31 data communication unit 32 control unit 33 multimedia data storage unit 41 specifying unit 42 setting unit 43 voice conversion unit 44 display control unit 45 user operation reception unit 46 image recognition Department

Claims (12)

Acquiring means for acquiring text data associated with the still image;
From the text data obtained by the obtaining means, specifying means for specifying the utterance sentence by a plurality of speakers,
Setting means for setting a plurality of speakers for the utterance sentence specified by the specifying means,
Speech means for vocalizing each utterance sentence according to the plurality of speakers set by the setting means,
Information processing device provided with.   The information processing apparatus according to claim 1, further comprising a display control unit configured to control to display the voice qualities of a plurality of speakers set by the setting unit.   The information processing apparatus according to claim 2, further comprising a setting change unit configured to change settings of the plurality of speakers set by the setting unit.   3. The information processing apparatus according to claim 2, further comprising adjusting means for adjusting voice qualities of a plurality of speakers set by said setting means.   The information processing apparatus according to claim 1, further comprising a display control unit configured to control to display utterances of a plurality of speakers set by the setting unit.   6. The information processing apparatus according to claim 5, further comprising utterance range changing means for changing utterance ranges of utterance sentences of a plurality of speakers set by said setting means.   The information processing apparatus according to claim 1, wherein the specifying unit specifies the utterances of a plurality of speakers when at least one speaker name is included in the text data obtained by the obtaining unit.   The information processing apparatus according to claim 1, wherein the specifying unit specifies utterances of a plurality of speakers when a predetermined symbol is included in the text data obtained by the obtaining unit.   The information processing apparatus according to claim 1, wherein the specifying unit specifies utterances of a plurality of speakers according to a language used in the text data acquired by the acquiring unit.   The information processing apparatus according to claim 9, wherein the setting unit sets a speaker corresponding to each of the languages used in the utterance sentence specified by the specifying unit.   2. The information processing apparatus according to claim 1, further comprising image data acquisition means for acquiring image data, wherein the identification means identifies an utterance sentence from a specific image in the image data acquired by the image data acquisition means. An obtaining step of obtaining text data associated with the still image;
From the text data obtained in the obtaining step, a specifying step of specifying utterances by a plurality of speakers,
A setting step of setting a plurality of speakers for the utterance sentence specified by the specifying step,
A voice-to-voice step of voice-to-voice utterances according to the plurality of speakers set by the setting step,
A program for causing a computer to execute.

Images