WO2024142184A1 - Sound generation program - Google Patents

Abstract

A sound generation program according to the present invention causes a computer connectable to at least one notification device to execute: a step of acquiring text data and first information relating to at least one first sound; a step of acquiring sound data based on the text data; and a step of combining first sound data relating to the first sound with the start and/or end of the sound data to generate synthesized sound data.

Description

Speech Generation Program

The present invention relates to a voice generation program, a voice generation method, a voice generation device, and an alarm device.

　In the past, there have been proposals for alarm devices that notify the user of abnormalities by voice when they occur in production machinery or other equipment (for example, see Patent Document 1). Such alarm devices are configured to read voice data that has been preregistered in ROM in response to an input signal to a control circuit, and output this from a speaker.

Japanese Utility Model Application Publication No. 7-25493

However, the problem with the notification device in Patent Document 1 is that the voice data is registered in advance and the user cannot change the voice data. Therefore, there is a demand for a device that can generate various notification sounds in response to user needs.

The present invention has been made to solve the above problems, and aims to provide a voice generation program, a voice generation method, a voice generation device, and a notification device that can generate various notification sounds.

The first voice generation program of the present invention causes a computer connectable to at least one alarm device to execute the steps of acquiring text data and first information relating to at least one first sound, acquiring voice data based on the text data, and combining first sound data relating to the first sound with at least one of the front and rear ends of the voice data to generate synthetic voice data.

The second voice generation program of the present invention causes a computer connectable to at least one notification device to execute the steps of acquiring text data, acquiring voice data based on the text data, acquiring first sound data to be combined with the voice data, and combining the first sound data with at least one of the front and rear parts of the voice data to generate synthetic voice data.

The above voice generation program can further execute a step of playing a synthetic voice based on the synthetic voice data on the notification device.

The above voice generation program can further execute a step of acquiring second information about a second sound, and a step of playing the second sound on the notification device before or after the synthetic voice in a specified order.

The above voice generation program can be configured to play either the second sound or the synthetic voice after the other has finished playing.

The above voice generation program can be configured so that, if playback of either the second sound or the synthetic voice becomes possible while the other is being played, playback of the one sound is interrupted and the other sound is played.

In the above voice generation program, the first information can be information that specifies one of a plurality of the first sound data stored in advance.

The voice generation method according to the present invention is a voice generation method for at least one alarm device, and includes the steps of acquiring text data and first information relating to at least one first sound, acquiring voice data based on the text data, and combining first sound data relating to the first sound with at least one of the front and rear of the voice data to generate synthetic voice data.

The voice generating device according to the present invention is a voice generating device that can be connected to at least one alarm device, and includes a first acquisition unit that acquires text data and first information related to at least one first sound, a voice data acquisition unit that acquires voice data based on the text data, and a synthesis unit that combines first sound data related to the first sound with at least one of the front and rear ends of the voice data to generate synthetic voice data.

The above voice generating device may further include a playback command unit that causes the alarm device to play back a synthetic voice based on the synthetic voice data.

The notification device according to the present invention includes the above-mentioned voice generating device and at least one of the notification devices.

According to the present invention, various alarm sounds can be generated.

1 is an example of a system configuration including an alarm device according to an embodiment of the present invention. FIG. FIG. FIG. 2 is a block diagram showing a hardware configuration of the notification device. FIG. 2 is a block diagram showing the software configuration of the notification device. FIG. 11 is a diagram showing synthetic voice data. 10 is a timing chart showing a reproduction process of synthetic voice data. 10 is a timing chart showing a reproduction process of synthetic voice data and second sound data. 13 is another example of a timing chart showing the reproduction process of the synthetic voice data and the second sound data.

Below, an embodiment of a voice generating device according to the present invention will be described with reference to the drawings. In this embodiment, an alarm device incorporating a voice generating device will be described as one embodiment. Figure 1 shows an example of the configuration of a system including an alarm device, which includes at least one alarm device 1 and equipment 3 connected to the alarm device 1, and various sounds are output in response to voice control signals transmitted from the equipment 3. A well-known TTS (Text-to-Speech) service 4 is connected to the alarm device 1 via a network 7. Each component will be described in detail below.

<1. Hardware configuration of the alarm device>

2 is a front view of the alarm device, FIG. 3 is a rear view of the alarm device, and FIG. 4 is a block diagram showing the hardware configuration of the alarm device. As shown in FIGS. 1 and 2, the alarm device 1 has a base 101 and a body 102 provided on the top of the base 101. The body 102 is provided with an LED unit (alarm device) 103 extending from the base 101. A speaker (alarm device) 105 and various operation buttons 106 are provided on the outer surface of the base 101. As shown in FIG. 4, the base 101 contains a control unit 11, a memory unit 12, a communication interface 13, and an external interface 14. In FIG. 4, the communication interface 13 is referred to as the "communication I/F" and the external interface 14 is referred to as the "external I/F".

The base 101 is formed in a rectangular shape when viewed from above, and functions as a housing that houses the control unit 11, etc. The LED unit 103 is formed in a cylindrical shape, and three light-emitting units are provided on the upper part, that is, first, second, and third light-emitting units 103a to 103c lined up from top to bottom. Each of the light-emitting units 103a to 103c is formed in a cylindrical shape, and has an LED built in to emit red, yellow, and green light, respectively. These light-emitting units 103a to 103c emit light according to the state of the equipment 3 described above.

As shown in FIG. 1, the above-mentioned speaker 105 is provided at the bottom of the front surface of the base 101, and as described below, sound indicating the state of the equipment 3 is output from this speaker 105. Although not shown in the figure, the base 101 is also provided with a volume switch for adjusting the volume of the sound. In addition, various operation buttons 106 are provided above the speaker 105 on the front surface of the base 101.

As shown in FIG. 3, the back surface of the base 101 is provided with connectors for the communication interface 13 and external interface 14 described above.

As shown in FIG. 4, the control unit 11 includes a CPU, RAM, ROM, etc., and is configured to execute various information processing based on programs and data. The storage unit 12 is configured, for example, with an auxiliary storage device such as an HDD or SSD, and stores a voice generation program 121 for generating voice, registered first sound data 122, text data 123 transmitted from the equipment 3, registered second sound data 124, and various data 125 for driving the alarm device 1. The voice generation program 121 is a program for generating synthetic voice data (described later) based on a voice control signal transmitted from the equipment 3, and reproducing this as synthetic voice. The generated synthetic voice data may be stored in the storage unit 12. The first sound data 122 and the second sound data 124 are data in formats such as mp3, raw, wav, etc., and are data for reproducing the first sound and the second sound, respectively. These sounds are various sounds such as notification sounds and voices. As described below, the first sound data is dedicated data for combining with synthetic voice data, and the second sound data is used for purposes other than synthesis. In other words, the second sound data is data for playing the second sound alone. The second sound is also a general term for sounds other than the first sound, and generally is a sound that differs depending on the event that occurs (for example, the occurrence of an abnormality), but it can also be composed of all the same sound.

The speaker 105 is composed of a known speaker, and outputs sound by playing back the synthetic voice data and the second sound data 124.

The communication interface 13 is, for example, a wired LAN (Local Area Network) module, a wireless LAN module, etc., and is an interface for performing wired or wireless communication. In other words, the communication interface 13 transmits and receives various data to and from the notification device 1 via a wired or wireless network in accordance with a predetermined communication protocol. An external TTS service 4 is connected to this communication interface 13 via a network such as the Internet.

The external interface 14 is an interface for connecting to an external device, and is configured appropriately according to the external device to be connected. In this embodiment, the equipment 3 is connected to this external interface 14. The equipment 3 may be, for example, a production facility, a printer, a server, a network camera, a disaster prevention system, a security system, an entrance/exit system, an environmental monitoring system, an order receiving system, etc., and may be any type of device that uses audio to notify of a change in status or the occurrence of some event (for example, a fault or abnormality). When an audio control signal is input from the equipment 3 to the alarm device 1 via the external interface 14, audio is output from the speaker 105 by the audio generation program 121 executed by the control unit 11.

The voice control signal transmitted from each facility 3 can be transmitted in various ways. For example, the voice control signal can be transmitted using HTTPS/HTTP communication commands, cloud communication, SSH/RSH commands, SOCKET communication commands, etc. This voice control signal includes the first information, second information, and text data described below.

2. Software configuration of the notification device
Next, a software configuration of the notification device 1 will be described. Fig. 5 is a block diagram showing the software configuration of the notification device 1. As shown in Fig. 5, when the control unit 21 of the voice registration device 2 expands the voice generation program 121 stored in the storage unit 22 into the RAM, the control unit 21 interprets and executes the voice generation program 121 by the CPU, and functions as a computer including a first acquisition unit 111, a second acquisition unit 112, a voice data acquisition unit 113, a synthesis unit 114, and a playback command unit 115.

The first acquisition unit 111 acquires the first information and text data transmitted from the equipment 3. The first information is information that specifies the above-mentioned first sound data 122. In other words, it is information that specifies one of the multiple first sound data 122 stored in the storage unit 12. In this embodiment, the first information specifies two first sound data 122 that are to be combined before and after the voice data described below. In this case, the two first sound data 122 may be the same or different. The specified first sound data is transmitted to the synthesis unit 114.

The first acquisition unit 111 also acquires text data from the equipment 3. The first information and the text data are transmitted to the first acquisition unit 111 as one data set.

The second acquisition unit 112 acquires the second information transmitted from the equipment 3. The second information is information that specifies the second sound data 124 described above. In other words, it is information that specifies one of the multiple pieces of second sound data 124 stored in the storage unit 12. The specified second sound data is transmitted to the playback command unit 115.

The voice data acquisition unit 113 transmits the acquired text data to the TTS service 4 and acquires the generated voice data.

As shown in FIG. 6, the synthesis unit 114 combines the first sound data specified by the first acquisition unit 111 before and after the voice data to generate synthetic voice data. For example, if the text data is "An abnormality has occurred," synthetic voice data is generated in which first sound data related to a notification sound such as "ping pong pan pong" is added before and after the corresponding voice data. This generates data for playing a continuous sound such as "ping pong pan pong An abnormality has occurred ping pong pan pong." Note that the first acquisition unit 111, the voice data acquisition unit 113, and the synthesis unit 114 perform processing in the order in which the data is acquired.

The playback command unit 115 has the function of playing back the generated synthetic voice data and second sound data. That is, the playback command unit 115 issues a playback command to the speaker 105 to play back the synthetic voice data and second sound data, and based on this, the speaker 105 plays back these data and outputs sound, etc. from the speaker 105. The playback command unit 115 also has a playback queue, and issues playback commands according to this playback queue. That is, the playback command unit 115 waits until playback of the previously transmitted synthetic voice data or second sound data by the speaker 105 is completed, and then transmits a playback command to the speaker 105 for the next data.

<3. Sound playback processing>
Next, the sound reproduction process in the alarm device 1 configured as described above will be described with reference to the timing charts in Fig. 7 and Fig. 8. The horizontal direction (from left to right) in Fig. 7 and Fig. 8 indicates the flow of the process, and the vertical direction (from top to bottom) indicates time. In other words, the vertical direction indicates the time of the process, and the longer the vertical direction of each process (each block), the longer the process time.

First, the playback of synthetic voice data will be described with reference to FIG. 7. When the voice data acquisition unit 113 receives text data, the voice data acquisition unit 113 transmits the received text data to the TTS service 4 and requests the generation of voice data. In response, the TTS service 4 generates voice data corresponding to the transmitted text data and transmits this to the voice data acquisition unit 113.

The generated voice data is sent to the synthesis unit 114, where it is synthesized with the first sound data. After the synthetic voice data is generated in this manner, it is sent to the playback command unit 115. The playback command unit 115 waits for playback according to the playback queue, but if there is no data to be played first, a playback command is sent to the speaker 105 without waiting for playback. The synthetic voice data is then played back by the speaker 105.

Next, the playback of the synthetic voice data and the second sound data will be described. As an example, as shown in FIG. 8, a case will be described in which the second acquisition unit 112 receives the second sound information after the text data is transmitted to the voice data acquisition unit 113. As described above, when the second acquisition unit 112 acquires the second sound information, it designates the corresponding second sound data and transmits it to the playback command unit 115. Since it does not take time to designate the second sound data but it takes time to generate the voice data, in this example, even if the second sound data is designated after the text data is transmitted to the voice data acquisition unit 113, the second sound data is transmitted to the playback command unit 115 before the synthetic voice data. In this example, since there is no data to be played before the second sound data transmitted to the playback command unit 115, the playback command for the second sound data is immediately executed.

When the second sound data is being played back, even if synthetic voice data is generated and a playback command can be executed, playback of the synthetic voice data is put on hold until playback of the second sound data is complete. Then, when playback of the second sound data is complete, the playback command unit 115 issues a command to play the synthetic voice data.

After that, when other second sound data is sent to the playback command unit 115, if playback of the synthetic voice data has been completed, the playback command for that second sound data is immediately executed. Note that in this example, an example of playing one synthetic voice and two second sounds has been described, but as described above, the second sound is a general term for notification sounds other than the first sound, so the two second sounds may be the same or different.

<4. Features>
As described above, according to this embodiment, the following effects can be obtained.
(1) The notification data can be freely generated by combining the first sound data and the voice data generated from a desired text, instead of the pre-stored data, so that the degree of freedom in generating the notification data can be improved according to the user's request.

(2) To play back the above-mentioned synthetic voice, for example, the voice data and the first sound data can be sent separately to the playback command unit 115, and the playback command unit 115 can execute a playback command to play them continuously. However, for example, if other sound data is sent to the playback command unit 115 between the voice data and the first sound data, there is a risk that the voice data and the first sound data cannot be played back continuously. In contrast, in this embodiment, the voice data and the first sound data are synthesized to generate synthetic voice data, which is then sent to the playback command unit 115, so that it is possible to reliably prevent the voice data and the first sound data from being played back separately.

5. Modifications
Although the embodiment of the present invention has been described above, the present invention is not limited to the above embodiment, and various modifications are possible without departing from the spirit of the present invention. Note that the modified examples described below can be appropriately combined.

<5-1>
In the above embodiment, one piece of first sound data is linked to the front and back of the voice data, but multiple pieces of first sound data may be linked. Also, in the above embodiment, the first sound data 122 is linked to the front and back of the voice data, but the first sound data 122 may be linked to only one of the front and back of the voice data.

<5-2>
In the above embodiment, as shown in Fig. 8, the synthetic voice data is played back after the playback of the second sound data is completed, but it is also possible to give priority to playback of data transmitted to the playback command unit 115 later. For example, as shown in Fig. 9, even during playback of the second sound data, if synthetic voice data is transmitted to the playback command unit 115 and becomes available for playback, the playback command unit 115 can execute a playback command for the synthetic voice data without waiting for the playback of the second sound data to be completed.

<5-3>
In the above embodiment, the voice data is acquired using the TTS service 4 external to the notification device 1, but the method of acquiring the voice data is not limited to this. For example, software for performing TTS processing may be built into the notification device 1, and the voice data may be generated using this software.

<5-4>
In the above embodiment, the first sound data 122 and the second sound data 124 are stored separately, but the first sound data and the second sound data can be acquired from a single sound data database. In the above embodiment, the first information and the second information are acquired from the equipment 3, and the sound data 122, 124 stored in the alarm device 1 are specified by this, but, for example, at least one of the first sound data 122 and the second sound data 124 can be acquired directly from the equipment 3. Alternatively, the database of the first sound data and the second sound data can be provided outside the alarm device, and the sound data specified by the first information and the second information can be acquired from outside the alarm device 1.

<5-5>
In the above embodiment, the first sound data is set based on the first information (information specifying the first sound data, or the first sound data itself) included in the voice control signal transmitted from the facility 3, but the selection of the first sound data can also be performed by the notification device 1 according to a predetermined criterion. For example, when the notification device 1 receives a voice control signal from the facility 3 at a specific time, the control unit 11 can select the first sound data corresponding to that time and combine it with the voice data. Alternatively, when a voice control signal is received from a specific facility 3, the control unit 11 can select the first sound data corresponding to that facility 3 and combine it with the voice data. If such a criterion is set in advance in the notification device 1, a synthetic voice according to the user's request can be generated. In addition, as for the second sound, for example, the facility 3 can transmit only a signal instructing a notification without transmitting the second information, and the notification device 1 can select the second sound based on the above-mentioned criterion.

<5-6>
In the above embodiment, in order to generate the synthetic voice data, the first sound and the text data are transmitted as one data set from the facility 3 to the alarm device 1, but if the data set does not include the first sound, it is also possible to generate only voice data from the text data without generating synthetic voice data, and to play this. Also, instead of transmitting the first sound and the text data as one data set, they can be associated with each other and transmitted at different times. Even if transmitted at different times in this way, the synthetic voice data is not transmitted to the transmission command unit 115 until the synthesis process is completed.

<5-7>
The aspect of the notification device shown in the above embodiment is merely an example, and various modifications are possible in terms of shape, arrangement of operation buttons, etc. For example, the notification device may be configured to notify by sound alone, without providing the LED unit 103.

<5-8>
In the above embodiment, the first acquisition unit 111, the second acquisition unit 112, the voice data acquisition unit 113, the synthesis unit 114, and the playback command unit 115 are provided in the notification device 1, but a device having at least these functional configurations may be configured as a voice data generation device, and a notification device for outputting sound such as a speaker may be connected to the device to configure the notification device. In this case, the voice generation device may be an information processing device designed specifically for the service to be provided, a general-purpose desktop PC, a tablet PC, or the like. In addition, the playback command unit 115 may not be provided in this voice generation device, and may be provided in another device. In other words, the main function of the voice generation device may be to generate synthetic voice data without issuing a playback command.

REFERENCE SIGNS LIST 1 Notification device 111 First acquisition unit 112 Second acquisition unit 113 Voice data generation unit 114 Synthesis unit 115 Playback command unit 121 Voice generation program 122 First voice data 123 Text data 124 Second voice data

Claims (11)

A computer connectable to at least one notification device,
obtaining text data and first information relating to at least one first sound;
obtaining voice data based on the text data;
combining first sound data relating to the first sound with at least one of the front and rear of the voice data to generate synthetic voice data;
A speech generation program that executes the following: A computer connectable to at least one notification device,
obtaining text data;
obtaining voice data based on the text data;
obtaining first sound data to be combined with the audio data;
combining the first sound data with at least one of the front and rear of the voice data to generate synthetic voice data;
A speech generation program that executes the following: The voice generation program according to claim 1 or 2, further comprising a step of playing a synthetic voice based on the synthetic voice data on the notification device. obtaining second information about a second sound;
playing the second sound on the notification device before or after the synthetic speech in a specified order;
4. The voice generating program according to claim 3, further comprising: The voice generation program according to claim 4, configured to play the second sound or the synthetic voice after playback of either one of them is completed. The voice generation program according to claim 4, configured to interrupt the playback of one of the second sound or the synthetic voice and play the other if playback of the other becomes possible while the other is being played. The voice generation program according to claim 1, wherein the first information is information that specifies one of a plurality of the first sound data stored in advance. 1. A method for generating sound for at least one notification device, comprising:
obtaining text data and first information relating to at least one first sound;
obtaining voice data based on the text data;
combining first sound data relating to the first sound with at least one of the front and rear of the voice data to generate synthetic voice data;
A method for generating voice comprising: A voice generating device connectable to at least one notification device,
a first acquisition unit that acquires text data and first information related to at least one first sound;
a voice data acquisition unit that acquires voice data based on the text data;
a synthesis unit that combines first sound data related to the first sound with at least one of the front and rear of the voice data to generate synthetic voice data;
A voice generating device comprising: The voice generating device according to claim 9, further comprising a playback command unit that causes the notification device to play back a synthetic voice based on the synthetic voice data. A voice generating device according to claim 10;
At least one of the notification devices;
The notification device includes: