KR20010096289A - System for proving voice message and method thereof - Google Patents

Abstract

PURPOSE: A system and method for providing a voice message is provided to enhance the transmission effect of the voice message and improve the quality of a voice message providing service by providing the voice message corresponding to a character message as a voice with a desired expression type of specific person. CONSTITUTION: The first database(213) stores at least one fixed voice message recorded as at least one specific person. The second database(215) stores voice data of phoneme unit of at least one person. A voice editing and synthesizing unit(217) performs an editing or synthesizing process with reference to the voice message or the voice data, or performs the editing and synthesizing process for providing a corresponding voice message. A server(211) retrieves the first database(213) and the second database(215) according to the editing and synthesis, transmits the retrieved voice message or voice data to the voice editing and synthesizing unit(217), and transmits the a voice message transmitted from the voice editing and synthesizing unit(217) as the corresponding voice message.

Description

System for proving voice message and method

The present invention relates to a voice message providing system and method, and more particularly, to a voice message providing system and method for providing a voice message corresponding to a text message received through a wired or wireless communication network.

With the rapid development of communication technology, it is possible to transmit and receive text messages as well as voice through wired and wireless communication networks. Accordingly, a communication service that allows a receiver to receive a voice message corresponding to a text message sent by a sender has been proposed. However, the voice message provided through the existing communication service is a synthesis of machine sounds made by collecting sound sources of several people.

1 is a schematic functional block diagram of a communication network equipped with a conventionally proposed voice message providing system, which is a text message transmitting means 102 and a voice message providing system 110 connected to a text message transmitting means 102 via a wired or wireless communication network. ), A voice message storage device 120 connected to the voice message providing system 110 through a wired / wireless communication network, and a wired / wireless terminal 130 connected to the voice message storage device 120 through a wired / wireless communication network.

In particular, the voice message providing system 110 converts the received text message into a corresponding voice message and provides the server 112 with the voice message storage device 120, and collects the sound sources of various people as data of phoneme units. And a speech synthesizer 116 for synthesizing the phoneme unit data retrieved from the phoneme unit database 114 and the phoneme unit database 114 and providing the synthesized unit data to the server 112.

A conventional method of providing a voice message corresponding to a text message through the communication network configured as described above is as follows.

That is, when an arbitrary text message is received from the text message transmitting means 102, the server 112 searches the phoneme unit database 114 based on this. As a result of the search, if the phoneme unit data is retrieved from the phoneme unit database 114, the phoneme unit 116 transmits the data to the voice synthesizer 116 to synthesize the voice message. The synthesized voice message is transmitted to the server 112, and the server 112 transmits it to the voice message storage device 120 through a wired or wireless communication network. Accordingly, the voice message storage device 120 notifies the wired / wireless terminal 130 of the corresponding message, and transmits a corresponding voice message when the wired / wireless terminal 130 is in a state in which it can be received.

As such, the voice message provided by the existing communication service is merely a dimension of delivering information regardless of user's taste.

The present invention has been made in order to improve the quality of a voice message providing service, and an object thereof is to provide a voice message providing system and method capable of providing a voice message corresponding to a desired text message with a specific person's voice.

Another object of the present invention is to provide a voice message providing system and method capable of providing a voice message corresponding to a desired text message in a desired expression form among various expression forms of a specific person.

1 is a functional block diagram of a communication network equipped with a conventional voice message providing system.

2 is a functional block diagram of a communication network equipped with a voice message providing system according to the present invention.

3 is a flowchart illustrating a method of providing a voice message according to the present invention.

<Description of the symbols for the main parts of the drawings>

120: voice message storage device 130: wired and wireless terminal

201: text message transmission means 210: voice message providing system

202: text message sending and voice message receiving terminal

211: server 213: first database

215: Second database 217: Voice editing synthesis means

In order to achieve the above objects, an apparatus according to the present invention is a voice message providing system for transmitting a voice message corresponding to a text message received through a wired or wireless communication network through a wired or wireless communication network, the voice recording of at least one specific person A first database storing at least one fixed voice message; A second database storing voice data of phoneme units of at least one specific person; Speech editing synthesizing means for performing editing or synthesizing or synthesizing or synthesizing the voice message or the voice data to provide a corresponding voice message; When the text message is received, the first database and the second database are searched according to editing or compositing, the searched voice message or voice data is transmitted to the voice editing synthesizing means, and then the voice message transmitted from the voice editing synthesizing means. It is preferable to include a server for transmitting a corresponding voice message.

In addition, the server may store the voice message transmitted through the wired and wireless communication network and / or a terminal capable of recording or reproducing the voice message transmitted through the wired or wireless communication network to a recording medium and / or a predetermined terminal connected through the wired or wireless communication network. It is configured to be able to connect with the voice message storage device for transmitting the.

In order to achieve the above object, the method according to the present invention is a voice message providing method for transmitting a voice message corresponding to a text message received through a wired or wireless communication network through a wired or wireless communication network, (a) to the voice of at least one specific person Constructing a first database storing at least one recorded fixed voice message; (b) constructing a second database storing voice data of at least one particular person's phoneme unit; (c) if a text message is received, searching the first database and the second database; (d It is preferable to include the step of transmitting a voice message generated by editing or synthesizing or editing and synthesizing the data retrieved in step (c) as a corresponding voice message.

Hereinafter, with reference to the accompanying drawings will be described in detail the present invention.

2 is a functional block diagram of a communication network equipped with a voice message providing system according to the present invention, a text message transmitting means 201, a text message transmitting and receiving terminal 202, a voice message providing system 210, voice Message storage device 120, and the wired and wireless terminal 130. The voice message providing system 210 is configured to include a server 211, a first database 213, a second database 215, and voice editing synthesizing means 217.

The text message transmitting means 201 is the same as that shown in FIG. 1, and an operator terminal which can be operated by an operator operating a terminal, a portable terminal, or a voice message providing system 210, such as a personal computer connected via a wired or wireless communication network. The same message is transmitted to the voice message providing system 210 by the operator. At this time, the text message transmitting means 201 transmits information on selecting a voice and expression form of a specific person who will provide a voice message corresponding to the text message.

That is, when wishing to deliver a happy birthday message to a friend who likes the friendly voice of "Joe Mary", the operator who operates the text message transmitting means 201 may correspond to the text message corresponding to the birthday message and the text message. The information on selecting the grandmother and the information on the selected expression type as the specific persons to provide the voice message are processed to be transmitted together.

To this end, the text message transmitting means 201 is connected to the voice message providing system 210 before transmitting the text message to provide the type of fixed voice message (or standardized voice message) and the voice of a person in a certain form. Find out if you can. The connection method for this is determined by how the wired / wireless communication network between the text message transmitting means 201 and the voice message providing system 210 is established. That is, the wired / wireless communication network between the text message transmitting means 201 and the voice message providing system 210 can be implemented in the form of the Internet, wired / wireless telephone network, leased line, satellite communication, broadcasting network, etc. To grasp the type, voice and expression of the fixed type of voice message that can be provided by the voice message providing system 210, and to select, specify or input the message, voice and expression to be delivered as described above voice message The corresponding information is transmitted to the providing system 210.

In addition, when a part of the selected standardized voice message is to be modified, the condition information on the part to be modified is transmitted together with the corresponding text message. The condition information includes information such as a part to be modified, a message to be inserted instead, and a voice and expression form of the message to be inserted. For example, in a fixed voice message that says "Happy Birthday", when you want to change "Happy Birthday" to "Graduation", the information about the part you want to modify is about "Happy Birthday," and instead of the message, The information is about "graduation", and the information about the voice and the expression form for the message "graduation" to be inserted is selected, specified or input as described above, and transmitted to the voice message providing system 210.

The text message transmission and voice message receiving terminal 202 is constituted by a terminal such as a personal computer or a portable terminal connected through a wired / wireless communication network, such as a desired message, voice and expression form, and the like as the above-described text message transmitting means 201; Information selected, designated or input to modify some of the fixed messages is transmitted to the voice message providing system 210, whereby a recording medium having the voice message received from the voice message providing system 210 installed or connected therein. The voice message recorded on the recording medium is reproduced for the operator to recognize. At this time, the recording medium uses a medium such as CD-ROM, flash memory, tape, hard disk, and the like, and the wired / wireless communication network with the voice message providing system 210 includes the Internet, a wired / wireless telephone network, a dedicated line. , Satellite communication, broadcasting network, etc. can be implemented. Therefore, the above-described text message transmission and voice message receiving terminal 202 may be a terminal installed in a doll manufacturer or a card manufacturer.

Meanwhile, the voice message providing system 210 establishes a first database 213 to store at least one fixed voice message (or a standardized voice message) recorded with at least one specific person's voice. That is, the plurality of fixed voice messages recorded with the original sound of the specific person are stored in the first database 213 in order to provide a plurality of fixed voice messages with the voice of a specific person such as a highly recognized entertainer. The fixed voice message may be a message that is expected to be used frequently, for example, "Happy Birthday."

Then, the second database 215 is constructed by collecting the voice data of the phoneme units of at least one specific person to be synthesized in various expression forms. That is, voice data in a phoneme unit is collected and stored in the second database 215 to provide a voice message of a specific person in various expression forms such as a friendly expression, a clerical expression, an angry expression, and a sad expression. At this time, the specific person targeted for the voice data handled by the second database 215 and the specific person targeted for voice data handled by the first database 213 can be constructed to be the same person. For example, in the case where fixed voice data such as "Cho, Mary, Chae Shira, Kim Mi-sook" is stored in the first database 213, "Cho, Mary, Chae Shira, Kim Mi-sook" also appears in the second database 215. It is possible to store voice data in units of phonemes.

However, the first database 213 and the second database 215 may be implemented such that voice data of a completely different person is stored. The purpose is to be able to provide a desired voice message in the voice of a plurality of specific persons. For example, if you provide a voice message saying "Happy birthday to Hong Gil Dong," a message that requires speech synthesis, such as "Mr. Hong Gil Dong," will be spoken by "Mr. Cho" and "Happy Birthday." In order to be able to provide a fixed message as the voice of "Che Shira". When providing a voice message as in this example, the voice data for "Mr. Hong Gil Dong" is retrieved through the second database 215, and the voice message for "Happy Birthday" is sent to the first database ( 213).

The voice editing synthesizing means 217 edits and / or synthesizes a voice message or voice data transmitted from the server 211 and transmits a voice message corresponding to the received text message to the server 211. For example, the message to send is "Hong Gil Dong, Happy Birthday", "Happy Birthday" is a fixed voice message stored in the first database 213, "Hong Gil Dong" is the second database In the case where it is necessary to synthesize using the phoneme unit speech data stored in 215, the voice editing synthesizing means 217 is provided with the phoneme unit speech data provided from the second database 215 for " Hong Gil Dong ". Synthesis processing is performed such that the above-described voice message is generated, and edited so that "Hong Gil-dong" generated by the synthesis process and "Happy Birthday" retrieved from the first database 213 can be provided together. In addition, even when condition information for modifying a part of the fixed voice message is received, the voice message for the part to be modified is generated by a synthesis process, and the voice message thus generated and the remaining unmodified voice message are edited. To the server 211. The synthesis and editing process for such speech data is based on existing speech synthesis and editing methods.

When the server 211 receives any text message and information on the selected person's voice and expression form from the text message transmitting means 201 or the text message transmitting and voice message receiving terminal 202 through the wired / wireless communication network, The database 213 and the second database 215 are searched to collect voice messages and / or voice data for generating corresponding voice messages.

That is, when the text message is received, the server 211 analyzes the received text message to determine whether voice editing and / or synthesis is necessary. If it is determined that voice editing and / or synthesis is not necessary, the corresponding voice message is a standardized voice message. Therefore, the voice message corresponding to the first database 213 based on the received voice information together with the text message is received. Search for and transmit the voice message storage device 120 or text message transmission and voice message receiving terminal 202.

However, when it is determined that only synthesis is necessary, the server 211 searches for the phoneme data of the corresponding phoneme in the second database 215 based on the received text and information on the expression type. The voice edit synthesis means 217, and a voice message corresponding to the voice edit synthesizer 217 is provided from the voice edit synthesizer 217, and then transmitted to the voice message storage device 120 or the text message transmitter and the voice message receiver terminal 202. do.

In addition, when it is determined that both editing and synthesis are necessary, the server 211 retrieves the corresponding voice message and the voice data from the first and second databases 213 and 215, respectively, and the voice editing synthesis means 217. The voice message generated by editing and synthesizing is transmitted to the voice message storage device 120 or the text message transmission and voice message receiving terminal 202. If it is determined that only editing is necessary, the server 211 retrieves the corresponding voice message from the first database 213, and edits the voice message generated by editing by the voice editing synthesizing means 217. 120 or a text message transmission and voice message reception terminal 202.

The wired / wireless communication network between the voice message storage device 120 and the server 211 may be implemented in the form of the Internet, a wired / wireless telephone network, a dedicated line, a satellite communication, a broadcasting network, and the like.

The voice message storage device 120 is like a voice mailbox connected to a carrier server or an exchange, and stores a voice message when the voice message is received from the server 211. Then, the wired / wireless terminal 130 is notified of this, and a response signal is received from the corresponding wired / wireless terminal 130 to transmit the voice message between the voice message storage device 120 and the wired / wireless terminal 130. When the state is set, the voice message storage device 120 transmits the stored voice message to the wired / wireless terminal 130.

The wired / wireless terminal 130 is configured as a terminal such as a personal computer connected to the voice message storage device 120 and a wired / wireless communication network, a portable terminal, or a wired telephone. The wired / wireless communication network between the wired / wireless terminal 130 and the voice message storage device 120 may also be implemented in the form of the Internet, a wired / wireless telephone network, a dedicated line, a satellite communication, a broadcasting network, and the like.

On the other hand, the voice message providing method according to the present invention is performed as shown in the flow chart shown in FIG.

First, before any text message is received, the voice message providing system 210 establishes a first database 213 and a second database 215 for the same purpose as shown in FIG.

Then, if any text message is received from the text message transmitting means 201 or the text message sending and voice message receiving terminal 202, the server 211 proceeds to step 301 to receive the received text message and the message received therewith. Analyze additional information such as speech and expression forms.

As a result of the analysis, if voice editing and / or synthesis is not necessary to generate a corresponding voice message, the process proceeds from step 303 to step 305. The first database 213 is searched based on the text message received in step 305 and voice information (voice information specifying a specific person). Next, the flow proceeds to step 307 to send the retrieved fixed voice message (or standardized voice message) to the voice message storage device 120 or the text message transmission and voice message receiving terminal 202, and the voice corresponding to the received text message. Terminate the message providing task.

However, as a result of the determination in step 303, if voice editing and / or synthesis is required to provide the corresponding voice message, the server 211 proceeds to step 309. In step 309, the server 211 checks whether only editing is necessary. As a result of the check, if only editing is necessary, the server 211 proceeds to step 311 to search the first database 213 based on the received text message and the voice information received therewith. Proceeding to step 313, each retrieved fixed voice message is edited via voice editing synthesizing means 217. For example, a fixed voice message of "Happy Birthday" is provided as a voice message of the Virgin Mary, and a fixed voice message of "Congratulations" is stored in the first database 213 when provided as a voice message of Chae Shira. The voice message " Happy Birthday " recorded by the voice of the Virgin Mary and " Congratulations " recorded by the voice of Chae Shira are searched for and edited by the voice editing synthesizing means 217, respectively. The voice message generated by the editing is sent to the voice message storage device 120 or the text message transmission and voice message receiving terminal 202, and the voice message providing operation is terminated.

If it is determined in step 309 that only editing is necessary, the server 211 proceeds to step 315 to check whether only synthesis is necessary. If it is checked, if only synthesis is needed, step 317 is reached. In operation 317, the server 211 searches the second database 215 based on the expression information of the specific person received with the text message. In step 319, the voice editing unit 217 performs the synthesis processing on the phoneme data found in the phoneme unit. In step 321, the server 211 stores the voice message generated by the synthesis processing. Sending to the device 120 or the text message transmission and voice message receiving terminal 202, and terminates the voice message providing operation.

As a result of checking in step 315, if only the synthesis is necessary, the server 211 proceeds to step 323 to check whether both synthesis and editing are necessary. As a result of the check, if all are necessary, the server 211 proceeds to step 325 in which the first database 213 and the second database 215 are based on the received text message and the voice and expression type information received therewith. ) Respectively. Then, in step 327, the speech processing of the phoneme unit retrieved from the second database 215 is performed through the voice editing synthesizing means 217, and in step 329, the first voice is synthesized through the voice editing synthesizing means 217. The voice message retrieved from the database 213 and the voice message synthesized in step 327 are edited. Next, in step 331, the voice message generated by the synthesis and editing process is sent to the voice message storage device 120 or the text message transmission and voice message receiving terminal 202, and the voice message providing operation is terminated.

If it is checked in step 323 that both composition and editing are not necessary, the server 211 proceeds to step 333 to perform error processing on the currently received text message and to end the operation.

On the other hand, if the received text message is a fixed message and some of the modifications are requested, the server 211 generates a corresponding voice message through the above-described editing process or the process requiring editing and synthesis. .

According to the present invention described above, it is possible to provide a voice message corresponding to a text message in the form of a desired expression of a specific person with high recognition or preference, thereby enhancing the delivery effect of the voice message and improving the quality of the voice message providing service. There is.

Claims (12)

A voice message providing system for transmitting a voice message corresponding to a text message received through a wired or wireless communication network through a wired or wireless communication network, A first database storing at least one fixed voice message recorded with the voice of at least one specific person; A second database storing voice data of phoneme units of at least one specific person; Voice editing synthesizing means for performing or editing or synthesizing the voice message or the voice data to provide the corresponding voice message; When the text message is received, the first database and the second database are searched according to the editing or synthesizing, the searched voice message or the voice data is transmitted to the voice editing synthesizing means, and then the voice editing synthesis is performed. And a server for transmitting the voice message transmitted from the means to the corresponding voice message. The system of claim 1, wherein the second database includes voice data of phoneme units capable of synthesizing a voice considering at least one expression form of the specific person. The method of claim 2, wherein when the server receives selection information for selecting at least one particular person among the specific persons and at least one expression form among the expression forms together with the text message, the server determines the first data based on the selection information. And a base and the second database are searched. The method of claim 1 or 2, wherein when the server receives the condition information for modifying a part of the text message together with the text message, the server determines the first database and the second database according to the condition information. Voice message providing system, characterized in that for searching. According to claim 1 or claim 2, wherein the server does not require a separate editing and synthesis to generate a voice message corresponding to the text message, the voice message retrieved from the first database to the corresponding voice Voice message providing system characterized in that the transmission to the message. The system of claim 1 or 2, wherein the server is connected to a terminal capable of recording or reproducing a voice message transmitted through the wired / wireless communication network on a recording medium connected or connected thereto. The apparatus of claim 1 or 2, wherein the server stores a voice message transmitted through the wired / wireless communication network and is connected to a voice message storage device for transmitting the voice message to a connected wired / wireless terminal. Voice message provision system. In a voice message providing method for transmitting a voice message corresponding to a text message received through a wired or wireless communication network through a wired or wireless communication network, (a) constructing a first database storing at least one fixed voice message recorded with the voice of at least one specific person; (b) constructing a second database storing voice data of phoneme units of at least one specific person; (c) if the text message is received, searching the first database and the second database; and (d) transmitting a voice message generated by editing, synthesizing, or editing and synthesizing the data retrieved in step (c) as the corresponding voice message. The method of claim 8, wherein the step (b) comprises: constructing the second database such that the voice data of the phoneme unit includes voice data capable of synthesizing the voice in consideration of at least one expression type of the specific person. Characterized in that the voice message providing method. 10. The method of claim 9, wherein the step (c) further comprises, if the selection information for selecting at least one of the specific persons and at least one of the expression forms is received together with the text message, based on the selection information. And searching the first database and the second database. 10. The method of claim 8 or 9, wherein in the step (c), when the condition information to modify a part of the text message is received together with the text message, the first database and the second database according to the condition information. A method for providing a voice message, comprising searching a database. 10. The method of claim 8 or 9, wherein step (c) searches only the first database when no additional editing and composition is necessary to generate a voice message corresponding to the text message. Voice message providing method.