Narration creation support system, narration creation support method, and program

Abstract

To provide a technique capable of accurately and efficiently supporting generation of narration according to a reproduction time.SOLUTION: The narration generation support system includes a first acquisition unit that acquires first information related to a narration script associated with each of one or a plurality of narration blocks, a second acquisition unit that acquires second information related to a playback time associated with each of one or a plurality of narration blocks, a calculation unit that calculates a speech rate for completing narration based on the narration script during the playback time for each of one or a plurality of narration blocks on the basis of the first information and the second information, and a generation unit that generates output information related to the speech rate for each of one or a plurality of narration blocks on the basis of a calculation result of the calculation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a narration creation support system, a narration creation support method, and a program. [Background technology]

[0002] 2. Description of the Related Art Conventionally, a technique for using a computer to synthesize speech from an original text written as a character file and reproducing it as natural language has been widely known.

[0003] In this regard, Patent Document 1 describes a device that can easily perform effective video editing to match the content of narration in video production. Specifically, this device generates synthetic voice from narration manuscript data, synchronizes with the playback position of the video editing device, and reads it at the reading speed of a pre-registered announcer or narrator, while simultaneously displaying the manuscript. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-080928 Summary of the Invention [Problem to be solved by the invention]

[0005] However, with the above-described conventional techniques, it is difficult to accurately and efficiently generate narration according to the playback time.

[0006] Therefore, the present invention has been made in view of the above, and has an object to provide a technology that can support the generation of narration in accordance with the playback time accurately and efficiently. [Means for solving the problem]

[0007] A narration generation support system according to one embodiment of the present invention is a narration generation support system that supports the generation of narration, and includes a first acquisition unit that acquires first information regarding a narration manuscript associated with each of one or more narration blocks, a second acquisition unit that acquires second information regarding a playback time associated with each of one or more narration blocks, a calculation unit that calculates, based on the first information and the second information, a speaking speed for completing narration based on the narration manuscript within the playback time for each of one or more narration blocks, and a generation unit that generates output information regarding the speaking speed for each of one or more narration blocks based on the calculation results of the calculation unit.

[0008] A narration generation support method according to one embodiment of the present invention is a narration generation support method executed by a computer that supports the generation of narration, and includes the steps of acquiring first information regarding a narration manuscript associated with each of one or more narration blocks, acquiring second information regarding a playback time associated with each of one or more narration blocks, calculating, based on the first information and the second information, a speaking speed for completing narration based on the narration manuscript within the playback time for each of one or more narration blocks, and generating output information regarding the speaking speed for each of one or more narration blocks based on the calculation result of the calculating step.

[0009] A program according to one embodiment of the present invention causes a computer that assists in the generation of narration to function as a first acquisition unit that acquires first information regarding a narration manuscript associated with each of one or more narration blocks, a second acquisition unit that acquires second information regarding the playback time associated with each of one or more narration blocks, a calculation unit that calculates, based on the first information and the second information, the speaking speed at which the narration based on the narration manuscript will be completed within the playback time for each of one or more narration blocks, and a generation unit that generates output information regarding the speaking speed for each of one or more narration blocks based on the calculation results of the calculation unit. [Effects of the Invention]

[0010] According to an aspect of the present invention, it is possible to support the generation of narration in accordance with the playback time accurately and efficiently. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a diagram showing the overall configuration and overview of a narration generation support system according to an embodiment; [Figure 2] 1 is a diagram showing functional blocks of a narration generation assistance device according to an embodiment; [Figure 3] FIG. 10 is a diagram illustrating an example of manuscript information according to an embodiment. [Figure 4] FIG. 10 is a diagram illustrating an example of a speech rate calculation process according to an embodiment. [Figure 5] 10 is a screen example showing an example of a narration when speech is synthesized at a standard speaking rate, according to one embodiment. [Figure 6] 10 is an example of a screen showing an example of a result of a speech rate calculation process according to an embodiment. [Figure 7] 10 is an example of a screen for explaining an example of a speech rate control process according to an embodiment. [Figure 8] 10 is an example of a screen for correcting a narration manuscript according to an embodiment. [Figure 9] 10 is a flowchart illustrating an example of a narration generation support process according to an embodiment. [Figure 10] 10 is a flowchart illustrating an example of a condition determination process and a speech rate control process according to an embodiment. [Figure 11] FIG. 10 is a diagram illustrating an example of a plurality of different speech speed data according to an embodiment. [Figure 12] FIG. 2 is a diagram illustrating an example of a hardware configuration of a computer according to an embodiment.

[0012] Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, the embodiments described below are merely examples, and are not intended to exclude various modifications or applications of techniques not explicitly described below. In other words, the present invention can be implemented in various modifications (such as combining the respective embodiments) without departing from the spirit of the invention. Furthermore, in the following description of the drawings, identical or similar parts are denoted by the same or similar reference numerals.

[0013] In the embodiments of the present invention, the terms "unit," "device," and "system" do not simply mean physical means, but also include cases where the functions of the "unit," "device," and "system" are realized by software. Furthermore, the functions of one "unit," "device," and "system" may be realized by two or more physical means or devices, and the functions of two or more "units," "devices," and "systems" may be realized by one physical means or device.

[0014] FIG. 1 is a diagram showing the overall configuration and overview of a narration generation support system according to one embodiment. The narration generation support system 100 is a system that supports the generation (including editing, etc.) of narrations performed by, for example, a broadcasting station. The narration generation support system 100 illustratively comprises a narration generation support server 1 (narration generation support device) for supporting the generation of narrations, and a user terminal 5 operated by, for example, an employee (user) of the broadcasting station. The user terminal 5 is equipped with, for example, predetermined video editing software.

[0015] An overview of a narration generation support system 100 according to one embodiment of the present invention will be described. Generally, when generating narration at a broadcasting station, a script for the narration is first prepared, and then the narration is recorded by, for example, an announcer, narrator, or assistant director. The narration is then manually edited by an employee or the like who edits the narration using predetermined video editing software. Because a large amount of manual work is involved in each step of the narration generation process depending on the generation time, it may be difficult to ensure the accuracy of the generated narration, and the work time is long, placing a heavy burden on employees and the like, and the cost of generating the narration is high. Therefore, it cannot be said that narration is generated accurately and efficiently according to the playback time.

[0016] Therefore, the narration generation support system 100 can execute, for example, items (1) to (8). (1) The user terminal 5 creates a manuscript in which TC (time code) (playback time) and a narration manuscript (e.g., text information) are associated, and transmits the manuscript information to the narration generation support server 1. For example, the manuscript is managed in CSV format. (2) The narration generation support server 1 acquires the manuscript created by the user terminal 5. (3) The narration generation support server 1 calculates a speaking speed according to the TC. (4) The narration generation support server 1 outputs output information related to the speaking speed based on the calculated speaking speed. Note that the "output information" includes at least one of information for prompting the user to control the calculated speaking speed and information for prompting the user to modify the narration manuscript.

[0017] (5) The narration generation support server 1 can control the speaking speed and modify the content of the narration manuscript based on instructions from the user or automatically. (6) The narration generation support server 1 sets the voice of the synthesized voice for the narration to be generated. For example, the spoken language (e.g., Japanese, English, French, Spanish, and Chinese), gender, and tone of voice can be set as appropriate. (7) Once the narration generation support server 1 generates an audio file for the narration, it sends it to the user terminal 5. (8) Upon receiving the audio file from the narration generation support server 1, the user terminal 5 imports the audio file into specified video editing software.

[0018] The specific processing contents of items (1) to (8) will be described later. The processing order of items (1) to (8) is not limited to the above and can be changed as appropriate. For example, item (6) is executed after items (3) to (5) in the above example, but it may be executed before items (3) to (5).

[0019] Specifically, a narration generation support system 100 according to one embodiment of the present invention acquires narration manuscript information (first information) relating to a narration manuscript associated with one or more narration blocks. The narration generation support system 100 acquires TC information (second information) relating to the TC associated with one or more narration blocks. Based on the narration manuscript information and the TC information, the narration generation support system 100 calculates, for one or more narration blocks, a speaking rate at which the narration based on the narration manuscript is to be completed within the TC. Based on the calculated speaking rate, the narration generation support system 100 generates output information relating to the speaking rate for one or more narration blocks. Therefore, the narration generation support system 100 can provide a technology that can accurately and efficiently support the generation of narration according to playback time.

[0020] In the narration generation support system 100 shown in FIG. 1, the narration generation support server 1 and the user terminal 5 are connected to each other via a predetermined communication network. The predetermined communication network may be a wired communication network or a wireless communication network. The narration generation support server 1 is configured, for example, by a server device configured by a computer system or a cloud server, and is implemented by a software program. The user terminal 5 may be, for example, a general-purpose personal computer, a smartphone, a tablet terminal, or other device. The number of user devices 5 is arbitrary, and the user terminal 5 is assumed to be one or more user terminals.

[0021] FIG. 2 is a diagram showing functional blocks of a narration generation assistance server according to an embodiment of the present invention. As shown in FIG. 2, the narration generation assistance server 1 functionally includes a communication unit 11 that transmits and receives various information to and from the user terminal 5 shown in FIG. 1, an information processing unit 12 that executes various processes for narration generation assistance, and a storage unit 13 that stores information for executing the various processes for narration generation assistance and the execution results of the various processes. As described above, the narration generation assistance server 1 is implemented by a software program and is configured, for example, as a server device implemented by a computer system or a cloud server. The program may be provided by being downloaded from outside the narration generation assistance server 1 via a predetermined network, or may be provided by various computer-readable information recording media such as a CD-ROM or DVD-ROM.

[0022] The information processing unit 12 functionally includes a narration manuscript acquisition unit 14 (first acquisition unit), a TC acquisition unit 15 (second acquisition unit), a speech rate calculation unit 16 (calculation unit), an output information generation unit 17 (generation unit), a condition judgment unit 18 (judgment unit), a speech rate control unit 19 (control unit), and a manuscript editing unit 20.

[0023] The narration manuscript acquisition unit 14 acquires narration manuscript information NMI (first information) relating to a narration manuscript associated with one or more narration blocks. The TC acquisition unit 15 acquires TC information TCI (second information) relating to TC (playback time) associated with one or more narration blocks BL.

[0024] FIG. 3 is a diagram illustrating an example of manuscript information related to a manuscript according to an embodiment. As shown in FIG. 3, manuscript information is information in which TC information TCI and narration manuscript information NMI are associated and managed for each one or more narration blocks BL, which are units for generating narration. The TC information TCI includes time information related to the start time (e.g., "Start Time") and end time (e.g., "End Time") of the narration block BL. The narration manuscript information NMI includes, for example, text information. In the example of FIG. 3, for example, if the start time of the narration block BL is (00:00:13:00) and the end time is (00:00:23:00), the required length (playback time) is the difference between the start time and the end time (10 [s]).

[0025] The narration manuscript acquisition unit 14 acquires narration manuscript information NMI relating to a narration manuscript associated with one or more narration blocks BL from manuscript information created by the user terminal 5. The TC acquisition unit 15 acquires TC information TCI associated with one or more narration blocks BL from manuscript information created by the user terminal 5.

[0026] The speech rate calculation unit 16 calculates, for each of one or more narration blocks BL, a speech rate at which the narration based on the narration manuscript is completed within the TC, based on the narration manuscript information NMI and the TC information TCI.

[0027] An example of the speech rate calculation process will be specifically described with reference to Fig. 4 to Fig. 6. Fig. 4 is a diagram for explaining an example of the speech rate calculation process according to an embodiment. Fig. 5 is an example screen showing an example of a narration when speech is synthesized at a standard speech rate (referred to as "reference speech rate"). Fig. 6 is an example screen showing an example of the result of the speech rate calculation process according to an embodiment.

[0028] When manuscript information is uploaded from the user terminal 5 shown in Figure 1 by user operation, the narration generation support system 100 generates narration for each of multiple narration blocks BL based on the narration manuscript information NMI and TC information TCI contained in the manuscript information.

[0029] Narration synthesized at a standard speaking rate based on manuscript information is called standard speaking rate narration. Standard speaking rate narration is a provisionally generated narration. For standard speaking rate narration associated with a narration block that exceeds the required length (playback time) according to the TC when synthesized at the standard speaking rate, the speaking rate can be converted (calculated) or the narration manuscript can be modified so that it fits within the required length.

[0030] In the example of FIG. 4, for example, the manuscript information includes a start time "Start Time" (00:00:02.200) and an end time "End Time" (00:00:04.840) as TC information TCI. In this example, the required length is 2.640 [s]. Furthermore, for example, the manuscript information includes text information such as "●●●●●●●●●●..." as narration manuscript information NMI. Based on this manuscript information, a standard speaking speed narration is generated when speech is synthesized at a standard speaking speed (for example, 1.0x speed). The playback time of the standard speaking speed narration is, for example, t [s]. Since the playback time t [s] exceeds the required length of 2.640 [s], the speech speed is converted (speech speed calculated) so that it fits within the required length. More specifically, in the narration generation support system 100, the standard speaking speed is converted (the speaking speed that fits within the required length is calculated) based on the ratio between the standard speaking speed narration playback time t [s] when speech is synthesized at the standard speaking speed and the required length of 2.640 [s].

[0031] As shown in Fig. 5, a standard speaking rate narration is generated for each of one or more narration blocks BL1 to BL4 and displayed on a screen DS1. The screen DS1 is generated by the narration generation assistance server 1 as long as it is presented to the user in a manner that is visible to the user. The screen DS1 can be output (presented) on the output unit (for example, the input / output interface 44 shown in Fig. 12) of the narration generation assistance server 1 or the user terminal 5. Other screens (for example, screens DS3, DS5, and DS7) described later can also be output in a similar manner.

[0032] In the example of Figure 5, the playback time of the standard speaking speed narration in narration blocks BL1 and BL4 exceeds the required length associated with each of the narration blocks BL1 and BL4. The time by which the playback time of the standard speaking speed narration in narration block BL1 exceeds the required length associated with narration block BL1 is shown as "00:00:01.73" (1.73 [s]). Also, the time by which the playback time of the standard speaking speed narration in narration block BL4 exceeds the required length associated with narration block BL4 is shown as "00:00:00.98" (0.98 [s]).

[0033] Here, buttons B1 and B4 for executing a speech rate calculation process are associated with and displayed on narration blocks BL1 and BL4, respectively, whose playback times of the standard speech rate narration exceed the requested length. For example, when the user selects (presses) button B1, the speech rate calculation unit 16 calculates the speech rate of the narration in narration block BL1 so that the playback time of the standard speech rate narration in narration block BL1, which exceeds the requested length, falls within the requested length. Similarly, when the user selects button B4, the speech rate calculation unit 16 calculates the speech rate of the narration in narration block BL4 so that the playback time of the standard speech rate narration in narration block BL4, which exceeds the requested length, falls within the requested length.

[0034] In the above, it has been explained that the narration speaking rate calculation process is triggered by pressing button B1 or B4, but this is not limited to this, and the speaking rate calculation process may also be triggered by other user input. Furthermore, the narration speaking rate calculation process may also be executed without user input. For example, if the playback time of the standard speaking rate narration of a specific narration block BL does not fit within the requested duration, the narration generation assistance server 1 may automatically (without user input) execute the narration speaking rate calculation process so that the narration fits within the requested duration.

[0035] When the user selects (presses) the play buttons PB1 to PB4 corresponding to each narration block BL1 to BL4, the narration of the narration block corresponding to the selected play button is played, allowing the user to check the content of the narration (e.g., speaking speed, playback time).

[0036] As shown in Fig. 6, among the multiple narration blocks BL1 to BL4, for narration block BL1 and narration block BL4, narration is generated at a speech speed (e.g., X times the standard speech speed) that is converted (calculated) so that the playback time of the standard speech speed narration falls within the required length. That is, as indicated by button B1 "x1.34," for narration block BL1, narration is generated at a speech speed 1.34 times the standard speech speed of the standard speech speed narration. Also, as indicated by button B4 "x1.11," for narration block BL4, narration is generated at a speech speed 1.11 times the standard speech speed of the standard speech speed narration.

[0037] The output information generation unit 17 generates output information regarding the speaking speed for each of one or more narration blocks BL based on the calculation result of the speaking speed calculation unit 16. The "output information" includes at least one of output information for prompting the user to control the speaking speed for each of one or more narration blocks BL, and output information for prompting the user to correct the narration manuscript.

[0038] Returning to FIG. 2 , the condition determination unit 18 determines whether the speech speed of each of one or more narration blocks BL satisfies a predetermined condition related to narration speech speed control. For example, the "predetermined condition" includes a plurality of different conditions related to narration speech speed control. For example, the "first condition" among the "predetermined conditions" includes a condition related to the ratio between the number of multiple narration blocks BL and the number of specific one or more narration blocks BL among the multiple narration blocks BL for which a speech speed equal to or greater than a predetermined threshold has been calculated. The "second condition" among the "predetermined conditions" includes a second condition related to the difference between a first speech speed calculated for a first narration block among the multiple narration blocks BL and a second speech speed calculated for a second narration block different from the first narration block, the second speech speed being slower than the first speech speed. The condition determination process will be described later with reference to FIGS. 10 and 11.

[0039] The speech rate control unit 19 controls the speech rate of each of one or more narration blocks BL. For example, the speech rate control unit 19 controls the speech rate of each of one or more narration blocks BL based on a user's operational input. For example, in the example of FIG. 6, as indicated by button B1 "×1.34," a narration is generated for narration block BL1 at a speech rate 1.34 times the standard speech rate of the standard speech rate narration. If the user selects play button PB1, the narration for narration block BL1 associated with the selected play button PB1 is played back, allowing the user to confirm the content of the narration. If the user feels that the calculated speech rate of the narration for narration block BL1 (for example, a speech rate 1.34 times the standard speech rate) is too fast, the calculated speech rate of the narration for narration block BL1 can be controlled to be slower by the user's operational input.

[0040] The speech rate control unit 19 may control the speech rate for one or more narration blocks BL automatically (independently of a user's operational input). As an example of automatically controlling the speech rate, the speech rate control unit 19 controls the speech rate for one or more narration blocks BL based on the calculation result of the speech rate calculation unit 16. The speech rate control unit 19 may also control the speech rate for one or more narration blocks BL based on the determination result of the condition determination unit 18. The process of controlling the speech rate for one or more narration blocks BL based on the determination result of the condition determination unit 18 will be described later with reference to FIGS. 10 and 11.

[0041] The speech speed control unit 19 can collectively control the standard speech speed of one or more narration blocks BL based on an operational input from the user.

[0042] An example of collective control of the standard speaking speed of narrations of multiple narration blocks BL will be described with reference to FIG. 7. FIG. 7 is an example screen for explaining an example of collective speaking speed control processing according to an embodiment. As shown in FIG. 7, for narration block BL1 and narration block BL4, narrations are generated at a speaking speed (e.g., X times the standard speaking speed) calculated so that the playback time of the standard speaking speed narration falls within the required length. That is, as indicated by button B1 "×1.15," a narration is generated for narration block BL1 at a speaking speed (calculated speaking speed) that is 1.15 times the standard speaking speed of the standard speaking speed narration. Furthermore, as indicated by button B4 "×1.26," a narration is generated for narration block BL4 at a speaking speed that is 1.26 times the standard speaking speed of the standard speaking speed narration.

[0043] In such a case, for example, the user presses play buttons PB2 and PB4 in order to play the narration associated with narration block BL2 and the narration associated with narration block BL4 in order. If the user feels that the speaking speed of the narration in narration block BL2 and the narration in narration block BL4 is significantly faster (louder) than the speaking speed of the narration in the other narration blocks, the user can control the standard speaking speed of the narration in all narration blocks BL collectively.

[0044] 7, the user can control the standard speech speed of the narration of all narration blocks BL collectively by operating the knob P on the slider SL left or right. For example, when the speech speed control unit 19 receives a user operation input relating to the movement of the knob P on the slider SL, it can control the standard speech speed of the narration of all narration blocks BL collectively to, for example, a speech speed (standard speech speed (after update)) that is 1.05 times the standard speech speed (standard speech speed (before update)).

[0045] Specifically, the narration speed of narration blocks other than narration block BL2 and narration block BL4 is 1.05 times the reference speech speed (reference speech speed (before update)) (reference speech speed (after update)). On the other hand, the calculated speech speed for the narration in narration block BL2 is 1.15 times the reference speech speed (reference speech speed (before update)) (reference speech speed (after update)), so the new speech speed is 1.095 (=1.15 / 1.05) times the reference speech speed. Furthermore, the calculated speech speed for the narration in narration block BL4 is 1.26 times the reference speech speed, so the new speech speed is 1.2 (=1.26 / 1.05) times the reference speech speed.

[0046] This configuration makes it possible to control the difference in speaking speed between the narrations of the multiple narration blocks BL so as to minimize the difference in speaking speed between them, thereby eliminating the sense of discomfort felt by the user due to the large difference in speaking speed between the multiple narrations of the multiple narration blocks BL being played back.

[0047] Returning to FIG. 2, the manuscript editing unit 20 can correct the narration manuscript based on the user's operational input.

[0048] Fig. 8 shows an example of a screen for correcting a narration script according to one embodiment. As shown in Fig. 8, on screen DS7, the playback time of narration block BL4 is 2.27 [s] longer than the requested length, so output information (for example, text information TI saying "X characters need to be reduced") is output to prompt the user to correct the narration script.

[0049] Here, the number of characters to be reduced in the narration manuscript is calculated, for example, using the following formula (1): Note that the "actual length" is the playback time of the narration after the speech rate has been calculated. Number of characters to be reduced = (1 - required length / actual length) x original number of characters (1)

[0050] If the user wishes to revise the narration manuscript, a screen (not shown) may be output in which the user can carry out a prescribed operation to revise the narration manuscript, for example, to reduce the number of characters in the text information "It looks quite strange... but it is also a very rare animal from an academic perspective." The user can then revise the text information on this screen.

[0051] Returning to Figure 2, the storage unit 13 stores, for example, narration manuscript information NMI, TC information TCI, condition information CI including predetermined conditions, and narration information NI regarding the narration generated by the information processing unit 12 through voice synthesis.

[0052] <Narration generation support processing> An example of a narration generation support process according to an embodiment will be described with reference to FIG. 9. FIG. 9 is a flowchart showing an example of a narration generation support process according to an embodiment. As a premise, in the narration generation support process, narration generation support application software including the narration generation support process according to an embodiment of the present invention is downloaded from, for example, a predetermined site on a network or a recording medium, and stored in an executable manner in the narration generation support server 1 shown in FIGS. 1 and 2. Then, when an instruction to execute the narration generation support process is given, program operation based on the software begins. Note that the software is also executed in advance in the user terminal 5 shown in FIG. 1 so as to operate appropriately as an element of the narration generation support system 100.

[0053] 9, the narration generation support server 1 acquires narration manuscript information NMI relating to a narration manuscript associated with one or more narration blocks (step S1). The narration generation support server 1 acquires TC information TCI relating to a TC associated with one or more narration blocks (step S3). Based on the narration manuscript information NMI and the TC information TCI, the narration generation support server 1 calculates, for one or more narration blocks, a speaking speed at which the narration based on the narration manuscript is to be completed within the playback time (step S5).

[0054] The narration generation assistance server 1 generates output information regarding the speaking rate for each of one or more narration blocks based on the result of the speaking rate calculation in step S5 (step S7).

[0055] An example of a condition determination process and a speech rate control process according to an embodiment will be described with reference to Fig. 10 and Fig. 11. Fig. 10 is a flowchart showing an example of a condition determination process and a speech rate control process according to an embodiment. Fig. 11 is a diagram showing an example of a plurality of different speech rate data according to an embodiment.

[0056] 10, the narration generation support server 1 determines whether a first condition regarding the number of narration blocks BL is satisfied (step S11 described later), and then determines whether a second condition regarding the speech speed calculated among the narration blocks BL is satisfied (step S15 described later). With this configuration, it is possible to more efficiently control the speech speed by first determining the block ratio based on the entirety of the narration blocks BL.

[0057] Specifically, for example, the narration generation assisting server 1 determines a first condition including a condition regarding the ratio between the total number of multiple narration blocks BL and the number of specific narration blocks BL for which a speech speed higher than a predetermined threshold has been calculated (step S11). More specifically, the narration generation assisting server 1 determines whether the ratio between the total number of multiple narration blocks BL (blocks 1 to 10 shown in "Speech Speed ​​Data A" in FIG. 11) and the number of specific narration blocks BL for which a speech speed higher than a predetermined threshold has been calculated (for example, "1" indicating the reference speech speed in the example of FIG. 11) is greater than "0.25 (1 / 4)." Note that the "Speech Speed ​​Data A" to "Speech Speed ​​Data D" in FIG. 11 include data indicating the ratio of the speech speed of each narration block to the reference speech speed.

[0058] In the example of "Speech Speed ​​Data A" in Figure 11, the ratio of the total number of multiple narration blocks BL (blocks 1 to 10 shown in "Speech Speed ​​Data A") to the number of specific narration blocks (blocks 1 to 5 shown in "Speech Speed ​​Data A") among the multiple narration blocks BL for which a speech speed faster than the reference speech speed has been calculated (specific narration blocks whose ratio to the reference speech speed is greater than "1") is "0.5". Therefore, the narration generation support server 1 determines that the ratio "0.5" is greater than "0.25" (Yes in step S11) and proceeds to step S13.

[0059] As shown by the speech rate data B in FIG. 11, the narration generation assistance server 1 controls the standard speech rate (before updating) of the narration in each narration block (block 1 to block 10) to a standard speech rate (after updating) of "+0.05" (for example, 1.05 times) (step S13). Here, for example, the speech rate of the narration in block 1 is controlled to "1.19" (=1.25 / 1.05), and the speech rate of the narration in block 2 is controlled to "1.14" (=1.20 / 1.05). The other blocks 3 to 5 are controlled in a similar manner. Note that the amount of speech rate control is arbitrary and is not limited to "+0.05", and other control amounts may be used.

[0060] Returning to step S11, the narration generation support server 1 determines whether the ratio between the total number of multiple narration blocks BL (blocks 1 to 10 shown in "speech speed data B") and the number of specific narration blocks (blocks 1 to 4 shown in "speech speed data B") among the multiple narration blocks BL for which a speech speed faster than a predetermined threshold (for example, "1" indicating the reference speech speed) is faster than "0.25".

[0061] In the example of "speech speed data B" in Figure 11, the ratio between the total number of multiple narration blocks BL (blocks 1 to 10 shown in "speech speed data B") and the number of specific narration blocks (blocks 1 to 4 shown in "speech speed data B") among the multiple narration blocks BL for which a speech speed faster than the reference speech speed has been calculated (specific narration blocks whose ratio to the reference speech speed is greater than "1") is "0.4". Therefore, the narration generation support server 1 determines that the ratio "0.4" is faster than "0.25" (Yes in step S11), and proceeds to step S13 again.

[0062] The narration generation assistance server 1 controls the standard speaking speed of the narration of each narration block (block 1 to block 10) to "+0.05" (step S13), as shown by the speaking speed data C in Fig. 11. Here, for example, the speaking speed of the narration of block 1 is controlled to "1.14" (=1.25 / 1.1), and the speaking speed of the narration of block 2 is controlled to "1.09" (=1.20 / 1.1). The same control is applied to the other blocks 3 and 4.

[0063] Returning to step S11, the narration generation support server 1 determines whether the ratio between the total number of multiple narration blocks BL (blocks 1 to 10 shown in "speech speed data C") and the number of specific narration blocks (blocks 1 to 3 shown in "speech speed data C") among the multiple narration blocks BL for which a speech speed faster than a predetermined threshold (for example, "1" indicating the reference speech speed) is faster than "0.25".

[0064] In the example of "speech speed data C" in Figure 11, the ratio between the total number of multiple narration blocks BL (blocks 1 to 10 shown in "speech speed data C") and the number of specific narration blocks (blocks 1 to 3 shown in "speech speed data C") among the multiple narration blocks BL for which a speech speed faster than the reference speech speed has been calculated (specific narration blocks whose ratio to the reference speech speed is greater than "1") is "0.3". Therefore, the narration generation assistance server 1 determines that the ratio "0.3" is faster than "0.25" (Yes in step S11), and proceeds to step S13 again.

[0065] The narration generation assist server 1 controls the standard speaking speed of the narration of each narration block (block 1 to block 10) to "+0.05" as shown by the speaking speed data D in FIG. 11 (step S13).

[0066] Returning to step S11, the narration generation support server 1 determines whether the ratio between the total number of multiple narration blocks BL (blocks 1 to 10 shown in "speech speed data D") and the number of specific narration blocks (blocks 1 and 2 shown in "speech speed data D") among the multiple narration blocks BL for which a speech speed faster than a predetermined threshold (for example, "1" indicating the reference speech speed) is faster than "0.25 (1 / 4)".

[0067] In the example of "speech speed data D" in Figure 11, the ratio between the total number of multiple narration blocks BL (blocks 1 to 10 shown in "speech speed data D") and the number of specific narration blocks (blocks 1 and 2 shown in "speech speed data D") among the multiple narration blocks BL for which a speech speed faster than the reference speech speed has been calculated (specific narration blocks whose ratio to the reference speech speed is greater than "1") is "0.2". Therefore, the narration generation support server 1 determines that the ratio "0.2" is smaller than "0.25" (No in step S11) and proceeds to step S15.

[0068] The narration generation support server 1 determines a second condition including a condition regarding the difference between a first speech rate calculated for a first narration block among a plurality of narration blocks and a second speech rate calculated for a second narration block different from the first narration block, the second speech rate being slower than the first speech rate (step S15).

[0069] More specifically, the narration generation assisting server 1 determines whether the difference (e.g., 0.09) between the maximum speech speed (e.g., 1.09) calculated for a narration block (e.g., block 1) among the multiple narration blocks and the minimum speech speed (e.g., 1) calculated for the other narration blocks (e.g., blocks 3 to 10) is faster than 0.25. In this case, since the difference (0.09) is smaller than 0.25, the narration generation assisting server 1 determines No in step S15 and terminates the process. On the other hand, if the determination in step S15 is Yes, the process returns to step S13.

[0070] In the above example, the narration generation support server 1 determines whether a first condition regarding the number of narration blocks BL is satisfied (step S11), and then determines whether a second condition regarding the speech speed calculated between the narration blocks BL is satisfied (step S15). However, the present invention is not limited to the above example, and the narration generation support server 1 may execute step S11 after first executing the processing of step S15. Furthermore, the narration generation support server 1 does not necessarily need to execute both step S11 and step S15, and may execute only one of step S11 or step S15.

[0071] Fig. 12 is a diagram showing an example of the hardware configuration of a computer according to an embodiment of the present invention. With reference to Fig. 12, an example of the hardware configuration of a computer that can be used to configure the narration generation support server 1 and the user terminal 5 shown in Fig. 1 will be described.

[0072] 12, a computer 40 mainly comprises, as hardware resources, a processor 41, a main storage device 42, an auxiliary storage device 43, an input / output interface 44, and a communication interface 45, which are interconnected via a bus line 46 including an address bus, a data bus, a control bus, etc. Note that an interface circuit (not shown) may be interposed between the bus line 46 and each hardware resource as appropriate.

[0073] The processor 41 controls the entire computer. The processor 41 corresponds to, for example, the information processing unit 12 shown in FIG. 2. The main storage device 42 provides a working area for the processor 41 and stores an SRAM ( S tatic R andom A access M emory) and DRAM ( D Dynamic R andom A access M The auxiliary storage device 43 is a volatile memory such as a memory card (RAM) or a hard disk drive (HDD), and is a non-volatile memory such as a hard disk drive (HDD), solid state drive (SSD), or flash memory that stores software programs and data. The programs and data are loaded from the auxiliary storage device 43 to the main storage device 42 via the bus line 46 at any time.

[0074] The input / output interface 44 presents information and / or receives input of information, and may be a camera, keyboard, mouse, display, touch panel display, microphone, speaker, etc. The communication interface 45 is connected to the above-mentioned predetermined communication network and transmits and receives data via the predetermined communication network. The communication interface 45 may also acquire information related to the network, such as information related to Wi-Fi access points.

[0075] It will be apparent to those skilled in the art that the cooperation of the hardware resources and software exemplified above enables the computer 40 to function as desired means, execute desired steps, and achieve desired functions.

[0076] It should be noted that the above-described embodiments are provided to facilitate understanding of the present invention and are not to be construed as limiting the present invention. The present invention may be modified or improved without departing from the spirit thereof, and equivalents thereof are also included in the present invention. Furthermore, the present invention can be formed into various disclosures by appropriately combining multiple components disclosed in the above-described embodiments. For example, some components may be deleted from all the components shown in the embodiments. Furthermore, components may be appropriately combined in different embodiments. [Explanation of symbols]

[0077] 1... narration generation support server, 5... user terminal, 11... communication unit, 12... information processing unit, 13... storage unit, 14... narration manuscript acquisition unit, 15... time code (TC) acquisition unit, 16... speaking rate calculation unit, 17... output information generation unit, 18... condition determination unit, 19... speaking rate control unit, 20... manuscript editing unit, 41... processor, 42... main recording device, 43... auxiliary recording device, 44... input / output interface, 45... communication interface, 46... bus line, 100... narration generation support system,

Claims

1. A narration generation support system for supporting the generation of narration, comprising: a first acquisition unit that acquires first information related to a narration manuscript associated with each of one or more narration blocks; a second acquisition unit that acquires second information related to a playback time associated with each of the one or more narration blocks; a calculation unit that calculates, for each of the one or more narration blocks, a speech speed at which the narration based on the narration manuscript is completed within the playback time based on the first information and the second information; a generating unit that generates output information regarding the speech rate for each of the one or more narration blocks based on the calculation result of the calculating unit; a determination unit that determines whether the speech rate of each of the one or more narration blocks satisfies predetermined conditions including a plurality of different conditions related to speech rate control of the narration; a control unit that controls the speech speed for each of the one or more narration blocks based on the determination result of the determination unit; Equipped with the determination unit determines whether a first condition regarding the number of narration blocks is satisfied, and then determines whether a second condition regarding a speech rate calculated between the narration blocks is satisfied. Narration generation support system.

2. the first condition includes a condition regarding a ratio between the number of a plurality of narration blocks and the number of one or more specific narration blocks among the plurality of narration blocks for which a speech rate equal to or higher than a predetermined threshold is calculated; The narration generation support system according to claim 1 .

3. the second condition includes a second condition related to a difference between a first speech rate calculated for a first narration block among a plurality of narration blocks and a second speech rate calculated for a second narration block different from the first narration block, the second speech rate being lower than the first speech rate; The narration generation support system according to claim 1 .

4. a control unit that collectively controls the reference speech rate associated with each of the one or more narration blocks based on a user input; The narration generation support system according to claim 1 .

5. the output information includes at least one of information for prompting a user to control the speech rate for each of the one or more narration blocks and information for prompting the user to correct the narration manuscript. The narration generation support system according to claim 1 .

6. A computer-implemented method for assisting in the generation of narration, comprising: obtaining first information about a narration manuscript associated with each of one or more narration blocks; obtaining second information relating to a playback time associated with each of the one or more narration blocks; calculating, for each of the one or more narration blocks, a speech speed at which the narration based on the narration manuscript is completed within the playback time based on the first information and the second information; generating output information regarding the speech rate for each of the one or more narration blocks based on the calculation result of the calculating step; determining whether the speech rate of each of the one or more narration blocks satisfies predetermined conditions, including a plurality of different conditions relating to speech rate control of the narration; a step of controlling the speech rate for each of the one or more narration blocks based on the determination result of the determining step; Including, the determining step determines whether a first condition regarding the number of narration blocks is satisfied, and then determines whether a second condition regarding a speech rate calculated among the narration blocks is satisfied; A method for assisting in the generation of narration.

7. A computer that helps generate narration a first acquisition unit that acquires first information related to a narration manuscript associated with each of one or more narration blocks; a second acquisition unit that acquires second information related to a playback time associated with each of the one or more narration blocks; a calculation unit that calculates, for each of the one or more narration blocks, a speech speed at which the narration based on the narration manuscript is completed within the playback time based on the first information and the second information; a generating unit that generates output information regarding the speech rate for each of the one or more narration blocks based on the calculation result of the calculating unit; a determination unit that determines whether the speech rate of each of the one or more narration blocks satisfies predetermined conditions including a plurality of different conditions related to speech rate control of the narration; a control unit that controls the speech speed for each of the one or more narration blocks based on the determination result of the determination unit; It functions as the determination unit determines whether a first condition regarding the number of narration blocks is satisfied, and then determines whether a second condition regarding a speech rate calculated between the narration blocks is satisfied. program.

Images