JPS62132459A - Telephone system - Google Patents

Abstract

PURPOSE:To eliminate the necessity of taking the trouble of going to the place of a telephone set for answering a phone call, by providing a voice synthesizing means which synthesizes voice by selectively leading out voice information necessary to inform a caller of the call from a voice registering and storing means in accordance with the recognized results of a voice recognizing means. CONSTITUTION:Each kind of information signal containing sound signals from a telephone line is received by a transmission/reception section 1 and inputted to a voice recognizing section 2 and voice information from a caller is recognized by the section 2. On the other hand, a voice registering and storing section 3 is provided with the 1st registration section, in which voice information necessary for informing the incoming of a call is registered in advance, and the 2nd registration section, in which voice information necessary for making automatic answer to a caller is registered in advance. At the time of incoming of a call, the voice recognizing section 2 recognizes the name of a caller and makes retrieval whether or not paragraphs or words for answering messages of the caller at the time of high absence are registered in the 2nd area of the voice registering and storing section 3 by using the name of the caller as a key. When they are registered, the section 2 selectively leads out the paragraphs or words and transmits them to the caller side as a message through a transmission/reception section 1 after they are synthesized by a voice synthesizing section 4. Therefore, automatic responses become possible even when a caller is absent.

Description

DETAILED DESCRIPTION OF THE INVENTION TECHNICAL FIELD The present invention relates to a telephone device, and more particularly to a telephone device that utilizes voice recognition and synthetic wave technology.

Prior Art Conventionally, in telephone equipment, when a call bell rings, the person being called and a member of his or her related group must go to the handset of the telephone to receive and answer the call, whether or not the person being called is nearby. The callee responds to calls, contacts the person being called, and if the person is not available, asks about the business on the person's behalf.

Above) In conventional telephone lines, the person who answers the phone instead receives the name of the person being called, or becomes busy with communication/telephone answering duties, resulting in a disadvantage to one's own work and wasting time. Pressure is also being applied to the country. Therefore, answering the phone with just the bell and the bell is a no-brainer! The disadvantage is that the I-person person has to answer the phone and is required to do the answering duties.

Also, having to answer the phone only when the phone rings rings irritates the nerves of the people in the office.

Purpose of the Invention The present invention has been made to eliminate the above-mentioned drawbacks of the conventional ones, and its purpose is to eliminate the need for a person to take the trouble to answer the telephone even when a call is received. The purpose of the present invention is to provide telephone equipment.

Another object of the present invention is to provide a telephone device that allows the telephone to automatically communicate with the sender even if the called party is absent.

Coincidence of the Invention According to the present invention, there is a voice recording storage means in which voice information necessary for notifying the arrival of a call is registered in advance, a voice recognition means for recognizing the voice of the sender, and a recognition result of the voice recognition means. A telephone device 17 is characterized in that it includes a voice synthesizing means for selectively deriving voice information necessary for notifying a called person of a call from the voice registration storage means and synthesizing the voice according to the voice registration storage means.

Furthermore, according to the present invention, a first voice registration storage means in which voice information necessary for notifying the incoming call is registered in advance;
a second voice registration storage means in which voice information necessary for responding to the sender is registered in advance; a voice recognition means for recognizing the voice of the sender;
a first voice synthesizing means for selectively deriving voice information necessary to notify a call to a called name from a voice registration storage means and synthesizing the voice; and a recognition result of the voice recognition means when the called person is absent. a second voice synthesizing means for selectively deriving necessary voice information for the sender from the second fame registration storage means and synthesizing the voice and outputting a response according to the above-mentioned second reputation registration storage means. A device is obtained.

Example Hereinafter, the present invention will be described in detail with reference to the drawings.

FIG. 1 is a schematic functional block diagram of an embodiment of the present invention.

Various information signals including voice signals from the telephone line are received by the transmitter/receiver 1 and input to the voice recognizer 2. Voice information from the sender is recognized by this voice recognition section. on the other hand,
A voice registration storage section 3 is provided, and this voice zero recording storage section 3 includes a first registration section (area) in which voice information necessary for notifying the arrival of a call is registered in advance, and a first registration section (area) in which voice information necessary for notifying an incoming call is registered. and a second registration i (area) in which voice information necessary for automatically responding to the person is registered in advance.

The voice information selectively derived from the voice registration storage unit 3 is synthesized in the voice synthesis unit 4, and the called party is notified of the call via the speaker 5 by voice, and the called name is not present. At this time, an automatic response is made via the transmitting/receiving section 1 by sending the message 18 and the synthesized voice. The operation of these units 1 to 4 is controlled by a controller 6 consisting of a CPtJ (data processing unit).

Now, let us consider a case in which, for example, a voice consisting of the following three sentences is output after the telephone bell rings.

(1)a Right now, there is an outside line to 4511 number 1 for ~.

(2) Right now, there is an extension number for Mr. △△ on number 2 of 4511. 1゜ (3) There is an extension number for ~ on number 3 of 4511 right now.

In this case, each underlined phrase and word portion is registered in the first area in the voice registration storage section 3, respectively. Segments and word parts other than the underlined parts have already been registered, so there is no need to register them, and the total length of the voice utterance of the underlined parts is up to 120 seconds (depending on the 8th interval of the speech synthesis section 4). 'C registration becomes possible.

The state of this zero recording is shown in Figure 2. Of course, as shown in FIG. 3, it is obvious that all sentences (1) to (3) above may be registered as they are.

In this state, for example, if Mr. △△ receives a call from the extension number 2 on 4511, it will be recognized that the number is ``Coke 6 is number 2 on r4511,'' and the voice recognition unit 2 will recognize the caller as the sender. Of the voices saying "Mr. △△, please", it particularly recognizes "Mr. ΔΔ". Based on the recognition results in the controller 6 and the voice recognition unit 2,
The corresponding phrases and words in the first area of the speech registration storage section 3 are selectively read out, and the speech synthesis section 4 outputs the speech of the sentence shown in (2) above. It will be uttered as follows.

By doing this, there is no need for anyone other than the person called 11'F to interrupt their work to respond to the telephone, and only Mr. ΔΔ, who is the called name uttered from the speaker, can answer the 451 call.
It would be good if it came in 1st and 2nd place.

Next, the operation of J2 when the called name is absent will be explained.

Before the called party leaves his/her seat to go out, information such as the destination, destination phone number, 111 seat time slot, whether or not to call, etc. is stored in the second voice registration storage section 3 using the called party's name as a key. Register in the area. The manner of registration in this case may also follow the example shown and explained in FIG. 2.3.

In this state, when a call is received, the voice recognition unit 2 recognizes the name of the called party, and uses the name of the called party as a key to form a response message in the absence of the & voice registration storage unit 3. Search to see if it is registered in the second area of . As a result of the search, if it is found that the phrases and words that form the response message corresponding to the called name are registered, these necessary phrases and words are selectively derived and synthesized by the speech synthesis unit 4. , the message is transmitted to the sender via the transmitting/receiving section 1.

This allows for automatic responses even when you are not available.

It goes without saying that known techniques may be applied to each method of speech recognition and speech synthesis.

As described above, according to the present invention, by equipping the telephone with voice recognition and speech synthesis functions, it is possible to eliminate the ringing sound of the telephone and directly speak the name of the called party in the office. This has the effect that even if a worker is not working, he or she can receive information in real time and is not forced to make unnecessary responses to other workers.

Furthermore, when the called party is seated at 111, by registering the destination and dialing J5, there is an effect that the telephone itself can automatically answer the call and tell the destination and so on.

[Brief explanation of drawings]

FIG. 1 is a block diagram of an embodiment of the present invention, FIG. 2 and FIG.
The figure is a diagram showing an example of registration in the voice registration storage unit. Explanation of symbols of main parts 2...Speech recognition section 3...Speech registration storage section 4...Speech synthesis section

Claims (2)

[Claims] (1) A voice registration storage means in which voice information necessary for notifying the arrival of a call is registered in advance, a voice recognition means for recognizing the voice of the sender, and a voice registration memory according to the recognition result of the voice recognition means. 1. A telephone device comprising speech synthesis means for selectively deriving speech information necessary for notifying a called person of a call from the means and synthesizing the speech information. (2) a first voice registration storage means in which voice information necessary to notify the incoming call is registered in advance; a second voice registration storage means in which voice information necessary for responding to the sender is registered in advance; a voice recognition means for recognizing the voice of the sender; and selectively deriving voice information necessary for notifying the called party of the call from the first voice registration storage means according to the recognition result of the voice recognition means. a first speech synthesis means for synthesizing speech;
A second device for selectively deriving necessary voice information to be sent to the sender from the second voice registration storage means according to the recognition result of the voice recognition means when the called party is absent, and outputting a response while synthesizing the voice information. A telephone device comprising a voice synthesis means.