KR101055732B1 - Device and method for transmitting key button signal during call using voice recognition - Google Patents

Abstract

 The present invention relates to an apparatus and method for transmitting a key button signal during a call using voice recognition, comprising: switching to a voice recognition mode; Receiving a voice signal; Retrieving key signal data corresponding to the voice signal through voice recognition; And transmitting a DTMF signal corresponding to the retrieved key signal data, thereby making it possible to transmit personal information data through voice instead of key input. It can be transmitted by the method.

 Speech Recognition, DTMF, Personal Information Data

Description

 Apparatus and Method for transmission of DTMF which is caused by voice recognition for dialing}

 1 is a flowchart of a keypad input during a call according to the prior art.

2 is a block diagram of a mobile communication terminal according to the present invention.

3 is a flowchart illustrating a voice recognition setting step according to an embodiment of the present invention.

4 is an exemplary view showing a voice recognition setting step according to an embodiment of the present invention.

5 is a flowchart illustrating an embodiment of a call of the present invention.

 The present invention relates to a mobile communication terminal, and more particularly, to a data transmission method using a voice recognition function instead of key input of desired data during a call.

1 is a flowchart of a keypad input during a call according to the prior art.

In the conventional mobile communication terminal, when a call input is requested from the other party (resident registration number, account number, card number, password, etc.), the user repeatedly presses the telephone key button by hand until all the buttons are pressed correctly. It is a method of transmitting data. If the key input exceeds the range that can be displayed on the screen of the terminal during the conventional call as described above, it may be impossible to confirm whether the corresponding key is correctly pressed and transmitted. There must be a problem that occurs if the wait or repeat the operation, and the next instruction can not feel.

 Accordingly, the present invention has been made to solve the above-described problems, the purpose of which is the dual frequency multi-frequency (DTMF) through the voice recognition of the user's personal data transmission during the call rather than the key input method It is intended to facilitate a procedural method by switching to a signal and transmitting.

 Features of the present invention for achieving the above object, the step of switching to the speech recognition mode; Receiving a voice signal; Retrieving key signal data corresponding to the voice signal through voice recognition; And transmitting a complex frequency code (DTMF) signal corresponding to the retrieved key signal data.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Detailed descriptions of well-known functions and configurations that may unnecessarily obscure the subject matter of the present invention will be omitted.

2 is a block diagram of a mobile communication terminal according to the present invention.

The mobile communication terminal according to the present invention includes a voice processing unit 10, a voice recognition unit 20, a key input unit 30, a control unit 40, a memory unit 50, a wireless communication unit 60, a DTMF generation unit 70 ), The display unit 80 is provided. The voice processing unit 10 processes the voice recorded by the user of the mobile communication terminal through the microphone (MIC) as data and transmits it to the control unit 40 or processes the data received from the outside to analog through the speaker SPK. It is in charge of outputting voice. In the present invention, the digital processing of the voice data to the voice recognition unit 20 performs a function. The voice recognition unit 20 performs a function of extracting and recognizing a user's voice from the voice data applied from the voice processing unit 10. The speech recognition technology used in the present invention is simpler than speaker-independent speech recognition because only the speech recognition for a specific word of a specific person is required by speaker dependent isolated word recognition. Therefore, since the speech recognition solution developed so far can be solved by applying to the mobile communication terminal, a detailed description thereof will be omitted. The key input unit 30 inputs the personal information data corresponding to the voice signal in the mobile communication terminal to the control unit 40 by the numeric key button and the general button. The controller 40 controls all functions of the mobile communication terminal. In the present invention, in particular, in addition to an operation for a general mobile communication call, the controller 40 receives voice data of the user, and the voice data extracted by the voice recognition unit 20 and When the voice recognition mode is set, voice data stored in the memory unit 50 is compared and the corresponding data is output when the voice data is matched. The memory unit 50 stores programs and data necessary for the mobile communication terminal to operate, and various devices such as erasable programmable read only memory (EPROM), static random access memory (SRAM), and flash memory may be used. According to the present invention, an input voice signal corresponding to a key signal and a program required for setting a voice recognition mode are stored. The complex frequency code (DTMF) generator 70 outputs a frequency sum of two sine waves according to a key signal received from the controller 40.

  Table 1 shows an example of a composite frequency code (DTMF) signal according to a key input of a mobile communication terminal.

1209 Hz
1336 Hz
1447 Hz
697 Hz

One
ABC
2
DEF
3
770 Hz

GHI
4
JKL
5
MNO
6
852 Hz

PRS
7
TUV
8
WXY
9
941 Hz

*
OPER
0
#

When receiving the number 3 from the key input unit according to Table 1, the DTMF generator outputs the corresponding 1477Hz and 697Hz simultaneously. The signal is applied to the wireless communication unit 60, converted into a wireless communication frequency band, and then transmitted to the outside through an antenna. The display unit 80 displays various menu screens, execution screens, and result screens in the mobile communication terminal under the control of the controller 40. In the present invention, the result after input of the voice signal is displayed on the screen.

3 is a flowchart illustrating a voice recognition setting step according to an embodiment of the present invention.

In step S300, the voice menu setting key input is confirmed and the voice menu registration key input is confirmed. (S301) In step S302, the control unit 40 displays a registration menu item on the display unit. The program is driven (S303). At the same time as receiving the numeric key input through the key input unit 30 receives a voice input through the microphone (S304). The controller 40 inputs the key input signal applied in step S305 and the voice data digitally signaled through the voice processor 10 to the voice recognition unit 20 to perform pattern matching between the two signals. A composite frequency code (DTMF) signal is output according to the key input signal, and the controller 40 converts the voice data into a composite frequency code (DTMF) signal (S306). The control unit 40 stores the voice data in the memory unit 50 (S307). If there is a key input corresponding to the voice recognition registration completion, the program is terminated, and if not, the process is repeated in step S304.

4 is an exemplary view showing a voice recognition setting step according to an embodiment of the present invention.

In FIG. 4, (a) illustrates a process of registering a 'number' as a voice in the voice menu by using the terminal display unit. Simultaneously receives voice and processes data. If there is additional key input, repeat voice recognition process. You can enter numeric keys (0 to 9), asterisks ('*'), ('#'), and so on. (b) shows the process of registering the 'account number' in the personal information data on the terminal display unit. After receiving the numeric key corresponding to the account number and outputting a specific sound through the speaker, and receives a voice signal indicating the account number. Voice recognition is performed by data processing of the input key signal and voice signal.

5 is a flowchart illustrating an embodiment of a call of the present invention.

In step S500 performs a call through a communication network. In step S501 to confirm the key input to switch to the voice recognition mode during the call. After switching the mode, a specific sound is output through the speaker and voice is input through the microphone. The input voice is displayed through the display unit or the speaker (S502). The controller 40 performs pattern recognition on the digital signaled voice data through the voice recognition unit 20 to output voice data stored in the memory unit 50. At this time, the control unit 40 transmits the composite frequency code (DTMF) signal to the output voice data (S503). The voice data converted into the DTMF signal is transmitted through the wireless communication unit 60 (S504). If there is a key signal input to which the voice input is completed (S505), the voice recognition mode is released. (S506) If there is no key signal, the process proceeds to step S502 to perform an iterative process.

 As described above, the present invention provides a method of transmitting a key button signal during a call by voice recognition, so that personal information data can be transmitted through voice instead of key input, thereby facilitating a procedural method as well as providing a safer method. Transmission is possible.

Claims (12)

 Switching to a voice recognition mode; Receiving a voice signal; Retrieving key signal data corresponding to the voice signal through voice recognition; Transmitting a complex frequency code (DTMF) signal corresponding to the retrieved key signal data; Method of transmitting a key button signal during a call using a voice recognition made, including.  The method of claim 1,  And displaying the retrieved key signal data by using a liquid crystal display of the terminal.  The method of claim 1, The displaying of the retrieved key signal data is a method of transmitting a key button signal during a call using voice recognition, characterized in that the voice output through the speaker.  The method of claim 1, The input voice signal is a key button signal transmission method during a call using voice recognition, characterized in that the personal information data such as password, account number, social security number and card number.  The method of claim 4, wherein The method of transmitting a key button signal during a call using note recognition, characterized in that the personal information data corresponding to the input voice signal is stored in the memory unit.  The method of claim 1, When a voice corresponding to one key input signal is input at a time interval, the key button signal transmission method during a call using voice recognition, characterized in that for searching and representing the corresponding key signal data.  The method of claim 1, The method of transmitting a key button signal during a call using voice recognition, characterized in that when a voice is input with a name representing personal information data, the corresponding key signal data is searched and displayed collectively.  The method of claim 1, Converting the input voice signal into a digital signal; Receiving a key signal corresponding to the digital signal; Generating a complex frequency code (DTMF) signal according to a key input signal; Storing complex frequency code (DTMF) signal data matching the voice signal; Method of transmitting a key button signal during a call using voice recognition, characterized in that the voice recognition setting is made, including.  The method of claim 8, The input voice signal is a method for transmitting a key button signal during a call using voice recognition, characterized in that for generating a compound frequency code (DTMF) signal corresponding to the allocation region of the language mode, numeric mode, special character mode.  A voice processor for encoding an analog voice signal into a digital signal and decoding the digital voice signal into an analog voice signal; A speech recognition unit for extracting speech feature data from the speech signal applied by the speech processor to perform a recognition process; A key input unit having key buttons for inputting personal information data and calling a complex frequency code (DTMF) signal; A controller for matching the key signal input from the key input unit with the voice data input from the voice recognition unit and outputting matching data by comparing with the voice signal input when the voice recognition mode is switched; A memory unit for storing voice data corresponding to a key signal and a program required for setting a voice recognition mode; A composite frequency code (DTMF) generator for outputting a sum of frequencies of two sine waves according to a key signal received from the controller; Apparatus for transmitting a key button signal during a call using voice recognition, including.  The method of claim 10, Voice recognition technology in the speech recognition unit is a speaker dependent isolated word recognition technology (Speaker Dependent Isolated Word Recognition) is a key button signal transmission device during a call using a speech recognition, characterized in that the speech recognition for a specific word of a specific person is made .  The method of claim 10, The signal transmission device is a key button signal transmission device during a call using voice recognition, characterized in that the mobile communication terminal or a communication terminal.

Images