JP7203259B1 - Broadcast audio transmission device, broadcast audio transmission method, and broadcast audio transmission program - Google Patents

Abstract

An object of the present invention is to broadcast with intonation suitable for the region where the broadcast is made. A broadcasting audio transmitting device 100 transmits weather comment audio 68 broadcast in a specific broadcasting area. The name conversion table 64 associates a code specifying a region name with a different intonation with a post-conversion name obtained by adding additional data representing a region or direction to the region name. The voice conversion table 66 associates the name after conversion with a voice with an intonation corresponding to the additional data. The audio data generation unit 130 generates audio data including codes including area names. The voice text creating unit 140 converts the code corresponding to the area name to the converted name using the name conversion table 64, and creates voice text 65 that is a broadcast comment candidate including the converted name. The voice transmission unit 150 uses the voice conversion table 66 to reproduce the clauses included in the voice text 65 and transmits the voice of the weather comment. [Selection drawing] Fig. 1

Description

The present disclosure relates to a broadcast audio transmission device, a broadcast audio transmission method, and a broadcast audio transmission program.

There is a technology for converting weather comments broadcast from a broadcasting station into voice and transmitting the voice. Weather comments broadcast by broadcasters are required to be intonation (dialect) according to the local station when converted to speech. This is because viewers in the region where the weather comment is broadcast will find it difficult to listen to the broadcast if there is an unfamiliar intonation.

Usually, the conversion of weather comments into speech is performed as follows.
First, sentences for weather comments are prepared as text data. Then, using a text data-to-speech tool, the text of the weather commentary is converted into speech with intonation that matches standard Japanese. Finally, the adjuster manually adjusts the accent position while listening to the intonation voice that matches the standard language, and generates the intonation (dialect) voice of the weather comment according to the local station.

At this time, there is a possibility that the adjustment operator's subjectivity will enter into the wrong intonation. Also, if the adjustment worker does not know the local intonation, it takes time and effort to obtain a voice sample from an announcer at a broadcasting station and adjust the accent position while listening to it.

Patent Literature 1 discloses a technique of extracting a place name in a text of a weather comment and synthesizing the accent of the place name part.

JP-A-8-160983

Among place names, there are place names that have the same pronunciation but have different intonations depending on the region, such as many place names that exist throughout the country. In addition, there are place names that are the same as words that indicate regions, directions, or directions, such as southern, central, west, upper, lower, or southeast, and even if the pronunciation is the same, the intonation may differ depending on the region.
The technique of Patent Document 1 simply converts the place name in the text of the weather comment. Therefore, there is a problem that it is not possible to correct place names that are the same as words indicating a region, a direction, or a direction, and place names that exist all over the country, into proper intonation according to the region where the weather comment is broadcast.

The purpose of the present disclosure is to automatically convert the voice of the weather comment into an appropriate intonation according to the region where the weather comment is to be broadcast, so as to provide an easy-to-listen voice with little discomfort to the viewer. do.

A broadcast audio transmission device according to the present disclosure is a broadcast audio transmission device that transmits broadcast comment audio broadcast in a specific broadcast area,
a name conversion table in which a code specifying an area name representing an area or direction and having a different intonation for each broadcasting area is associated with a converted name obtained by adding additional data representing the area or direction to the area name; a voice conversion table in which phrases used in the broadcast comment are associated with voices of the phrases, and voices of intonation corresponding to the additional data are associated with the converted names that are the phrases; a storage unit that stores
audio data for generating audio data representing an audio configuration of the broadcast comment and including a code specifying the area name, using broadcast data in area information included in the specific broadcast area; a data generator;
Using the name conversion table, the region name corresponding to the code included in the audio data is converted into the post-conversion name, and an audio text, which is a candidate for the broadcast comment including the post-conversion name, is created. a voice sentence creation unit for
and a voice transmission unit for transmitting the voice of the comment for broadcast by reproducing the phrase included in the text for voice using the voice conversion table.

The storage unit
storing the name conversion table for each data type representing the type of the broadcast data;
The audio data generation unit is
Acquiring the data type included in the broadcast data of the specific broadcasting area, generating the audio data representing the configuration of the audio according to the data type,
The voice text creation unit is
The speech text is generated using the name conversion table corresponding to the data type.

The voice conversion table is
The phrase is associated with a voice file storing voice of the phrase, and the converted name, which is the phrase, is associated with a voice file storing voice of intonation corresponding to the additional data. and
The audio transmission unit is
Using the voice conversion table, the order of the voice files is determined according to the order of the phrases included in the voice text, and the voice of the broadcast comment is transmitted by reproducing the voice files in the determined order. .

The voice text creation unit is
It is determined whether or not the reproduction time of the voice text is within a specified length, and if not within the specified length, the voice text is adjusted according to a predetermined rule.

The broadcasting audio transmission device includes:
As the broadcasting comment, the voice of the weather comment used for broadcasting the weather in the specific broadcasting area is transmitted.

A broadcast audio transmission method according to the present disclosure is a broadcast audio transmission method used in a broadcast audio transmission device that transmits broadcast comment audio broadcast in a specific broadcast area,
A name conversion in which a computer associates a code specifying an area name representing an area or direction and having a different intonation for each broadcasting area with a post-conversion name obtained by adding additional data representing the area or direction to the area name. A table, phrases used in the broadcast comment, and voices of the phrases are associated with each other, and voices of intonation corresponding to the additional data are associated with the converted names, which are the phrases. memorize a conversion table and
A computer uses broadcast data in area information included in the specific broadcast area to generate audio data representing an audio configuration of the broadcast comment and including a code specifying the area name. death,
The computer converts the region name corresponding to the code included in the audio data into the converted name using the name conversion table, and converts the area name into the post-conversion name to be a candidate for the broadcast comment containing the post-conversion name. create sentences,
The computer uses the voice conversion table to reproduce the phrases included in the voice text, thereby transmitting the voice of the broadcast comment.

The broadcast audio transmission program according to the present disclosure is a broadcast audio transmission program used in a broadcast audio transmission device that transmits broadcast comment audio broadcast in a specific broadcast area,
The broadcasting audio transmission device includes:
a name conversion table in which a code specifying an area name representing an area or direction and having a different intonation for each broadcasting area is associated with a converted name obtained by adding additional data representing the area or direction to the area name; a voice conversion table in which phrases used in the broadcast comment are associated with voices of the phrases, and voices of intonation corresponding to the additional data are associated with the converted names that are the phrases; and a storage unit that stores
audio data for generating audio data representing an audio configuration of the broadcast comment and including a code specifying the area name, using broadcast data in area information included in the specific broadcast area; a data generation process;
Using the name conversion table, the region name corresponding to the code included in the audio data is converted into the post-conversion name, and an audio text, which is a candidate for the broadcast comment including the post-conversion name, is created. voice sentence creation processing to
A computer is caused to execute a voice transmission process of transmitting the voice of the comment for broadcasting by reproducing the phrase contained in the sentence for voice using the voice conversion table.

In the broadcast audio transmission device according to the present disclosure, by automatically converting the broadcast comment into a voice with appropriate intonation according to the region where the broadcast is to be broadcast, the voice of the broadcast comment is provided that is easy to hear with less sense of incongruity for listeners. It has the effect of being able to

1 is a diagram showing a configuration example of a broadcasting audio transmission device according to Embodiment 1; FIG. FIG. 4 is a flow chart showing an example of the operation of the broadcasting audio transmission device according to the first embodiment; 4 is a diagram showing a configuration example of weather data according to Embodiment 1; FIG. 4 is a diagram showing a configuration example of audio data according to Embodiment 1. FIG. FIG. 3 is a flowchart showing an example of operation continued from FIG. 2 in the example of operation of the broadcasting audio transmitting apparatus according to Embodiment 1; 4 is a diagram showing a configuration example of a name conversion table according to the first embodiment; FIG. FIG. 4 is a diagram showing an example of a text for speech according to Embodiment 1; 4 is a diagram showing a configuration example of a speech conversion table according to Embodiment 1; FIG. 4 is a diagram showing a configuration example of an audio file according to Embodiment 1; FIG. 4 is a diagram showing an example of the order of audio files determined by an audio transmission unit according to the first embodiment; FIG. FIG. 10 is a diagram showing a functional configuration example of a broadcasting audio transmission device according to a modification of Embodiment 1; FIG. 2 is a diagram showing a configuration example of a broadcasting audio transmission device according to a modification of Embodiment 1; 4 is a diagram showing a configuration example of a definition file according to the first embodiment; FIG.

The present embodiment will be described below with reference to the drawings. In each figure, the same reference numerals are given to the same or corresponding parts. In the description of the embodiments, the description of the same or corresponding parts will be omitted or simplified as appropriate. Arrows in the figure mainly indicate the flow of data or the flow of processing. Also, in the following drawings, the size relationship of each component may differ from the actual size. Also, in the description of the embodiments, directions or positions such as up, down, left, right, front, back, front, and back may be indicated. These notations are for the convenience of explanation, and do not limit the arrangement, direction, and orientation of devices, instruments, parts, and the like.

Embodiment 1.
*** Configuration description ***
FIG. 1 is a diagram showing a configuration example of a broadcasting audio transmitting apparatus 100 according to this embodiment.
The broadcasting sound transmitting apparatus 100 transmits the sound of broadcasting comments broadcasted in a specific broadcasting area.
Specifically, a weather comment voice 68 to be broadcast about the weather in a specific broadcasting area is transmitted. Weather comments are generated using weather data obtained from a weather company or the like as original data. A weather comment is an example of a broadcast comment that is broadcast in a specific broadcast region. Also, weather data is an example of broadcast data that is source data for broadcast comments.
Broadcast audio transmitting apparatus 100 is, for example, a computer provided in a broadcasting station.
A weather company or the like refers to a company or the like that provides actual data and forecast data related to weather as weather data.

Broadcast audio transmission device 100 is a computer. Broadcast audio transmitting apparatus 100 includes processor 910 and other hardware such as memory 921 , auxiliary storage device 922 , input interface 930 , output interface 940 and communication device 950 . The processor 910 is connected to other hardware via signal lines and controls these other hardware.

Broadcast audio transmitting apparatus 100 includes a data receiving unit 110, a data registering unit 120, an audio data generating unit 130, an audio text creating unit 140, an audio transmitting unit 150, and a storage unit 160 as functional elements. Storage unit 160 stores weather data 61, weather database 62, voice data 63, name conversion table 64, voice text 65, voice conversion table 66, voice file 67, and definition file .

The functions of the data receiving section 110, the data registering section 120, the voice data generating section 130, the voice sentence creating section 140, and the voice transmitting section 150 are implemented by software. The storage unit 160 is provided in the memory 921 . Note that the storage unit 160 may be provided in the auxiliary storage device 922 , or may be distributed between the memory 921 and the auxiliary storage device 922 .

Processor 910 is a device that executes a broadcast audio transmission program. The broadcasting audio transmission program is a program that implements the functions of the data receiving section 110 , the data registration section 120 , the audio data generating section 130 , the audio text creating section 140 and the audio transmission section 150 .
The processor 910 is an IC that performs arithmetic processing. Examples of processor 910 are CPU, DSP, GPU. The IC is the back of the Integrated Circuit. CPU is an abbreviation for Central Processing Unit. DSP is an abbreviation for Digital Signal Processor. GPU is an abbreviation for Graphics Processing Unit.

The memory 921 is a storage device that temporarily stores data. A specific example of the memory 921 is SRAM or DRAM. SRAM is an abbreviation for Static Random Access Memory. DRAM is an abbreviation for Dynamic Random Access Memory.
Auxiliary storage device 922 is a storage device that stores data. A specific example of the auxiliary storage device 922 is an HDD. The auxiliary storage device 922 may be a portable storage medium such as an SD (registered trademark) memory card, CF, NAND flash, flexible disk, optical disk, compact disk, Blu-ray (registered trademark) disk, or DVD. Note that HDD is an abbreviation for Hard Disk Drive. SD® is an abbreviation for Secure Digital. CF is an abbreviation for CompactFlash®. DVD is an abbreviation for Digital Versatile Disk.

The input interface 930 is a port connected to an input device such as a mouse, keyboard, or touch panel. The input interface 930 is specifically a USB terminal. Note that the input interface 930 may be a port connected to a LAN. USB is an abbreviation for Universal Serial Bus. LAN is an abbreviation for Local Area Network.

The output interface 940 is a port to which a cable of an output device such as a display is connected. The output interface 940 is specifically a USB terminal or an HDMI (registered trademark) terminal. The display is specifically an LCD. Output interface 940 is also referred to as a display interface. HDMI (registered trademark) is an abbreviation for High Definition Multimedia Interface. LCD is an abbreviation for Liquid Crystal Display.

Communication device 950 has a receiver and a transmitter. A communication device 950 is connected to a communication network such as a LAN, the Internet, or a telephone line. The communication device 950 is specifically a communication chip or NIC. NIC is an abbreviation for Network Interface Card.

The broadcast audio transmission program is executed in the broadcast audio transmission device 100 . The broadcast audio transmission program is read into processor 910 and executed by processor 910 . The memory 921 stores not only the broadcasting audio transmission program but also the OS. OS is an abbreviation for Operating System. The processor 910 executes the broadcasting audio transmission program while executing the OS. The broadcasting audio transmission program and OS may be stored in the auxiliary storage device 922 . The broadcast audio transmission program and OS stored in auxiliary storage device 922 are loaded into memory 921 and executed by processor 910 . Part or all of the broadcasting audio transmission program may be incorporated in the OS.

Broadcast audio transmitting apparatus 100 may include a plurality of processors in place of processor 910 . These multiple processors share the execution of the broadcast audio transmission program. Each processor, like processor 910, is a device that executes a broadcast audio transmission program.

Data, information, signal values and variable values that are used, processed or output by the broadcast sound transmission program are stored in memory 921, auxiliary storage device 922, or registers or cache memory within processor 910. FIG.

Data receiving unit 110, data registration unit 120, voice data generation unit 130, voice text creation unit 140, and voice transmission unit 150 are represented by “circuit,” “process,” “procedure,” and “processing.” ”, or may be read as “circuitry”. The broadcast audio transmission program causes the computer to execute data reception processing, data registration processing, audio data generation processing, audio text creation processing, and audio transmission processing. "Processes" of data reception processing, data registration processing, voice data generation processing, voice text creation processing, and voice transmission processing are defined as "program", "program product", and "computer-readable storage medium storing the program". , or "a computer-readable recording medium on which a program is recorded". The broadcast audio transmission method is a method performed by the broadcast audio transmission device 100 executing the broadcast audio transmission program.
The broadcast audio transmission program may be stored in a computer-readable recording medium and provided. Also, the broadcast audio transmission program may be provided as a program product.

FIG. 13 is a diagram showing a configuration example of the definition file 70 according to this embodiment.
As shown in FIG. 13, the definition file 70 includes a speech text template 70a, a weather conversion table 70b, a precipitation probability conversion table (for W1 conversion) 70c, and a precipitation probability conversion table (for W2 conversion) 70d. As will be described later, the voice sentence template 70a is referred to when the voice data generator 130 generates the voice data 63. FIG. Further, the speech sentence template 70a, the weather conversion table 70b, the precipitation probability conversion table (for W1 conversion) 70c, and the precipitation probability conversion table (for W2 conversion) 70d are created by the speech sentence creation unit 140 from the speech data 63 for speech. It is referred to when generating sentences 65 . FIG. 13 illustrates three conversion tables, a weather conversion table 70b, a precipitation probability conversion table (for W1 conversion) 70c, and a precipitation probability conversion table (for W2 conversion) 70d. An arbitrary number of conversion tables are set in the definition file 70 by association with the variables (defined as W1, W2, . . . ) in the speech sentence template 70a.

***Description of operation***
Next, the operation of the broadcasting audio transmitting apparatus 100 according to this embodiment will be described. The operating procedure of the broadcast audio transmission device 100 corresponds to the broadcast audio transmission method. Also, the program that realizes the operation of the broadcast audio transmission device 100 corresponds to the broadcast audio transmission program.

FIG. 2 is a flow chart showing an operation example of the broadcast audio transmitting apparatus 100 according to this embodiment.
In the present embodiment, broadcast sound transmitting apparatus 100 transmits weather comment sound 68 to be broadcast about the weather in a specific broadcast area.

<Data reception processing>
In step S101, the data receiving unit 110 receives raw data of the weather data 61 from a weather company or the like. Specifically, the data receiving unit 110 receives XML-format weather data 61 from a weather company or the like. XML is an abbreviation for Extensible Markup Language.
Note that the weather data 61 is an example of broadcast data that serves as source data for broadcast comments broadcast in a specific broadcast area.

FIG. 3 is a diagram showing a configuration example of weather data 61 according to this embodiment.
The weather data 61 is transmitted from a weather company or the like as data for each prefecture. Since the weather data 61 is transmitted as data for each prefecture, the data receiving unit 110 can recognize and receive the weather data 61 including the specific broadcast area where the weather comment is broadcast.

The weather data 61 is transmitted from a weather company or the like for each data type. The data type represents the type of weather data 61 . Types of the weather data 61 include, for example, prefectural forecasts and AMeDAS information.

<Data registration process>
In step S102, the data registration unit 120 extracts weather data in area information included in a specific broadcast area from the weather data 61, and registers it in the weather database 62 for each data type.
Specifically, the data registration unit 120 extracts area information from the weather data 61 based on the tags of the weather data 61 . Area information is an area name representing an area or a direction (including direction). The area information also includes area names with different intonations for each broadcasting area. A specific example of the area name will be described later.

In the example of FIG. 3, the area information is the information within the tag <Area>, which is "Southern" with the code "420010". In the following, area information may be simply referred to as area.
The data registration unit 120 also determines the data type of the weather data 61 from the tag information. In the example of FIG. 3, the information in the tag <Title> is "prefectural weather forecast", so the data type is determined as "prefectural forecast". The correspondence between the information in the tag <Title> and the data type can be arbitrarily set.
The data registration unit 120 extracts the weather data in the area information from the weather data 61 and registers it in the weather database 62 together with the data type.

<Audio data generation processing>
In step S103, the audio data generation unit 130 generates the audio data 63 representing the audio configuration of the weather comment using the weather data in the area information included in the specific broadcast area. The audio data generation unit 130 acquires the data type included in the weather data of a specific broadcast area, and generates audio data 63 representing the configuration of audio according to the data type. The audio data generation unit 130 generates the audio data 63 by referring to the audio text template 70a.
In this embodiment, it is assumed that the audio data 63 includes, as area information, an area name indicating an area or a direction (orientation) and having a different intonation for each broadcasting area. Specifically, in the present embodiment, the audio data 63 includes a code that indicates a region or direction (orientation) and specifies a region name that has different intonations for each broadcasting region.

FIG. 4 is a diagram showing a configuration example of audio data 63 according to the present embodiment.
FIG. 4 shows voice data 63 with a data type of "prefectural forecast" and voice data 63 with a data type of "AMeDAS information".
A specific description will be given using the weather data 61 shown in FIG. 3, the voice text template 70a shown in FIG. 13, and the voice data 63 of the data type "prefectural forecast" shown in FIG.

The voice data 63 of the data type "prefectural forecast" shown in FIG. 4 represents the configuration of the voice of the weather comment when the "prefectural forecast" is broadcast. [Sound_FIX] is a tag indicating that the audio data 63 is fixed, and [Sound01] is the right part of "Comment=" registered in the [Sound01] tag of the audio document template 70a. It is a tag that indicates that it is included as a part. The sentence on the right side of "Comment=" is "today's weather in the prefecture" as shown in FIG. The audio data generation unit 130 operates to input [Sound_FIX] and [Sound01] in a standard manner.
[Sound02] is a tag indicating the weather forecast, and [Sound03] is a tag indicating the probability of rain. For example, when it is preset that <WeatherCodePart> of the weather data 61 corresponds to [Sound02] and refID="1" corresponds to "Southern (code is 420010)", the audio data generation unit 130 , [Sound02], the character string "=:201::" following "Nanbu (code is 420010)" is registered.
If it is set in advance that <Probability of Precipitation Part> of the weather data 61 corresponds to [Sound03] and refID="1" corresponds to "Southern (code is 420010)", the audio data generation unit 130 Register the character string “=::10:30” following “Nanbu (code is 420010)” in [Sound03].
Although FIG. 3 illustrates a part of the weather data 61 and does not show all the original data for generating the voice data 63, the voice data generator 130 operates in this way to generate the weather data. 61 to generate audio data 63 .

"Nanbu" is assumed to be a region name 201 that represents a region, direction, or direction and has a different intonation for each broadcasting region.
For example, in the weather comment for "prefecture forecast", "in the southern part of Nagasaki Prefecture" means the area south of Nagasaki Prefecture. "Nanbu" in the weather comment of "prefectural forecast" has a code of 420010.
On the other hand, suppose that the proper name Nanbu exists in Yamanashi Prefecture, and that the intonation is different from Nanbu in standard Japanese. At this time, in the meteorological comment of "AMEDAS information", "in the southern part (town) of Yamanashi Prefecture" means a specific "southern part (town)". "Nanbu" in the meteorological comment of "AMeDAS Information" has a code of 49316.
For example, if ``Nanbu'' in ``In the southern part of Nagasaki prefecture'' is broadcast with an intonation peculiar to Yamanashi prefecture, viewers living in Nagasaki will feel uncomfortable and the broadcast will be difficult to listen to.

The area name 201, which indicates an area, a direction, or a direction and has a different intonation for each broadcast area, includes names such as south, central, north, upper, lower, upper, and lower, as well as names such as west, north-south, and east-west. Names representing directions are also included. In addition, the area names 201 that represent an area, a direction, or a direction and have different intonations for each broadcast area include place names such as Fukuoka, Fujimi, Hiroshima, Gojo, and Oji (Oji), which are numerous throughout the country. In the following description, directions also include azimuths.

FIG. 5 is a flow chart showing an operation example following FIG. 2 in the operation example of the broadcasting audio transmitting apparatus 100 according to the present embodiment.

<Speech text generation processing>
In step S104, the voice sentence creating unit 140 prepares the voice sentence template 70a, the weather conversion table 70b, the precipitation probability conversion table (for W1 conversion), and converts the tags and character strings included in the voice data 63 into sentences. ) 70c and a precipitation probability conversion table (for W2 conversion) 70d. The voice sentence creation unit 140 refers to the voice sentence template 70a and sequentially converts the definition information of the voice data 63 into sentences. First, [Sound01] is converted to "Today's weather in the prefecture" by referring to the voice text template 70a.
Next, [Sound02] is converted. At this time, using the name conversion table 64, the voice text creation unit 140 converts the area name 201 included in the voice data 63 into the post-conversion name 202. FIG. Then, the voice text creation unit 140 creates voice text 65 that is a candidate for the weather comment including the post-conversion name 202 . At this time, the voice text creating unit 140 generates the voice text 65 using the name conversion table 64 corresponding to the data type.

FIG. 6 is a diagram showing a configuration example of the name conversion table 64 according to this embodiment.
The name conversion table 64 includes a code specifying an area name 201 that expresses an area or direction and has a different intonation for each broadcasting area, and a converted name 202 obtained by adding additional data 301 representing an area or direction to the area name 201. is a table for associating .
The name conversion table 64 is stored for each data type representing the type of weather data.

In the name conversion table 64, a data type 641, a code 642 indicating an area, and post-conversion name text data 643 are set.
A data type indicating the type of weather data is set in the data type 641 . Data types include, for example, prefectural forecasts and AMeDAS information. As in the example of FIG. 6, the name conversion table 64 has data type 641 items, and the setting items of the name conversion table may be divided for each data type. Alternatively, name conversion tables that are physically separated for each data type may be used. In that case, the data type 641 item may not be included.
A code indicating an area corresponding to the data type 641 is set in the code 642 . In FIG. 6, the area name 201 is written in parentheses after the code, such as "420010 (southern)". However, this is described to make it easier to understand the correspondence between the data type and the post-conversion name, and is not actually set.

A combination of the data type 641 and the code 642 , for example, when the data type 641 is prefectural forecast and the code 642 is 420010, the text data of the converted name 202 is set in the converted name text data 643 . In the example of FIG. 6, "Southern <prefecture>" is set as the post-conversion name 202 for "Southern", which is the area name 201 of the prefectural forecast. Further, for example, when the data type 641 is AMeDAS information and the code 642 is 49316, "Nanbu <Yamanashi>" is set as the post-conversion name 202 for the area name 201 "Nanbu".
"<Prefecture>" in "Southern <Yamanashi>" and "<Yamanashi>" in "Southern <Yamanashi>" are additional data 301 representing areas or directions.

Then, the character string "=:201::" refers to the weather conversion table 70b and becomes "It will be cloudy and sometimes sunny." will be cloudy with occasional sunshine".
[Sound03] is then converted. The odds are 10% by noon and 30% by 6pm." At this time, referring to the precipitation probability conversion table (for W1 conversion) 70c, since W1 is 10, "10% until noon" is specified, and referring to the precipitation probability conversion table (for W2 conversion) 70d, Since W2 is 30, "30% until 6:00 pm" is specified.

FIG. 7 is a diagram showing an example of the speech text 65 according to this embodiment.
The upper and lower parts of the speech sentences 65 in FIG. 7 are examples of the speech sentences 65 before adjustment of the length of the reproduction time in the upper row, and examples of the sentences 65 for speech after the length of the reproduction time is adjusted in the lower row. represents The adjustment of the length of the reproduction time of the voice text 65 will be described later.

For example, using the name conversion table 64 of the data type "prefectural forecast" shown in FIG. The sentence 65 for speech in the upper row is created.
In the speech text 65 shown in the upper part of FIG. 7, the region name 201 "Nanbu" included in the speech data 63 is converted to the post-conversion name 202 "Nanbu <prefecture>". Also, the information in parentheses "<>" is determined in advance as information that is not to be spoken.

In step S105, the voice sentence creation unit 140 determines whether or not the playback time of the created voice sentence 65 is within a prescribed length.
Specifically, the speech text creation unit 140 totals the playback time of each audio file of all phrases used in the speech text 65, and determines whether the total playback time is within a prescribed length. By doing so, it is determined whether or not the reproduction time of the text for speech 65 is within a prescribed length.
Here, a phrase indicates a unit of an audio file. Therefore, clauses also include words.
If the reproduction time of the voice text 65 is not within the prescribed length, the process proceeds to step S106.
If the reproduction time of the voice text 65 is within the specified length, the process proceeds to step S107.

If the reproduction time of the voice sentence 65 is not within the specified length, the voice sentence creation unit 140 adjusts the voice sentence 65 according to a predetermined rule in step S106.
The example of FIG. 7 shows an example in which the text for speech 65 in the upper row is adjusted to the text for speech 65 in the lower row. In the audio sentence 65 in the upper row, "the probability of precipitation is 10% until noon and 30% until 6:00 PM" is changed to "the probability of precipitation is 10% until noon" in the audio sentence 65 in the lower row. ” to shorten the playback time of the speech text 65 .
The predetermined rule is, for example, "delete from the latest forecast information" (W2 part in the example of FIG. 7). The process of S106 is repeated.

In step S107, the voice text creating unit 140 outputs the voice text 65 whose reproduction time is within the prescribed length.

<Audio transmission processing>
When the speech sentence 65 is completed, the speech transmission unit 150 uses the speech conversion table 66 to reproduce the clauses included in the speech sentence 65 to send out the weather comment speech 68 .
Specifically, it is as follows.

First, in step S 108 , the voice transmission unit 150 uses the voice conversion table 66 to determine the order of the voice files 67 according to the order of the clauses included in the text for voice 65 .

FIG. 8 is a diagram showing a configuration example of the voice conversion table 66 according to this embodiment.
FIG. 9 is a diagram showing a configuration example of the audio file 67 according to this embodiment.
The speech conversion table 66 associates clauses used for weather comments with the speech of the clauses. Specifically, the speech conversion table 66 associates text data of phrases used for weather comments with speech file identification information for identifying speech files storing speeches of the phrases.

Phrase text data 661 and speech file identification information 662 of the speech file storing the speech of the phrase set in the phrase text data 661 are set in the speech conversion table 66 .
The example of the 1st to 3rd lines of the phrase text data 661 corresponds to "%Pwa" of the voice sentence template 70a [Sound02] tag shown in FIG. "%P" corresponds to area information and is followed by a particle "wa", so in the example, "Northern wa", "Southern <prefecture>wa", and "Southern <Yamanashi>wa". A voice file 67 is constructed by specifying the tag of the voice text template 70a, with arbitrary particles added after the area information.
As shown in FIG. 9, each audio file 67 is configured to be searchable by audio file identification information 662 .

In the speech conversion table 66 , phrases used for weather comments are set as phrase text data 661 .
In the case of the regional name 201 in which the phrase has different intonations depending on the broadcasting region, the post-conversion name 202 is set in the phrase text data 661 . Therefore, as shown in FIG. 8, in the phrase text data 661, "Nanbu <prefecture>" and "Nanbu <Yamanashi>" are set as post-conversion names 202 corresponding to the area name 201 "Nanbu".
Each post-conversion name 202 is associated with a voice file in which intonation voice corresponding to the additional data is stored.

In this way, in the speech conversion table 66, phrases are associated with speech files in which the speech of the phrases is stored. associated with the audio file.
For example, as the voice of the post-conversion name 202, voice obtained from a local announcer is stored in advance to store voice of appropriate intonation.

In step S109, the voice transmission unit 150 transmits the weather comment voice 68 by reproducing the voice files 67 in the determined order.

FIG. 10 is a diagram showing an example of the order of the audio files 67 determined by the audio transmission unit 150 according to this embodiment.
As shown in FIG. 10, by reproducing the audio files 67 in the determined order of the audio files 67, the weather comment audio 68 is transmitted.

***Other Configurations***
<Modification 1>
In the present embodiment, the broadcast sound transmitting device 100 that transmits the sound of the broadcast comment (weather comment) broadcast about the weather in a specific broadcast area has been described. However, the broadcast audio transmitting device can also be applied when transmitting broadcast comments that broadcast information other than weather.

<Modification 2>
In the present embodiment, it has been described that the broadcast audio transmitting apparatus 100 is a computer installed in a broadcasting station. More specifically, the broadcasting audio transmitting device 100 may be composed of a receiving terminal 10 and a transmitting terminal 20 .

FIG. 11 is a diagram showing a functional configuration example of the broadcasting audio transmitting apparatus 100 according to the modification of the present embodiment.
As shown in FIG. 11, the functions of the broadcasting audio transmitting apparatus 100 may be distributed between the receiving terminal 10 and the transmitting terminal 20. FIG.
In the receiving terminal 10, the weather data 61 is obtained from the weather company, and the audio data generating section 130 generates the audio data 63 by the audio data generating process described above.
The audio data 63 is transferred from the receiving terminal 10 to the transmitting terminal 20 .
In the transmitting terminal 20, using the voice data 63 and the name conversion table 64 transferred from the receiving terminal 10, the voice text creating unit 140 creates the voice text 65 by the voice text creating process described above. Subsequent processing is also the same as the processing described above.

<Modification 3>
In this embodiment, the functions of the data receiving section 110, the data registering section 120, the voice data generating section 130, the voice text creating section 140, and the voice transmitting section 150 are implemented by software. As a modified example, the functions of the data receiving section 110, the data registering section 120, the voice data generating section 130, the voice sentence creating section 140, and the voice transmitting section 150 may be realized by hardware.
Specifically, the broadcast audio transmitting apparatus 100 includes an electronic circuit 909 instead of the processor 910 .

FIG. 12 is a diagram showing a configuration example of a broadcasting audio transmission device 100 according to a modification of the present embodiment.
The electronic circuit 909 is a dedicated electronic circuit that implements the functions of the data receiving section 110 , the data registering section 120 , the voice data generating section 130 , the voice sentence creating section 140 and the voice transmitting section 150 . Electronic circuit 909 is specifically a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a logic IC, GA, ASIC, or FPGA. GA is an abbreviation for Gate Array. ASIC is an abbreviation for Application Specific Integrated Circuit. FPGA is an abbreviation for Field-Programmable Gate Array.

The functions of the data receiving section 110, the data registering section 120, the voice data generating section 130, the voice sentence creating section 140, and the voice transmitting section 150 may be realized by one electronic circuit, or may be realized by a plurality of electronic circuits. It may be implemented in a distributed manner.

As another modification, part of the functions of the data receiving section 110, the data registering section 120, the voice data generating section 130, the voice sentence creating section 140, and the voice transmitting section 150 are realized by electronic circuits, and the remaining functions are realized. may be implemented in software. Also, part or all of the functions of the data receiving section 110, the data registering section 120, the voice data generating section 130, the voice sentence creating section 140, and the voice transmitting section 150 may be realized by firmware.

Each of the processor and electronic circuitry is also called processing circuitry. In other words, the functions of the data receiving section 110, the data registering section 120, the voice data generating section 130, the voice sentence creating section 140, and the voice transmitting section 150 are realized by the processing circuitry.

***Description of the effects of the present embodiment***
As described above, in the broadcasting audio transmission apparatus according to the present embodiment, for example, when the weather program broadcasting system audio transmission is performed, the weather comment is created from the weather data, and the weather comment is converted into an audio file. , even for words with the same pronunciation, it is possible to select a voice file with intonation according to the region. Therefore, it is possible to prevent intonation errors in words with the same reading.
In the case of broadcasting, it is necessary to keep the reproduction time of the weather comment voice 68 within a specified length due to restrictions on broadcasting time and the like. When determining the reproduction time of the weather comment voice 68 in step S105, since the reproduction time is calculated using the intonation voice file corresponding to the additional data, there may be a difference between the judgment result and the actual reproduction time. It can be said that the accuracy of the judgment result is high.
Therefore, according to the broadcast sound transmitting apparatus according to the present embodiment, in transmitting the voice of the weather comment, the voice of the weather comment can be automatically converted into an appropriate intonation according to the region where the broadcast is being made, thereby preventing the listener from feeling uncomfortable. It is possible to provide an easy-to-hear voice with a low volume.

In the above-described Embodiment 1, each part of the broadcasting audio transmission device has been described as an independent functional block. However, the configuration of the broadcasting audio transmission device may not be the configuration of the above-described embodiment. The functional blocks of the broadcasting audio transmitting apparatus may have any configuration as long as the functions described in the above embodiments can be realized. Also, the broadcasting audio transmitting device may be a system composed of a plurality of devices instead of a single device.
Moreover, it is also possible to combine a plurality of portions of the first embodiment. Alternatively, one portion of this embodiment may be implemented. In addition, this embodiment may be implemented as a whole or partially in any combination.
That is, in Embodiment 1, it is possible to freely combine each embodiment, modify any component of each embodiment, or omit any component from each embodiment.

The above-described embodiments are essentially preferable examples, and are not intended to limit the scope of the present disclosure, the scope of application of the present disclosure, and the range of applications of the present disclosure. Various modifications can be made to the above-described embodiments as required. For example, procedures described using flow diagrams or sequence diagrams may be modified as appropriate.

10 receiving terminal 20 transmitting terminal 61 weather data 62 weather database 63 voice data 64 name conversion table 65 voice text 66 voice conversion table 67 voice file 68 weather comment voice 70 definition file , 70a Sentence template for voice, 70b Weather conversion table, 70c Precipitation probability conversion table (for W1 conversion), 70d Precipitation probability conversion table (for W2 conversion), 100 Broadcast sound transmitting device, 110 Data receiving unit, 120 Data registering unit , 130 voice data generation unit 140 voice text creation unit 150 voice transmission unit 160 storage unit 201 region name 202 converted name 301 additional data 641 data type 642 code 643 converted name text data , 661 phrase text data, 662 audio file identification information, 909 electronic circuit, 910 processor, 921 memory, 922 auxiliary storage device, 930 input interface, 940 output interface, 950 communication device.

Claims (7)

In a broadcast audio transmission device that transmits broadcast comment audio broadcast in a specific broadcast area,
a name conversion table in which a code specifying an area name representing an area or direction and having a different intonation for each broadcasting area is associated with a converted name obtained by adding additional data representing the area or direction to the area name; a voice conversion table in which phrases used in the broadcast comment are associated with voices of the phrases, and voices of intonation corresponding to the additional data are associated with the converted names that are the phrases; a storage unit that stores
audio data for generating audio data representing an audio configuration of the broadcast comment and including a code specifying the area name, using broadcast data in area information included in the specific broadcast area; a data generator;
Using the name conversion table, the region name corresponding to the code included in the audio data is converted into the post-conversion name, and an audio text, which is a candidate for the broadcast comment including the post-conversion name, is created. a voice sentence creation unit for
A broadcasting sound transmitting device, comprising: a sound transmitting unit for transmitting the sound of the broadcasting comment by reproducing the phrase included in the sound sentence using the sound conversion table. The storage unit
storing the name conversion table for each data type representing the type of the broadcast data;
The audio data generation unit is
Acquiring the data type included in the broadcast data of the specific broadcasting area, generating the audio data representing the configuration of the audio according to the data type,
The voice text creation unit is
2. The broadcasting audio transmitting apparatus according to claim 1, wherein said audio text is generated using said name conversion table corresponding to said data type. The voice conversion table is
The phrase is associated with a voice file storing voice of the phrase, and the converted name, which is the phrase, is associated with a voice file storing voice of intonation corresponding to the additional data. and
The audio transmission unit is
Using the voice conversion table, the order of the voice files is determined according to the order of the phrases included in the voice text, and the voice of the broadcast comment is transmitted by reproducing the voice files in the determined order. 3. The broadcasting audio transmission device according to claim 1 or 2. The voice text creation unit is
It is determined whether or not the reproduction time of the speech text is within a prescribed length, and if not within the prescribed length, the speech text is adjusted according to a predetermined rule. 4. The broadcast audio transmission device according to any one of 3. The broadcasting audio transmission device includes:
5. The broadcasting sound transmitting apparatus according to claim 1, wherein the broadcasting comment is a weather comment sound used for broadcasting the weather in the specific broadcasting area. In a broadcast audio transmission method used in a broadcast audio transmission device for transmitting broadcast comment audio broadcast in a specific broadcast area,
A name conversion in which a computer associates a code specifying an area name representing an area or direction and having a different intonation for each broadcasting area with a post-conversion name obtained by adding additional data representing the area or direction to the area name. A table, phrases used in the broadcast comment, and voices of the phrases are associated with each other, and voices of intonation corresponding to the additional data are associated with the converted names, which are the phrases. memorize a conversion table and
A computer uses broadcast data in area information included in the specific broadcast area to generate audio data representing an audio configuration of the broadcast comment and including a code specifying the area name. death,
The computer converts the region name corresponding to the code included in the audio data into the converted name using the name conversion table, and converts the area name into the post-conversion name to be a candidate for the broadcast comment containing the post-conversion name. create sentences,
A broadcast audio transmission method, wherein a computer reproduces phrases included in the audio text using the audio conversion table, thereby transmitting the audio of the broadcast comment. In a broadcast audio transmission program used in a broadcast audio transmission device that transmits broadcast comment audio broadcast in a specific broadcast area,
The broadcasting audio transmission device includes:
a name conversion table in which a code specifying an area name representing an area or direction and having a different intonation for each broadcasting area is associated with a converted name obtained by adding additional data representing the area or direction to the area name; a voice conversion table in which phrases used in the broadcast comment are associated with voices of the phrases, and voices of intonation corresponding to the additional data are associated with the converted names that are the phrases; and a storage unit that stores
audio data for generating audio data representing an audio configuration of the broadcast comment and including a code specifying the area name, using broadcast data in area information included in the specific broadcast area; a data generation process;
Using the name conversion table, the region name corresponding to the code included in the audio data is converted into the post-conversion name, and an audio text, which is a candidate for the broadcast comment including the post-conversion name, is created. voice sentence creation processing to
A broadcasting sound transmission program for causing a computer to execute a sound transmission process of transmitting the sound of the broadcasting comment by reproducing the clauses included in the sound sentence using the sound conversion table.

Images