JPH0757336A - Sound input operation device - Google Patents

Abstract

PURPOSE:To improve a recognition rate of an operation command and to improve the reliability. CONSTITUTION:The sound signal S11 of the operation command by a sound input is supplied to a voice recognition board 14, and a most likeliest operation command candidate and a semi-likeliest operation command candidate are extracted, and the numbers data are fetched to a CPU board 15. In the CPU board 15, while considering a frequency distribution, the operation command with higher probability is selected from two operation command candidates to be made an execution operation command, and when the execution operation command concerned is suitable, a control command is transferred to a VTR 17. Thus, the VTR 17 becomes an operation mode corresponding to the operation command sound inputted from a microphone 12. Since the operation command with higher probability is preferentially selected according to the frequency distribution data among from the operation command candidates, the recognition rate of the operation command is increased. Further, the unsuitable operation command is eliminated, and the abnormal operation of the VTR 17 is prevented.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice input operation device for operating a device to be operated, such as a VTR, by voice input.

[0002]

2. Description of the Related Art Conventionally, as shown in FIG. 9, a voice input operation device for operating an information recording / reproducing device such as a VTR by voice input has been proposed.

In FIG. 9, reference numeral 1 is a voice input operation device having voice recognition means. This voice input operation device 1
Then, the operation command is recognized based on the audio signal S1 supplied from the microphone 2. Then, from the voice input operation device 1, the recognized operation command S
2 is supplied to an information recording / reproducing device 3 such as a VTR.

[0004]

However, the information recording / reproducing apparatus 3 such as a VTR has various operation modes,
There is a prohibit mode that should not be directly switched from the current operation mode. When this prohibition mode is ignored and an abnormal operation command S2 is supplied to the information recording / reproducing apparatus 3, the information recording / reproducing apparatus 3 may be confused and operate abnormally.

The cause of the abnormal operation command S2 being supplied to the information recording / reproducing apparatus 3 is as follows. For example, there is a case where noise is mixed when the voice signal S1 is supplied to the voice input operation device 1, and the voice input operation device 1 misrecognizes the voice. Further, for example, there is a case where an operator who is unfamiliar with the operation by voice input inputs an operation command having incorrect contents by voice.

For these reasons, the reliability of the operation of the information recording / reproducing apparatus 3 by voice input is not sufficient for practical use.

Therefore, the applicant first removes the operation command from the current status (operation mode) of the information recording / reproducing apparatus when it is inappropriate, and prevents the information recording / reproducing apparatus from operating. Therefore, a device that can improve reliability has been proposed (see Japanese Patent Laid-Open No. 61-172239). According to this, the malfunction of the information recording / reproducing apparatus can be prevented, but it does not contribute to improving the recognition rate of the operation command.

Therefore, in the present invention, the recognition rate of the operation command is improved and the reliability is improved.

[0009]

According to a first aspect of the present invention, there is provided a voice input operation device which recognizes an operation command by voice input to obtain a predetermined number of operation command candidates for an operated device, and a certain operation. The memory means for storing the frequency distribution data from the command to the next operation command and the operation command having a high probability in accordance with the frequency distribution data stored in the memory means are preferentially selected from the operation command candidates obtained by the voice recognition means. The operation command selecting means for selecting is provided, and the operation command selected by the operation command selecting means is supplied to the operated device.

A voice input device according to a second aspect of the present invention includes voice recognition means for recognizing an operation command by voice input to obtain a predetermined number of operation command candidates for the operated device.
A memory means for storing frequency distribution data from one operation command to the next operation command, and an operation command having a high probability is prioritized among the operation command candidates obtained by the voice recognition means according to the frequency distribution data stored in the memory means. And an operation command suitability determination means for determining whether it is appropriate to change the status of the operated device to the status corresponding to the operation command selected by the operation command selection means. The operation command appropriateness is judged by the operation command suitability judging means and is supplied to the operated device.

According to a third aspect of the present invention, in the voice input operation device according to the first or second aspect, the frequency distribution data of the memory means is automatically updated every time an operation command is supplied to the operated device. It is a thing.

[0012]

According to the first aspect of the invention, a predetermined number of operation command candidates are obtained by voice recognition, and an operation command having a high probability is preferentially selected from the operation command candidates according to the frequency distribution data. The command recognition rate can be increased, and the reliability can be improved.

According to the second aspect of the invention, a predetermined number of operation command candidates are obtained by voice recognition, and an operation command with a high probability is preferentially selected from the operation command candidates according to the frequency distribution data. The command recognition rate can be increased, and the reliability can be improved. Further, when it is not appropriate to change the status of the operated device to the status corresponding to the selected operation command, the operation command is not supplied to the operated device, and thus the malfunction of the operated device can be prevented,
This also makes it possible to improve reliability.

According to the third aspect of the present invention, since the frequency distribution data of the memory means is automatically updated every time an operation command is supplied to the operated device, it is possible to eliminate bias by the operator.

[0015]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to FIG. In this example, the VTR is operated.

In the figure, 11 is a voice input operation device. The voice signal S11 from the microphone 12 is supplied to the voice recognition board 14 which constitutes the voice recognition system 13. A control command is supplied from the CPU (central processing unit) board 15 to the voice recognition board 14,
The operation command designated by the voice signal S11 is recognized, and the recognition data is taken into the CPU board 15.

The CPU board 15 has a VTR 17
Further, the recognition data is processed while referring to the status data supplied via the VTR interface 16, and a control command for the VTR 17 is generated based on the processing result. This control command is V
It is supplied to the VTR 17 via the TR interface 16. As a result, the VTR 17 is controlled to the operation mode corresponding to the operation command input by voice from the microphone 12.

At the same time, the CPU board 15 generates message data regarding the operation or the like to be performed by the operator. This message data is displayed on an LCD (liquid crystal display element) as a display means via the LCD interface 18.
The message is supplied to the module 19 and the LCD module 19 displays a message such as an operation to be performed by the operator.
As a result, the operator of the voice input operation device 11 is L
While reading and interacting with the message displayed on the CD module 19, operation commands for the VTR 17 can be sequentially input by voice.

Reference numeral 20 denotes a keyboard, which is used to input data for confirming operation each time one program ends or to input an interrupt in the middle of the program. ing.

FIG. 2 shows the configuration of the voice recognition board 14.

In the figure, the audio signal S11 supplied from the microphone 12 is supplied to the arithmetic processor 14B via the analog interface 14A. Here, the analog interface 14A controls the level of the audio signal S11 by the control data S12 supplied from the system controller 14C, and the audio signal S1.
1 is converted into a digital audio signal S13 and supplied as serial data to the arithmetic processor 14B.

The arithmetic processor 14B has a digital audio signal S1 supplied from the analog interface 14A.
3 is divided into a plurality of channels, for example, 8 channels by a digital filter and frequency analysis is performed to form a voice pattern, and temporal distortion of the voice pattern due to fluctuations in voice generation speed is corrected (this is referred to as "time axis normalization"). Called ")." Then, the arithmetic processor 14B calculates the matching distance (time-axis normalized distance) between the patterns by comparing this time-axis-normalized detected voice pattern with all the standard patterns registered in the standard pattern registration memory 14D. The registration number data of the standard pattern with the smallest matching distance is extracted as the most probable operation command candidate CNO1, and the registration number data of the standard pattern with the second smallest matching distance is extracted as the quasi-potential operation command candidate CNO2. To do.

Here, when the operator inputs an operation command for the VTR 17 by voice into the standard pattern registration memory 14D from the microphone 12, the voice signal S is output.
11 is subjected to digital frequency analysis, and the result is stored as a standard pattern with a registration number. The registration process of the standard pattern in the standard pattern registration memory 14D is performed by VTR.
Before entering the control operation for 17, the microphone 12,
Analog interface 14A, arithmetic processor 14B
Is performed using.

Under the control of the CPU board 15, the system controller 14C controls the standard pattern registration memory 14D by storing a standard pattern in the standard pattern registration memory 14D and the matching processing operation by the arithmetic processor 14B. Control at the timing of.

The most probable operation command candidate CNO1 and the quasi-potential operation command candidate CNO2 extracted by the matching processing executed by the arithmetic processor 14B as described above.
The registration number data of is supplied to the bus 15A of the CPU board 15 via the interface 14F formed of, for example, a serial input / output device.

Here, the system controller 14C is
The CPU 15B of the CPU board 15 (see FIG. 6) is used as a host processor to receive control command data and send status code data representing the current operating state to the CPU 15B of the CPU board 15.

The voice recognition board 14 is, for example, "Voice Recognition LS" commercially available from NEC Corporation.
I set ”may be used.

FIG. 3 shows the structure of the VTR interface 16.

The VTR interface 16 connects the processor board input / output device (PIO) to the bus 15A of the CPU board 15.
It has a decoder 16B and an encoder 16C coupled via 16A.

Code data CODE1 corresponding to the control command CMD is supplied from the CPU board 15 to the decoder 16B via the processor input / output device 16A. There are 19 types of control commands CMD, as shown in FIG. The decoder 16B uses the code data CO
DE1 is taken into the latch circuit 16B1 and the latch output is supplied to the decode circuit 16B2.

The decoding circuit 16B2 is a ROM, and the code data CODE1 of FIG. 4 is converted into the driver drive data DR.
It is converted to D and supplied to the driver 16B3. As a result, the driver 16B3 sends to the VTR 17 the drive command data DRV in a signal format capable of controlling the switching of the operation mode.

Further, the encoder 16C has status data STATUS indicating the current operation mode of the VTR 17.
Is received by the receiver 16C1 and supplied to the ROM-configured encoding circuit 16C2. The encoding circuit 16C2 is
As shown in FIG. 5, 12 types of status data STAT
It is for converting the US into the corresponding code data CODE2. The code data CODE2 output from the encoding circuit 16C2 is latched by the latch circuit 16C3, and then the CPU via the processor input / output device 16A.
It is output to the bus 15A of the board 15.

The VTR interface 16 uses the VT
Control pulse signal C reproduced from the tape at R17
The control pulse receiver 16D receives the TL, and the interrupt signal INT synchronized with the timing is supplied to the bus 15 of the CPU board 15 via the processor input / output device 16A.
By supplying the output of the control pulse receiver 16D to the latch circuit 16C3 of the encoder 16C as a latch signal, the status signal STAT
The code data CODE2 corresponding to US is loaded into the CPU board 15 side in synchronization with the playback operation of the VTR 17.

FIG. 6 shows the configuration of the CPU board 15.

The CPU board 15 is the voice recognition board 14.
Data transferred from the bus 15A to the CPU 15B
The data stored in the memory 15C via the VTR interface 16 and transferred to the bus 15A from the VTR interface 16 is transferred to the C
The data is stored in the memory 15C via the PU 15B. Memory 1
5C has a voice recognition board memory unit 15C1, a VTR memory unit 15C2, a message memory unit 15C3, and a frequency distribution memory unit 15C4.

The voice recognition board memory unit 15C1 is R
It is composed of OM and RAM, and the control command necessary for driving and controlling the voice recognition board 14 is previously R
The control command is stored in the OM, read out as needed, and transferred to the voice recognition board 14. Further, when the status data indicating the current operation mode and the voice pattern registration number data are transferred from the voice recognition board 14, this is temporarily stored in the RAM, and then the voice recognition board 14 and the VTR 17 are based on this status data. The control command to be transferred is determined.

The VTR memory section 15C2 is also composed of a ROM and a RAM, and a control command necessary for driving and controlling the VTR 17 is stored in the ROM in advance.
The control command is stored in the VTR 17, and is read out as needed to be transferred to the VTR 17. On the other hand, when the status data indicating the current operation mode is transferred from the VTR 17, this is transferred to RA.
Temporarily store in M. The frequency distribution memory unit 15C4 is composed of a rewritable memory backed up by a battery, and stores the frequency distribution data corresponding to the operation command to be executed next from the current status of the VTR 17, as shown in FIG. is there. The CPU 15B uses the status data stored in the VTR memory unit 15C2 and the frequency distribution data stored in the frequency distribution memory unit 15C4 to supply the most probable operation command candidate CNO1 and the semi-potential operation command supplied from the voice recognition board 14. It is determined whether or not the operation command corresponding to the registration number data corresponding to the candidate CNO2 should be transferred to the VTR 17.

Further, the message memory unit 15C3 includes
Data about a message to be displayed is stored in the LCD module 19, and the CPU 15B sends message data to be presented to the operator from the message memory unit 15C3 based on the data transferred from the voice recognition board 14 and the VTR 17. Read and LC
The LCD module 19 can be supplied through the D interface 18.

The recognition or interrupt data input from the keyboard 20 is read by the CPU 15B via the processor input / output device 15D.

Further, the CPU board 15 is provided with a counter timer controller 15E for counting the number of pulses of the control pulse signal CTL transferred from the VTR interface 16 and continuing when voice pattern registration number data is input. Functions such as measuring time are
It is designed to be executed under the control of the PU 15B.

In the above configuration, the CPU 15B of the CPU board 15 follows the VTR according to the processing procedure shown in FIG.
Reference numeral 17 is a microphone 12 as an operation command input means.
The drive control is performed based on the audio signal S11 supplied from the device.

When power is supplied to the entire system in step SP1, the CPU 15B determines in step SP
2, the control command is read from the voice recognition board memory unit 15C1 and transferred to the system controller 14C of the voice recognition board 14 to adjust the voice input level. The system controller 14C, in step SP3, the microphone 12
When the voice signal S11 for one operation command is input from the analog interface 14A, the signal level of the voice signal S11 is controlled by the analog interface 14A, and in the next step SP4, the signal level of the output signal S13 matches the reference level. Judge whether or not. When a negative result is obtained, the CPU 15B returns to step SP2 to execute the level adjustment operation of the analog interface 14A again, and thereafter, this operation is repeated until the signal level of the audio signal S11 for the one word reaches the reference level. . As a result, when the signal level of the output signal S13 of the analog interface 14A or the reference level is reached, a positive result is obtained in step SP4, so that the next step SP
Go to 5.

In this way, the CPU 15B normalizes the signal level of the voice signal S11 input from the microphone 12 so as to match the predetermined reference level, and thereby the influence of the difference in the voice input level of the operation command by the operator. It is designed to be removed.

Next, in step SP5, the CPU 15B causes the system controller 1 of the voice recognition board 14 to operate.
4C is controlled to the standard pattern registration mode. At this time, the system controller 14C causes the audio signal S1 currently input from the microphone 12 in step SP6.
The standard pattern data is detected by fetching the data for one word of 1 into the arithmetic processor 14B and analyzing the frequency component. Based on the status data transferred from the voice recognition board 14, the CPU 15B confirms in step SP7 whether or not the detection operation of the operation command for one word is completed, and while the detection operation is not completed, Then, the process returns to step SP5 again, and the standard pattern detection operation is continuously executed.

In this way, when the detection of the standard pattern data for one word is completed, a series of registration numbers are attached to the detected voice pattern and stored in the standard pattern registration memory 14D as a registration pattern. As a result, CPU1
5B moves to step SP8 by obtaining a positive result in step SP7, and determines whether or not the registration of the standard pattern for all operation commands is completed.

If a negative result is obtained here, the CPU 1
5B again returns to step SP5 to execute the detection operation of the standard pattern for one word of the operation command by the voice signal S11 for the next operation command, and adds the registration number to this to store it in the standard pattern registration memory 14D. .

Similarly, the CPU 15B detects a standard pattern based on the voice signal S11 input from the microphone 12 for all operation commands, and assigns the standard pattern data to the standard pattern registration memory 14D with a registration number. To store. When this process ends, CP
Since the U15B can obtain a positive result in step SP8, the U15B ends the processing operation in the standard pattern registration mode and enters the next operation command recognition mode. The ROM in which the standard pattern is registered may be incorporated as the standard pattern registration memory 14D, and the above-described registration processing may be omitted.

In the case of this example, as shown in FIG.
Control command CM that can be given to
There are 19 types of D, and accordingly, the operation commands that can be registered in the standard pattern registration memory 14D via the microphone 12 have the same contents as the control command CMD of FIG. 4, and are “STOP”, “PLAY”, ...・ 、
By inputting "RS4 (x1 / 20)" by voice, the standard pattern for each operator is detected and registered with the registration numbers "1", "2" ... "19". Become.

The operating state of the voice recognition board 14 and the registration number data in steps SP5 to SP8 are transferred to the CPU 15B as status data, and the operating state of the voice recognition board 14 is sequentially displayed on the LCD module 19 and the standard pattern is registered. The content of the operation command and the registration number registered in the memory 14D are displayed on the LCD module 19.

When the operation command recognition mode is entered, the CPU 15B transfers a control command instructing execution of the operation command recognition mode to the system controller 14C in step SP9. Then, in the next step SP10, the microphone 12
When the voice signal S11 is input via the operation command for one word, the CPU 15B causes the system controller 14 to operate.
The voice signal S11 is converted to an analog interface 1 by C.
The input voice pattern is detected by being loaded into the arithmetic processor 14B via 4A and performing frequency analysis, and then matching processing of the detected voice pattern and all the standard patterns registered in the standard pattern registration memory 14D is performed. Run.

As a result, the registration number data of the standard pattern with the smallest matching distance is extracted as the most probable operation command candidate CNO1, and the matching distance is 2
The registration number data of the second smallest standard pattern is extracted as the semi-potential operation command candidate CNO2, and these registration number data are the data indicating the operation command input in the operation command recognition mode currently being executed. Transferred to the memory 1
It is stored in the voice recognition board memory unit 15C1 of 5C.

In this state, the CPU 15B confirms the end of the above-described extraction operation in step SP11, and when a positive result is obtained in step SP11, moves to the next step SP12.

In step SP11, before the operation command candidates CNO1 and CNO2 are extracted as described above, for example, the signal level of the audio signal S11 is within a predetermined level range, or audio is input to the microphone 12. It is also determined whether the tone of the operation command has a predetermined length, for example, within 2 seconds, and the like, and it is confirmed that the audio signal S11 corresponds to the control command CMD as shown in FIG. Thereby, the recognition accuracy of the voice input can be improved.

If a negative result is obtained regarding the voice input level and the tone in step SP11, the CPU 15
B ignores the voice input data and returns to step SP9 to redo the operation command recognition program.

In this way, the operation command candidate CNO
1, CNO2 is confirmed, the CPU 15B sends V through the VTR interface 16 in step SP12.
The status data is read from TR17 and loaded into the VTR memory section 15C2. Then, based on the acquired status data, the most probable operation command candidate C
VTR of NO1 or CNO2, a quasi influential operation command candidate
17 determines whether to execute.

First, in step SP13, the CPU 15B confirms the status of the VTR 17, that is, the current operation mode, for the following three items.

The CPU 15B firstly executes the step SP13.
At, in the case of confirming "whether the power of the VTR 17 is turned on", and when a negative result is obtained, move to step SP15 to display the message "Power ON the VTR" on the LCD module 19 and then return to step SP9. Retry the voice input.

The CPU 15B secondly executes the step S
In P13, confirm "whether the tape is set", and if a negative result is obtained, move to step SP15 and display the message "Stand by the Cassette" in LC.
After the display on the D module 19, the process returns to step SP9 and the voice input is performed again.

Further, the CPU 15B thirdly executes step S.
In P13, it is confirmed whether "the connector is connected". If a negative result is obtained, the process moves to step SP15 and the message "Connect with the VTR" is sent to the LC.
After the display on the D module 19, the process returns to step SP9 and the voice input is performed again.

On the other hand, when a positive result is obtained in step SP13, the CPU 15B moves to next step SP20. In step SP20, with respect to the most probable operation command candidate CNO1 and the semi-potential operation command candidate CNO2 recognized in the operation command recognition mode according to the operation command input this time, the status of the current VTR 17 (or the operation command previously executed) ), And make a comprehensive judgment as follows.

It is assumed that a correspondence frequency distribution table (TBL) of operation commands to be executed next is previously created from the current VTR 17 status as shown in FIG. This is stored in the frequency distribution memory unit 15C4 of the CPU board 15. For example, when the “REC” command is currently being executed and the status of the VTR 17 is in the “REC” state, the operation command to be instructed next is usually “STOP” with the highest frequency and other operation commands. Indicates almost 0 degrees. Referring to the frequency distribution table of FIG. 7, the operation command with the highest frequency in relation to the current VTR 17 status is the most likely operation command candidate CNO.
1 or quasi influential operation command candidate CNO2.

At this time, if the operation command with the highest frequency coincides with the most probable operation command candidate CNO1 or the quasi-possible operation command candidate CNO2, this is set as the execution operation command EXEC, and the process proceeds to step SP14 and the prohibition described later is carried out. The mode is judged. The current V
When the status of TR17 is "STOP", the next operation command cannot be specified, so the most probable operation command candidate CNO1 is set as the execution operation command EXEC.

At step SP20, the most promising operation command candidate CNO1 or the semi-possible operation command candidate CN
If both O2 are judged to be inappropriate, "Speak Anothe
LCD Command 19
After that, the process returns to step SP9 to enter a new operation command recognition program.

The processing in step SP20 is, for example, when the input operation command is ambiguous or when another operation command is erroneously generated, the two candidates to be recognized are listed and the statistical data is more probabilistically correct. By selecting a likely operation command candidate, the recognition rate of voice input can be positively improved.

If a positive result is obtained in step SP20, the CPU 15B moves to the next step SP14 and checks the relationship between the command previously executed by the VTR 17 and the execution operation command EXEC selected in step SP20. Thus, it is determined whether the content of the execution operation command EXEC determined in step SP20 is appropriate considering the operation mode of the VTR 17. That is, it is determined whether or not to execute the execution operation command EXEC in the following prohibition mode.

In practice, the system controller of the VTR 17 has a prohibition mode which should not be switched when switching the current operation mode of the VTR 17 to the next operation mode, thus preventing the VTR 17 from abnormal operation. CPU15B is the VTR1
In consideration of the relation with the system controller of No. 7, when an improper operation command is input as described below, the VTR 17 responds to the improper operation command by determining this in step SP14. It is designed not to. (1) When the status of the VTR 17 is the rewind mode The CPU 15B executes the execution operation command E when the status of the VTR 17 is the rewind mode (REW).
When XEC is "PLAY", the previous execution operation command EXEC is referenced, and if the content is "PLAY", a negative result is obtained in step SP14, and the process moves to step SP15 and is called "Wait For A While". A message is displayed on the LCD module 19 and step SP9
Return to.

This is because the previous execution operation command EXEC is "PLAY" and the status of the VTR 17 is "REW" means that the VTR 17 is reproduced by the last execution command "EXEC" of PLAY. This means that the system controller of the VTR 17 has entered the automatic rewind mode after the mode tape has been entered and the magnetic tape has been reproduced to the end. The automatic rewinding operation is executed according to the judgment of the system controller of the VTR 17, and in order not to confuse the operation of the system controller, do not supply a new control command to the VTR 17 until the rewinding operation is completed. It is necessary to. (2) When "STOP" mode is required The system controller of the VTR 17 has "PLAY", "REC", "FF", in order to ensure its operation.
To enter "REW" or "EJECT" mode, enter the VTR
Controls the VTR 17 on the condition that it is in the "STOP" mode.

When the operation command is input and the VTR 17 is in a status that does not satisfy the necessary condition, the CPU 15B executes this at step SP14.
And make a negative result. And step SP
After displaying the message "Speak Another Command" on the LCD module 19 in step 15, step SP
Returning to step 9 and returning to the new operation command recognition program. (3) When the same operation command is input by voice The CPU 15B proceeds to VTR1 in step SP14.
If it is determined that the status data transferred from No. 7 and the execution operation command EXEC are the same, VT
Since the operation command is inappropriate for the status of R17, a negative result is generated and the process proceeds to step SP15.
After displaying the message "Speak Another Command" on the LCD module 19, the process returns to step SP9 to enter a new operation command recognition program. (4) When an operation command that cannot be executed is input by voice The VTR 17 is controlled by the system controller so that it cannot directly switch from the “FF” or “REW” operation mode to the “REC” or “EJECT” operation mode. Under control, the VTR 17 must be switched to the "STOP" mode and then to the "REW" and "EJECT" modes when in the "FF" or "REW" mode.

Therefore, the CPU 15B has the VTR 17
Is in the "FF" or "REW" status, the execution operation command EXEC is "REC" or "EJECT".
If so, a negative result is determined in step SP14, a message "Speak Another Command" is displayed on the LCD module 19 in step SP15, and the process returns to step SP9 to recognize a new operation command. Enter the program.

If it is determined in step SP14 that the execution command is appropriate, EXEC, step SP14.
16, the control command corresponding to the input operation command is read from the VTR memory unit 15C2 and transferred to the VTR 17 via the VTR interface 16. As a result, the VTR 17 switches to the operation mode.

At step SP21, the frequency distribution shown in FIG. 7 is updated. That is, the frequency distribution memory unit 15C4
1 is added to the frequency of the part corresponding to the status and the operation command. At this time, if the relevant portion of the frequency distribution memory unit 15C4 is likely to overflow, -1 is added to the frequencies of the portions other than the relevant portion in the status (underflow is clipped to 0). In this way, the frequency distribution memory unit 15C4 is always
The frequency distribution data of is updated so that the bias of the operation in the operator or the operating environment can be sufficiently taken into consideration.

When a positive result is obtained in step SP17, the CPU 15B moves to step SP18 and ends the program. Here, as a method of determining the end of the program in step SP17, the microphone 12 causes “END” so that the “END” control command of the registration number “9” in FIG. 5 is transmitted.
The operation command may be input by voice or the keyboard 20 may be used to interrupt the CPU 15B.

In the above embodiment, the most probable operation command candidate CNO1 and the quasi-potential operation command candidate C are used.
The execution operation command EXEC is selected from the two candidates of NO2 according to the frequency distribution.
The number of candidates may be one, or may be three or more.

Further, instead of the above description, individual frequency distributions of a plurality of operators may be prepared in the frequency distribution memory unit 15C4 so that each operator can selectively use his or her own frequency distribution.

Further, in the above-mentioned embodiments, the case where the present invention is applied to the VTR has been described, but the present invention is not limited to this and can be widely applied to the information recording / reproducing apparatus. Also L
Of course, the message displayed on the CD module 19 can be changed as needed.

[0076]

According to the invention of claim 1, a predetermined number of operation command candidates are obtained by voice recognition, and an operation command having a high probability is preferentially selected from the operation command candidates according to the frequency distribution data. Therefore, the recognition rate of the operation command can be increased, and the reliability can be improved.

According to the second aspect of the invention, a predetermined number of operation command candidates are obtained by voice recognition, and operation commands with a high probability are preferentially selected from the operation command candidates according to the frequency distribution data. The recognition rate of operation commands can be increased, and the reliability can be improved. Further, when it is not appropriate to change the status of the operated device to the status corresponding to the selected operation command, the operation command is not supplied to the operated device, and thus the malfunction of the operated device can be prevented. Also, the reliability can be improved.

According to the third aspect of the present invention, since the frequency distribution data of the memory means is automatically updated every time the operation command is supplied to the operated device, it is possible to eliminate bias by the operator.

[Brief description of drawings]

FIG. 1 is a block diagram showing a configuration of an embodiment of a voice input operation device according to the present invention.

FIG. 2 is a block diagram showing a configuration example of a voice recognition board.

FIG. 3 is a block diagram showing a configuration example of a VTR interface.

FIG. 4 is a diagram showing control commands processed by a VTR interface.

FIG. 5 is a diagram showing status data processed by a VTR interface.

FIG. 6 is a block diagram showing a configuration example of a CPU board.

FIG. 7 is a diagram showing an example of frequency distribution data.

FIG. 8 is a flowchart showing a processing procedure of the embodiment.

FIG. 9 is a diagram showing a conventional voice input operation device.

[Explanation of symbols]

 11 voice input operation device 12 microphone 13 voice recognition system 14 voice recognition board 15 CPU board 16 VTR interface 17 VTR 18 LCD interface 19 LCD module 15C4 frequency distribution memory unit

Claims (3)

[Claims] 1. A voice recognition means for recognizing an operation command by voice input to obtain a predetermined number of operation command candidates for an operated device, and a memory means for storing frequency distribution data from one operation command to the next operation command. An operation command selecting means for preferentially selecting an operation command having a high probability according to the frequency distribution data stored in the memory means from among the operation command candidates obtained by the voice recognizing means, the operation command selecting means A voice input operation device, which supplies an operation command selected in step 1 to the operated device. 2. A voice recognition means for recognizing an operation command by voice input to obtain a predetermined number of operation command candidates for an operated device, and a memory means for storing frequency distribution data from one operation command to the next operation command. , Operation command selecting means for preferentially selecting an operation command having a high probability in accordance with frequency distribution data stored in the memory means from operation command candidates obtained by the voice recognition means, and a status of the operated device. An operation command suitability determination means for determining whether or not it is appropriate to change to a status corresponding to the operation command selected by the operation command selection means, and the operation command suitability determination means determines that it is appropriate. A voice input operation device, which supplies an operation command to the operated device. 3. The voice input operation device according to claim 1, wherein the frequency distribution data of the memory means is automatically updated every time an operation command is supplied to the operated device.