KR950007091B1 - The voice dialing method of cellular phone - Google Patents

Abstract

The method improves the efficiency of usage and recognition ratio on voice recognition and synthesis, reduces the danger of traffic accident, and minimizes the damage to the life and property. The method includes the 1st step which transmitts the synthesis voice, the 2nd step which inputs the voice of the user, the 3rd step which questions the speaker dependent unit with synthesis voice, the 4th step which inputs the voice of the user to the speaker dependent unit, the 5th step which identifies the telephone number, the 6th step which decides the communicationable area, the 7th step which executes the 1st step, the 8th step which decides the communication quantity, the 10th and the 11th steps which trnasmitt the synthesis voice, the 12th step which executes the 1st step, the 13th step which executes the 4th step, and the 14th step which executes the receiving and belling of cellular phone after 1st step "Thank you" transmission.

Description

Voice dialing method of cell phone

1 is a control flowchart for performing a voice dialing method of the present invention.

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice dialing method, and more particularly, to a method for voice dialing of a cellular phone that improves subordinate recognition rate and convenience in use by voice recognition and synthesis for dialing a conversational voice history in a driving vehicle.

In general, if you need to make a phone call while driving a car, you need to operate the dial button of the cell phone, so there is a high risk of an accident. A voice dialing system is used that dials the corresponding phone number of a voice input name when a name stored as a voice is input after storing a name and a phone number of the callee. The voice dialing system filters out vehicle noise when voice is input, performs voice recognition, and transmits synthesized sound to help guide and operate the voice recognition process using a dedicated voice synthesis integrated circuit, and uses a dedicated digital signal circuit. Eliminate noise and perform voice recognition.

Conventionally, only speaker-independent names such as home, office, company, friends, etc. can be recognized, and thus, voice dialing that can be frequently used is limited to a predetermined number of names, thereby causing a problem in lack of flexibility in system operation.

SUMMARY OF THE INVENTION The present invention has been made in view of the above-described problems, and aims to improve the dependency recognition rate by speech recognition and synthesis by classifying five groups storing dependent names, and to facilitate convenience of use. .

The present invention for achieving the above object is a first step of transmitting a synthesized sound that the speech recognition is ready when the power supply to the cell phone, after the first step performed by the user to the speaker independent unit that the user is going to talk to the voice of the user In the second step, after the second step is performed, the speaker independent unit is repeatedly transmitted to the synthesized sound, and the third step of questioning the speaker dependent part as the synthesized sound, and after performing the third step, the speaker dependent part outputted as the synthesized sound is inputted by the user's voice. After performing the fourth step, the fourth step of confirming the telephone number sent to the user after transmitting the telephone number of the speaker dependent inputted by the user's voice after the fourth step, and transmitting the synthesized sound after performing the fifth step A sixth step of determining a callable distance (area) of the mobile wireless telephone when the telephone number and the user's telephone call coincide with the telephone number; Fixed station which relays mobile radiotelephone when the distance (area) is the distance (area) where no call is made after the execution of the system and transmits the non-call state as synthesized sound and the distance (area) is available after the 6th step is performed. Eighth step of determining the call volume of the mobile station, if the mobile station is unable to connect the mobile wireless phone after the call volume of the fixed station is congested after performing the eighth step; If the connection is possible, the caller's call state of the other party to determine the other party's phone state to be called, if the other party is not busy after performing the step 10 determines the predetermined number of rings (N = 7) of the other party's phone state An eleventh step of transmitting information as a synthesized sound; a twelveth step of performing a first step after transmitting the other party's telephone state information as a synthesized sound if the other party is busy after performing the tenth step; Performing the first step according to the synthesized tone information transmitted after the first step, the thirteenth step of performing the fourth step, and the other party's call after the tenth step is connected, and when the call is completed, Thank you ”is to provide a voice dialing method comprising a fourteenth step of performing a first step and waiting for the reception and transmission of the cellular phone after transmitting the synthesized sound. Speaker Independence Phone, Preparation, Home, Office, Emergency, Company, Account (Customer), Friend, Family (Family), Name… It is a part that recognizes the words such as etc. without distinction in the speaker, and the speaker dependent part recognizes the voice input in the first step of the command as company, customer (customer), friend, relative (family), name, etc. This part recognizes the voice of the command 2 step of inputting the voice. Five slaves can be stored under five speaker independent groups, and up to 20 slave sounds can be stored in other common memories.

DETAILED DESCRIPTION OF THE EMBODIMENTS Hereinafter, an exemplary embodiment of a voice dialing method of a cellular phone according to the present invention will be described in detail with reference to FIG. 1.

The phone number set by the user is stored in the home, office, and emergency, and up to 5 users can be inputted in the 5 groups such as company, customer (customer), friend, relative (family), and name under each group. Stored individual names, etc. A telephone number is stored in a memory designated by each of the stored names.

When the user of the cellular phone makes a phone call and supplies power to the cellular phone installed in the vehicle (S1), the synthesized answering sound “hello” is transmitted from the voice dialing device. When the user inputs a voice of "telephone" (S2), a confirmation sound "beep ~" is transmitted. When the voice “ready” is input (S3) within a predetermined time (0 to 5 seconds) after the execution of the step S2, the voice recognition preparation step of transmitting the synthesized response sound “ready” is executed. After performing the voice recognition preparation step, if the other party (for example, "friend") to talk to is voice input (S4), the voice dialing device repeatedly sends the voice input counterpart (for example, a friend) to the synthesized confirmation tone. (S5) and "Who are you" synthesized sound (S6).

According to the synthesized sound sent out in the step S6, a detailed counterpart (Hong Gil-dong) inputted in the speaker slave is designated and the voice input (S7) is performed. After detecting the number, the telephone number of the other party (for example, Hong Gil-dong) is repeatedly transmitted to the synthesized sound, and then a confirmation sound of “is correct” is transmitted (S9). If the phone number of the other party (for example, Hong Gil-dong) that is input after the step (S8) is not stored and the phone number of the other party (for example, Hong Gil-dong) is not detected, the voice number is transmitted after transmitting the synthesized sound “No number”. The recognition preparation step S3 is executed. After executing the step (S9), when the user calls and inputs a voice of "Yes" when the phone number and the confirmation sound transmitted from the voice dialing device are matched (S10), the voice dialing device is the current location of the cellular phone. In step S11, it is determined whether the callable area is free of obstacles. After performing the step S11, if it is not possible to call, the synthesized sound “It is not a call” is transmitted, and then the voice recognition preparation step 3S is executed. If the area is available to call, the phone number searched in the step S8 is used. After the automatic redialing, it emits a synthesized sound of “outgoing”. After the execution of the step S11, the usage of the fixed station relaying the mobile radiotelephone is determined (S12). After executing the step (S12), if the number of mobile radio telephones relayed from the fixed station is too busy to make a connection with the other party (for example, Hong Gil-dong), the telephone is repeatedly attempted to connect to a certain number of times. The phone cannot be used because the phone is too busy. ”After the synthesized sound is transmitted, the voice recognition preparation step (3S) is performed. If the usage of the fixed station can be relayed after executing step S12, the use state of the other party's telephone to be called is determined (S13).

If the other party's phone is busy after executing the step (S13), the busy tone and the synthesized sound of “in a call” are simultaneously transmitted, and if the other party's phone is not busy, the incoming ring of the other party's phone is detected as a ringing tone and then fixed. The number of times (for example, seven times) is counted (S18). If the call is not made even after a certain number of times (for example, 7 times) in the above step (S18), the call is not answered. Do you want to call again? ”, And when the user inputs the voice of“ Yes ”(S12), the above step (S10) is executed. When the voice of“ Cancel ”is input (S20), the voice recognition is ready. Execution is carried out in step S3. After the step S13 is executed, if a call is established with the other party (S14), the user enters the call mode (S15) and makes a call with the other party (for example, Hong Gil-dong). When the call is terminated in the step S15, the synthesized sound “thank you” is transmitted, and the voice recognition preparation step S3 is performed to have a transmission / reception standby state. When the voice of "back" is input after the execution of the step (S9) (S17) by executing the step (S7) to wait for the voice input of the new call target. When the voice of “Cancel” is input after the execution of the step S9 (S16), the voice recognition preparation step (S3) is executed.

As described above, the inventor's voice dialing method automatically dials the other party's telephone number as a voice input of the user, thereby improving convenience in use and greatly reducing the risk of a traffic accident, thereby reducing human and property damage. It can be minimized.

Claims (1)

A voice dialing method of a cellular phone, comprising: a first step of transmitting a synthesized sound that voice recognition is ready when power is supplied to a cellular phone, and a method of inputting a speaker independence part to be called by a user as a user's voice after performing the first step; A second step of repeatedly transmitting the speaker independent part to the synthesized sound after performing the second step, and a fourth step of inputting the speaker dependent part output as the synthesized sound after performing the third step as a voice of the user Step 5, after transmitting the telephone number of the speaker dependent inputted by the user's voice after the fourth step as a synthesized sound, and confirming the telephone number sent to the user, the telephone transmitted to the synthesized sound after performing the fifth step A sixth step and a sixth step of determining a callable distance (area) of the mobile wireless telephone when the number and the user's telephone number match. If the distance (area) is not available after the call is performed in the seventh step of transmitting a non-call state as a synthesized sound and performing the first step, if the distance (area) available to call after performing the sixth step of the fixed station that relays the mobile wireless telephone Eighth step of determining the call volume, if the fixed station is congested after performing the eighth step is impossible to connect the mobile radio telephone, the ninth step to perform the first step, after performing the eighth step of the fixed station and the mobile wireless phone If it is possible to connect, if the other party is not busy after the tenth step of determining the other party's telephone state to be called by the speaker dependent, and judges a predetermined number (N = 7) of the incoming ring after performing the tenth step, the other party's telephone state information The eleventh step of transmitting the synthesized sound to the synthesized sound; if the other party is busy after performing the tenth step, the twelveth and eleventh steps of transmitting the first call state information to the synthesized sound and then performing the first step After performing the first step according to the synthesized tone information transmitted after the execution, the thirteenth step of performing the fourth step, and the other party's call is connected after performing the tenth step, the other party is called, and when the call is completed, “Thank you. And a fourteenth step of performing a first step after transmitting the synthesized sound and waiting for reception and transmission of the cellular phone.