JP2023073901A - Information processing device, information processing method, and information processing program - Google Patents

Abstract

To reduce a workload on a caption creation staff when correcting transcription, when superimposing a statement of a performer or the like performing in a program of a broadcast or the like on a screen as a caption.SOLUTION: An information processing device comprises an acquisition unit, a determination unit, and a transmission control unit. The acquisition unit acquires voice data about a program, and schedule data of the program. The determination unit determines whether or not acquisition time of the voice data is included in a time zone of the program, on the basis of the schedule data. The transmission control unit, when it is determined that the acquisition time is included in the time zone of the program, transmits the voice data to a transcription unit which executes transcription of the voice data, and when it is determined that the acquisition time is not included in the time zone of the program, stops the transmission of the voice data to the transcription unit.SELECTED DRAWING: Figure 3

Description

TECHNICAL FIELD Embodiments of the present invention relate to an information processing apparatus, an information processing method, and an information processing program.

For example, there is a technology for superimposing statements of performers appearing in the program as closed captions on the screen when live broadcasting a news program or the like. With this kind of technology, since it is necessary to immediately transcribe the statements of the performers, etc. in the program, mistranslations may occur during transcription, and the work burden on the person in charge of subtitle production is also increased. big.

JP 2013-68783 A

One of the problems to be solved by the present invention is to reduce the workload of the person in charge of producing subtitles when proofreading the transcription when superimposing the words of the performers appearing in a program such as broadcasting on the screen as subtitles. to reduce.

An information processing apparatus according to an embodiment includes an acquisition unit, a determination unit, and a transmission control unit. The acquisition unit acquires audio data related to a program and schedule data of the program. The determination unit determines whether or not the acquisition time of the audio data is included in the time slot of the program based on the schedule data. When the acquisition time is determined to be included in the time slot of the program, the transmission control unit transmits the voice data to a transcription unit that transcribes the voice data, and the acquisition time is within the program. When it is determined that the time period does not fall within the time period, the transmission of the voice data to the transcription unit is stopped.

It is a figure showing an example of composition of an information processing system concerning a 1st embodiment. It is a figure showing an example of hardware constitutions of an information processor concerning a 1st embodiment. 3 is a diagram showing an example of functional blocks of a processor of the information processing apparatus according to the first embodiment; FIG. FIG. 4 is a diagram showing an example of schedule data regarding broadcast programs according to the first embodiment; It is a figure which shows an example of the procedure of the caption information production|generation process which concerns on 1st Embodiment. FIG. 3 is a diagram showing an example of a graphical user interface displayed on the display of the information processing apparatus according to the first embodiment; FIG. 10 is a diagram illustrating an example of functional blocks of a processor of an information processing apparatus according to a second embodiment; FIG. FIG. 10 is a diagram showing an example of the procedure of subtitle information generation processing according to the second embodiment;

An information processing apparatus, an information processing program, an information processing method, and an information processing system according to embodiments will be described below. The information processing apparatus and the like according to the embodiments superimpose the remarks of the performers appearing in the program as subtitles on the corresponding screen with as little time difference as possible when broadcasting or distributing a news program or the like.

In each of the following embodiments, an information processing apparatus and the like used for live broadcasting of a program wirelessly or by wire will be described as an example in order to make the description more specific. However, the information processing apparatus and the like according to the embodiments can be used not only when broadcasting a program but also when distributing a program via a communication network, for example.

[First Embodiment]
FIG. 1 is a diagram showing an example of the configuration of an information processing system SY according to the first embodiment. As shown in FIG. 1, the information processing system SY includes a switcher 1, an information processing device 3, an inserter 5, a terminal device 6, and a first external device . The information processing device 3 is connected to the terminal device 6 and the first external device 7 via the network N so as to be able to communicate therewith.

The switcher 1, the information processing device 3, and the inserter 5 are provided, for example, in a master room that transmits broadcasts. Here, the master room is one of the facilities provided in a broadcasting station, and is also called a main control room. In the master room, processing is executed to edit image and sound data shot inside and outside the broadcasting station, and to transmit the data as program material to the transmitting station in accordance with the broadcasting progress table. Note that the switcher 1, the information processing device 3, and the inserter 5 can also be provided in a room equipped with real-time subtitle creation equipment, or on the cloud, in addition to the master room.

The switcher 1 receives image and sound data from a program production device in a sub-control room (also called a "news sub-room" or "sub-control room"), a relay device at a relay site, etc. to execute the switching process. Here, the image and sound data is data including image data and sound data associated with each other by time information. Image/sound data for broadcasting is generated from a plurality of pieces of image/sound data by switching processing of the switcher 1 . The switcher 1 outputs the generated image and sound data for broadcasting to the information processing device 3 .

The information processing device 3 executes processing for generating subtitle information using the image and sound data acquired from the switcher 1 (hereinafter referred to as subtitle generation processing). That is, the information processing device 3 separates the image and sound data acquired from the switcher 1 into image data and sound data. The information processing device 3 acquires character information using the separated voice data. The information processing device 3 outputs (transmits) the acquired character information to the terminal device 6 .

Further, the information processing device 3 encodes the character information received from the terminal device 6, and generates caption information including the encoded character information and supplementary information. Here, the incidental information is information including the position (coordinates) on the screen where character information is displayed, character size, color, scrolling speed, time information for associating with image data, and the like. The information processing device 3 outputs (transmits) the image/sound data and the generated caption information to the inserter 5 .

Here, for example, a case where character information is obtained using separated speech data by transcription processing using speech recognition application software built in the first external device 7 on the cloud is taken as an example. A speech recognition application is executed in the transcription unit in the first external device 7 . The speech recognition application software is implemented by a program that transcribes speech data or a speech recognition engine. A known program or speech recognition engine for transcribing can be used, so the description is omitted. Note that the transcription unit may be installed in the information processing device 3 .

Note that the caption information generation processing executed by the information processing device 3 will be described later in detail.

The inserter 5 uses the caption information received from the information processing device 3 to perform insert processing for inserting the caption information into the image/sound data received from the switcher 1 . The inserter 5 outputs the inserted image/sound data to the transmission device 8 provided in the transmission station. Note that the insert processing by the inserter 5 is not synchronized with the time information of the image/sound data. This is based on the premise that there is a delay time associated with the calibration described below. Therefore, from the viewer's point of view, the caption information can be viewed several seconds after the image and sound.

The terminal device 6 is a computer that is communicably connected to the information processing device 3 and used by a person in charge of creating subtitles. The terminal device 6 outputs (displays) a calibration screen including the character information acquired from the information processing device 3 . A person in charge of producing subtitles can use the proofreading screen including the text information to perform proofreading processing of the text information. The terminal device 6 transmits the corrected character information to the information processing device 3 .

The first external device 7 is communicably connected to the information processing device 3 via the network N, for example. The first external device 7 incorporates speech recognition application software. The first external device 7 performs transcription processing using the voice data received from the information processing device 3 to generate character information.

(Information processing device 3)
Next, the configuration and functions of the information processing device 3 will be described in detail with reference to FIGS. 2 and 3. FIG.

FIG. 2 is a diagram showing an example of the hardware configuration of the information processing device 3 according to the first embodiment. The information processing device 3 has a hardware configuration similar to that of a normal computer. That is, as shown in FIG. 2, the information processing device 3 includes a processor 301 , a main storage device 303 , a device interface 305 , an auxiliary storage device 307 and a network interface 309 .

The processor 301 is a processing circuit that performs overall control of the information processing device 3 and the second external device 9 connected to the information processing device 3 . Specifically, the processor 301 includes a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), and an FPGA (Field Programmable Gate) as electronic circuits including a computer control device and an arithmetic device. array ), etc. Also, the processor 301 may be realized by an optical circuit using optical logic elements. The processor 301 reads an information processing program, which will be described later, from the main storage device 303 or the auxiliary storage device 307, and develops it in its own memory. The processor 301 controls, for example, various hardware in the information processing device 3 according to the developed information processing program.

The main storage device 303 is a storage device that stores instructions and various data executed by the processor 301 , and information stored in the main storage device 303 is read by the processor 301 . More specifically, the main storage device 303 or the auxiliary storage device 307 stores image and sound data acquired from the switcher 1 and a program for realizing subtitle information generation processing, which will be described later. The main storage device 303 also stores schedule data relating to broadcast programs. Schedule data will be explained later. Note that the schedule data may be stored in the auxiliary storage device 307 .

The device interface 305 connects the second external device 9 and the processor 301 via the bus B directly or indirectly. Note that the device interface 305 may have a connection terminal such as a USB. Also, the device interface 305 may be connected to an external storage medium, a storage device (memory), or the like via a connection terminal.

Auxiliary storage device 307 is a storage device other than main storage device 303 .

The main storage device 303 and the auxiliary storage device 307 mean arbitrary electronic components capable of storing electronic information, and may be semiconductor memories. Typically, the main storage device 303 and the auxiliary storage device 307 are composed of a RAM (Random Access Memory), a semiconductor memory device such as a flash memory, a hard disk, an optical disk, or the like. The main storage device 303 and the auxiliary storage device 307 may be composed of portable media such as USB (Universal Serial Bus), memory, and DVD (Digital Versatile Disk).

A network interface 309 is an interface for connecting to the network N wirelessly or by wire. The network interface 309 can transmit and receive information to and from the first external device 7 via the network N. FIG.

The second external device 9 includes, for example, an input device (microphone, keyboard, mouse, touch panel, etc.), an output device (LCD (Liquid Crystal Display), a display device such as an organic EL (Electro Luminescence) panel), a storage device ( memory).

FIG. 3 is a diagram showing an example of functional blocks of the processor 301 of the information processing device 3 according to the first embodiment. As shown in FIG. 3, the processor 301 has an acquisition unit 31, a determination unit 33, and a transmission control unit . A function executed by the acquisition unit 31 (hereinafter referred to as an acquisition function), a function executed by the determination unit 33 (hereinafter referred to as a determination function), and a function performed by the transmission control unit 35 (hereinafter referred to as transmission control function) is stored in the main storage device 303 or the auxiliary storage device 307 in the form of a computer-executable program, for example. That is, the information processing programs for executing the acquisition function, the determination function, and the transmission control function are stored in the main storage device 303 or the auxiliary storage device 307 . Note that the information processing program may be stored in the first external device 7 .

Acquisition unit 31 acquires audio data about a program and schedule data of the program. Specifically, the acquisition unit 31 acquires the audio data separated by the switcher 1 and the image data corresponding to the audio data from the switcher 1 . Acquisition unit 31 also acquires schedule data of programs related to the broadcast from main storage device 303, auxiliary storage device 307, or the second storage device. The acquisition unit 31 also acquires data transcribed from the voice data in the transcription unit of the first external device 7 (hereinafter referred to as transcribed data). Note that when the transcription unit is installed in the information processing device 3, the acquisition unit 31 may acquire the transcription data generated by the transcription unit from the transcription unit.

FIG. 4 is a diagram showing an example of schedule data SD regarding broadcast programs. As shown in FIG. 4, the schedule data SD has the temporal order of program corners in the broadcast and the temporal order of advertisements broadcast during the program. As shown in FIG. 4, the schedule data SD includes, for example, broadcast date, program start time, program end time, program name, audio mode, device name or studio name used for broadcasting, material name (program segment, CM (commercial) Messages: Commercial Messages, advertisements)), scheduled broadcast start times of materials, and the like. The schedule data SD shown in FIG. 4 is an example, and more various information is described in the implementation. Also, the format of the schedule data SD shown in FIG. 4 differs depending on the broadcasting station.

For example, the broadcast date is described in the first line of the schedule data SD shown in FIG. The second line of the schedule data SD shown in FIG. 4 describes the program start time, program end time, program name, and audio mode (stereo: S). The third line of the schedule data SD shown in FIG. 4 describes that the material XXX (opening corner, etc.) will be on air from 4:00:00 on the device PG. The fourth line of the schedule data SD shown in FIG. 4 describes that the material AAA (CM) will be on air from 4:30:00 on the device named CM. After that, from 4:30:15, 4:30:30, and 4:30:45, the material BBB (CM), the material CCC (CM), and the material DDD (CM) will be on air, respectively. It is stated that That is, it states that four commercials will be on air at 15-second intervals from 4:30:00.

Also, in the eighth line of the schedule data SD shown in FIG. 4, it is described that the news section 1 will be on air at studio L1 from 4:31:00. Further, the ninth line of the schedule data SD shown in FIG. 4 describes that the material EEE will be on-air by the user's take operation, although the time is undecided. Further, the 10th line of the schedule data SD shown in FIG. 4 describes that the news section 2 will be on air at the studio L1 after the CM, although the time is undecided.

Also, in the 11th and 12th lines of the schedule data SD shown in FIG. 4, it is described that two programs will be on air at 15-second intervals from 4:50:00. Also, in the 13th line of the schedule data SD shown in FIG. 4, it is described that the weather corner will be on air by the device WN. In addition, in the 14th to 17th lines of the schedule data SD shown in FIG. 4, four commercials (Material GGG, Material HHH, Material III, Material JJJ) were aired at 15-second intervals from 4:59:00. It is stated that The 18th line of the schedule data SD shown in FIG. 4 describes the name of the next program to be aired from 5:00:00.

The determination unit 33 determines whether or not the acquired audio data is being broadcast based on the schedule data SD. That is, the determining unit 33 determines whether or not the time when the audio data (and the image data corresponding to the audio data) was acquired by the acquiring unit 31 (hereinafter referred to as acquisition time) is included in the time slot of the program. do. The time zone of the program is the time zone during which the program is broadcast (hereinafter referred to as the broadcast time zone), excluding commercials. The broadcasting time zone may be not limited to commercials, but may include time zones such as during provision, during program, during VTR, etc., as a time zone during which transcription is not performed for the production of subtitles. More specifically, the determination unit 33 can determine whether or not transcription is possible based on device names such as "PG", "CM", "L1", and "WN". For example, the determination unit 33 inquires the acquisition time and the time in the schedule data SD. Thereby, the determination unit 33 determines whether or not the acquisition time is included in the broadcast time zone of the program in the schedule data SD.

When it is determined that the acquisition time is included in the broadcast time slot of the program, the transmission control unit 35 transmits the audio data to the transcription unit that transcribes the audio data. Specifically, the transmission control unit 35 transmits the acquired audio data to the first external device 7 having the transcription unit when the acquisition time is included in the broadcasting time slot of the program.

The transmission control unit 35 stops transmitting the audio data to the transcription unit when it is determined that the acquisition time is not included in the broadcast time slot of the program. Specifically, the transmission control unit 35 stops transmitting the audio data to the first external device 7 having the transcription unit when the acquisition time is included in the broadcasting time slot of the program. More specifically, the transmission control unit 35 stops transmitting the voice data to the transcription unit when the acquisition time is included in the advertisement time period in the schedule data SD.

Subtitle information generation processing according to the present embodiment will be described below. FIG. 5 is a diagram illustrating an example of the procedure of subtitle information generation processing.

(Caption information generation processing)
(Step S501)
Acquisition unit 31 acquires audio data and schedule data SD. Note that the acquisition unit 31 may acquire the schedule data SD prior to acquiring the audio data.

(Step S502)
The determination unit 33 determines whether or not the acquired audio data is being broadcast based on the schedule data SD. If the acquisition time of the acquired audio data is not included in the broadcast time slot of the program in the schedule data SD (No in step S502), the process of step S503 is executed. In other words, when the acquisition time of the audio data is included in the advertisement broadcast time slot in the schedule data SD, the process of step S503 is executed.

If the acquisition time of the acquired audio data is included in the broadcast time slot of the program in the schedule data SD (Yes in step S502), the process of step S504 is executed. In other words, if the acquisition time of the audio data is not included in the advertisement broadcast time slot in the schedule data SD, the process of step S504 is executed.

(Step S503)
The transmission control unit 35 stops transmission of voice data to the first external device 7 having the transcription unit. Note that if the transcription unit is installed in the information processing device 3, the transmission control unit 35 stops outputting the acquired voice data to the transcription unit.

(Step S504)
The transmission control unit 35 transmits the acquired voice data to the first external device 7 having a transcription unit. It should be noted that when the transcription unit is installed in the information processing device 3, the transmission control unit 35 outputs the acquired voice data to the transcription unit.

(Step S505)
The acquisition unit 31 acquires transcription data from the first external device 7, which is the transcription result. The transmission control unit 35 transmits the acquired transcription data to the terminal device 6 . At this time, the terminal device 6 displays a caption proofreading screen including character information based on the transcription data. The person in charge of subtitle production uses the displayed proofreading screen to proofread the character information. In response to the completion of the proofreading process, the terminal device 6 transmits the character information subjected to the proofreading process to the information processing device 3 .

(Step S506)
The acquisition unit 31 acquires character information from the terminal device 6 . A caption information generating unit (not shown) in the information processing device 3 encodes the character information received from the terminal device 6 and generates caption information including the encoded character information and supplementary information. The transmission control unit 35 outputs (transmits) the image/sound data and the generated caption information to the inserter 5 . The inserter 5 uses the image/sound data and caption information received from the information processing device 3 to execute insert processing for inserting the caption information into the image/sound data, and provides the image/sound data subjected to the insert processing to the transmitting station. output to the sending device 8.

(Step S507)
The determination unit 33 determines whether or not the program has ended based on the current time and the schedule data SD. Specifically, the determination unit 33 determines whether or not the program has ended by comparing the current time with the schedule data SD. If the program has not ended (No in step S507), the process of step S508 is executed. If the program has ended (Yes in step S507), the caption information generation process ends.

(Step S508)
Acquisition unit 31 acquires audio data. Subsequently, the process of step S502 is executed again.

As a modified example of the present embodiment, the transmission control unit 35 causes the first transcribing unit having a transcription unit according to the user's input to the graphical user interface displayed on the display of the information processing device 3. Transmission of audio data to the external device 7 may be stopped.

FIG. 6 is a diagram showing an example of the graphical user interface DP displayed on the display of the information processing device 3. As shown in FIG. In FIG. 6, the button LB corresponding to "cover" is pressed when the acquisition time of the acquired audio data is not included in the broadcast time zone of the program in the schedule data SD in the process of step 502 (No in step S502). displayed in highlight. At this time, the transmission of the voice data to the first external device 7 having the transcription unit is closed. That is, the transmission control unit 35 stops transmitting audio data to the first external device 7 . Further, when the user presses the button LB corresponding to the "lid", the button LB corresponding to the "lid" is highlighted. In this case as well, the transmission control unit 35 stops transmitting audio data to the first external device 7 .

As described above, the information processing apparatus 3 according to the present embodiment acquires the audio data relating to broadcasting and the schedule data SD of the program relating to broadcasting, and based on the schedule data SD, the acquisition time of the audio data corresponds to the time of the program broadcasting. It is determined whether or not the acquisition time is included in the broadcast time zone, and if it is determined that the acquired time is included in the broadcast time zone, the voice data is transmitted to a transcription unit that transcribes the voice data, and the acquisition time is determined to be within the broadcast time zone. If it is determined that the time is not included in the time period, the transmission of the voice data to the transcription unit is stopped. Further, in the information processing device 3, the schedule data SD has the time sequence of program corners in the broadcast and the time sequence of advertisements broadcast during the program. is included in the time period of the advertisement, the transmission of voice data to the transcription unit is stopped.

According to such a configuration, the information processing apparatus 3 according to the present embodiment can limit transcription-related operations to the broadcast time of the program by determining the start/end of the program and/or CM. . Thus, according to the information processing device 3, by acquiring the broadcast schedule data SD, transcription corresponding to the program can be realized. From the above, according to the information processing device 3, when the remarks of the performers appearing in a program such as broadcasting are superimposed on the screen as subtitles, the work load of the person in charge of subtitle production when proofreading the transcription can be reduced. can be reduced.

When the technical idea of the first embodiment is realized by an information processing method, the information processing method acquires audio data related to broadcasting and program schedule data related to the broadcasting, and based on the schedule data, generates audio data. determines whether or not the acquisition time is included in the broadcast time slot of the program, and if it is determined that the acquisition time is included in the broadcast time slot, the audio data is transmitted, and when it is determined that the acquired time is not included in the broadcast time slot, the transmission of the voice data to the transcription unit is stopped. The procedure and effect of the subtitle information generation process by this information processing method are the same as those described in the first embodiment, and thus the description is omitted.

When the technical idea of the first embodiment is realized by an information processing program, the information processing program acquires audio data related to broadcasting and schedule data of programs related to the broadcasting into a computer, and based on the schedule data , a transcription unit that determines whether or not the acquisition time of the audio data is included in the broadcast time slot of the program, and transcribes the audio data if it is determined that the acquisition time is included in the broadcast time slot. When it is determined that the acquisition time is not included in the broadcast time slot, the transmission of the voice data to the transcription unit is stopped.

For example, the caption information generation process can be realized by installing the information processing program in a server device placed in the master room or a server device on the cloud, and deploying the program on the memory. . At this time, the program that allows the computer to execute the caption information generation process can be distributed by storing it in a storage medium such as a magnetic disk (hard disk, etc.), optical disk (CD-ROM, DVD, etc.), semiconductor memory, etc. is. The procedure and effect of the subtitle information generation process by the information processing program are the same as those of the first embodiment, and thus description thereof is omitted.

[Second embodiment]
In the second embodiment, the configuration of the information processing system and the hardware configuration of the information processing apparatus are the same as those in the first embodiment, so description thereof will be omitted. The difference between this embodiment and the first embodiment is that a speech recognition dictionary to be applied to transcription of voice data is specified based on broadcast program information, and the specified voice recognition dictionary is used to transcribe voice data. (hereinafter referred to as application information) to be applied to the transcription unit. Application information relating to application of the voice recognition dictionary is stored in the main storage device 303 or the auxiliary storage device 397 in association with the type of program section in the program information. That is, the speech recognition dictionary is a dictionary that is associated with the type of corner of the program in the program information and that is applied to transcription of the speech data. For example, the speech recognition dictionary is used in a transcription section to convert hiragana characters resulting from transcription of voice data into kanji characters according to morphemes. The speech recognition dictionaries are stored, for example, in the memory of the first external device 7 having a transcription unit according to the types of program corners. When the transcription unit is installed in the information processing device 3, the speech recognition dictionary is stored in, for example, the main storage device 303 or the auxiliary storage device 397 according to the type of corner of the program.

The application information is associated with the type of corner of the program to which the audio data belongs by the schedule data SD (for example, corners of programs such as news, weather, sports competitions, etc.). The correspondence is stored in the main storage device 303 or the auxiliary storage device 397 in the form of a lookup table, for example. Units different from the first embodiment will be described below.

FIG. 7 is a diagram showing an example of functional blocks of the processor 301 of the information processing device 3 according to the second embodiment. As shown in FIG. 7, the processor 301 has an acquisition unit 31, an identification unit 34, and a transmission control unit 35. The acquisition function, the function executed by the identification unit 34 (hereinafter referred to as the identification function), and the transmission control function are stored in the main memory 303 or the auxiliary memory 307 in the form of a computer-executable program, for example. remembered. That is, the information processing programs for executing the acquisition function, the specific function, and the transmission control function are stored in the main storage device 303 or the auxiliary storage device 307 . Note that the information processing program may be stored in the first external device 7 .

The acquisition unit 31 acquires audio data related to broadcasting and program information of the broadcasting. The program information is included in the schedule data SD, for example, as shown in FIG. 4, and is code or information indicating the type of corner of the program. Therefore, specifically, the acquisition unit 31 may acquire audio data related to broadcasting and schedule data SD related to broadcasting.

The specifying unit 34 specifies a voice recognition dictionary to be applied to transcription of voice data based on the program information. Specifically, the identifying unit 34 identifies the voice recognition dictionary by matching the program name in the schedule data SD with the reference correspondence table. For example, if the program name is news as shown in FIG. 4, the identifying unit 34 identifies the speech recognition dictionary corresponding to the news. Note that the specifying unit 34 may specify a voice recognition dictionary applied to the past voice data of the same type as the type of the corner of the program relating to the voice data, based on the program information. For example, when a speech recognition dictionary is specified for a morning news program, the specifying unit 34 uses the voice recognition dictionary used in the morning news program for the transcription of news programs in other time zones and on other days of the day. Identify a dictionary. At this time, the application information includes contents instructing that the speech recognition dictionary used in the morning news program be used for transcription in news programs in other time zones and other days of the day.

The transmission control unit 35 transmits the voice data and application information for applying the specified voice recognition dictionary to transcription to the transcription unit that transcribes the voice data. That is, the transmission control unit 35 transmits application information for applying the specified voice recognition dictionary to the first external device 7 having the transcription unit together with the voice data in the transcription of the voice data.

Subtitle information generation processing according to the present embodiment will be described below. FIG. 8 is a diagram showing an example of the procedure of subtitle information generation processing according to the present embodiment.

(Caption information generation processing)
(Step S801)
Acquisition unit 31 acquires audio data and program information. Specifically, the acquisition unit 31 acquires audio data and schedule data SD including program information. Note that the acquisition unit 31 may acquire program information prior to acquiring audio data.

(Step S802)
The specifying unit 34 specifies the voice recognition dictionary based on the program information. For example, the identifying unit 34 identifies the program (program section) to which the audio data belongs, using the time schedule in the schedule data SD and the time of the audio data. Next, the specifying unit 34 specifies the voice recognition dictionary corresponding to the program section to which the voice data belongs. At this time, the specifying unit 34 may register an identifier related to the specified voice recognition dictionary in the main storage device 303 or the auxiliary storage device 307 .

Note that if an identifier related to the voice recognition dictionary specified in the past is stored in the main storage device 303 or the auxiliary storage device 307, the specifying unit 34 selects the same type of program section for voice data based on the program information. A speech recognition dictionary applied to the past speech data of the type may be specified in the main storage device 303 or the auxiliary storage device 307 . For example, the identification unit 34 searches the main storage device 303 or the auxiliary storage device 307 for an identifier relating to the type of program segment to which the audio data belongs. Next, the specifying unit 34 specifies the voice recognition dictionary corresponding to the identifier that matches the identifier as the voice recognition dictionary corresponding to the program to which the voice data belongs.

(Step S803)
The transmission control unit 35 transmits the acquired voice data and application information to the first external device 7 having a transcription unit. If the transcription unit is installed in the information processing device 3, the transmission control unit 35 outputs the acquired voice data and application information to the transcription unit. At this time, the transcription unit transcribes the voice data using the speech recognition dictionary specified in the application information.

(Step S804)
The acquisition unit 31 acquires transcription data from the first external device 7, which is the transcription result. The transmission control unit 35 transmits the acquired transcription data to the terminal device 6 . The contents of the processing in this step are the same as in step S505, so the description is omitted.

(Step S805)
The acquisition unit 31 acquires character information from the terminal device 6 . The subtitle information generation unit generates subtitle information based on the character information. The transmission control unit 35 outputs (transmits) the image/sound data and the generated caption information to the inserter 5 . Other processes are the same as those in step S506, so the description is omitted.

(Step S806)
If the program has not ended (No in step S806), the process of step S807 is executed. If the program has ended (Yes in step S806), the caption information generation process ends.

(Step S807)
Acquisition unit 31 acquires audio data. Then, the processing after step S802 is executed again.

As described above, the information processing apparatus 3 according to the present embodiment acquires audio data related to broadcasting and program information of the broadcasting, and based on the program information, the audio data associated with the type of corner of the program in the program information. A voice recognition dictionary to be applied to transcribe data is specified, and voice data and application information for applying the specified voice recognition dictionary are transmitted to a transcriber that transcribes the voice data. Further, the information processing device 3 identifies the voice recognition dictionary applied to the past voice data of the same type as the corner type of the program relating to the voice data, based on the program information.

According to such a configuration, the information processing apparatus 3 according to the present embodiment receives program information (program corner information) from equipment in the master room, and automatically creates a voice recognition dictionary corresponding to the program corner. can be selected. As a result, the information processing device 3 transmits the application information for applying the selected speech recognition dictionary to transcription to the first external device 7, thereby transferring the speech recognition dictionary used for transcription to the corner of the program. can be specified according to As described above, according to the information processing apparatus 3, it is possible to obtain transcribed data transcribed using an appropriate (specialized) speech recognition dictionary corresponding to the section of the program to which the audio data belongs. Therefore, in the case of superimposing, as captions, statements of performers appearing in a program such as broadcasting on the screen, the work load of the person in charge of creating captions when proofreading the transcription can be reduced.

When the technical concept of the second embodiment is realized by an information processing method, the information processing method acquires audio data related to broadcasting and program information of the broadcasting, and based on the program information, displays corners of the program in the program information. specifies a speech recognition dictionary that is associated with the type of and is applied to the transcription of the speech data, and converts the speech data and application information that applies the specified speech recognition dictionary to a transcription unit that transcribes the speech data Send to The procedure and effect of the subtitle information generation process by this information processing method are the same as those described in the second embodiment, so the description is omitted.

When the technical idea in the second embodiment is realized by an information processing program, the information processing program acquires audio data related to broadcasting and program information of broadcasting in a computer, and based on the program information, A speech recognition dictionary that is associated with the type of corner of the program and applied to the transcription of the audio data is specified, and the speech data and application information for applying the specified speech recognition dictionary are used to transcribe the audio data. sending to a transcription unit. The procedure and effect of the subtitle information generation process by the information processing program are the same as those of the second embodiment, and thus description thereof is omitted.

Although several embodiments of the present invention have been described above, the embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the scope of the invention described in the claims and equivalents thereof.

REFERENCE SIGNS LIST 1 switcher 3 information processing device 5 inserter 6 terminal device 7 first external device 8 sending device 9 second external device 31 acquiring unit 33 determining unit 34 specifying unit 35 transmission control unit 301... Processor 303... Main storage device 305... Device interface 307... Auxiliary storage device 309... Network interface

Claims (8)

an acquisition unit that acquires audio data related to a program and schedule data of the program;
a determination unit that determines whether or not the acquisition time of the audio data is included in the time slot of the program based on the schedule data;
When it is determined that the acquisition time is included in the time slot of the program, the audio data is transmitted to a transcription unit that transcribes the audio data, and the acquisition time is included in the time slot of the program. a transmission control unit for stopping transmission of the voice data to the transcription unit when it is determined that there is no
Information processing device. the schedule data includes a temporal order of corners of the program and a temporal order of advertisements in the middle of the program;
The transmission control unit stops transmitting the voice data to the transcription unit when the acquisition time is included in the time period of the advertisement.
The information processing device according to claim 1 . an acquisition unit that acquires audio data related to a program and program information;
a specifying unit that specifies, based on the program information, a voice recognition dictionary that is associated with the type of corner of the program in the program information and that is applied to transcription of the voice data;
a transmission control unit that transmits the voice data and application information to which the specified voice recognition dictionary is applied to a transcription unit that performs transcription of the voice data;
Information processing device. The identifying unit identifies, based on the program information, a speech recognition dictionary applied to past audio data of the same type as a corner type of the program relating to the audio data.
The information processing apparatus according to claim 3. Acquiring audio data related to a program and schedule data of the program;
determining whether or not the acquisition time of the audio data is included in the time slot of the program based on the schedule data;
transmitting the audio data to a transcription unit that transcribes the audio data when it is determined that the acquisition time is included in the time slot of the program;
stopping transmission of the audio data to a transcription unit when it is determined that the acquisition time is not included in the time slot of the program;
An information processing method comprising: to the computer,
Acquiring audio data related to a program and schedule data of the program;
determining whether or not the acquisition time of the audio data is included in the time slot of the program based on the schedule data;
transmitting the audio data to a transcription unit that transcribes the audio data when it is determined that the acquisition time is included in the time slot of the program;
stopping transmission of the audio data to a transcription unit when it is determined that the acquisition time is not included in the time slot of the program;
Information processing program that realizes Acquiring audio data related to a program and program information,
based on the program information, identifying a speech recognition dictionary that is associated with the type of corner of the program in the program information and that is applied to transcription of the audio data;
transmitting the voice data and application information to which the specified voice recognition dictionary is applied to a transcription unit that performs transcription of the voice data;
An information processing method comprising: to the computer,
Acquiring audio data related to a program and program information,
Based on the program information, identifying a speech recognition dictionary that corresponds to the type of program section in the program information and is applied to transcription of the audio data;
transmitting the voice data and application information to which the specified voice recognition dictionary is applied to a transcription unit that performs transcription of the voice data;
Information processing program that realizes

Images