JPH06104973A - Automatic answering telephone set - Google Patents

Abstract

PURPOSE:To reply a call of a caller in its language at the setting of the automatic message recording mode and to record a message of the caller or the like. CONSTITUTION:When the automatic message recording mode is set to a telephone set 1, a call tone is inputted from an input output section 2, discriminated by a call discrimination section 3 via a control section 12 and a handset is hooked off by a hook control section 4. A voice signal from the telephone line is analyzed by a voice analysis section 5, a language discrimination section 7 compares the analyzed language with data read from a language storage section 6 to discriminate a language offering the highest coincidence. Data from the language discrimination section 7 are inputted to a discrimination section 9 and data of a language are discriminated based on the data read from a message storage section 8, a speech synthesis section 10 synthesizes the data into a message voice signal, and it is sent from the input output section. Then a recording section 11 is controlled for the recording via the control section to record a voice signal from the telephone line.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION The present invention relates to an answering machine,
The present invention relates to a device which determines a language of a partner and sends a response message in a corresponding language.

[0002]

2. Description of the Related Art An answering machine takes an off-hook with a preset number of ring tones according to a required answering machine setting, and outputs a message voice to record a message because it is absent, and then an inputted voice. Is to be recorded. Normally, only one type of message voice is prepared. Therefore, for example, in the case of a telephone call from a foreigner who is unfamiliar with Japan, the message may not be recorded because the meaning does not make sense. Message voice may be sent in multiple languages one after another, but this will increase the message delivery time, annoy the other party, or hang up before the native message is sent. There are also problems such as being lost.

[0003]

In view of such a point, the present invention analyzes the inputted voice, compares it with the data of each language stored in advance, and discriminates which language it is. An object is to provide a message in which a message in a corresponding language is read out, sent to the other party, and the input voice is recorded.

[0004]

SUMMARY OF THE INVENTION In order to solve the above problems, the present invention provides an input / output unit for inputting / outputting a call signal and an input / output unit for inputting / outputting a call signal in an answering machine for recording a receiving signal by a required answering machine setting. A voice analysis unit that analyzes voice, a language storage unit that stores voice data for each language, a language determination unit that compares the data from the voice analysis unit with the data read from the language storage unit, and a message voice by language A message storage unit for storing, a determination unit for determining a message corresponding to the data from the language determination unit based on the data read from the message storage unit, the input / output unit, a voice analysis unit, a language storage unit, a language determination unit , A message storage unit and a control unit for controlling the discrimination unit, so that the message voice discriminated by the discrimination unit is sent out through the input / output unit and the input voice is recorded. And there is provided a telephone answering device.

[0005]

With the above construction, in the answering machine according to the present invention, when the telephone is set to answering machine,
Off-hook with the required number of ringing tones, analyze the input voice, determine the language by comparing with the pre-stored data, read the message data of the corresponding language, synthesize it into voice and send it out and input. Record voice.

[0006]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of an answering machine according to the present invention will be described in detail below with reference to the drawings. FIG. 1 is a block diagram of essential parts of an embodiment of an answering machine according to the present invention. In the figure, 1 is a telephone. An input / output unit 2 inputs / outputs a call signal and the like with the telephone line when the telephone 1 is set to be away. Reference numeral 3 is a call discrimination unit, which outputs a signal with a ringing sound of a required number of times. Reference numeral 4 is a hook control unit, which takes the device off-hook by a signal from the call discrimination unit 3. A voice analysis unit 5 frequency-analyzes the input voice signal to extract a characteristic pattern.
A language storage unit 6 stores, for each language, a characteristic pattern of voice, such as a word that is often used first when calling a telephone. A language discrimination unit 7 compares the data from the voice analysis unit 5 with the data read from the language storage unit to discriminate the language with the highest degree of coincidence. 8 is a message storage unit,
Since I am out, I will memorize the message to record the message by language. A discrimination unit 9 discriminates the data read from the message storage unit 8 and corresponding to the data from the language discrimination unit 7. A voice synthesis unit 10 synthesizes the data read from the message storage unit 8 into a voice based on the determination by the determination unit 9. Reference numeral 11 is a recording section for recording the input voice. A control unit 12 controls each unit of the device.

Next, the operation of the answering machine according to the present invention will be described. Switch the telephone 1 to answering machine operation. As a result, when calling from the telephone line, the ringing tone is input from the input / output unit 2 to the ringing determining unit 3 via the control unit 12, and a signal is output with the required number of ringing tones. In response to the signal from the call discrimination unit 3, the hook control unit 4 via the control unit 12 takes the device off-hook. Then, the voice input via the input / output unit 2 is input to the voice analysis unit 5 via the control unit 12, and is divided into, for example, continuous voice regions, and the spectrum is extracted by sampling at a required frequency. The language storage unit 6 stores, for example, a spectrum pattern of a word often spoken first when making a call, such as a word of each country corresponding to "Hello" or a name of a subscriber of the phone. It is stored as a standard pattern for each language. Then, the spectrum pattern from the voice analysis unit 5 is input to the language discrimination unit 7 and compared with the data read from the language storage unit 6 to discriminate the one having the highest degree of coincidence.

Next, the message data is read from the message storage unit 8 via the control unit 12, the discrimination unit 9 discriminates the data corresponding to the language discriminated by the language discrimination unit 7 via the control unit 12, and the speech synthesis unit It is input to 10, synthesized into a message voice, and sent to the other party of the call via the input / output unit 2. In response to the message transmission, the recording unit 11 via the control unit 12
Is controlled to a recording operation, and the voice input through the input / output unit 2 is recorded on a recording tape or the like for a required time.

The language may be discriminated by fuzzy inference. In this case, the similarity from the data read from the voice analysis unit 5 to the data read from the language storage unit 6 is inferred, the maximum similarity is compared, and a similar language is inferred.

[0010]

As described above, according to the answering machine according to the present invention, when a call is made to the telephone set to the answering machine, the answering machine is answered in the language of the other party of the telephone and the message etc. is recorded. Therefore, it is effective when installed in an office or the like where multinational people often call. If the type of language is inferred by fuzzy inference, the program can be simplified and high-speed processing can be performed as compared with the case of comparing input voice data one by one.

[Brief description of drawings]

FIG. 1 is a block diagram of a main part of an embodiment of an answering machine according to the present invention.

[Explanation of symbols]

 1 Telephone 2 Input / output unit 3 Call detection unit 4 Hook control unit 5 Voice analysis unit 6 Language storage unit 7 Language discrimination unit 8 Language discrimination unit 8 Message storage unit 9 Discrimination unit 10 Speech synthesis unit 11 Recording unit 12 Control unit

Claims (1)

[Claims] 1. An answering machine for recording an incoming call signal according to a required answering machine setting, an input / output unit for inputting / outputting a call signal, and a voice analysis unit for analyzing voice from the input / output unit.
A language storage unit that stores voice data by language, a language determination unit that compares data from the voice analysis unit with data read from the language storage unit, a message storage unit that stores message voice by language, and a message storage Controls the input / output unit, the voice analysis unit, the language storage unit, the language determination unit, the message storage unit and the determination unit, which determines the message corresponding to the data from the language determination unit based on the data read from the unit. An answering machine which is configured to control the control unit, sends the message voice discriminated by the discriminating unit through the input / output unit, and records the input voice.