JPH08163228A - Voice remote control automatic answering telephone system and operation instruction receiving method by voice - Google Patents

Abstract

PURPOSE: To remotely control the operation of the telephone system through a line corresponding to the input of a voice. CONSTITUTION: A previously decided voice, command for instructing the operation of an automatic answering telephone means and password for specifying a speaker are stored in a word pattern model 111 while being made mutually correspondent. The password due to the voice is received through a telephone line and a line interface 102, and a comparison processing part 110 compares the received password voice with a password stored in a command storage means. When the speaker is matched as a result of comparison, the operating instruction of an automatic answering telephone set due to the voice is received. Next, the 'reproduction' of a command for reproducing the automatic answering telephone is received and the received 'reproduction' is compared with the voice stored in the word pattern model 110 by a comparison processing part 109. When they are matched as a result of comparison, the reproduction of a recorded message is executed.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a telephone device having an answering machine function for receiving and answering an incoming call from a destination, and more particularly, a voice remote control answering machine device capable of operating the telephone by voice input. Regarding

[0002]

2. Description of the Related Art Conventionally, a telephone device having an answering machine function receives an incoming call from a destination and responds to the incoming call.
It has a function to record the message of the other party and play the recorded message. This reproduction can be performed by the user operating the reproduction button of the answering machine. Further, as shown in FIG. 8, reproduction can be instructed using the PB signal by the public telephone terminal 810 or the telephone terminal 820 via the telephone line. For example, when a message is reproduced, remote control can be performed by instructing a code of a predetermined combination of PB signal codes 0 to 9, #, and * from the public telephone terminal 810 or the like.

[0003]

In the above-mentioned conventional answering machine, the key operation by the PB signal is required. Further, there is a problem in that it is necessary to remember the code and procedure of a predetermined combination of these key operations.

In order to solve the above-mentioned problems, the present invention provides a voice remote control answering machine and a voice operation instruction receiving method capable of remotely controlling the operation of the telephone device via a line by voice input. The purpose is to do.

[0005]

In order to solve the above problems, the present invention comprises answering machine means for receiving an incoming call from a destination, recording a message of the destination, and reproducing the recorded message. In a telephone device, a voice input means for inputting voice through a telephone line, a command storage means for storing a predetermined voice and a command for instructing the operation of the answering machine in association with each other, and the voice input. Comparing means for comparing the voice input by the means with the voice stored in the command storing means, and the command corresponding to the voice that matches as a result of the comparison by the comparing means is extracted from the command storing means, And executing means for executing an operation corresponding to.

As another solution, in a telephone device connected to a line and controlling the line, a voice input unit for inputting voice through the telephone line, and a voice input by the voice input unit. Is a judgment means for judging whether or not it is a voice input indicating an instruction of a predetermined operation of the telephone device, and a command storage means for storing a predetermined voice and a command indicating the operation in association with each other, The voice input by the voice input unit is compared with the voice stored in the command storage unit, and the voice input by the voice input unit is input by the determining unit. If it is determined that the command corresponding to the matched voice is extracted from the command storage unit as a result of the comparison by the comparison unit, Having execution means for executing an operation corresponding to the mode.

As a method for receiving operation instructions by voice in the answering machine, a step of receiving and responding to an incoming call from the other party, a step of receiving voice through a telephone line, and the received voice is a specific talk. A step of determining whether or not the voice is by a person, and as a result of the determination, if the received voice is a voice by a specific speaker, a voice for instructing a predetermined operation regarding reproduction of the message is received. And a step of performing a predetermined operation regarding reproduction of the message when the voice is accepted.

[0008]

In the command storage means, a predetermined voice and a command for instructing the operation of the answering machine are stored in association with each other.

The voice input means inputs voice through the telephone line, and the comparing means compares the voice input by the voice input means with the voice stored in the command storage means. As a result of the comparison by the comparison means, the execution means extracts a command corresponding to the matched voice from the command storage means and executes an operation corresponding to the command.

Thus, the operation such as reproduction of the answering machine can be remotely controlled by voice through the telephone line.

Further, for security, the password is registered in the password storage means for each speaker so that only the registered speaker can perform operations such as reproduction of the answering machine. Good.

[0012]

DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of a voice operation telephone device according to the present invention will be described below.

FIG. 1 is a block diagram of a voice response / recognition function telephone system. In FIG. 1, a voice response / recognition function telephone system is connected to a public network (PSTN) through a transmission line, a call circuit 120 for controlling a call, and a handset 170 for outputting voice of a communication partner. , A receiver amplifier 160 for amplifying voice, a transmitter 190 for inputting voice, a transmitter amplifier 180 for amplifying voice, a headset 155 in which a speaker and a microphone are integrated,
Headset controller 15 for controlling input / output of voice
0, a voice recognition control unit 140 that performs voice recognition by collating with a voice pattern registered in advance, and an answering machine control unit 130 that has an answering machine function for answering the telephone of the other party at the time of absence. The answering machine control unit 130 has an answering machine mode set when the answering machine control unit makes a response, and when the answering machine mode is set, it answers the telephone of the other party. The headset 155 may not be provided.

The voice remote control answering machine according to the present embodiment accepts a voice operation instruction when performing an operation instruction such as a reproduction instruction of a message recorded in the answering machine via the line.

The internal circuit of the voice-operated telephone device is constructed as shown in FIG. In FIG. 2, the SPC unit 2
Reference numeral 00 denotes the voice recognition control unit 140 in FIG. 1, which performs voice recognition. In addition, the H / S hands-free control unit 208
Corresponds to the headset control unit 150 shown in FIG. 1 and controls the input / output of voice. The answering machine control unit 230 corresponds to the answering machine control unit 130 shown in FIG. Answering control unit 230
Can receive an incoming call from the other party, record the message of the other party, and reproduce the recorded message. The absence control unit 230 includes an absence message recording / playback unit 236 for recording / playing a message when the user is away.
A fixed message section 235 that stores a message to be sent when an incoming call is answered, a recording / playback controller 233 that controls recording and playback, and an analog signal such as voice
Modulates to CM signal (Pulse Code Modulation), and P
A modulator 232 for modulating the CM signal into an analog signal;
It has a DRAM 234 that stores a signal modulated in CM and a MIX unit 231 that mixes an audio signal. Also, the communication path switch 211 and the office line interface 220
The telephone function unit control CPU 250 corresponds to the call circuit 120 shown in FIG. The call path switch 211 is
The determination unit is for determining whether or not the input voice is a voice for an operation instruction. C for controlling telephone function unit
The PU 250 controls the absence controller 230 according to the operation command recognized by the SPC unit 200.

As shown in FIG. 2, modular lines 223 and 224 connect the central office line 221 and the central office line interface 220 controls the originating or terminating central office line. The speech path switch 211 sends the voice input from the office line to the SPC unit 200, the answering machine control unit 230 or the office line interface 220 that performs voice recognition. In the conventional telephone device, the answering machine is operated by the PB signal through the line, but in the present embodiment, these operations are performed by voice instruction. In the SPC unit 200 that performs voice recognition, as will be described later, when the operation command is recognized by voice, the C for telephone function unit control is executed via the parallel interface 202.
The PU 250 is instructed, and the telephone function unit control CPU 250 follows the operation command to instruct the absence control unit 23.
Control 0. When the message recorded in the absence message recording / playback unit 236 is played back, it is controlled by the recording / playback controller 233. In this embodiment, the playback instruction is for controlling the telephone function unit via the SPC unit 200. It is output from the CPU 250. Further, when performing remote control, the station line interface 220 other than the answering machine control unit 230 may be controlled. In addition, the RO that stores the control program in the CPU 250 for controlling the telephone function unit in the parallel interface 202.
M (Read Only Memory) and EEPROM (Electric
ally Erasable and Programmable RandomAccess Memor
y) and a RAM (Random memory) for temporarily storing data.
m Access Memory) and RTC (R for measuring time)
It is possible to access these memories and the like from the CPU 250 for controlling the telephone function unit by connecting to the eal time clock).

Next, the operation of each functional block will be described with reference to the functional block diagram of the voice operation telephone device shown in FIG.

In FIG. 3, 101 is a main control unit for managing the entire apparatus, and 102 is a line i / f connected to a telephone line.
Section, 103 is a line control section for monitoring and controlling incoming and outgoing calls, 1
Reference numeral 04 is a call path control unit that controls connection of the call path, 105 is a sound source unit that outputs a service sound and a guidance message,
106 is an answering machine recording / playback control section, 107 is a voice recording section for answering machine recording, 108 is an A / D converter for converting an analog sound and a digital sound, 109 is a voice analyzing section for analyzing a digital voice signal, and 110 is a voice A comparison processing unit that compares the analysis result with the word pattern model, and 111 is a word pattern model unit that stores in advance the parameters of the words necessary for speech recognition. The word pattern model unit 110 stores a voice pattern model corresponding to the operation command in advance. The answering machine recording / playback control unit 106 corresponds to the answering machine control unit 130 shown in FIG.

In the present embodiment, the voice analysis unit 108 extracts a parameter representing a voice feature, and the extracted parameter and the parameter of the word (command) registered in advance in the word pattern model unit 110 are used. , DP (Dynamic Programming) matching and HMM
(Hidden Markov Model) is used for speech recognition. The DP matching method absorbs expansion and contraction between two patterns of the parameter extracted from the input voice and the standard model registered in the word pattern model unit 110, and
The HMM method uses the Markov model to efficiently find the best corresponding path of two patterns. The output spectrum of various symbols in each state of the Markov model and the transition probabilities between the states make the speech spectrum The stochastic variation of is calculated and the word output with the maximum probability is used as the recognition result. Voice recognition can be performed by these methods. A signal processing DSP can be used for voice recognition. Further, in the present embodiment, it is possible to perform the voice recognition by the specific speaker recognition so that the use by another person is excluded and only the specific registered user can give the operation instruction by the voice. Security can be achieved by recognizing the speaker based on the characteristics of the individual included in the voice.

FIG. 9 shows an example of the voice command. As shown in FIG. 9, the operation is defined for each command, and the voice parameter for each command is registered in the word pattern model unit 110 in advance. Further, the main control unit 101 shown in FIG. 3 gives an operation instruction in accordance with the recognized command. As shown in FIG. 9, the commands include “play” for instructing to start playing the message recorded most recently among the recorded messages, and further, in terms of time from the played message. It is possible to register "rear" or the like for instructing to prepare the reproduction of the message recorded later. Furthermore, a command or the like for confirming the number of recorded messages can be provided. Also, a password command for determining the telephone user can be registered in advance such as "Suzuki". In the case of voice recognition by a specific speaker, even if the registered command and the uttered voice match, if the speakers do not match, it can be recognized as non-match.

Further, the speaker 11 displays a guidance message indicating that it is possible to accept a voice input indicating an operation instruction.
After outputting the guidance message, the voice input from the microphone 112 may be determined to be the voice indicating the operation instruction. For example,
If the word "Suzuki" is input after sending out a guidance message such as "Please speak", it is compared with the password command registered in the word pattern model unit 110, and if they match, thereafter. It is possible to execute the input operation instruction by the voice and not execute the operation instruction by the voice input thereafter if they do not match.
The guidance message can be registered in the sound source 105 in advance. In addition, as a guidance message, if there is no matching command or if voice recognition is not possible, such as "Unrecognized.""Password did not match." The guidance message of can be output. If voice recognition is possible, the voice registered in the word pattern model unit 110 can be notified by echo back. Thereby, the operating state can be easily confirmed. Furthermore, the procedure may be ensured by transmitting the voice recognition result so that the user can confirm the recognition result and utter a confirmation word.

As a method of registering the voice corresponding to the command in the word pattern model section 110, it can be registered in advance according to the registration procedure flow as shown in FIG. As shown in FIG. 10, registration is performed by inputting a voice to be registered after instructing an identification number of a command by key input provided in the telephone device. For example, when registering a call command, after pressing the command identification number "3" shown in FIG. 9 in step 1806 and step 1807 or step 1808, the voice to be registered is spoken as "back". Then
Register. In this way, the voice pattern can be registered in advance.

Further, a method of registering a password for each speaker will be described with reference to a speaker registration flowchart shown in FIG.

As shown in FIG. 11, the password is registered after the user presses the dial indicating that the password is registered (S1701, 1702, 1703 and 1).
704), the speaker number is registered (S1705), and the password is uttered after there is a notification sound to start the registration. When the password registration and the speaker number are instructed, the voice remote control answering machine outputs a notification sound to the effect that registration is started, and the registration is completed (may be completed after a specific time has passed). Output a confirmation sound. After that, the registration address of the word pattern model unit 110 is designated, and registration is performed at the designated registration address. Alternatively, the registered addresses may be sequentially registered in the vacant addresses instead of being designated. In this way, the speaker can be registered.

Next, in the case of actually remotely controlling the answering machine by voice, the realization form of the voice remote control answering machine shown in FIG. 4 and the control operation in the voice remote control answering machine shown in FIG. 3 are shown in FIG. Also, description will be made with reference to the flow shown in FIG. 6 and the sequence shown in FIG. 7.

As shown in FIG. 4, in the voice remote control answering machine according to the present embodiment, the public telephone terminals 410 and 420 and the telephone terminals 430 and 440 are used to send DP signal or PB signal. The operation can be instructed from either phone regardless of whether or not it is used. For example, when reproducing a message, the public telephone terminal 41
This can be done by uttering the voice "play" from 0 etc. via the telephone line of the public network. This allows remote control of message playback.

FIGS. 5 and 6 are flowcharts of control of the voice remote control answering machine shown in FIG. Further, in FIG. 7, the CPU of the main control unit 101 and the voice analysis unit 1
08, a comparison processing unit 109 and a voice recognition board corresponding to the sound source 105, and a sequence diagram showing the exchange with the network. Between the CPU and the voice recognition board, identification numbers of a command for instructing the voice recognition board to operate from the CPU and a response that the voice recognition board responds to the CPU are predetermined. For example, command 0 is a command for instructing initialization of the voice recognition board, command 2 is a command for instructing a speaker or a word, and command 7 is a command for specifying a speaker. Yes, command 10 is a command for instructing voice recognition. Also, the response 2 is
Response 3 is a response output when voice recognition is possible, and response 3 indicates a response output when voice recognition is not possible. Also, a guidance message can be output from the voice recognition board. The guidance message output from the voice recognition board may be directly output to the network via the CPU of the main control unit 101, or the guidance message may not be output to the network when not necessary.

As shown in FIG. 5, when the voice remote control answering machine is in the standby state, the incoming call from the line is monitored, and when the incoming call is detected (S501), the normal answering machine mode is set if the answering machine is not set. Incoming call processing. When the answering machine is set, the loop is closed, the incoming call is answered (S502), the answer message is output to the line, the answer message confirmation sound is sent (S504), and the other party's message is recorded. In order to do so, the answering machine recording is started (S505). Further, when the voice path between the voice analysis unit 109 and the line control unit 103 is connected (S512) and voice is received via the line, the main control unit 101 causes the comparison processing unit 1
10 is instructed to compare whether the received voice matches the password of the user confirmation word voice, and the comparison processing unit 110 notifies the main control unit 101 of the comparison result,
If they do not match (S507), it is determined that it is the message recording and the answering machine recording is continued (S509).

If they match, the answering machine recording is stopped (S
509), the recording up to the start of recording the message is erased (S510), and the answering machine voice instruction standby state is set (S511).

In FIG. 6, in the standby state (S
511), when a sound is received from the line (S601), the sound is transmitted to the voice analysis unit 109 via the communication path control unit 104.
Then, the comparison processing unit 109 performs voice recognition processing, and notifies the main control unit 101 of the recognition result. When it is recognized as the message reproduction instruction word voice (S602), the reception confirmation sound or the guidance message, or the echo back of the recognized voice is output to the line, and the voice accumulation unit 107 is output.
If the message is stored in, the message is played (S60
5) Output a completion sound or guidance message to the line. When the message is not accumulated, the incomplete sound is output to the line. When it is recognized as the backward message reproduction instruction word voice (S603), the reception confirmation sound or the guidance message, or the echo back of the recognized voice is output to the line, and the backward message is accumulated in the voice accumulation unit 107. If so, prepare to play back messages (S604),
A completion sound or a guidance message is output to the line (S533). When the backward requirement is not accumulated, an incomplete sound or guidance message is output to the line.
After that, the process returns to the standby state (S511).

In this way, the answering machine recording / shown in FIG.
It is possible to receive a voice instruction from a remote place to reproduce the message recorded in the reproduction control unit 106, and control according to the received instruction. Further, if the password is accepted and the passwords do not match, the reproduction instruction can be rejected. In addition, a guidance message can be output to prompt utterance. Further, when the recognition is not possible, the user can know that the voice cannot be recognized by outputting a guidance message to that effect. Further, as shown in FIG. 7, as a result of the comparison by the comparison processing unit 109, the word pattern model 1
The voice stored in 10 or the voice input via the line may be echoed back to the line. This allows the user to know the voice recognition result.
Furthermore, in the case of voice recognition by a specific speaker, it is possible to accept an operation instruction such as "play" without accepting a password.

Further, FIGS. 12 to 14 show more detailed flow charts of the control of the voice remote control answering machine shown in FIG.

As shown in FIG. 12, when the voice remote control answering machine is in the standby state 300, the incoming call from the line is monitored (301), and when the incoming call is detected, the normal incoming call processing is performed unless the answering machine is in the answering machine mode. Become. In the answering mode, the speaker 11 is receiving while receiving the 16 Hz signal from the line.
A ring tone is output from 2 (305) to notify that there is an incoming call. When the 16 Hz signal from the line is interrupted, the number of ringing tones is counted up (307), and when the number of ringing tones exceeds the set value, the loop is closed and the call is answered (308), and a response message is sent to the line. Output to (30
9), the communication path between the answering machine recording / playback unit 106 and the line control unit 103 is connected (310), and the answering machine recording is started (311). Furthermore, the voice analysis unit 109 and the line control unit 1
The communication path between the communication terminals 03 and 03 is connected (312), and the main controller 101
Outputs a speaker selection command to the comparison processing unit 110 (31
3), the process moves to the speaker selection state (314).

In FIG. 13, the speaker selection state (314)
When a sound is received from the line at the time, the sound is input to the voice analysis unit 109 via the communication path control unit 104, the comparison processing unit 109 performs voice recognition processing, and the recognition result is sent to the main control unit 101. Notice. If it is recognized as a voice word voice for speaker selection, answering machine recording is stopped (31
8) Then, the sound recorded from the time when the answering machine recording is started is discarded from the voice storage unit 107 (319), the utterance start sound of the voice remote operation word is output to the line (320), and the instruction waiting state (321) is set. Move. If the speaker selection password word cannot be recognized as voice, the communication path between the voice analysis unit 109 and the line control unit 103 is disconnected (317), and the normal answering machine recording process is performed.

In FIG. 14, an instruction waiting state (321)
When a sound is received from the line at the time, the sound is input to the voice analysis unit 109 via the communication path control unit 104, the voice recognition process is performed in the comparison processing unit 110, and the recognition result is sent to the main control unit 101. Notice. When it is recognized as the message reproduction instruction word voice, a reception confirmation sound is output to the line (32
5) If the message is stored in the voice storage unit 107, the message is reproduced (327), and a completion sound or a guidance message for prompting the next operation is output to the line (3).
28). If the message is not stored, an incomplete sound or a guidance message indicating that is output to the line (329). After that, an utterance start instruction sound of the voice remote control word is output to the line (335), and the instruction waiting state (32
Return to 1). When it is recognized as the backward message reproduction instruction word voice, a reception confirmation sound is output to the line (330), and when the backward message is accumulated in the voice accumulation unit 107, the backward message is prepared for reproduction (332). ), And outputs a completion sound or guidance message to the line (333). If no backward message is stored, an incomplete sound or guidance message is output to the line (334). After that, a voice start instruction sound of the voice remote operation word or a guidance message is output to the line (335), and the instruction waiting state (32
Return to 1).

In addition, as a result of the comparison, if it is not recognizable, an unrecognizable notification sound or "Could not be recognized"
A guidance message such as "" may be sent to the line. Further, the number of unrecognizable times may be counted, and when the number of unrecognizable times reaches a specific number, a beep sound or a guidance message indicating that the unrecognizable times may be output. Alternatively, a cancellation instruction word for instructing cancellation of reproduction may be registered as a command, and execution of reproduction may be stopped when the cancellation instruction word is received and recognized.

In this way, it is possible to receive a voice instruction from a remote place to reproduce the recorded message and control according to the received instruction.

As described above, according to the above embodiment, in the voice remote control answering machine, it is possible to remotely control the operation of the answering machine by voice input without operating the instruction such as the PB signal. You can For this reason, it is easy to use even for the elderly and handicapped persons who cannot operate by hand, and it is possible to provide an easy operation by voice recognition.

Further, by registering the password and accepting the input of the password for comparison, it is possible to prevent the operation instruction from being accepted unless the passwords match. Therefore, it is possible to exclude the operation instruction of the person other than the registrant. . This can be useful for security. If voice recognition is performed by a specific speaker instead of accepting the password, it is possible to eliminate an operation instruction from another person other than the registered speaker.

Further, a guidance message indicating that it is possible to accept a voice input indicating an operation instruction is transmitted to the line, and after the guidance message is transmitted, the voice input from the line can be accepted as an operation instruction. .

In addition, as a guidance message, when there is no matching command or when voice recognition cannot be performed, a guidance message to that effect is output, such as "Failed to recognize." The user can know the recognition result.

[0042]

According to the present invention, in the voice remote control answering machine, the operation of the telephone can be remotely controlled by voice input through the line. In addition, by identifying the speaker at the time of voice recognition, it is possible to eliminate the operation of another person and achieve security.

[Brief description of drawings]

FIG. 1 is a configuration diagram of a voice response / recognition function telephone system in the present embodiment.

FIG. 2 is a block diagram of a voice response / recognition function telephone system according to the present embodiment.

FIG. 3 is a functional configuration diagram of a voice remote control answering machine according to the present embodiment.

FIG. 4 is an explanatory diagram showing an implementation form of a voice remote control answering machine according to the present embodiment.

FIG. 5 is a voice activation flowchart of the voice remote control answering machine according to the present embodiment.

FIG. 6 is a flowchart of voice operation control according to the present embodiment.

FIG. 7 is an explanatory diagram showing an audio remote control sequence in the present embodiment.

FIG. 8 is an explanatory diagram showing an external operation of a conventional answering machine.

FIG. 9 is an explanatory diagram showing voice commands according to the present embodiment.

FIG. 10 is a voice command registration flowchart in the present embodiment.

FIG. 11 is a speaker registration flowchart in the present embodiment.

FIG. 12 is a flowchart (part 1) of voice operation control in the present embodiment.

FIG. 13 is a voice operation control flowchart (part 2) in the present embodiment.

FIG. 14 is a voice operation control flowchart (part 3) in the present embodiment.

[Explanation of symbols]

100 ... Public network, 111 ... Speaker, 120 ... Call line, 130 ... Answering machine control section, 140 ... Voice recognition control section,
150 ... Headset control unit, 155 ... Headset,
160 ... Reception amplifier, 170 ... Reception device, 180 ... Transmission amplifier, 190 ... Transmission device

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Noboru Kanmura 1-6, Uchisaiwaicho, Chiyoda-ku, Tokyo Inside Nippon Telegraph and Telephone Corporation (72) Yoshitake Suzuki 1-6-1, Uchisaiwaicho, Chiyoda-ku, Tokyo No. Japan Telegraph and Telephone Corporation

Claims (8)

[Claims] 1. A voice input means for inputting voice through a telephone line in a telephone device having an answering machine for receiving an incoming call from a destination, recording a message of the destination, and reproducing the recorded message. And a command storage unit that stores a predetermined voice and a command for instructing the operation of the answering machine, in association with each other, a voice input by the voice input unit, and a voice stored in the command storage unit. And a executing unit that extracts a command corresponding to a voice that matches as a result of the comparison by the comparing unit from the command storing unit and executes an operation corresponding to the command. Voice remote control answering machine. 2. The password storage means for storing a password by voice according to claim 1, and when it is determined that the voice input by the voice input means is not the password stored in the password storage means, thereafter. The voice remote control answering machine according to claim 1, further comprising a control unit that controls the execution unit so as not to execute the operation instruction by the voice input by the voice input unit. 3. The password storage means according to claim 2, wherein the password is stored in association with the speaker, and the control means stores the voice input by the voice input means in the password storage means. A voice remote control answering machine that determines whether or not the password is a voice of a speaker. 4. The voice remote control answering machine according to claim 1, further comprising a message sending means for sending a guidance message indicating that a voice input indicating the operation instruction can be accepted. 5. The voice remote control answering machine according to claim 1, further comprising message output means for outputting a guidance message to that effect when there is no matching command as a result of the comparison by the comparing means. apparatus. 6. A telephone device connected to a line for controlling the line, wherein voice input means for inputting voice through the telephone line, and voice input by the voice input means are preliminarily stored in the telephone device. Determination means for determining whether or not the input is a voice input indicating a predetermined operation instruction; command storage means for storing a predetermined voice and a command indicating the operation in association with each other; When the voice input by the voice input unit is determined by the comparing unit that compares the voice stored in the command storage unit with the voice stored in the command storage unit as the voice input indicating the operation instruction, In addition, as a result of the comparison by the comparison means, a command corresponding to the matched voice is extracted from the command storage means, and the operation corresponding to the command is executed. Voice remote control telephone apparatus characterized by comprising an execution means that. 7. A method of receiving an operation instruction by voice in an answering machine for recording a message of a destination and reproducing the recorded message, the method comprising: Receiving a voice through, a step of determining whether the received voice is a voice by a specific speaker, the result of the determination, if the received voice is a voice by a specific speaker, A voice operation characterized by having a step of receiving a voice for instructing a predetermined operation regarding reproduction of a message, and performing a predetermined operation regarding reproduction of the message when the voice is received. Instruction reception method. 8. The method according to claim 7, wherein as a result of the determination, the accepted voice is a voice by a specific speaker,
A method for accepting an operation instruction by voice, further comprising the step of transmitting a guidance message indicating that an instruction to reproduce the message can be accepted.