JPH04212552A - Telephone set with voice recognizing device - Google Patents

Abstract

PURPOSE:To present the telephone set with voice recognizing device omitting the work of taking the memorandum of a phone number onto a paper sheet or the like by recognizing a voice telling the phone number, storing the number and originating a call with one action of pushing an exclusive button or the like. CONSTITUTION:A voice recognition part 3 recognizes the voice expressing a numerical value transmitted through a telephone line. These voices are successively stored in a numerical storage device 4 as the phone number. This phone number is successively outputted to a telephone line 14 by a phone number output part 5 corresponding to information instructing the output of an instruction input part 10. Thus, even without inputting the phone number severally, the call is originated by the simple input operation. Further, the excess work of taking the memorandum of the phone number onto the paper sheet or the like is omitted. A voice synthesizing part 6 generates the voice corresponding to the phone number stored in the numerical storage part 4, and the phone number is easily transferred to a phone number directory or an address book, etc.

Description

[Detailed description of the invention]

0001

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a telephone equipped with a voice recognition device that utilizes voice recognition.

0002

2. Description of the Related Art Conventionally, when making a call to a party whose telephone number is unknown, the telephone number guidance system of Nippon Telegraph and Telephone Corporation (NTT) is often used. This is a service that calls an operator at a predetermined telephone number (104), tells the operator the name and address of the person whose telephone number you want to know, and then tells the operator the telephone number using a synthesized voice.

[0003] In this case, the operator writes down the given telephone number on a piece of paper and makes a call by inputting the telephone number of the other party while looking at the memo paper. In addition, phone numbers are copied from paper notes and stored in address books, etc.

0004

[Problems to be Solved by the Invention] However, when using the above-mentioned services, there is a problem in that it is necessary to write down the given telephone number on paper or the like.

[0005]

[Means for Solving the Problems] In the invention as set forth in claim 1, a handset connected to a telephone line is provided, a voice recognition section is provided for recognizing voice representing a numerical value sent through the telephone line, and the voice recognition unit A numerical storage section is provided for sequentially storing the voice recognized by the section as numerical information, an instruction input section is provided, and the numerical information stored in the numerical storage section is read in response to information instructing output of the instruction input section. A telephone number output unit was provided to sequentially output the telephone number to the telephone line.

[0006] In the invention as set forth in claim 2, in claim 1, the instruction input section is also used as a redial switch.

[0007] According to the third aspect of the invention, in the first aspect, a registration means is provided for registering the numerical information stored in the numerical storage section into the speed dial.

[0008] According to a fourth aspect of the invention, in the first aspect, a voice synthesizing section is provided which generates a voice corresponding to the numerical information stored in the numerical storage section.

[0009]

[Operation] In the invention as set forth in claim 1, the voice recognition section recognizes the voice representing a numerical value sent through the telephone line, and the voice recognized by the voice recognition section is sequentially stored as numerical information in the numerical storage section. The number output section sequentially outputs the numerical information stored in the numerical storage section to the telephone line in accordance with the information instructing the output of the instruction input section, so you can make calls with simple input operations without having to input each telephone number one by one. This also makes it possible to eliminate the extra work of writing down phone numbers on paper or the like.

[0010] In the invention as claimed in claim 2, since the instruction input section is also used as a redial switch, it is possible to make a call with one touch to the destination of the telephone number last stored in the numerical storage section. , it is possible to make an unlimited number of calls in succession.

In the invention as claimed in claim 3, the numerical information stored in the numerical storage section is registered in the speed dial by the registration means, so that it is possible to register the telephone number without inputting it one by one. , it becomes possible to make a call to the other party of the registered telephone number at any time with a simple input operation.

[0012] In the invention as set forth in claim 4, the voice synthesis section generates a voice corresponding to the numerical information stored in the numerical storage section, so that the telephone number can be easily transferred to a telephone number book, an address book, etc. becomes possible.

[0013]

DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be explained based on the drawings. This device includes an input section 1, a control section 2, a speech recognition section 3, a numerical storage section 4, a telephone number output section 5, and a speech synthesis section 6.
It can be broadly classified into a telephone circuit 7, and a handset 8. The configuration of each part is as follows.

First, the input unit 1 includes a dial key 9, a memory button 10a, a redial and call button 10b as a redial and call switch, a confirmation button 10c,
The dial key 9 and the instruction input section 10 are connected to the control section 2, respectively. The output side of this control section 2 includes the voice recognition section 3, the numerical storage section 4,
They are respectively connected to the input side of the telephone number output section 5.

[0015] The speech recognition section 3 also includes a feature extraction section 1.
1, standard pattern storage section 12, and pattern matching section 13
The output side of each of the feature extraction section 11, the standard pattern storage section 12, and the control section 2 is connected to the input side of the pattern matching section 13. The output side of this pattern matching section 13 is connected to the input side of the numerical value storage section 4. The output side of the numerical storage section 4 is
It is connected to the input sides of the voice synthesis section 6 and the telephone number output section 5, respectively. The output side of this telephone number output section 5 is connected to the telephone call circuit 7.

The telephone circuit 7 connected to the telephone line 14 is connected in parallel to the handset 8. This handset 8 is equipped with a microphone 15 and a receiver 16, the microphone 15 is connected to the communication circuit 7 via a transmission line 17, and the receiver 16 is connected to the communication circuit 7 via a reception line 18. has been done. The receiving line 18 is connected to the output side of the speech synthesis section 6 and the input side of the feature extraction section 11, respectively.

[0017] In such a configuration, the operation will be explained by comparing the case where NTT's directory assistance (104) is used to check a telephone number. First, press dial key 9 to
When you call TT's directory assistance (104) and tell the operator the name and address of the person you are calling, the person will be told the phone number using a synthesized voice. Therefore, the operator determines that the synthesized voice is
What is the phone number you are looking for? ．． ．． ” and pauses, the user presses the memory button 10a of the instruction input unit 10. The control unit 2 controls the pattern matching unit 13 so that the voice generated thereafter is recognized as a number. This pattern matching unit 13 uses the numerical values “0” to “9” whose features are extracted by the feature extracting unit 11 through the receiver 16 of the handset 8.
The audio signal representing the value is compared with the reference audio signal representing the numerical values "0" to "9" previously stored in the standard pattern storage unit 12, and the most similar patterns are sequentially selected and stored in the numerical value storage unit 4. Send the results. In the speech recognition unit 3 of this embodiment,
Synthetic speech that is discretely generated one digit at a time is used as the speech unit to be recognized, ensuring reliable recognition. Next, the numerical storage unit 4 sequentially stores the sent numerical sequences as telephone numbers.

The operator then hangs up the phone, picks up the handset 8 again, and presses the redial and call button 10b of the instruction input section 10. In response to this operation, the telephone number stored in the numerical storage section 4 is output from the telephone number output section 5 to the telephone line 14 according to a command from the control section 2 . In this way, one-touch dialing to the person you want to call becomes possible. Here, redial button 10b
is also used as the call button 10b, but they may be separate buttons.

Further, after the above-described storage operation, by pressing the shortcut button 10d, the telephone number can be registered in the speed dial. Since a known technique can be used for the registration operation in the speed dial, a description thereof will be omitted in this embodiment.

Furthermore, after the memorization operation, a confirmation button 10 is pressed.
Press c. Upon receiving this operation, the telephone number is output as a voice signal from the voice synthesis section 6 according to a command from the control section 2. This audio signal is output as audio from the receiver 16 of the handset 8 via the receiving line 18. This results in
It becomes possible to easily reproduce the information in telephone number books, address books, etc.

[0021]

Effects of the Invention The invention as set forth in claim 1 provides a handset connected to a telephone line, a voice recognition unit that recognizes voice representing a numerical value transmitted through the telephone line, a numerical storage unit for sequentially storing voice data as numerical information, an instruction input unit, and the numerical information stored in the numerical storage unit is transmitted to the telephone line in response to information instructing output from the instruction input unit. A phone number output section that outputs sequentially is provided, so you can make a call with a simple input operation without having to input each phone number one by one, and also eliminate the extra work of writing down phone numbers on paper, etc. It has effects such as being able to.

[0022] In the invention as claimed in claim 2, in claim 1, the instruction input section also serves as a redial switch, so that a call can be made with one touch to the destination of the telephone number last stored in the numerical storage section. , it also has the advantage of allowing you to make as many calls as you like in a row.

[0023] The invention according to claim 3 is the invention according to claim 1, which is provided with a registration means for registering the numerical information stored in the numerical storage unit in the speed dial, so that the telephone number can be registered without inputting the telephone number one by one. It also has the advantage of being able to make a call to the other party of the registered telephone number at any time with a simple input operation.

[0024] The invention according to claim 4 is characterized in that, in claim 1, a voice synthesis unit is provided which generates a voice corresponding to the numerical information stored in the numerical storage unit. This has the effect that it can be easily reprinted.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing one embodiment of the present invention.

[Explanation of symbols]

3 Speech recognition section 4 Numerical storage unit 5 Telephone number output section 6 Speech synthesis section 8　　　　　　　　　　　　　Handset 10 Instruction input section 10b Redial switch 10d Registration means 14　　　　Telephone line

Claims (4)

[Claims] 1. A handset and receiver connected to a telephone line, a voice recognition unit that recognizes voices representing numerical values transmitted through the telephone line, and numerical values that sequentially store the voices recognized by the voice recognition unit as numerical information. a storage section, an instruction input section,
A telephone with a voice recognition device, comprising a telephone number output section that sequentially outputs the numerical information stored in the numerical storage section to the telephone line in accordance with information that instructs the output of the instruction input section. 2. The telephone with a voice recognition device according to claim 1, wherein the instruction input section also serves as a redial switch. 3. The telephone with a voice recognition device according to claim 1, further comprising a registration means for registering the numerical information stored in the numerical storage section into a speed dial. 4. The telephone with a speech recognition device according to claim 1, further comprising a speech synthesis section that generates speech corresponding to the numerical information stored in the numerical storage section.