KR102479899B1 - Server, device and method for providing speech systhesis service - Google Patents

Abstract

A server providing a voice synthesis service includes a receiving unit for receiving voice recording data of a plurality of users for at least one of a plurality of pre-registered sample scripts, and a pitch value related to each user's voice based on the received voice recording data. A learning unit for learning a synthesized sound prediction model, a generation unit for generating sample synthesized data for at least one of a plurality of sample scripts based on the learned synthesized voice prediction model when a sample request command is received from a user terminal, and a sample synthesized data It may include a provision unit providing the user terminal and a voice registration unit registering voice information about the user of the user terminal based on whether or not the quality of the synthesized sample data received from the user terminal is satisfactory.

Description

Server, terminal and method for providing voice synthesis service {SERVER, DEVICE AND METHOD FOR PROVIDING SPEECH SYSTHESIS SERVICE}

The present invention relates to a server, a terminal, and a method for providing a voice synthesis service.

A text-to-speech (TTS) system uses a voice synthesis method to convert input text into voice and synthesize natural and high-quality voice. These speech synthesis methods include a corpus method, a hidden markov mode (HMM) method, and a deep learning method.

A large-capacity corpus-based speech synthesis system requires a large-capacity database for storing music pieces, so it is expensive, and it is impossible to expand speech synthesis using voice actor recording in various areas where artificial intelligence services are required, and it is not stored in the database. There is a disadvantage in that it is not natural to synthesize voice for unseen music.

HMM (Hidden Markov Mode)-based voice synthesis system can provide uniform voice synthesis quality regardless of whether or not the database stores music pieces, and is suitable for navigation voice synthesis with many proper nouns such as place names, but is not suitable for large-capacity terminal-based embedded However, it has the disadvantage of unnatural voice synthesis like a mechanical sound.

The deep learning-based voice synthesis system is used in various services because it can perform natural voice synthesis even with voice recording data recorded in a short time.

Recently, voice synthesis services using the voices of general customers have been expanded from existing professional voice synthesis services.

In the case of voice synthesis services targeting general customers, unlike professional voice actors, it is difficult for general customers to maintain vocalization and reading speed. In addition, in order to obtain the voice synthesis quality desired by the general customer, it is inconvenient to repeat voice recording until the general customer is satisfied.

Korean Registered Patent Publication No. 1996-0007129 (registered on May 27, 1996)

The present invention is to solve the above-mentioned problems of the prior art, by using the user's voice recording data for the pre-registered sample script to learn a synthesized sound prediction model related to the user's voice, and based on the learned synthesized sound prediction model It is intended to generate sample synthesized data and provide it to a user terminal. However, the technical problem to be achieved by the present embodiment is not limited to the technical problems described above, and other technical problems may exist.

As a technical means for achieving the above technical problem, a server providing a voice synthesis service according to a first aspect of the present invention receives voice recording data of a plurality of users for at least one of a plurality of pre-registered sample scripts. receiver; a learning unit for learning a synthesized sound prediction model for a pitch value related to each user's timbre based on the received voice recording data; a generator configured to generate sample synthesized data for at least one of the plurality of sample scripts based on the learned synthesized sound prediction model when a sample request command is received from a user terminal; a provision unit providing the sample synthesized data to the user terminal; and a voice registration unit registering voice information about a user of the user terminal based on whether or not the quality of the synthesized sample data received from the user terminal is satisfactory.

A user terminal receiving a voice synthesis service according to a second aspect of the present invention includes a transmitter for transmitting a sample request command for voice synthesis to a voice synthesis service providing server; a receiver configured to receive, from the speech synthesis service providing server, at least one sample synthesized data generated based on the learned synthesized speech prediction model; and an input unit receiving quality satisfaction information for the sample synthesis data. The transmission unit transmits the input quality satisfaction information to the voice synthesis service providing server, and the synthesized sound prediction model is configured to generate each user based on voice recording data of a plurality of users for at least one of a plurality of pre-registered sample scripts. It is a model learned with respect to pitch values related to timbres, and voice information about the user of the user terminal may be registered in the voice synthesis service providing server based on whether or not the quality of the sample synthesized data is satisfactory.

A method for providing a voice synthesis service by a voice synthesis service providing server according to a third aspect of the present invention includes receiving voice recording data of a plurality of users for at least one of a plurality of pre-registered sample scripts; learning a synthesized sound prediction model for a pitch value related to each user's voice based on the received voice recording data; generating sample synthesis data for at least one of the plurality of sample scripts based on the learned synthesized sound prediction model when a sample request command is received from a user terminal; providing the sample synthesized data to the user terminal; and registering voice information about a user of the user terminal based on whether or not the quality of the synthesized sample data received from the user terminal is satisfactory.

The above-described means for solving the problems is only illustrative and should not be construed as limiting the present invention. In addition to the exemplary embodiments described above, there may be additional embodiments described in the drawings and detailed description.

According to any one of the above-described problem solving means of the present invention, the present invention uses the user's voice recording data for the pre-registered sample script to learn a synthesized sound prediction model related to the user's voice, and the learned synthesized sound prediction model Based on this, sample synthesized data may be generated and provided to the user terminal. Through this, in the present invention, since the user can check the quality of sample synthesized data expected when registering the user's voice, it is possible to relieve the user from having to repeatedly record the script as before.

1 is a block diagram of a voice synthesis service providing system according to an embodiment of the present invention.
2 is a block diagram of a voice synthesis service providing server shown in FIG. 1 according to an embodiment of the present invention.
3A to 3D are diagrams for explaining a method of registering voice information of a user according to an embodiment of the present invention.
4 is a block diagram of a user terminal shown in FIG. 1 according to an embodiment of the present invention.
5 is a diagram for explaining a method of providing a voice synthesis service according to an embodiment of the present invention.
6 is a flowchart illustrating a method for providing a voice synthesis service according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail so that those skilled in the art can easily practice the present invention with reference to the accompanying drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected" but also the case where it is "electrically connected" with another element interposed therebetween. . In addition, when a certain component is said to "include", this means that it may further include other components without excluding other components unless otherwise stated.

In this specification, a "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized using two or more hardware, and two or more units may be realized by one hardware.

In this specification, some of the operations or functions described as being performed by a terminal or device may be performed instead by a server connected to the terminal or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal or device connected to the corresponding server.

Hereinafter, specific details for the implementation of the present invention will be described with reference to the accompanying configuration diagram or process flow chart.

1 is a block diagram of a voice synthesis service providing system according to an embodiment of the present invention.

Referring to FIG. 1 , a voice synthesis service providing system may include a voice synthesis service providing server 100 and a user terminal 110 . However, since the voice synthesis service providing system of FIG. 1 is only one embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1, and may be configured differently from FIG. 1 according to various embodiments of the present invention. there is.

In general, each component of the voice synthesis service providing system of FIG. 1 is connected through a network (not shown). A network refers to a connection structure capable of exchanging information between nodes such as terminals and servers, such as a local area network (LAN), a wide area network (WAN), and the Internet (WWW: World Wide Web), wired and wireless data communication network, telephone network, and wired and wireless television communication network. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi, Bluetooth communication, infrared communication, ultrasound communication, visible light communication (VLC: Visible Light Communication), LiFi, and the like, but are not limited thereto.

The user terminal 110 may record the user's voice recording data for at least one sample script among a plurality of pre-registered sample scripts, and then transmit the voice recording data to the voice synthesis service providing server 100.

The voice synthesis service providing server 100 may learn a synthesized voice prediction model for a pitch value related to the user's voice based on the voice recording data received from the user terminal 110 .

The user terminal 110 sends a sample request command for synthesizing the user's voice to the voice synthesis service providing server 100 after a predetermined period of time from the time when the user's voice recording data is registered in the voice synthesis service providing server 100. can transmit

When receiving a sample request command from the user terminal 110, the speech synthesis service providing server 100 provides sample synthesized data for at least one of a plurality of sample scripts based on the learned synthesized sound prediction model of the user terminal 110. It is possible to generate and provide the generated sample synthesized data to the user terminal 110 .

The user terminal 110 may transmit quality satisfaction information on the sample synthesized data to the voice synthesized service providing server 100 after checking the quality satisfaction with respect to the sample synthesized data received from the voice synthesized service providing server 100. .

The voice synthesis service providing server 100 may register voice information about the user of the user terminal 110 based on whether or not the quality of the synthesized sample data received from the user terminal 110 is satisfactory.

Thereafter, when receiving a content request command from the user terminal 110, the voice synthesis service providing server 100 transmits content synthesis data for a content script corresponding to the content request command among a plurality of pre-registered content scripts to the registered user. It may be generated based on the voice information of the user and provide the generated content synthesized data to the user terminal 110 .

Hereinafter, the operation of each component of the voice synthesis service providing system of FIG. 1 will be described in detail.

FIG. 2 is a block diagram of a voice synthesis service providing server 100 shown in FIG. 1 according to an embodiment of the present invention.

Referring to FIG. 2, the voice synthesis service providing server 100 includes a receiving unit 200, a learning unit 210, a generating unit 220, a providing unit 230, a voice registering unit 240, and a speed adjusting unit 250. , a verification unit 260, a pause adjustment unit 270, and a voice input unit 280. However, the voice synthesis service providing server 100 shown in FIG. 2 is only one implementation example of the present invention, and various modifications are possible based on the components shown in FIG. 2 .

The receiving unit 200 may receive voice recording data of a plurality of users for at least one of a plurality of pre-registered sample scripts from terminals of a plurality of users.

The receiving unit 200 receives voice recording data in which the user's voice is recorded for at least one sample script among a plurality of pre-registered sample scripts from the user terminal of each of a plurality of users who want to use the service of moving picture content containing the user's voice. can do. Also, the receiving unit 200 may receive each voice recording data and identification information for each user terminal together from a plurality of user terminals. For example, referring to FIG. 3A , a randomly extracted sample script (301, for example, 'Children go to school early today') among a plurality of sample scripts pre-registered in the user terminal 110 is sent to the user terminal ( 110), the receiving unit 200 may receive the voice recording data of the user reading the sample script 301 and identification information of the user terminal 110 from the user terminal 110.

The verification unit 260 may verify pronunciation accuracy of voice recorded data received from a plurality of user terminals.

The verification unit 260 performs voice recognition on voice recorded data received from a plurality of user terminals, and determines the similarity between the result of performing voice recognition on the received voice recorded data and sample scripts corresponding to the received voice recorded data. If it is below the set threshold, it may be determined that the pronunciation accuracy of the received voice recorded data is inaccurate. For example, referring to FIG. 3A , the verifier 260 determines that, when the similarity between the result of performing voice recognition on the voice recorded data received from the user terminal 110 and the sample script 301 matches by 80% or more, the user If it is determined that the pronunciation of the voice recorded data received from the terminal 110 is correct, and the similarity is less than 80%, it may be determined that the pronunciation of the voice recorded data received from the user terminal 110 is incorrect.

The voice input unit 280 guides the user terminal for which the pronunciation accuracy of the voice recording data for each of the plurality of user terminals is determined to be inaccurate to receive new voice recording data for the sample script, and the new voice for the sample script from the corresponding user terminal. Recording data can be re-entered. For example, referring to FIG. 3A , the voice input unit 280 determines that the similarity between the result of performing voice recognition on the voice recorded data received from the user terminal 110 and the sample script 301 does not match by 80% or more, New voice recording data for the sample script 301 may be re-inputted from the user terminal 110 . If the similarity between the voice recorded data re-entered from the user terminal 110 more than a predetermined number of times (eg, 3 times) and the sample script corresponding to the corresponding voice recorded data is less than 80%, the voice input unit 280 may provide a new sample script different from the sample script 301 to the user terminal 110, and may re-enter the user's voice recording data for the new sample script.

The speed control unit 250 may provide a speed control interface to the user terminal 110 so that each user's reading speed for at least one sample script among a plurality of sample scripts is adjusted to a predetermined reading speed. For example, referring to FIGS. 3A and 3B , the speed control unit 250 provides a speed control interface 303 (eg, a cursor) so that the user can read the sample script 301 according to a preset reading speed. It can be provided to the user terminal 110 . Thereafter, the speed control unit 250 considers the user's reading speed of the sample script 301 and uses the speed control interface 303 to guide the reading speed of the sample script corresponding to the next sentence of the sample script 301. You can adjust the movement speed.

The voice input unit 280 may request the user to read the sample script again according to a comparison between the reading speed of at least one sample script among a plurality of sample scripts for each user and a predetermined threshold value (eg, 20%). For example, the voice input unit 280 may request a user terminal whose reading speed for the sample script of the user exceeds a preset threshold value to read the sample script again according to the preset reading speed.

The speed control unit 250 may measure the speech speed of the voice recording data received from a plurality of user terminals for each user.

Meanwhile, in order to improve the quality of voice synthesis, it is important to minimize pauses between voice sections in voice recorded data.

The pause adjustment unit 270 may detect at least one voice section from each of the voice recorded data received from a plurality of user terminals. For example, the pause controller 270 may detect a voice section from voice recorded data using a Voice Activity Detection (VAD) algorithm.

The pause adjustment unit 270 may calculate pause estimation reliability between at least one detected speech section, and adjust pause periods between speech sections based on the calculated pause estimation reliability. Here, a high pause period estimation reliability may mean a long pause period between speech sections, and a low pause estimation reliability may mean a short pause period between speech sections. For example, the pause adjustment unit 270 may delete pauses between voice sections or adjust the pauses between voice sections to an average value so that pauses between voice sections are minimized.

The learning unit 210 may learn a synthesized sound prediction model related to the voice characteristics of each user for each user based on the received voice recording data of each of the plurality of users.

In detail, the learning unit 210 may train a synthesized sound prediction model for a pitch value related to the timbre of each user for each user based on the received voice recording data of each of the plurality of users. For example, referring to FIG. 3C , the learning unit 210 derives a pitch value related to the user's voice tone from the user's voice recording data using a neural network algorithm 305, and uses the derived pitch value to produce a synthesized sound. Predictive models can be trained. Here, the neural network algorithm 305 is configured based on multi-layer recurrent neural networks (RNNs) capable of learning high-dimensional continuous distributions such as audio data.

)를 구성하는 각 음절의 확률값은 [수학식 1]과 같이 표현될 수 있다. The learning unit 210 may train the synthesized sound prediction model so that the probability value of each syllable constituting the received voice recording data of each of the plurality of users is maximized in relation to the pitch value. User's voice recording data (

The probability value of each syllable constituting ) can be expressed as in [Equation 1].

[Equation 1]

Referring to FIG. 3D , the learning unit 210 inputs a pitch value related to the user's voice included in the voice recording data for each user, a sample script corresponding to the corresponding voice data, and a user ID to the synthesized sound prediction model to obtain the voice recording data. A synthesized sound prediction model may be trained so that the probability value of each syllable constituting is maximized.

When the generator 220 receives a sample request command from at least one user terminal 110 among a plurality of user terminals (a terminal that has transmitted the user's voice recording data to the voice synthesis service providing server), the learned user terminal ( Sample synthesized data for at least one of a plurality of sample scripts may be generated based on the synthesized sound prediction model of 110). For example, the generation unit 220 transmits the user's pitch value and the user's vocalization speed measured by the speed control unit 250 to at least one sample script based on the learned synthesized sound prediction model of the user terminal 110. Reflected sample synthesis data can be created.

The providing unit 230 may provide the generated sample synthesized data to the user terminal 110 .

The voice registration unit 240 may register voice information about the user of the user terminal 110 based on whether or not the quality of the synthesized sample data received from the user terminal 110 is satisfactory. For example, when a registration approval message indicating that the user satisfies the quality of sample synthesis data is received from the user terminal 110, the voice registration unit 240 registers voice information of the user terminal 110 for the user. can do. If the user receives a registration non-approval message indicating dissatisfaction with the quality of the sample synthesized data from the user terminal 110, the learning unit 210 receives the user's voice recorded data from the user terminal 110 again The synthetic sound prediction model can be retrained. Here, the voice information may include a pitch value for each user derived based on a synthesized speech prediction model, and may further include a measured voice rate of the user.

When receiving a content request command (including information on the content script selected by the user) from the user terminal 110, the generating unit 220 selects a content script corresponding to the content request command from among a plurality of pre-registered content scripts. Content synthesis data for the voice may be generated based on the pitch value included in the registered voice information.

The generation unit 220 may generate content synthesis data for a content script corresponding to a content request command based on a pitch value and vocalization rate included in registered voice information.

The provision unit 230 may provide content composition data to the user terminal 110 .

On the other hand, if you are skilled in the art, the receiving unit 200, the learning unit 210, the generating unit 220, the providing unit 230, the voice registration unit 240, the speed adjusting unit 250, the verification unit 260, the pause adjustment unit ( 270) and the voice input unit 280 may be separately implemented, or one or more of them may be integrated and implemented.

4 is a block diagram of the user terminal 110 shown in FIG. 1 according to one embodiment of the present invention.

Referring to FIG. 4 , the user terminal 110 may include a transmitter 400 , a receiver 410 , an input unit 420 and a speed control interface providing unit 430 . However, the user terminal 110 shown in FIG. 5 is only one implementation example of the present invention, and various modifications are possible based on the components shown in FIG. 5 .

The transmission unit 400 may transmit the user's voice recording data for at least one of a plurality of pre-registered sample scripts to the voice synthesis service providing server 100 . For example, referring to FIG. 5 , when a user who wants to use a service of fairy tale content containing a user's voice selects voice recording 501 through the 'My Voice Story' application, the receiver 410 provides a voice synthesis service. A screen of the user terminal 110 receives a randomly extracted sample script (reference numeral 301 in FIG. can be output to When the user records the user's voice for the corresponding sample script, the transmission unit 400 may transmit identification information of the user terminal 110 to the voice synthesis service providing server 100 together with the user's voice recording data.

Here, the speech speed of the user's voice recorded data transmitted to the voice synthesis service providing server 100 may be measured by the voice synthesis service providing server 100 .

The speed control interface providing unit 430 provides a speed control interface (reference numeral 303 in FIG. 3B ) for guiding the user's reading speed of at least one sample script provided to the user terminal 110 to be adjusted to a predetermined reading speed. It may be provided from the voice synthesis service providing server 100 . The user may read the sample script according to the speed of the speed control interface displayed in the sample script.

The speed control interface providing unit 430 adjusts the reading speed of the sample script corresponding to the next sentence provided to the user terminal 110 after providing the corresponding sample script in consideration of the reading speed of the user's sample script. It is possible to control the speed control interface to be adjusted through the moving speed of the .

When the user's voice recording data is transmitted to the voice synthesis service providing server 100, the voice synthesis service providing server 100 may learn a synthesized sound prediction model related to the user's voice characteristics based on the user's voice recording data. Specifically, the voice synthesis service providing server 100 may derive a pitch value related to the user's voice from the user's voice recording data, and use the derived pitch value to train a synthesized sound prediction model.

The transmitter 400 may transmit a sample request command for voice synthesis to the voice synthesis service providing server 100 . For example, referring to FIG. 5 , when a user selects an interface 503 for listening to sample synthesized data through the 'My Voice Story' application, the transmitter 400 sends the voice synthesis service providing server 100 a voice. You can send a sample request command for synthesis.

Then, when receiving a sample request command from the user terminal 110, the speech synthesis service providing server 100 synthesizes a sample of at least one of a plurality of sample scripts based on the learned synthesized sound prediction model of the user terminal 110. Data may be generated and transmitted to the user terminal 110 . Here, the sample synthesized data for at least one may be data in which a pitch value related to the user's tone color and the user's vocalization speed are reflected.

The receiver 410 may receive from the speech synthesis service providing server 100 sample synthesis data for at least one sample generated based on the learned synthesized speech prediction model.

The input unit 420 may receive quality satisfaction information for the sample synthesized data. For example, referring to FIG. 5 , when the output voice of the synthesized sample data is finished, the input unit 420 transmits quality satisfaction information for the corresponding sample synthesized data through the 'My Voice Story' application to a satisfaction button or a dissatisfied button (505). ) can be input.

The transmitter 400 may transmit quality satisfaction information input for the sample synthesis data to the voice synthesis service providing server 100 .

Voice information about the user of the user terminal 110 may be registered in the voice synthesis service providing server 100 based on whether or not the quality of the sample synthesized data is satisfactory. Here, the voice information may include a pitch value for a user derived based on a synthesized speech prediction model. Also, the voice information may further include a voice rate of the user's voice recording data.

For example, if the user satisfies the quality of the sample synthesis data, voice information about the user is registered in the speech synthesis service providing server 100, but if the user does not satisfy the quality of the sample synthesis data, the user's voice information is registered in the speech synthesis service providing server 100. re-inputs voice recording data, and the voice synthesis service providing server 100 may retrain a synthesized sound prediction model with the re-input voice recording data.

The transmission unit 400 may transmit a content request command to the voice synthesis service providing server 100 . For example, referring to FIG. 5 , after voice information about a user is registered in the voice synthesis service providing server 100 as a quality satisfaction for sample synthesized data, the transmitter 400 transmits a plurality of pre-registered content scripts. In step 507, a content request command for the content script selected by the user may be transmitted to the voice synthesis service providing server 100.

The receiving unit 410 may receive from the voice synthesis service providing server 100 content synthesis data generated based on a pitch value included in voice information of a registered user. Here, the content synthesis data may be content synthesis data for a content script corresponding to a content request command among a plurality of pre-registered content scripts. Content synthesis data may be generated based on the pitch value and vocalization rate included in the voice information of the registered user.

On the other hand, those skilled in the art will fully understand that each of the transmission unit 400, the reception unit 410, the input unit 420, and the speed control interface providing unit 430 can be implemented separately or implemented by integrating one or more of them. will be.

6 is a flowchart illustrating a method for providing a voice synthesis service according to an embodiment of the present invention.

Referring to FIG. 6 , in step S601, the voice synthesis service providing server 100 may receive voice recording data of a plurality of users for at least one of a plurality of pre-registered sample scripts from a plurality of user terminals.

In step S603, the voice synthesis service providing server 100 may train a synthesized voice prediction model for a pitch value related to the tone of each user based on the voice recording data received for each of a plurality of user terminals.

In step S605, when receiving a sample request command from the user terminal 110, the speech synthesis service providing server 100 generates at least one of a plurality of sample scripts based on the synthesized sound prediction model corresponding to the learned user terminal 110. Sample synthesis data can be created for

In step S607, the voice synthesis service providing server 100 may provide the generated sample synthesized data to the user terminal 110.

In step S609, the voice synthesis service providing server 100 may register voice information about the user of the user terminal 110 based on whether or not the quality of the synthesized sample data received from the user terminal 110 is satisfactory.

In the above description, steps S601 to S609 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present invention. Also, some steps may be omitted if necessary, and the order of steps may be changed.

An embodiment of the present invention may be implemented in the form of a recording medium including instructions executable by a computer, such as program modules executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The above description of the present invention is for illustrative purposes, and those skilled in the art can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts thereof should be construed as being included in the scope of the present invention. .

100: Speech synthesis service providing server
110: user terminal
200: receiver
210: learning unit
220: generating unit
230: provision unit
240: voice register
250: speed control unit
260: verification unit
270: rest period adjustment unit
280: voice input unit
500: transmission unit
510: receiver
520: input unit
530: speed control interface providing unit

Claims (18)

In a server providing a voice synthesis service,
a receiving unit which receives voice recording data of a plurality of users for at least one of a plurality of pre-registered sample scripts;
a learning unit for learning a synthesized sound prediction model for a pitch value related to each user's timbre based on the received voice recording data;
a generator configured to generate sample synthesized data for at least one of the plurality of sample scripts based on the learned synthesized sound prediction model when a sample request command is received from a user terminal;
a provision unit providing the sample synthesized data to the user terminal; and
Voice registration unit for registering voice information about the user of the user terminal based on whether or not the quality of the synthesized sample data received from the user terminal is satisfactory
Including,
Further comprising a speed control unit for measuring the speech speed of the received voice recording data for each user,
The voice information includes a voice rate of the measured voice recording data of the user of the user terminal, the voice synthesis service providing server.
According to claim 1,
The voice information includes a pitch value for the user derived based on the synthesized sound prediction model, a voice synthesis service providing server
According to claim 2,
When the generating unit receives a content request command from the user terminal, content synthesis data for a content script corresponding to the content request command among a plurality of pre-registered content scripts is based on a pitch value included in the registered voice information. to create,
Wherein the providing unit provides the content synthesis data to the user terminal, a voice synthesis service providing server.
According to claim 3,
The speech synthesis service providing server, wherein the speed control unit provides a speed control interface to a user terminal so that the reading speed of the at least one sample script is adjusted according to a preset reading speed.
delete According to claim 3,
The voice synthesis service providing server, wherein the generation unit generates content synthesis data for the content script corresponding to the content request command based on a pitch value and a voice rate included in the registered voice information.
According to claim 1,
wherein the learning unit learns the synthesized sound prediction model so that a probability value of each syllable constituting the received voice recorded data is maximized in relation to the pitch value.
According to claim 1,
Verification unit for verifying the pronunciation accuracy of the received voice recording data
To further include, a speech synthesis service providing server.
According to claim 8,
The verification unit performs voice recognition on the received voice recorded data, and a similarity between a result of performing voice recognition on the received voice recorded data and a sample script corresponding to the received voice recorded data is equal to or less than a preset threshold. If it appears, it is determined that the pronunciation accuracy of the received voice recorded data is inaccurate.
According to claim 9,
The voice synthesis service providing server further comprises a voice input unit for re-inputting new voice recording data for the sample script when it is determined that the pronunciation accuracy of the received voice recording data is incorrect.
According to claim 1,
and a pause adjustment unit configured to calculate a pause estimation reliability between at least one voice interval detected from the voice recording data and adjust a pause period between the voice intervals based on the calculated pause estimation reliability. server.
In a user terminal receiving a speech synthesis service,
a transmission unit for transmitting the user's voice recording data for at least one of a plurality of pre-registered sample scripts to a voice synthesis service providing server;
a receiver configured to receive, from the voice synthesis service providing server, at least one sample synthesized data generated based on a learned synthesized voice prediction model when a sample request command for voice synthesis is transmitted to the voice synthesis service providing server; and
an input unit for receiving quality satisfaction information for the sample synthesized data;
The transmission unit transmits the input quality satisfaction information to the voice synthesis service providing server;
The synthesized sound prediction model is a model learned for a pitch value related to the user's voice based on the user's voice recording data for the at least one,
Voice information about the user is registered in the voice synthesis service providing server based on whether or not the quality of the sample synthesis data is satisfactory,
A speech speed of the user's voice recorded data transmitted to the voice synthesis service providing server is measured by the voice synthesis service providing server;
The user terminal, wherein the voice information includes a voice rate of the measured voice recording data of the user.
According to claim 12,
The voice information includes a pitch value for the user derived based on the synthesized speech prediction model.
According to claim 13,
The transmission unit transmits a content request command to the voice synthesis service providing server;
The receiving unit receives content synthesis data generated based on a pitch value included in voice information of the registered user from the voice synthesis service providing server;
The content synthesis data is content synthesis data for a content script corresponding to the content request command among a plurality of pre-registered content scripts, the user terminal.
15. The method of claim 14,
Further comprising a speed control interface providing unit receiving a speed control interface for guiding the user's reading speed of the at least one sample script to be adjusted according to a preset reading speed from the speech synthesis service providing server, .
delete 15. The method of claim 14,
The content synthesis data is generated based on the pitch value and speech rate included in the registered voice information of the user, the user terminal.
A method for providing a voice synthesis service by a voice synthesis service providing server,
Receiving voice recording data of a plurality of users for at least one of a plurality of pre-registered sample scripts;
learning a synthesized sound prediction model for a pitch value related to each user's voice based on the received voice recording data;
generating sample synthesis data for at least one of the plurality of sample scripts based on the learned synthesized sound prediction model when a sample request command is received from a user terminal;
providing the sample synthesized data to the user terminal; and
Registering voice information for a user of the user terminal based on whether or not the quality of the sample synthesized data received from the user terminal is satisfactory,
Further comprising the step of measuring the vocalization speed of the received voice recording data for each user,
The voice synthesis service providing method of claim 1 , wherein the voice information includes a voice rate of the measured voice recorded data of the user of the user terminal.

Images