KR20020028501A - Method for conversion between sound data and text data in network and apparatus thereof - Google Patents

Abstract

PURPOSE: A conversion method between voice data and text data in a communication network and a system thereby are provided to service voice data and text data under various environments. CONSTITUTION: An IVR(Interactive Voice Response) unit or a VoIP(Voice over Internet Protocol) gateway receives a message and the data for the destination of the message from a user's terminal(200). The IVR unit or the VoIP gateway transmits information containing the received message and the data for the destination of the message to a dictation server(210). If the transmitted message is text data, the dictation server converts the text message into voice data. In case that the transmitted message is voice data, the dictation server converts the voice message into text data. Then the dictation server transmits the converted message to an SMS(Short Message Service) server together with the data for the destination of the message(220). The SMS server receives the converted message and transmits to the destination of the message(230).

Description

Method for conversion between sound data and text data in communication network and device therefor {Method for conversion between sound data and text data in network and apparatus}

The present invention relates to message processing through a communication network, and more particularly, to a method and apparatus for converting voice data and text data to and from each other in a communication network.

Conventional SMS (Short Message Service) provides a service that is transmitted to the other party through the terminal of the other party via text or voice when the text input by using the keyboard of the mobile phone or PC. While it provides a great deal of convenience, it is necessary to have a means to enter characters using the keyboard, which can be used. That is, in order to use this service, an environment (for example, a keyboard) must be provided for the party to which the message is to be transmitted, and the environment for receiving a certain amount of environment (for example, a voice can be heard). Terminal) should be provided.

Therefore, in order to use a conventional SMS, a message must be input by text, and there is a problem that a mobile phone or a computer capable of text input must be used for this purpose.

In addition, when the other party is using a regular phone or a mobile phone, the other party can hear the contents of the call by voice, but does not provide a function of transmitting the contents of the call to the other party by text. In an environment where the other party cannot hear a voice, for example, an environment using a device such as a computer that cannot hear a voice, it may be inconvenient to communicate with the other party by telephone.

SUMMARY OF THE INVENTION The present invention has been made in an effort to provide a method for servicing voice data and text data in various terminal environments in order to solve the above problems.

Another technical problem to be solved by the present invention is to provide an apparatus for servicing voice data and text data in various terminal environments in order to solve the above problems.

Another technical problem to be solved by the present invention is to provide a computer readable recording medium having recorded thereon a program for servicing voice data and text data in various terminal environments in order to solve the above problems.

1 shows a brief illustration of a communication network environment in which the present invention is implemented and its configuration.

2 is a flowchart illustrating a method of serving voice data and text data according to the present invention.

According to the present invention for solving the above technical problem, a dictation server providing a function including converting a voice into a character corresponding thereto or a character into a voice corresponding thereto, a public line of data including the voice Between voice data and text data in a communication network connected to a PSTN, an interactive voice response means, a VoIP gateway that is transmitted through the Internet, or a SMS transmission server. The conversion method includes the steps of: (a) receiving, at the interactive voice response means or VIP gateway, a message sent by a user through a predetermined terminal device and data on the destination of the message; (b) transmitting information, including the message received at the interactive voice response means or BIP gateway and data about the destination of the message, to the dictation server through the communication network according to a predetermined protocol; and (c) converting the transmitted message from the dictation server into voice corresponding to the text data, and converting the voice data into text data corresponding to the voice data and the destination of the message. Transmitting the converted message as a result of the service determined as information about the destination to the short message transmitting server together with the data about the destination; And (d) the short message transmitting server receiving the converted message and transmitting the converted message to a destination determined by the data for the destination.

At this time, the terminal device of step (a) is a wired terminal for transmitting a message through a public switched telephone network (PSTN), a mobile communication terminal for transmitting a message over a mobile communication network and an electronic device connected to the communication network using the Internet protocol It is preferable to include the calculation means.

In this case, the destination may preferably include a wired terminal for transmitting a message through a public circuit switched telephone network, a mobile communication terminal for transmitting a message through a mobile communication network, and electronic computing means connected to the communication network using an Internet protocol. .

According to the present invention for solving the other technical problem, a dictation server that provides a function including converting a voice to a character corresponding to it or a character to the corresponding voice, the data including the voice Voice and text data in the network connected to the PSTN's Interactive Voice Response means, the VoIP gateways delivered via the Internet, and SMS servers. The apparatus for translating each other may include means for transmitting a message sent by a user through a predetermined terminal device and data about a destination of the message to the interactive voice response means or VIP gateway; Means for transmitting information, including a message received at the BIP gateway and data about a destination of the message, to the dictation server through the communication network according to a predetermined protocol; If the transmitted message is text data, the service is determined by information about the terminal device of the user and the type of the message and the destination of the message, which includes converting the voice data into the corresponding voice and the voice data into the corresponding text data. Means for sending the resulting message converted at the dictation server to the short message transmission server together with the data for the destination; And means for forwarding the message according to the nature of the destination when the short message transmission server receives the converted message and transmits the converted message to the destination determined by the data for the destination.

According to the present invention for solving the another technical problem, a dictation server that provides a function including converting a voice to a character corresponding to it or a character to the corresponding voice, a data including the voice Voice data and text on a communications network connected to a public voice switch (PSTN), a Voice over IP (VoIP) gateway, or a Short Message Server (SMS) server. The computer-readable recording medium which records a program for converting data to and from each other includes: (a) a message transmitted by a user through a predetermined terminal device and data on the destination of the message; Receiving at; (b) transmitting information, including the message received at the interactive voice response means or BIP gateway and data about the destination of the message, to the dictation server through the communication network according to a predetermined protocol; and (c) converting the transmitted message from the dictation server into voice corresponding to the text data, and converting the voice data into text data corresponding to the voice data and the destination of the message and destination of the message. Transmitting the converted message as a result of the service determined as information about the destination to the short message transmitting server together with the data about the destination; And (d) the short message transmitting server receiving the converted message and transmitting the converted message to a destination determined by the data for the destination.

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

1 shows a brief illustration of a communication network environment in which the present invention is implemented and its configuration. The communication network 100 transmits and receives data by the TCP / IP protocol. Servers such as dictation server 110, VIP server 120, short message transmission server 130, web server 140 and DB server 150 is connected to this communication network. In addition, an interactive voice response (hereinafter referred to as IVR) means 160 to which an interactive voice technology is applied is connected to a public circuit switched network (PSTN) 122.

The Internet is a representative example of a communication network. Servers such as the dictation server 110, the VOIP server 120, the SMS server 130, the web server 140, the DB server 150 and the IVR means 160 in the communication network 100 as described above. The environment in which the devices are connected may be referred to as a communication network in which the present invention operates. In the following description, it will be described without distinguishing between a single communication network and a communication network to which servers are connected.

The dictation server 110 provides a function that includes converting a voice into a text corresponding thereto or a text into a voice corresponding thereto. VOIP gateways (hereinafter referred to as `` VOIP gateways '') deliver voice-containing data over the Internet using Internet protocols or IVR means 160 connected to a public switched telephone network (PSTN). In addition, the short message service (SMS) server 130 (hereinafter, referred to as an SMS server) performs a function of transmitting a short message. The web server 140 allows the communication network 100 to be connected to the internet network 142, and the DB server 150 stores data necessary for operating the communication network in a database.

The VOIP gateway 120 may be connected to a telephone 126 via a public switched telephone network (PSTN) 122 through a PBX 124 that is an exchange, and a wireless telephone 129 through a mobile telephone network 128. have. The SMS server 130 for short message transmission may also be connected to the PSTN 122 or the mobile telephone network 128 to transmit a message. In addition, the web server 140 is connected to the Internet network 142, which is connected to an electronic computing device 144 such as a personal computer.

The IVR means 160 is coupled to the PSTN 122 and provides the ability to respond voicely to the response of a mobile or regular telephone. The IVR means 160 is a device that internally performs a protocol processing function and transmits value-added information through voice media by incorporating a database search function and voice guide language support function for voice-related data.

In addition to the configuration as shown in FIG. 1, servers having different functions may be connected to the communication network 100 according to a method of operating a communication network. For example, a gatekeeper can be connected that functions such as Internet address translation, call control, and network bandwidth management.

2 is a flowchart illustrating a method of serving voice data and text data according to the present invention.

This method of serving voice data and text data in a communication network to which the dictation server 110, the VOIP gateway 120, and the SMS server 130 is connected is provided. Receive data from the IVR means 160 or the VOIP gateway 120 (step 200), and receive information including the message received from the IVR means 160 or the VOIP gateway 120 and data about the destination of the message. According to the protocol, the communication is transmitted to the dictation server 110 through the network 100 (step 210). If the message transmitted from the dictation server 110 is text data corresponding to the voice, and if it is voice data, the text data corresponding thereto. Converted into a result of the service determined by the terminal device of the user and the type of message and information about the destination of the message, which includes converting The message is sent to the SMS server 130 along with the data about the destination (step 220), and the SMS server 130 receives the converted message and sends the converted message to the destination defined by the data for the destination. In step 230, the message is transmitted.

Hereinafter, the operation of the present invention will be described in detail with reference to the embodiment using the configuration of FIG. 1 and the method of FIG.

Calling another person using a conventional regular telephone is either a regular call over the PSTN or a call using the Internet protocol, or voice transmission, and the user's voice sent to another person by e-mail, i.e., by text. It does not use the method of transmission.

The user transmits a message to another person using the terminal device (step 200). A terminal device that can be used by a user includes a wired terminal 126 that transmits a message through a public switched telephone network (PSTN) 122, a mobile communication terminal 129 that transmits a message through a mobile communication network 128, and a user. It is preferable to include the electronic calculation means 144 connected to the communication network to be connected through the Internet network 142 using the Internet protocol.

As the wired terminal 126, a typical landline telephone is representative. Calls using the telephone will be connected to the PSTN 122 through an exchange, such as a PBX 124, which is an on-premises exchange, and is connected to the VOIP gateway 120 through an exchange device for the PSTN. In the case of a private telephone that does not use an on-premises exchange, it will be connected directly to the PSTN 122. The call through the mobile communication terminal 129 connects the mobile telephone network 128 to the VOIP gateway 120 through an exchange for the mobile telephone network. The connection through the web server 140 is then connected to the VOIP gateway 120 through the Internet network 142 using an electronic computing means 144 such as a personal computer.

At this time, the user inputs information on the destination to which his message is delivered. The destination preferably includes a wired terminal for transmitting a message via a public switched telephone network (PSTN), a mobile terminal for transmitting a message via a mobile communication network and electronic computing means connected to the communication network using an Internet protocol. At this time, if the destination is a wired or wireless telephone, the other party's phone number, if the destination is the other's computer, the other party's e-mail address or the other computer's IP address will be information about the destination.

This message may be sent to IVR means 160 when the user transmits the message using a terminal device such as a telephone. In particular, in FIG. 1, when voice data and text data are converted between a mobile phone and a regular phone or only between a regular phone (that is, without considering the PC of reference number 144), the message sent from the phone is transmitted to the IVR means 160. The message is transmitted from the IVR means 160 to the dictation server 110. In this case, the message is processed through the same process as in the case of the above-described message except that the VOIP gateway 120 does not go through.

This section describes how to make it easy to enter the destination address, such as the other party's phone number or the address of the other party's computer, and the contents to be delivered.

The telephone is used to dial the number for using the service according to the present invention. This number is a service identification number and will be a unique number for using the service according to the invention. The voice guidance provided through the voice information system (VMS) for this telephone selects a service that includes the user converting the voice to text or the text to voice. For example, if the destination of the message is a phone, enter the phone number. If the other party's computer, enter the computer's IP address, or if the destination is the other party's e-mail address, enter the address. In this case, if the destination is the other party's e-mail address, it is possible to select whether the user's message is transmitted to the other party by voice or text. After inputting the destination address, the voice information system prompts the user to input the content of the message to be delivered. This message may be voice or text data.

In the case of using the service according to the present invention using a computer, it is possible to access the web server 140 and select the service according to the present invention and input the phone number or address of the other party. In this case, if the destination is the other party's e-mail address, the user can select whether the user's message is transmitted to the other party by voice or text. Then enter the message you want to send to the person. The message could also be text data, or voice input using a device such as a microphone that can be connected to a computer.

As described above, the input message and the destination data are received by the VOIP gateway 120 (step 100). All calls or connections using the service according to the present invention are input to the VOIP gateway 120 and processed. Of course, in this case, a means (not shown) may be used to aggregate all requests for using the service according to the present invention into one and send them to the VOIP gateway 120. In either case, the gist of the present invention is not changed.

Information including the message received by the VOIP gateway 120 and data about the destination of the message is transmitted to the dictation server 110 through the communication network according to a predetermined protocol (step 210). Since the data transmitted through a communication network such as the Internet is packet data, a protocol for loading voice data in the packet data is required. The VOIP gateway 120 converts voice data so that it can be transmitted through the Internet. The VOIP gateway 120 converts voice data so that voice can be transmitted using the Internet protocol, as can be understood from the name of Voice over Internet Protocol (VOIP). It also serves as a gateway because it allows a network of other nature, such as a PSTN or a mobile telephone network, to be connected to the communication network 100 according to the present invention. At this time, the operating protocol in the communication network 100 uses TCP / IP. In other words, the communication network 100 becomes a TCP / IP communication network. However, this is just an example. If another device having a function for voice processing is used instead of the VOIP gateway 120, the communication network 100 will be a network using a protocol according to the device.

When the VOIP gateway 120 receives a message by voice, the VOIP gateway 120 converts the message into a format for loading on the Internet and transmits the message to the dictation server 110 through the communication network 100. May transmit to the server 110. As described above, the data of selecting the type of service or inputting the other party's address and phone number according to the voice information using the voice information system is also transmitted to the dictation server 110.

The conversion method in the VOIP gateway 120 is omitted because it is not related to the gist of the present invention. In addition, the VOIP gateway 120 may transmit the message and the destination information to the dictation server 110 by using a transmission means not shown in the figure. This means could be built into the VOIP gateway and implemented in a hardware or software way, or it could be implemented to connect to the VOIP gateway and send the converted data at the VOIP gateway. In either case, the subject matter of the present invention is not impaired.

If the transmitted message is text data, the dictation server 110 converts it to voice corresponding to the text message. If the message is voice data, the dictation server 110 converts the text data into text data. This is determined by information about the terminal device of the user, the type of the message, and the destination of the message. This has the same effect as converting or not converting depending on the contents of the service you choose. For example, if the user sends a message by voice to the other party's phone via a regular phone, there will be no need for conversion. In this case, conversion at the VOIP gateway 120 will be sufficient.

If the user intends to use the service according to the present invention to deliver a voice message to the other party or to send a text message to the other party by voice, the dictation server 110 receives the received message as the voice, the text is the voice. The object of the present invention can be achieved by only converting to. As described above, when the user selects a service, the dictation server 110 may selectively operate according to a case of converting or not converting a message. For example, if the user selects a corresponding service to send a voice message to the mobile phone 129 of the other party using a mobile phone 129 as a text message, the user inputs to the dictation server 110. The data may include the converted voice data and the voice data to be converted into text so that the VOIP gateway 120 can transmit the Internet. Therefore, the dictation server 110 converts the input voice data into text and transmits the text to the SMS server 130 together with the data about the destination. If the other party uses a computer and wishes to deliver the text to the other party, the dictation server 110 converts the voice message and transmits the voice message to the SMS server 130 along with the other party's address. Will be sent to the other party via computer.

If the destination chosen by the user is a regular phone and the user wants to have the message delivered by text, the normal phone cannot receive and display the text, so this service cannot be executed. In this case, since the error will occur at the final destination even after the conversion, the voice information system guiding the voice stops it or receives the error through the reverse process of the transmission path described above and informs the user of the correct service. You might be able to guide them through.

A simple description will be given of a method of converting a voice into a character corresponding to the voice or a character into a voice corresponding to the dictation server 110. When a voice or text, which is a user's message, is input, a processor such as a DSP (Digital Signal Processor) converts the input message into a waveform when it is spoken. The context is created by generating the corresponding character based on the data of. If the input message is text data, each letter is divided into a phoneme unit, a syllable unit, or a word unit, and voice data corresponding to each unit is determined to transmit the voice data. In this case, if the voice data is generated by converting the word unit, it may be converted similarly to the normal word. For example, the letters 'p', 'a', 's' and 's' are converted to 'pass' rather than 'P', 'A', 'S' and 'S'. The operation of the dictation server may take a different method from the above description, but the structure and operation of the dictation server are not directly related to the spirit of the present invention, and further description thereof will be omitted.

As described above, the information about the message and the destination, which are determined or not converted according to the information on the type of the terminal device and the message of the user and the destination of the message, or the service selected by the user, is transmitted to the communication network 100. Through the SMS server 130 is transmitted (step 220). This transmission can be performed by using a transmission means not shown in the figure. The transmission means may be implemented in a hardware or software method embedded in the dictation server 110, or may be implemented to be connected to the dictation server to transmit the result data through the dictation server. As in the case described above, any case can be executed without impairing the gist of the present invention.

The SMS server 130 transmits the received message to the destination determined by the data on the destination (step 230). At this time, if the destination is a regular phone, the data converted and transmitted from the dictation server 110 is voice data, and this data is transmitted to the phone 126 of the other party through the PSTN 122 so that the other party can listen to the user's message. . When a user sends a text message to a counterpart user who is a general phone user by using the mobile phone 129 or the computer 144, the text message may be transmitted by voice to the other party who uses the general phone. If the destination is a user using a mobile phone, the voice or text message transmitted from the SMS server 130 is transmitted to the other party through the service of the mobile communication operator operating the mobile phone network 128. If the destination is the computer of the other party, the SMS server 130 transmits the message to the Internet network 142 through the web server 140 and delivers the message to the computer 144 of the other party. The computer may store the received voice or text message and listen or view it by voice or text, depending on the recipient's choice.

The transmission from the SMS server 130 may be transmitted by the SMS server 130, and may be performed using a separate transmission means not shown in the drawing. The transmission means may be embedded in the SMS server 130 or implemented in a hardware or software manner, or may be implemented to connect to the SMS server and transmit data. As in the case described above, any case can be executed without impairing the gist of the present invention.

Through the above process, the user using the service provided by the present invention can enjoy a convenient communication environment converted between voice data and text data. According to the communication environment of the user and the other party, a communication environment for transmitting a message to the other party by converting a voice into a voice or a text and a text into a voice or a text is provided. That is, it is possible to input by voice, not text, and can use the service according to the present invention in a general telephone or a public telephone without a keyboard, and can use a text service to the other party by voice input through a microphone in a computer, and thus a restricted environment. Compared to the conventional SMS that operates only to facilitate the user's use.

Those skilled in the art will appreciate that the present invention can be implemented in a modified form without departing from the essential features of the present invention. Therefore, the disclosed embodiments should be considered in descriptive sense only and not for purposes of limitation. Examples included in the above description are introduced for the understanding of the present invention, and these examples do not limit the spirit and scope of the present invention. It will be apparent to those skilled in the art that various embodiments in accordance with the present invention in addition to the above examples are possible. The scope of the present invention is shown not in the above description but in the claims, and all differences within the scope will be construed as being included in the present invention.

In addition, it can be easily understood by those skilled in the art that each of the above steps according to the present invention can be variously implemented in software or hardware using a general programming technique.

And some steps of the invention may also be embodied as computer readable code on a computer readable recording medium. The computer-readable recording medium includes all kinds of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, CD-RW, magnetic tape, floppy disks, HDDs, optical disks, magneto-optical storage devices, and carrier wave (e.g. It also includes the implementation in the form of). The computer readable recording medium can also be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion.

According to the present invention, a dictation server providing a function including converting a voice into a corresponding text or a text into a corresponding voice, a VOIP gateway for transmitting data including the voice through the Internet, and an SMS server are connected. In a communication network, a message sent by a user through a predetermined terminal device and data about a destination of a message are received at a VOIP gateway, and information including the message received at the VOIP gateway and data about a destination of the message is transmitted to a predetermined protocol. And transmits the message converted to the dictation server through the communication network, and if the transmitted message is text data to the corresponding voice, and if the voice data is to the text data corresponding to the voice data, the message is converted to the dictation server. SMS with data about destination Sending the message to the server, the SMS server receives the converted message and transmits the message by transmitting the converted message to the destination determined by the data for the destination, flexibly according to the communication environment of the sender and receiver The ability to transmit text data provides a very convenient and free communication environment for sending and receiving messages to communication users.

Claims (15)

A dictation server that provides a function comprising converting a voice to a corresponding text or a text to a corresponding voice, interactive voice response to a public switched telephone network (PSTN) In a method of converting between voice data and text data in a communication network to which a Voice over IP (VoIP) gateway and a short message transmission (SMS) server are transmitted through a voice response means or the Internet, (a) receiving, at the interactive voice response means or VIP gateway, a message sent by a user through a predetermined terminal device and data on the destination of the message; (b) transmitting information, including the message received at the interactive voice response means or BIP gateway and data about the destination of the message, to the dictation server through the communication network according to a predetermined protocol; and (c) converting the transmitted message from the dictation server into voice corresponding to the text data, and converting the voice data into text data corresponding to the voice data and the destination of the message. Transmitting the converted message as a result of the service determined as information about the destination to the short message transmitting server together with the data about the destination; And (d) receiving, by the short message transmission server, the converted message and transmitting the converted message to a destination determined by the data for the destination to deliver a message. And how to convert character data to each other. The method of claim 1, And the terminal device of step (a) comprises a wired terminal for transmitting a message via a public switched telephone network (PSTN). The method of claim 1, The terminal device of step (a) comprises a mobile communication terminal for transmitting a message through a mobile communication network, the method of converting voice data and text data with each other in a communication network. The method of claim 1, And the terminal apparatus of step (a) comprises an electronic calculation means connected to the communication network using an internet protocol. The method according to any one of claims 1 to 4, The destination includes a wired terminal for transmitting a message through a public switched telephone network (PSTN), a mobile communication terminal for transmitting a message over a mobile communication network, and electronic computing means connected to the communication network using an Internet protocol. A method of converting voice data and text data in a communication network to each other. The method according to any one of claims 1 to 4, In step (a), a user selects a service including voice to text or text to voice by voice guidance provided through a voice information system (VMS), and inputs information on a destination of a message. Process, Information about the type of service selected by the user in step (b) is included in the information transmitted to the dictation server, In the step (c), if the service selected by the user in the step (a) is a service to be converted, the transmitted message is converted into voice corresponding to the text data, and if it is voice data, converted into text data corresponding thereto. If the service selected by the user is a service that does not want to convert, the method of converting the voice data and the text data to each other, characterized in that the data format of the transmitted message is not changed. A dictation server that provides a function comprising converting a voice to a corresponding text or a text to a corresponding voice, interactive voice response to a public switched telephone network (PSTN) In a device for converting voice data and text data to and from a communication network to which a Voice over IP (VoIP) gateway and a SMS server, which are transmitted through a VoiceResponse means or the Internet, Means for transmitting a message sent by a user through a predetermined terminal device and data on the destination of the message to an interactive voice response means or a VIP gateway of the public switched telephone network (PSTN); The dictation through the communication network according to a predetermined protocol, information including a message received from an interactive voice response means of the public switched telephone network (PSTN) or a BOE gateway and data about the destination of the message; Means for transmitting to a server; If the transmitted message is text data, and the voice corresponding to the data, if the voice data corresponding to the corresponding data and the type of the message and the destination of the service determined by the destination of the message and the destination Means for sending the resulting message converted at the dictation server to the short message transmission server together with the data for the destination; And Means for delivering the message according to the nature of the destination when the short message transmission server receives the converted message and transmits the converted message to the destination determined by the data for the destination. Device that converts voice data and text data of each other. The method of claim 7, wherein And said terminal device of said user comprises a wired terminal for transmitting a message via a public switched telephone network (PSTN). The method of claim 7, wherein And the terminal device of the user comprises a mobile communication terminal for transmitting a message through a mobile communication network. The method of claim 7, wherein And said terminal device of said user comprises electronic computing means connected to said communication network using an internet protocol. The method according to any one of claims 7 to 10, The destination includes a wired terminal transmitting a message through a public switched telephone network (PSTN), a mobile communication terminal transmitting a message through a mobile communication network, and electronic computing means connected to the communication network using an Internet protocol. A device for converting voice data and text data from each other in a communication network. The method according to any one of claims 7 to 10, The means for transmitting to the VIP gateway allows the user to select a service including voice to text or text to voice by voice guidance provided through a voice information system (VMS), and to the destination of the message. To enter information about the Information transmitted by the means for transmitting to the dictation server includes information on the type of service selected by the user, In this case, when the service selected by the user is a service that the user wants to convert, the dictation server converts the transmitted message into voice corresponding to text data, and converts into voice data corresponding to voice data. In the case of a service that does not want to convert, the apparatus for converting the voice data and the text data with each other in the communication network, characterized in that the data format of the transmitted message is not changed. A dictation server that provides the function of converting a voice into a corresponding character or a corresponding voice, and a VoIP gateway that transmits data including the voice through the Internet. A computer-readable recording medium having recorded thereon a program for converting voice data and text data from a communication network to which a short message transmission (SMS) server is connected, (a) receiving, at the VIP gateway, a message sent by a user through a predetermined terminal device and data on a destination of the message; (b) transmitting information including a message received at the BIP gateway and data about a destination of the message to the dictation server through the communication network according to a predetermined protocol; and (c) converting the transmitted message from the dictation server into voice corresponding to the text data, and converting the voice data into text data corresponding to the voice data and the destination of the message. Transmitting the converted message as a result of the service determined as information about the destination to the short message transmitting server together with the data about the destination; And (d) the short message transmitting server receiving the converted message and transmitting the converted message to a destination determined by the data for the destination to deliver the message. A computer-readable recording medium having a program for converting text and character data to and from each other. The method of claim 13, The terminal device of step (a) and the destination are each connected to a wired terminal for transmitting a message through a public switched telephone network (PSTN), a mobile communication terminal for transmitting a message through a mobile communication network, and the communication network using an Internet protocol. A computer-readable recording medium having recorded thereon a program for converting voice data and text data to and from a communication network. The method according to claim 13 or 14, In step (a), a user selects a service including voice to text or text to voice by voice guidance provided through a voice information system (VMS), and inputs information on a destination of a message. Process, Information about the type of service selected by the user in step (b) is included in the information transmitted to the dictation server, In the step (c), if the service selected by the user in the step (a) is a service to be converted, the transmitted message is converted into voice corresponding to the text data, and if it is voice data, converted into text data corresponding thereto. A computer-readable recording medium having recorded thereon a program for converting voice data and text data in a communication network if the service selected by the user is a service that does not want to be converted.