KR100247009B1 - Digital cellular telephone capable of recognizing a vioce and method for recognizing the voice - Google Patents

Abstract

A method of registering a function mode voice of a digital portable telephone, comprising: a first process of checking flip on / off in a standby state and switching to a voice recognition mode upon detecting a flip on; and registering a function mode voice after switching to the voice recognition mode And a second process of selecting a function mode, and if the function mode voice registration is selected, inputs a predetermined function key and then processes and inputs a voice that speaks a function corresponding to the function key. A third process of reproducing a voice, a fourth process of secondly inputting a voice that speaks a function corresponding to the function key after reproducing the first voice, and characteristics of the first and second input voices And a fifth step of registering the voice in a function mode corresponding to the function key if detected and compared with each other, and checking the similarity.

Description

DIGITAL CELLULAR TELEPHONE CAPABLE OF RECOGNIZING A VIOCE AND METHOD FOR RECOGNIZING THE VOICE}

The present invention relates to a digital portable telephone, and more particularly, to a digital portable telephone for registering and recognizing a function mode by voice and a control method thereof.

Mobile phones often use their phones while driving a car or doing other tasks. In this respect, various operations or dialing using the keypad, which is an existing user interface means, may be inconvenient or dangerous. Although the voice dialing is somewhat convenient, the voice recognition function added to the conventional portable phone still leaves room for improvement because only the phone dialing function is registered as a voice.

Accordingly, an object of the present invention is to provide a digital portable telephone capable of recognizing a function mode as a voice and a recognition method thereof.

Another object of the present invention is to provide a method for registering a voice corresponding to each function mode so that the digital portable telephone can recognize the function mode as voice.

In accordance with another aspect of the present invention, there is provided a function mode voice registration method of a digital portable telephone, comprising: a first process of checking a flip on / off in a standby state and switching to a voice recognition mode when detecting a flip on; A second process of selecting a function mode voice registration after switching to the recognition mode; and if the function mode voice registration is selected, input a predetermined function key and then input a voice that speaks a function corresponding to the function key; A third process of reproducing the first input voice and a second process of inputting a second voice that speaks a function corresponding to the function key after reproducing the first voice; And a fifth process of detecting the characteristics of the first and second input voices, comparing them with each other, and checking the similarity and registering the voices in a function mode corresponding to the function key if similar. And a gong.

1 is a view showing the configuration of a digital portable telephone having a voice recognition function to which the present invention is applied

2 is a block diagram of a memory according to an embodiment of the present invention.

3 is a flowchart illustrating the overall operation of the digital portable telephone having a voice recognition function according to an embodiment of the present invention.

4 is a flowchart illustrating a function mode voice registration method according to an exemplary embodiment of the present invention.

5 is a flowchart illustrating a function mode speech recognition method according to an embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. First of all, in adding reference numerals to the components of each drawing, it should be noted that the same reference numerals have the same reference numerals as much as possible even if displayed on different drawings. Also, in the following description, many specific details such as components of specific circuits are shown, which are provided to help a more general understanding of the present invention, and the present invention may be practiced without these specific details. It is self-evident to those of ordinary knowledge in Esau. In the following description of the present invention, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the subject matter of the present invention, the detailed description thereof will be omitted.

In order to perform the voice recognition function, the voice itself is input and signal processing for extracting various features such as frequency characteristics from the input voice signal is performed.

1 illustrates a configuration of a digital portable telephone having a voice recognition function to which the present invention is applied. For the parts not directly related to the gist of the present invention, such as an RF (radio frequency) unit and a dual tone multu frequency (DTMF) unit, FIG. Illustration and description are omitted.

The analog voice signal input through the microphone 30 is analog / digital (hereinafter referred to as A / D) conversion unit 20, and the digital pulse code modulation (hereinafter referred to as PCM). Is converted into a signal. The PCM signal is transmitted to the voice encoder 45, and the voice encoder 45 compresses the PCM signal and outputs packet data. For example, the voice coder 45 may use 8 Kbps Qualcomm Code Excited Linear Predictive coding (QCELP) in the case of a CDMA digital portable telephone or a regular pulse excitation with long term termination (RPE-LTP) in the case of a GSM digital portable telephone. have.

The packet data output from the voice encoder 45 is transferred to the microprocessor 50 which collectively controls the overall operation of the digital portable telephone. The first memory 60 is a nonvolatile memory (eg, flash memory, EEPROM), and stores program and initial service data that collectively controls the overall operation of the digital portable telephone. The second memory 80 is a RAM and temporarily stores various data according to the operation of the digital portable telephone. The speech recognition unit 85 outputs characteristic data for any speech. The characteristic data consists of 20 bytes per second and is a frequency characteristic, a signal size, a function of magnitude change, and the like. The voice recognition unit 85 may be implemented in hardware or software. If the voice recognition unit 85 is implemented in software, the voice recognition unit 85 may be stored in the first memory 60 that the digital portable telephone already has, without being added separately as shown. The microprocessor 50 controls the operation of a known digital portable telephone and performs the following voice recognition control operations. First, the packet data output from the voice encoder 45 is transferred to the voice recognition unit 85. In addition, a control operation is performed such that a predetermined operation (for example, dialing) is performed as a result of recognition according to the characteristic data index and the difference value output from the voice recognition unit 85. When the voice of the user is packetized by the voice encoder 45 and stored in a specific area of the first memory 60, the microprocessor 50 receives the address of the area from the voice encoder 45 and stores the address. When notifying the user of the recognition of the voice, the packet data is read from the address of the first memory 60 and used. The read voice data is referred to as playback voice data for convenience of explanation and explanation. The voice encoder 45 converts the reproduced data into a PCM signal and transmits the reproduced data to a digital to analog converter (D / A). The PCM signal input to the D / A converter 75 is converted into an analog form, and then amplified by the speaker 80 and output as an audible sound. As described above, instead of using the reproduced voice data, a guide message for notifying completion of voice recognition may be separately stored and stored. The hands free kit connection unit 500 digitizes the voice input through the connection of a known hands free kit and the terminal and the hands free kit microphone through the A / D conversion unit 20 to deliver the voice encoder 45.

The key input unit 55 has a plurality of keys such as keys for setting various modes, numeric keys for dialing, and function mode voice registration keys. The beeper 90 generates a beep to signal the start of a given task. The flip state detector 95 senses an on / off state of a flip (not shown) to cause the microprocessor 50 to determine whether to enter the voice recognition mode.

2 is a diagram schematically illustrating a configuration of a first memory according to an embodiment of the present invention. It consists of a control program, characteristic data, reproducing voice data, telephone number, an area for storing a guide message, and a spare area. Reference numeral ADD denotes an address appropriately occurring in each case in the microprocessor 50.

The characteristic data area stores characteristic data of a voice input when registering each function mode (eg, help, add, delete, ...), and the user can recognize each function mode as a voice in the playback voice data area. The voices to be played back for confirmation are stored as illustrated, and this storage has already been made in the registration step.

3 is a flowchart illustrating the overall operation of the digital portable telephone having a voice recognition function according to an embodiment of the present invention.

When the user opens the flip of the standby digital portable phone, the microprocessor 50 detects this in step 110 and enters the voice recognition mode in step 120. In step 130, the input of a predetermined key or voice is examined. In this case, if a predetermined key or voice input is not detected, the process proceeds to step 140 to check whether a predetermined time (for example, 5 seconds) has elapsed. As a result of the test, if the corresponding time has not elapsed, the process returns to step 130, and if it passes, the process returns to step 110.

In step 130, if a predetermined key or voice input is detected, in step 160, if it is determined that the key is a function mode voice registration key, and if it is determined that it is a function mode voice registration key, the process proceeds to step 170. Run the routine. On the other hand, if it is not the function mode voice registration key, if it is determined in step 180 that it is a key for the registration mode, and the registration key proceeds to step 190 to execute the registration routine. For example, the registration routine may register a name. Specifically, it is to enable voice dialing using a voice recognition function by registering a name as a voice and storing a phone number corresponding to the name.

If it is not the registration key in step 180, the process proceeds to step 200 to execute the recognition routine, and in step 210 performs a routine for processing the recognized function. For example, in the recognition and processing routine, when a user speaks a name of a person who wants to make a call for voice dialing, the user recognizes the name and finds a corresponding telephone number to dial.

4 is a flowchart illustrating a function mode voice registration method according to an embodiment of the present invention. When the user inputs a function key corresponding to a function mode to be registered, for example, an 'F1' key, the microprocessor 50 detects this in step 310. In operation 320, the beeper is controlled to generate a beep sound notifying the start of the function mode voice registration. Then, when the user speaks a predetermined function mode with the microphone 30, for example, "help", the corresponding voice is transmitted to the voice encoder 45 in the form of a PCM signal through the A / D converter 20, and the voice encoder 45 is The PCM signal is encoded to generate packet data. The microprocessor 50 recognizes the voice input by checking whether the packet data is received from the voice encoder 45 in step 330, and controls to reproduce the input voice in step 340. That is, the reproduced voice data corresponding to the voice is read from the first memory 60 and transferred to the voice encoder 45. In this case, the voice encoder 45 processes the reproduced voice data and delivers the same to the D / A converter 75, and the D / A converter 75 converts it into an analog form and hears it through the speaker 80 ("help"). Will output Subsequently, the user inputs a voice related to a predetermined function mode ("help" according to the present assumption) spoken by the user in step 350, and checks whether the two input voices are similar in step 360. If this is the case, the function key is registered. In this case, the user only needs to say "help" instead of entering the function key 'F1' of the existing help. On the other hand, if the two voices are completely irrelevant, an error message is output in step 380 and the process returns to step 310.

5 is a flowchart illustrating a function mode speech recognition method according to an embodiment of the present invention.

If the user opens the flip of the standby digital portable phone before speaking the desired function mode, the microprocessor 50 detects this in step 410 and enters the voice recognition mode. In operation 420, the beeper is controlled to generate a beep sound notifying the start. After that, if the user speaks a desired function mode, it detects it in step 430. In this case, if the voice input of the function mode does not pass, for example, 5 seconds, steps 130 to 150 of FIG. 3 may be applied.

For example, suppose the user said "help". This voice data will be delivered to the voice encoder 45, where the microprocessor 50 checks if the packet data is delivered from the voice encoder 45 in response to the user's voice " help ". If there is packet data delivered as a result of the inspection, it is transmitted to the voice recognition unit 85. The voice recognition unit 85 checks whether similar characteristic data indexes and difference values are input. The similar characteristic data index means an index in a memory having characteristic data similar to the current input voice among characteristic data already registered, and the difference value corresponds to a difference between the two characteristic data. When a similar characteristic data index and a difference value are input, it is determined whether the difference value is smaller than a predetermined threshold. If the determination result is less than the threshold value, it is determined that the recognition is correct, and the flow proceeds to step 440 where the read voice data corresponding to the characteristic data index is read from the first memory 60 and transferred to the voice encoder 45. In this case, the voice encoder 45 processes the reproduced voice data and transmits the reproduced voice data to the D / A converter 75. The D / A converter 75 converts the received voice data into an analog form and outputs the audible state through the speaker 80. Subsequently, the process proceeds to step 450 and the user's intention is again confirmed by reading the voice guidance message (eg, is the desired function?) From the first memory 60 asking the user to the voice encoder 45 as described above. Instead of the voice guidance message, a character may be displayed on the indicator (liquid crystal display device). In response to this, when the user responds with a voice of "Yes" to the microphone 30, the voice is transmitted to the voice encoder 45 in the form of a PCM signal through the A / D converter 20, and the voice encoder 45 receives the PCM signal. Encoding generates packet data. The key may be recognized according to a known method. However, if you want to execute all the procedures using the voice recognition function as described above, it is necessary to register a positive or negative voice, such as "yes" or "no".

In operation 460, if the microprocessor 50 detects whether the user response is positive or negative, and detects the positive response, the microprocessor 50 executes the function processing routine in operation 470. According to this assumption, the help is actually displayed on the indicator. If a specific name is input by voice instead of "help", the function processing routine finds and dials a telephone number previously stored corresponding to the name.

On the other hand, if the positive response is not detected in step 460, the process proceeds to step 480, where the next function mode among the function modes registered in the characteristic data area of the first memory 60 is reproduced corresponding to "addition". Play back audio data. In step 490, it is checked whether steps 450 through 480 have been repeatedly performed for a predetermined number of times or more, and if it is determined that the steps have been repeated for a predetermined number of times or more, the process returns to step 401.

Meanwhile, in the detailed description of the present invention, specific embodiments have been described, but various modifications are possible without departing from the scope of the present invention. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be defined not only by the scope of the following claims, but also by the equivalents of the claims.

As described above, the present invention can recognize the function mode by voice, so that the user does not need to operate keys one by one, and the hand is free when driving or other tasks in parallel. There is this.

Claims (5)

In the function mode voice registration method of the digital portable telephone, A first step of switching to the voice recognition mode by detecting flip on / off by detecting flip on / off in a standby state; A second step of selecting a function mode voice registration after switching to the voice recognition mode; If the function mode voice registration is selected, a third process of inputting a predetermined function key and then reproducing the primary input voice while simultaneously processing and processing a voice that speaks a function corresponding to the function key; , A fourth process of secondly inputting a voice that speaks a function corresponding to the function key after playing the first voice; And a fifth process of detecting the characteristics of the first and second input voices, comparing them with each other, and checking the similarity and registering the voices in a function mode corresponding to the function key if they are similar. . The method of claim 1, If the predetermined voice or key input is not detected within a predetermined time after the switch to the voice recognition mode in the first process, the method further comprises the step 1-1 of releasing the voice recognition mode and checking flip on / off again. How to feature. The method according to claim 1 or 2, And if the function mode voice registration is selected in the second process, generating a beep to notify the start of the function mode voice registration. A function mode speech recognition method of a digital portable telephone having a voice registration memory for a plurality of function modes, A first process of switching from the standby state to the voice recognition mode; A second process of recognizing a corresponding function mode by inputting a predetermined voice after switching to the voice recognition mode and reproducing the voice; A third process of requesting a response from the user whether the desired function mode is corrected after the reproduction; A fourth process of performing a corresponding function mode when a user's positive response to the request is detected; And a fifth process of returning to the third process after reproducing the next function mode from the memory when the negative response is detected in the fourth process. In a flip type digital portable telephone having a voice encoder, Means for detecting an on / off state of the flip for entering the voice recognition mode; A nonvolatile memory for pre-registering a voice corresponding to each function mode; A microphone for speaking a desired function mode by the registered voice; And a voice recognition unit for processing the packet data corresponding to the voice input through the microphone, output from the voice encoder, and comparing the pre-registered voice to recognize the corresponding function mode.

Images