JPH0927845A - Automatic dial telephone set - Google Patents

Abstract

PROBLEM TO BE SOLVED: To obtain an automatic dial telephone set in which a telephone number is entered in voice. SOLUTION: A telephone number entered by the voice of the user is recognized by a voice recognition section 11, a numeral string recognized is used for voice information by a voice synthesis section 13 and it is recognized by the user. The voice input is recognized as a voice by each block of 2 to 5 digits and confirmed through voice synthesis. The user depresses a switch corresponding to the start of entry and confirmation of the synthesized voice, it is recognized by a switch input reception section 12, and a command is given to the voice recognition section 11 to command voice recognition. Furthermore, a command is given to a memory section 14 and an entered numeral string confirmed to be correct is stored. When the entry of all the numbers is confirmed, the stored number string in the memory section 14 is sent to a dial section 15, and a telephone circuit section 16 sends it to a telephone line 17 as a dial signal.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an automatic dial telephone device for inputting a telephone number by voice and used in, for example, a car telephone.

[0002]

2. Description of the Related Art As a telephone device using a voice recognition device,
For example, the telephone set disclosed in JP-A-1-131156 is known. The voice recognition device set on this phone is
The name of the other party of the call, voice information, and address information (telephone number) paired with this voice information are stored, and the corresponding address information recognized by voice input is read. Then, the output address information is converted into a voice by a voice synthesizer and is transmitted to the user side. For example, the telephone number can be inquired at the destination.

When such a device is used, a voice recognition device operates for a number registered in advance and a telephone number can be transmitted. However, the telephone number can be directly inputted by voice. You cannot make a call.

[0004] For example, in a telephone device installed in an automobile, when the driver calls the other party, it is possible to make a dial call to a previously registered party based on a voice command. Voice dialing cannot be made to the other party. Especially in car telephones, when the driver intends to use the telephone, since both hands are occupied for driving operation, voice dialing is desired,
Naturally, it is desired to be able to easily dial an unspecified number of parties who are not registered in advance.

[0005]

SUMMARY OF THE INVENTION The present invention has been made in view of the above points, and enables dialing using voice freely even to a partner who is not registered. , An automatic dial telephone device that can be effectively applied to, for example, a car telephone.

[0006]

According to the present invention, a switch input discriminating means discriminates a user's command input, and a voice recognizing means recognizes a voice input of a user's number. The voice corresponding to the number recognized by the voice recognition means is synthesized, transmitted to the user side, and the number recognized by this voice recognition means is stored in the storage means. Then, the number stored in the storage means is sent to the telephone line as an input telephone number based on a command from the switch input determination means. In the voice recognition means, the voice number from the user side is limited to a limited digit. The number of digits is accepted, the number of digits is converted into voice by the voice synthesizer, the voice is returned to the user side, and the voice is stored in the storage means.

[0007] Here, the voice input from the user side is performed by dividing the 2 to 5 digits of the number as a unit by a silent part,
The voice recognition means includes means for determining a silent portion of the input voice to determine the unit input, and the voice synthesis means converts the input voice.

Therefore, in the telephone device configured as described above, even if the telephone number or the name of the other party of the call is not registered in advance, the arbitrary number can be input by voice input. Then, it becomes possible to make a call by selecting an unspecified number of destinations. In this case, by dividing the number into, for example, 2 to 5 digits and inputting the voice, the number recognition rate is improved as compared with the case of reading and recognizing the 10-digit number, and the input number can be easily corrected. As a result, it is possible to safely and easily make a telephone call while operating a car, for example.

[0009]

BEST MODE FOR CARRYING OUT THE INVENTION An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 shows the configuration thereof, in which a switch input is appropriately made together with a voice input of a user (user). For the voice input, for example, in the case of a car telephone, a microphone installed near the steering wheel is used. The switch input is also performed using a switch mechanism in the vicinity of the steering wheel or by voice.

The voice input from the user is the voice recognition unit.
Switch input is performed on 11
Accepted and recognized at 12. In this case, the voice input corresponds to the telephone number of the call destination, and the voice recognition unit 11 recognizes this input voice and converts it into information of a numerical string.
Then, the information of the number string converted by the voice recognition unit 11 is supplied to the voice synthesizing unit 13, synthesized into a voice corresponding to the number sequence, and output to the user side.

At the time of such voice synthesis, a switch input for instructing the start of voice number input is made, and the switch input accepting unit 12 issues a recognition command to the voice recognition unit 11 in response to this switch input. give. The switch signal received by the switch receiving unit 12 also gives a command to the memory unit 14.

Here, the voice synthesized and output by the voice synthesizer 13 is recognized by the user and its correctness is determined, and when it is confirmed that the correct voice is input, the switch input is changed. To be done. This switch signal is
The command is received by the switch reception unit 12 and gives a command to the memory unit 14. Based on this command, the memory unit 14 reads the number string which is recognized as correct by the voice recognition unit 11,
Retain. The number stored in this memory unit 14 is
It is sent to the transmitting unit 15 based on the switch signal instructing the completion of the voice number input, and is sent to the telephone line 17 via the telephone circuit unit 16. The telephone circuit unit 16 further ends the call. A switch signal corresponding to is sent.

Here, when inputting the telephone number, the user inputs the voice by dividing it into, for example, 2 to 5 digits.
For example, a telephone number is usually composed of 10-digit numbers, but 10-digit numbers are continuously input by voice,
Speech recognition of this is an obstacle to improvement of recognition accuracy. Even if a 10-digit number is recognized by voice, the voice synthesizer 13 continuously converts the 10-digit number into voice and outputs the voice to the user side. Then, the user synthesizes the 10-digit number. It may be difficult to accurately recognize and discriminate. Therefore, in this example, the input number is divided into numbers of 2 to 5 digits corresponding to hyphens and the like, and voice input is made for each of the division units.

FIG. 2 shows the flow of such a number input process. In step 101, a voice telephone number is input. In this case, the input telephone number is divided into, for example, 2 to 5 digits and is input by voice, and a silent state is clearly set in the divided portion. And
In step 102, the input voice is recognized in the unit of the division to obtain information of 2 to 5 digits, and in step 103, the recognition result is synthesized with the voice and output to the user side.

The user listens to the output of the synthesized voice and operates the switch, and when it is determined that the number of the synthesized voice matches the number of the inputted voice, a switch input for instructing the fact is made. Run. In step 104, this switch input is checked to determine whether or not the voice recognition result is the correct answer. If the answer is correct, the process proceeds to the next step 105 and it is determined that it is incorrect. If so, the process returns to step 101.

In step 105, it is determined whether or not all digits of the telephone number have been input by voice. If it is determined that all the digits have not been input yet, the procedure returns to step 101 again and the division is performed. Wait for the next number to be entered. Then, the voice recognition of this number and the voice synthesis are performed to complete the voice input of all digits of the telephone number, and it is confirmed that all the numbers to be input in step 105 have been uttered. If so, step 106
Go to and dial the recognized number on the telephone line.

Here, when it is determined in step 104 that the voice recognition result is correct, an instruction is given to the memory section 14 to store and hold the recognized correct answer number,
In step 106, the numbers stored and held in the memory section 14 are transmitted to the telephone line as a telephone number.

FIG. 3 illustrates the steps in FIG. 2 for a user to enter a telephone number for a voice-automatic dial telephone.
The processing of 101 to 104 will be described more specifically, and particularly the processing when inputting a telephone number divided into 2 to 5 digits is shown.

That is, at the time of voice input of the telephone number, the user first performs switch input to instruct the start of voice input. This switch input may be performed by using a switch mechanism as appropriate, but may be a switch command by voice input. Also, the beginning of voice input may be automatically recognized by signal processing.

When the switch signal for instructing the start of voice input is turned on in step 201, voice input of a telephone number is performed in step 202. In this example, this voice number input is divided into 2 to 5 digits, and a clear silent portion is set in the divided portion. And
In step 203, after uttering this number, it is recognized that a certain period of silence continues, and the completion of one unit numeral string of voice input is recognized.

In step 204, the voice input switch is turned on and the voice string of numbers separated by the voice input completion point is recognized. If the voice string of numbers is recognized in this way, in step 205. The recognized number string is converted into synthetic voice and output to the user. Then, the user listens to the synthesized voice, and determines whether or not the inputted numeric sequence has been correctly recognized by matching the numeric sequence obtained by the synthetic voice with the inputted numeric sequence. .

This determination is appropriately made by switch input, and the switch signal of the determination result is determined in step 206, and when it is determined that the correct input is made, the voice input of this number string is completed. Then, if the synthesized character string is incorrect, the cancel instruction is given by the switch signal, and the process returns to step 201 to input the character string again.

In this way, a process of inputting a large number digit string constituting a telephone number divided into 2 to 5 digits and recognizing the telephone number by the divided digit string was shown. By repeating the input process of such a delimited number string, all the phone numbers will be entered, and if such an entry is completed, the outgoing switch is input,
The telephone number input and stored in the memory unit 14 is sent to the telephone circuit unit 16 and transmitted to the telephone line 17.

In the above description, the input switch is basically used to confirm the recognition result of the voice-inputted digit string and to input the start of the voice section, but this has been described above. Thus, an interface by voice input may be used. Further, the point at which the voice input is completed is the point after the silent period of the specific time after the voice is uttered, but this may naturally be confirmed by recognizing the switch input by the user.

[0025]

As described above, according to the automatic dial telephone device of the present invention, it is possible to make a dial call using voice when calling an unregistered partner. The telephone number transmission by recognition can be applied to a wider range, and it can be effectively applied to, for example, a car telephone and the like, and the telephone transmission can be performed without taking a hand from a steering system such as a steering wheel.

[Brief description of drawings]

FIG. 1 is a configuration diagram for explaining an embodiment of the present invention.

FIG. 2 is a flowchart illustrating the operation of the above embodiment.

FIG. 3 is a flowchart for explaining a voice input process in which telephone numbers are similarly divided.

[Explanation of symbols]

11 ... Voice recognition section, 12 ... Switch input acceptance section, 13 ... Voice synthesis section, 14 ... Memory section, 15 ... Transmission section, 16 ... Telephone circuit section, 17 ... Telephone line.

Claims (4)

[Claims] 1. A switch input determination means for determining a command input of a user, a voice recognition means for identifying and recognizing a voice input of the user's number, and a voice recognition means corresponding to the number recognized by the voice recognition means. A voice synthesizing means for synthesizing voice and transmitting it to the user side, a storage means for storing the number recognized by the voice recognizing means, and a command from the switch input determining means for storing the number stored in the storage means. Based on the above, there is provided a transmitting means for transmitting to the telephone line as an input telephone number, wherein the voice recognition means accepts a voice number from the user side in a limited number of digits, and the number of digits is An automatic dial telephone device characterized in that it is converted into a voice by a voice synthesizing means and returned to the user side, and is stored and held in the storage means. 2. The voice input from the user side is performed by dividing 2 to 5 digits of a number into one unit numeral string with a silent part, and the voice recognition means determines a silent part of the input voice. 2. The automatic dial telephone device according to claim 1, further comprising: a unit for judging each input of the unit numeral string and converting the unit number string into a voice by the voice synthesizing means. 3. The automatic dial telephone device according to claim 1, wherein the switch signal input to the switch input determination means is constituted by a switch mechanism operated by a user. 4. The automatic dial telephone device according to claim 1, wherein the switch signal input to the switch input determination means is input by voice and is recognized by the voice recognition device.