JPH03239052A - Automatic answering telephone set - Google Patents

Abstract

PURPOSE:To discriminate from which party a telephone call comes at a glance by using a voice recognition means to recognize the opposite party so as to light a display device of a relevant one-touch dial. CONSTITUTION:A call signal detection circuit 3 detects a call signal at the arrival of a call, the signal is subject to 2/4-wire conversion by a speech network circuit 8 and the result enters a voice recording reproduction circuit 10 and recorded in a storage element 11. When a 'specific word' registered in advance is detected in a message during the recording of the message, a CPU 13 sets a flag (identification information) to an internal register (2nd storage section) in response to a detection signal by a voice recognition circuit 18. The flag information is stored corresponding to a voice message and initialized after the reproduction of the voice message. Then a display device corresponding to a one-touch dial with a telephone number of a recognition party registered therein is lighted.

Description

[Detailed description of the invention] [Industrial application field] The present invention relates to an answering machine.

[Prior Art] Conventional answering machines use magnetic tape or memory to store response messages and business matters.

[Problem to be Solved by the Invention] However, in the conventional example described above, the only way to know who is calling is to play and listen to the recorded contents of the business, so it is difficult to receive calls from multiple people. In some cases, it took a long time to play.

[Means for Solving the Problems] The present invention provides a voice recognition means, a recording means, and a display means for displaying information about the other party recorded by the recording means according to the result of the voice recognition means. This makes it possible to know the other person without having to play back a recorded message.

[Example] In this example, a voice recognition unit detects a voice signal of a specific word of a recognition target person registered in advance in correspondence with one-touch dialing from among a large number of voice signals received. Furthermore, when storing the detected audio signal, identification information indicating the detected recognition target person is also stored. Therefore, even if the transmitter side does not have a function of generating an identification number, the transmitter can be identified based on this identification information. Additionally, it is possible to light up the display that corresponds to one-touch dialing with the phone number of the person registered in advance, so you can know that a specific person has called you before playing the message. .

FIG. 1 shows the basic configuration of an embodiment of the present invention.

In FIG. 1, reference numeral 100 denotes a voice recognition unit that compares the registered voice signals of at least one recognition target person registered in advance and the received voice signal for characteristic patterns, and detects the voice signal of any one of the recognition target people. be. 200 is a first storage unit that stores received audio signals. 300 is the first
The second storage unit stores identification information indicating the detected recognition target person in association with the audio signal stored in the storage unit. Reference numeral 400 is an instruction unit that instructs reproduction of an audio signal.

Reference numeral 500 denotes a reading unit that reads out an audio signal corresponding to the identification information from the first storage unit based on the identification information in the second storage unit in response to an instruction from the instruction unit. 600 is an output section that reproduces and outputs the audio signal read out by the reading section.

Note that the voice of the recognition target person is the voice of the recognition target person's name, and when the voice recognition unit 100 detects any voice signal of the recognition target person, it outputs the registered voice signal of the recognition target person to the output unit. do.

FIG. 2 shows a circuit configuration of an embodiment of the present invention.

In FIG. 2, 1 is a telephone line for transmitting information. 2 and 4 are diode bridges for full-wave rectification. 3 is a ringing signal detection circuit, and 5 is a relay, which is linked to on-hook and off-hook states of the handset, but is not connected when on-hook. 5 relay 5 is connected when off-hook. Also, when the relay 5 detects a call signal, the central processing unit! Connection can also be made under the control of the (CPU) 13. 6 is a power supply stabilizing circuit for operating this device, and 7 is a tone or pulse dialer for sending a selection signal. 8 is a speech network circuit for 2-wire to 4-wire conversion, and 9 is a receiver. 1
0 is an audio recording for writing and reading an audio signal into the storage element 11;
The playback control circuit L1 constitutes a readout section together with the audio recording and playback control circuit IO or the CPU 13, which is a storage element (R1 storage section) for storing digitized audio signals.

Reference numeral 12 denotes a parallel interface (I 10 ) for determining the presence or absence of a calling signal, controlling the audio recording/playback control circuit IO, and controlling the clock generation circuit 4.

13 has built-in read-only memory (ROM) and random access memory 'J (RAM) (7) CPU"t"
be. The CPU 13 executes the processing procedure shown in FIG. 3 and instructs the various parts of the apparatus to operate. 14 is a clock generation circuit. Reference numeral 15 denotes an operation/display section for setting whether to record an answering machine, playback, and one-touch dialing. The operation/display section 15 operates as an instruction section. Reference numeral 18 denotes a speech recognition circuit, which converts the speech of a recognition target person inputted from a transmitter (not shown) regarding a "specific word" into a characteristic pattern and registers it in an internal memory.

At this time, as shown in Figure 6, "Koizuku" is on the touch dial A and "Iroha" is on the one-touch dial B.
In the one-touch dial C, a ``specific word'' such as a name is recorded in correspondence with the one-touch dial switch 15, such as ``nihohej''. The voice recognition circuit 18 converts the voice signal received via the telephone line l into a characteristic pattern, and then performs a match comparison with each registered pattern in the internal memory to detect a "specific word" in the received voice. .

Note that, for example, a word recognition circuit may be used.

Next, the operation of the above configuration will be explained using the flowchart shown in FIG.

In FIG. 3, when there is an incoming call, the calling signal detection circuit 3 detects the calling signal (step 520). When the calling signal is detected, the relay 5 is connected, and the voice signal is sent to the speech network circuit 8 through the 2-4 wires. The audio signal input to the audio recording/reproducing circuit 10 is converted into a line and input to the audio recording/reproducing circuit 10 (step 530).
It is sampled by the tying clock created in step S40 and recorded in the memory element 11 (steps S40 to
560).

During message recording, if a pre-registered "specific word" is detected in the message, the CPU 13 sets a flag (identification information) in the internal register (second storage section) in response to the detection signal from the voice recognition circuit 18. (Step S7
0-5100). After voice recognition, set rlJ,
Later, when the message is played back, it is set to "0".

This flag information is stored in association with the voice message as shown in FIG. 5, and is initialized after the voice message is played back. Next, the display corresponding to the recognized person's phone number or the registered one-touch dial is turned on.

This notifies the user that a specific person has called. By doing this, you can avoid recording sales calls and prank calls.

The contents of the audio signal in this embodiment are shown in FIG. 5, and the words to be recognized are shown in FIG. 6.

Next, when reproducing the audio signal, when the reproduction switch of the switch 15 is turned ON based on the processing procedure shown in FIG.
The message stored in the memory element 11 is reproduced by the audio recording/reproducing circuit 10, the audio signal is amplified by the amplifier circuit 16, and is output from the speaker 17. in this case,
The voice message having the flag information stored during message recording is first played back via the voice recording and playback control circuit 10 according to instructions from the CPU 13, and the rest are deferred, so that the voice message can be registered in one-touch dialing and can be sent to a specific person. Priority is given to outgoing messages.

[Other Examples] Another example regarding the procedure for reproducing audio will be described. The configuration of this embodiment is the same as that in FIG.

When the answering mode is set by the operation/display unit 19, a message from the other party is recorded when a call arrives. When a message or a message is recorded from a person registered on a one-touch key of the operation/display section 19, a lamp provided corresponding to the one-touch key is lit. The CPU 13 stores the recording position of the message from the other party registered in the one-touch key and the identification code of the other party.

On the other hand, the playback mode is set using the operation/display section 19.
When the operator presses the one-touch key corresponding to the lit lamp, the CPU 13 detects this and reproduces the instructed message based on the pre-stored recording position and the other party's identification code.

Note that the name of the other party may be displayed on the liquid crystal display. In this case, the other party may display the other party registered in the voice recognition circuit 18 in advance, regardless of the other party registered in the one-touch dial. It is possible.

[Effects of the Invention] As explained above, according to the present invention, voice recognition means is used to recognize the other party, and the one-touch dial indicator corresponding to the recognized person is lit. I know if there was.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing the basic configuration of an embodiment of the present invention. FIG. 2 is a block diagram showing a specific circuit configuration of an embodiment of the present invention. Fig. 3 is a flowchart of an embodiment of the present invention, Fig. 4 is a flowchart of an embodiment of the invention, Fig. 5 is an explanatory diagram showing the content of the audio signal in an embodiment of the invention, and Fig. 6 is an embodiment of the invention. FIG. 2 is an explanatory diagram showing words to be recognized. 13 is a CPU; 15 is an operation/display unit 18 is a voice recognition circuit. Figure 1 Figure 4 Flowchart diagram

Claims (1)

[Scope of Claims] An answering machine comprising: a voice recognition means; a recording means; and a display means for displaying information about the other party recorded by the recording means in accordance with the result of the voice recognition means.