KR20020087297A - KIOSKs having function of handling voice signal - Google Patents

Abstract

PURPOSE: A kiosk having a voice processing function is provided to execute input/output process by a voice and to process a graphic having a specific purpose such as a finger language. CONSTITUTION: The kiosk comprises an input tool having a key input tool(111) or a touch screen tool(112), an output tool for driving a monitor(142), an information database(130) storing the service information, and a central processing part(120). The central processing part extracts a respond information according to an input code from the input tool while guiding a using method through the monitor and transfers the extracted data in a signal displayed on the monitor to the output tool. The input tool also includes a microphone(151) inputting the voice of a user and a voice recognition part(152). The voice recognition part transfers the input code to the central processing part after understanding the input code ordered by the user's voice by analyzing the user's voice inputted from the microphone as an analog mode.

Description

KIOSKs having function of handling voice signal}

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a kiosk having a voice processing function, and more particularly to a kiosk capable of inputting or outputting by voice and processing a graphic screen for a specific purpose such as a sign language graphic screen.

Currently, KOSKs of various types, such as cash dispensers, bus route guides, and tourist guides, are installed and operated in many places. The utilization rate of these kiosks is increasing day by day, and applied to various fields.

1 is a schematic configuration diagram of a conventional kiosk, the input means for allowing a user to input a desired item, the key input means 111 for inputting via a key, the specific item on the screen by hand It is provided with a touch screen means 112 to enable input by touching.

The input code input through the input means 111 and 112 is transmitted to the central processing unit 120, and the central processing unit 120 guides the use of the kiosk through the monitor 142 while inputting from the input means 111 and 112. The response information is extracted with reference to the informational database 130 according to the code.

The response information extracted by the central processing unit 120 is transmitted to the outside through the output means so that the user can contact, and is generally displayed on the screen of the monitor 142. Therefore, the response information has a data structure in a form that can be displayed on the monitor 142 and is output to the monitor 142 through the monitor interface 141. Here, the information database 130 is a component that stores various service target information, and the monitor interface 141 refers to a component for controlling a monitor such as a video board (VGA card).

As described above, the conventional kiosk has only means for the user to directly use his or her hand, such as a keyboard or a touch screen. As a result, the handicapped have difficulty in using the kiosk. In addition, since it is true that voices are more convenient than normal hands, it is necessary to combine the voice processing function with the kiosk, so that the kiosk can be used more conveniently.

Accordingly, the present invention has been invented in order to meet the necessity as described above, and an object thereof is to provide a kiosk capable of inputting or outputting by voice and processing a graphic screen for a specific purpose such as a sign language graphic screen. .

In order to achieve the above object, the present invention analyzes the microphone for inputting the user's voice as an input means, and the input code indicated by the user's voice by analyzing the user's voice in the form of an analog input to the microphone and then identified And a voice recognition unit for transmitting an input code to the central processing unit.

The output means is preferably configured to further include a voice synthesizer for synthesizing the response information extracted by the central processing unit into an analog voice signal, and a speaker for externally outputting the voice signal synthesized by the voice synthesizer. Can be done.

The output unit may include a graphic information storage unit for storing various graphic information required for graphic output and a graphic screen corresponding to the response information transmitted from the central processing unit by referring to the graphic information storage unit and outputting the synthesized graphic screen to the monitor. It can be carried out more preferably by further including a graphic synthesizing unit to be processed.

In this case, if the graphic information storage unit is configured to include graphic information about the sign language operation, and the graphic synthesis unit is configured to synthesize the response information into the corresponding sign language graphics, disabled people can use the kiosk more conveniently.

1 is a block diagram of a conventional kiosk,

2 is a block diagram of a preferred embodiment of the kiosk according to the present invention,

3 is a flowchart illustrating an operation of a voice recognition unit;

4 is a flowchart of an embodiment of a voice recognition process;

5 is a flowchart illustrating an operation of a speech synthesis unit;

6 illustrates an embodiment of the operation of the graphic synthesizing unit.

* Explanation of symbols for the main parts of the drawings

100: kiosk 111: key input means

112: touch screen means 120: central processing unit

130: Informational Database 141: Monitor Interface

142: monitor 150: voice input means

151: microphone 152: voice recognition unit

153: voice data storage unit 161: voice synthesis unit

162: speaker 171: graphics synthesis unit

172: graphic information storage unit

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

Referring to FIG. 2, the kiosk 100 according to the present invention includes voice input means 150 for allowing a user to operate the kiosk 100 by voice. The voice input means 150 is preferably provided with the conventional key input means 111 or the touch screen means 112, but may be provided with only the voice input means 150, if necessary.

The user inputs a desired item by using the microphone 151 provided in an internal or external form, and the voice input by the user is transmitted to the voice recognition unit 152. Here, the microphone 151 is preferably configured as a directional microphone, because the kiosk 100 is generally located in a public place, so that ambient noise can be mixed.

To describe an example of an item input by the user with reference to the case where the kiosk is a cash dispenser, "cash service", "cash withdrawal", "correction", "100 thousand won", "confirmation", etc. are spoken.

Referring to FIG. 3, the function of the voice recognition unit 152 will be described. When the voice of the user is input through the microphone 151 (S310), the user voice in analog form is analyzed and the user voice is interpreted. After grasping the indicated input code (S320), it transmits to the central processing unit 120 (S330).

Herein, the input code means a code to be input to the central processing unit 120, and the same code as the code transmitted to the central processing unit 120 when the corresponding item is selected by the key input unit 111 or the touch screen unit 112. . That is, the voice recognition unit 152 determines which service item the voice spoken by the user relates to and delivers the service item.

4, the voice recognition unit 152 first detects the start point and the end point of the voice signal input through the microphone 151 (S321). The feature of the audio signal is extracted (S322). Here, step S321 may include a filtering process for amplifying the input voice signal and removing noise outside the audible frequency band.

The most similar voice data code is determined by comparing the feature data extracted in step S222 with the voice data code previously stored in the voice data storage unit 153 (S323). Here, the feature data means a general "feature parameter" used in speech recognition technology. Then, the input code corresponding to the determined voice data code is grasped (S324) and transmitted to the central processing unit 120 (S330).

Now, according to the input code transmitted from the voice recognition unit 152, the central processing unit 120 retrieves the response information for the corresponding selection item from the information database 120 and transmits it to each output means. . The central processing unit 120 is generally implemented by a microprocessor, and its configuration is generally widely used, so a detailed description thereof will be omitted.

The response information retrieved from the central processing unit 120 is transmitted to the voice synthesizer 161 and the graphic synthesizer 171. The voice synthesizer 161 outputs the response information by voice and the graphic synthesizer 171. The response information is output in the form of a graphic-processed screen such as a sign language for the deaf.

In this case, it is preferable that the central processing unit 120 has a form of a character string in response information transmitted to the voice synthesizing unit 161 and the graphic synthesizing unit 171.

Referring to FIG. 5, a function performed by the voice synthesizer 161 will be described. When the voice synthesizer 161 receives response information in the form of a string transmitted from the central processing unit 120 (S510), the voice string is received. After synthesized into an analog voice signal (S520), the synthesized voice signal is output through the speaker 162.

Here, a technique for synthesizing a string into a voice is widely known, and it is generally implemented through morphological analysis, syntax analysis, sentence preprocessing, realization of rhyme, and speech waveform synthesis. The present invention does not have a point in the speech synthesis technology itself, but since the present invention applies the conventional speech synthesis technology to a kiosk, a detailed description of the speech synthesis technology will be omitted.

The graphic synthesizing unit 171 performs a function of outputting the response information transmitted from the central processing unit 120 in a special graphic form.

Referring to FIG. 6, when the graphic synthesizing unit 171 receives response information in the form of a string transmitted from the central processing unit 120 (S610), the graphic information storage unit stores various graphic information necessary for graphic output. In operation 172, the graphic information defined as displaying the corresponding response information is searched and synthesized (S620), and then processed to be displayed on the monitor 142 (S630).

In a preferred embodiment, if the graphic information storage unit 172 is configured to include graphic information about the sign language operation, and the graphic synthesis unit 171 is configured to synthesize the response information to the sign language graphics, for the hearing impaired This can be a very good embodiment. Of course, in this case, the user may input the kiosk using a touch screen.

For example, when the kiosk 100 is a kiosk for guiding a road, a message for guiding a desired path is output through a sign language screen. The sign language screen does not limit the form whether the entire person is animated or only hands are sign language.

The speech recognition function performed by the speech recognition unit 152 and the speech synthesis function performed by the speech synthesis unit 161 have been developed and applied to various techniques, and the present invention is limited to a specific speech recognition technique or a speech synthesis technique. It is not. In addition, the speech recognition technology or the speech synthesis technology may be any technology conventionally developed and applied as needed, and the form may be a hardware implementation using a DSP chip, which is controlled by the central processing unit 120. It may also be a software implementation by a computer program.

When using the present invention, the kiosk located in a number of places, such as public places can be used through the voice, the use of the kiosk is more convenient. In particular, by outputting the voice output and sign language graphics screen at the same time can be very convenient for the disabled.

Claims (6)

The input means having key input means and / or touch screen means, an output means for driving a monitor, an information database for storing service target information, and the input while guiding a usage method on the monitor through the output means. In a kiosk comprising a central processing unit which extracts response information with reference to the information database according to an input code input from the means and transmits the response information to the output means as a signal that can be displayed on the monitor. , The input means includes a microphone for inputting a user's voice; And a voice recognition unit for interpreting the user's voice in the analog form to be input by the microphone to grasp the input code indicated by the user's voice, and transmitting the determined input code to the central processing unit. Kiosk with processing capabilities. The method of claim 1, wherein the output means A voice synthesizer for synthesizing the response information extracted by the central processing unit into an analog voice signal and a speaker for outputting the voice signal synthesized by the voice synthesizer to the outside, The central processing unit is a kiosk having a voice processing function, characterized in that configured to pass the response information as the data in the form of a string to the voice synthesis unit. The method of claim 2, wherein the output means A graphic information storage unit for storing various graphic information necessary for graphic output and a graphic screen corresponding to the response information transmitted from the central processing unit by referring to the graphic information storage unit, and then processing the graphic to be output to the monitor Kiosk having a speech processing function, characterized in that further comprising a synthesis unit. The method of claim 3, wherein And the graphic information storage unit is configured to include graphic information about a sign language operation, and the graphic synthesis unit is configured to synthesize the response information into a corresponding sign language graphic. The method according to any one of claims 1 to 4, The microphone is a kiosk having a voice processing function, characterized in that the directional microphone. The method according to any one of claims 1 to 4, The voice recognition unit A function of detecting a start point and an end point from a voice signal input through the microphone; Extracting features of the detected voice signal; A function of discriminating the most similar voice data code by comparing the feature of the extracted voice signal with a predetermined voice data code; And And a function of finding an input code corresponding to the determined voice data code and delivering the same to the central processing unit.