JPH05130676A - Device for selecting voice input function - Google Patents

Abstract

PURPOSE:To make it possible to select one of functions displayed on a screen by means of voice only by glancing the screen. CONSTITUTION:The function selectors of a controlled apparatus 4 are displayed on the screen of a display device 3 by respectively different colors, and when the name of a selected color is voiced, a voice recognizing device 1 detects the voice and outputs its detection outputs to a code image operation instruction converting circuit 6, which converts the name of the voiced color into an operation instruction. A control circuit 2 selects a function selector corresponding to the color on the screen based upon the operation instruction. Consequently the function can be intuitively and simply selected by speaking of the small number of words without need of reading out characters on the screen.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice input function selection in a voice control system in which a function is selected by uttering an image corresponding to the function, not a name of the function or a number corresponding to the function. It relates to the device.

[0002]

2. Description of the Related Art FIG. 5 shows, for example, Japanese Patent Publication No. 63-2695.
5 is a block diagram of a conventional voice input function selection control device shown in Japanese Patent No. In FIG. 5, reference numeral 1 denotes a voice recognition device, which is composed of a voice division circuit, a voice pattern registration memory, a voice discrimination circuit, etc., performs voice recognition processing, and sends the recognition result to the control circuit 2.

The control circuit 2 is a microcomputer,
It is composed of a ROM for storing programs, a RAM for storing data, and the like.

Reference numeral 3 denotes a display, which is composed of a CRT and its drive circuit, is connected to the control circuit 2, and is connected to the control circuit 2.
Screen is displayed by the command.

Reference numeral 4 denotes a controlled device, which is a radio, an air conditioner, a cassette tape recorder, a compact disc (hereinafter referred to as CD) player, various electric devices such as a navigation device, and an electronic device, which are connected to the control circuit 2. Each operation is performed according to an instruction from the control circuit 2.

Reference numeral 5 denotes a microphone which is connected to the voice recognition device 1 and converts the uttered voice into an electric signal and sends it to the voice recognition device 1.

Next, the operation will be described. In general, the voice control system is often composed of a large number of controlled devices 4, and therefore the first function is to select various functions of the controlled device 4.
As a step, it is usual to perform a two-step control of selecting the controlled device 4 and then selecting the function of the controlled device 4.

When selecting the controlled device at the first stage, the control circuit 2 first causes the display device 3 to display the names of the controlled devices that can be selected. FIG. 6 is a diagram showing an example of a screen display when selecting a controlled device in the first stage. The controlled devices selected in FIG. 6 are of four types: radio, air conditioner (hereinafter referred to as air conditioner), cassette tape, and CD player.

When a cassette tape is selected among these, when a "cassette" is uttered, this voice is collected by the microphone 5, converted into an electric signal and sent to the voice recognition device 1. The voice recognition device 1 analyzes the voice characteristic parameter from this voice, compares it with the voice parameter already registered, and sends a command code for selecting a cassette tape to the control circuit 2.

When the cassette tape is selected, the control circuit 2 causes the display device 3 to display the function name that can be selected in order to perform the detailed function selection of the cassette tape in the second step. FIG. 7 is a diagram showing an example of a screen display when the second stage function is selected. In the figure, the selection function is
Five kinds of selectors of REW, PLAY, STOP, FF and SKIP are displayed. The functions are rewind,
It corresponds to tape play, stop, fast forward, and skip one song.

Now, when the driver tries to operate the cassette tape and utters "play", this voice is collected by the microphone 5, and the voice recognition device 1 converts it into an electric signal and outputs the voice characteristic parameter from this voice. Is analyzed to make a comparison judgment with the already registered voice parameters,
An instruction code for selecting the "play" function is sent to the control circuit 2.

The control circuit 2 receives this signal and sends a "play" command to the cassette tape player which is the controlled device 4. The cassette tape player receives this "play" command and starts the tape reproducing operation. When other functions are selected, the same operation is performed, and the rewind, stop, fast forward, and skip one song operations are performed by the utterances of "rewind", "stop", "fast forward", and "skip", respectively.

In the first stage of FIG. 6 as well, a radio, an air conditioner, and a CD player are similarly selected by uttering "radio", "air conditioner", and "seed", and the function can be selected on the respective function selection screens.

[0014]

Since the conventional voice control device is configured as described above, it is necessary to select many controlled device names and selected function names. Therefore, the voice recognition device 1 has many vocabulary words. A large amount of memory is required for recognizing, the recognition performance must be high, and there is a problem that it takes a long time to select because the user pays close attention to the screen and reads the displayed characters. there were.

There is also a method of applying a number to each selected function and uttering this number to select a function. With this method, the number of uttered words can be reduced, but at the time of selection, the characters displayed while gazing at the screen are displayed. However, the problem that the selection takes a long time is not solved.

The invention of claim 1 has been made in order to solve the above-mentioned problems, and has an ability of recognizing an unspecified speaker of a small number of vocabulary words, and the function selecting operation can be done by voice just by looking at the screen. The purpose is to obtain an input function selection device.

According to the second aspect of the present invention, the controlled device can be easily selected by pronouncing the graphic corresponding to each type of the controlled device, and it is not necessary to read the characters on the screen, which is intuitive. It is another object of the present invention to provide a voice input function selection device capable of easily selecting a controlled device.

According to the third aspect of the present invention, by audibly uttering the display arrangement order of the controlled devices, the controlled devices can be easily selected and the selection operation can be simplified. The purpose is to obtain the device.

[0019]

A voice input function selecting device according to the present invention recognizes a voice by uttering an image of a function selector displayed on a display screen of a display device. And a symbol image motion command conversion circuit for converting the result recognized by the voice recognition device into a motion command and outputting it to a control device for controlling the overall function.

[0020]

In the voice recognition device according to the present invention, when the image of the function selector displayed on the screen of the display device is uttered by voice, the voice recognition of this image is performed, and the recognition result is the symbol image name operation command conversion circuit. Then, the recognition result is converted into a motion command by the symbol image name motion command conversion circuit and output to the control device.

[0021]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of a voice input function selecting device of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing the configuration of the first embodiment, but the configurations of second and third embodiments described later are also the same on the block diagram. This Figure 1
In the above, since 1 to 5 are the same as those in the conventional example, the description thereof will be omitted. A symbol image operation instruction conversion circuit 6 is a part newly added by the present invention and is a feature of the present invention. That is, the symbol image code from the voice recognition device 1 is converted into an operation command code and sent to the control circuit 2.

Next, the operation will be described. An example of the detailed function selection of the cassette tape in the second stage will be described.
In order to select the detailed function of the cassette tape, the control circuit 2 displays the selectable function name in color on the display device 3 as a display device. FIG. 2 shows an example of screen display in the case of a cassette tape as in FIG. In FIG. 9, the selection functions are REW, PLAY, STOP, FF,
Five types of SKIP selectors are displayed, each of which is red,
It is displayed in a blue, yellow, green, and brown frame.

Now, when the operator utters "blue" which is the color of the selector of PLAY to operate the cassette tape deck, this voice is collected by the microphone 6 and converted into an electric signal to recognize the voice recognition device 1. Sent to. Speech recognition device 1
Recognizes this vocal sound and determines that it is "blue",
The code corresponding to "blue" is sent to the symbol image operation instruction conversion circuit 6. The symbol image operation command conversion circuit 6 converts the code corresponding to this “blue” into a command code for selecting the “play” function, and sends this code to the control circuit 2. Table 1 shows an example of the conversion table of the symbol image operation instruction conversion circuit 6.

[0024]

[Table 1]

The control circuit 2 receives this signal and sends a "play" command to the cassette tape player which is the controlled device. The cassette tape player receives this "play" command and starts the tape reproducing operation. The same operation is performed when other functions are selected, and “red”, “yellow”, “green”, and “brown” are selected.
The voice is recognized, and rewinding, stopping, fast-forwarding, and skipping one song are performed. In the case of selecting functions for other controlled devices such as radios, air conditioners, and CDs as well, the functions can be selected by the same color display and color name voice input.

Therefore, as the performance of the voice recognition device 1, it is not necessary to recognize a large number of vocabularies, and it is sufficient if it has an unspecified speaker recognition performance of a small number of vocabularies. The screen changes,
Even if the content of the selector changes, all the functions can be selected simply by rewriting the conversion table of the symbol image operation instruction conversion circuit 6.

In the embodiment of FIG. 2, the function selector has a rectangular shape, but the function selector does not have to be rectangular.

Next, a second embodiment of the present invention will be described with reference to the drawings. Since the configuration of the second embodiment is the same as that of the first embodiment, the description will be omitted.

Next, the operation of the second embodiment will be described. An example of the detailed function selection of the cassette tape in the second stage will be described. The control circuit 2 causes the display device 3 to display a selectable function name with a frame in order to select a detailed function of the cassette tape. FIG. 3 is a diagram showing an example of a screen display in the case of a cassette tape as in FIG. In FIG. 3, the selection functions are REW, PLAY, STOP, FF, SK.
Five types of IP selectors are displayed, and each is displayed in a frame of a square, a triangle, a diamond, a circle, and an ellipse.

Now, in order to operate the cassette tape, the operator utters "triangle," which is the framework of the selector of PLAY, and this voice is collected by the microphone 5 and converted into an electric signal to produce a voice. It is sent to the recognition device 1. The voice recognition device 1 recognizes this uttered voice, determines that it is a “triangle”, and sends a code corresponding to the “triangle” to the symbol image operation command conversion circuit 6. The symbol image operation instruction conversion circuit 6 "plays" the code corresponding to this "triangle".
It is converted into an instruction code for selecting a function, and this code is sent to the control circuit 2. Table 2 shows the symbol image operation instruction conversion circuit 6
The example of the conversion table of is shown.

[0031]

[Table 2]

The control circuit 2 receives this signal and sends a "play" command to the cassette tape player which is the controlled device. The cassette tape player receives this "play" command and starts the tape reproducing operation.

The same operation is performed in the case of selecting other functions, and by uttering "square", "diamond", "circle", "oval",
Recognizing the voice, rewinding, stopping, fast-forwarding, and skipping one song are performed. In the case of function selection in other controlled devices such as radio, air conditioner, and CD, function selection can be performed by the same frame display and frame name voice input.

Next, a third embodiment of the present invention will be described with reference to the drawings. Since the configuration of the third embodiment is the same as that of the first embodiment shown in FIG. 1, the description thereof will be omitted.

Next, the operation of the third embodiment will be described. An example of the detailed function selection of the cassette tape in the second stage will be described. The control circuit 2 displays the function names that can be selected on the display device 3 in a horizontal row in order to select the detailed function of the cassette tape. FIG. 4 is a diagram showing an example of a screen display in the case of a cassette tape as in FIG. In the figure, the selection functions are REW, PLAY, STOP, F
Five types of selectors of F and SKIP are displayed, and the selectors are arranged in a horizontal row.

Now, when the operator utters "second from left", which is the position of the selector of PLAY, in order to operate the cassette tape, this voice is output by the microphone 5
Are collected, converted into electric signals and sent to the voice recognition device 1. The voice recognition device 1 recognizes this uttered voice, determines that it is "second from left", and sends a code corresponding to "second from left" to the symbol image operation command conversion circuit 6.
The symbol image operation command conversion circuit 6 converts the code corresponding to “second from the left” into a command code for selecting the “play” function, and sends this code to the control circuit 2. Table 3
Shows an example of a conversion table of the symbol image operation instruction conversion circuit 6.

[0037]

[Table 3]

The control circuit 2 receives this signal and sends a "play" command to the cassette tape player which is the controlled device. The cassette tape player receives this "play" command and starts the tape reproducing operation. The same operation is performed when other functions are selected, "first from left" and "center".
By uttering "second from right" and "first from right", the voice is recognized, and rewinding, stopping, fast-forwarding, and skipping one song are performed. In the case of function selection in other controlled devices such as radio, air conditioner, and CD, function selection can be performed by the same display and position name voice input. Further, the input voice is not limited to this embodiment, and may be any word indicating a position.

Further, in each of the above embodiments, the case where the color, the shape, and the position are different has been described, but the same effect can be obtained by using them in combination.

Further, in each of the above-described embodiments, the case of selecting functions such as radio, air conditioner, cassette tape, and CD has been described, but the same effect is also obtained in function selection in general electric equipment, electronic equipment, computers and the like. There is also the same effect in selecting the controlled device.

[0041]

As described above, according to the present invention, the function selector and the display device are color-coded and displayed, and when the utterance of the name of the color is detected by the voice recognition device, the detection output is converted into an image operation command conversion. The color name uttered by the circuit is converted into an operation command and transmitted to the control device, and the control device is configured to select the function corresponding to the color on the screen of the display device. Since the symbol image type of the selector can be identified and this symbol image can be input by voice, it is not necessary to read the characters on the screen, and the number of words that can be spoken is small, making it intuitive and easy to select functions. There is an effect that can be done.

According to the second aspect of the present invention, the function selector is changed in shape and displayed on the screen of the display device, and the name of the shape is uttered to be detected by the voice recognition device, and its detection output. Is converted into a motion command by the symbol image motion command conversion circuit,
Since the control device is configured to select the function selector corresponding to the shape on the screen based on the operation command, the number of spoken words is small, the controlled device can be easily selected, and the characters on the screen need to be read. Moreover, there is an effect that the controlled device can be selected intuitively and easily.

Further, according to the invention of claim 3,
Change the position of the function selector on the screen of the display device and display it.
When you say the name of that position, it is detected by the voice recognition device,
The detection output is converted into a motion command by the symbol image motion command conversion circuit, and based on the output, the controller selects the function selector corresponding to the position on the screen, so that the number of uttered words is small. The controlled device can be easily selected, and the selection operation can be simplified.

[Brief description of drawings]

FIG. 1 is a block diagram of an embodiment of a voice input function selection device according to an embodiment of the present invention.

FIG. 2 is an explanatory diagram showing a display example of a display device according to the embodiment.

FIG. 3 is an explanatory diagram showing a display example of a display device of a second embodiment of the voice input function selection device of the invention.

FIG. 4 is an explanatory diagram showing a display example of a display unit of a third embodiment of the voice input function selection device of the invention.

FIG. 5 is a block diagram of a conventional voice input function selection device.

FIG. 6 is an explanatory diagram showing a display example of a display unit in a conventional voice input function selection device.

FIG. 7 is an explanatory diagram showing another display example of the same display unit.

[Explanation of symbols]

 1 voice recognition device 2 control circuit 3 display device 4 controlled device 5 microphone 6 symbol image operation command conversion circuit

─────────────────────────────────────────────────── ───

[Procedure amendment]

[Submission date] June 22, 1992

[Procedure Amendment 1]

[Document name to be amended] Statement

[Name of item to be amended] Claims

[Correction method] Change

[Correction content]

[Claims]

[Procedure Amendment 2]

[Document name to be amended] Statement

[Correction target item name] 0009

[Correction method] Change

[Correction content]

When a cassette tape is selected among these, when a "cassette" is uttered, this voice is collected by the microphone 5, converted into an electric signal and sent to the voice recognition device 1. The voice recognition device 1 extracts a voice characteristic parameter from this voice, compares it with a voice parameter already registered, makes a judgment, and sends an instruction code for selecting a cassette tape to the control circuit 2.

[Procedure 3]

[Document name to be amended] Statement

[Correction target item name] 0011

[Correction method] Change

[Correction content]

Now, when the operator tries to operate the cassette tape and utters "play", this voice is collected by the microphone 5, and the voice recognition apparatus 1 converts it into an electrical signal and outputs the voice feature parameter from this voice. Is extracted , and it is compared and judged with the already registered voice parameter,
An instruction code for selecting the "play" function is sent to the control circuit 2.

[Procedure amendment 4]

[Document name to be amended] Statement

[Correction target item name] 0016

[Correction method] Change

[Correction content]

[0016] This invention has been made in order to solve the problems as described above, has a speaker-independent recognition performance of minority vocabulary, input function that allows the function selection operation at a glance the screen with voice The purpose is to obtain a selection device.

[Procedure Amendment 5]

[Document name to be amended] Statement

[Correction target item name] 0017

[Correction method] Change

[Correction content]

Further, this invention, by pronouncing the color or shape that is corresponding to each vessel type of the controlled device, easy to selection of the controlled device, it is not necessary to read the text on the screen,
An object is to obtain a voice input function selection device that allows intuitive and easy selection of controlled devices.

[Procedure correction 6]

[Document name to be amended] Statement

[Correction target item name] 0018

[Correction method] Change

[Correction content]

Furthermore, this invention, by pronouncing the display arrangement order of the controlled device by voice, easily can be selected for the controlled device, voice input function selection capable sake of simplification of the selection operation The purpose is to obtain the device.

[Procedure Amendment 7]

[Document name to be amended] Statement

[Correction target item name] 0039

[Correction method] Change

[Correction content]

Further, in each of the above embodiments, the case where the color, the shape, and the position are different has been described, but the same effect can be obtained by using them in combination. Also before
Represents a symbolic image concept other than the described colors, shapes, and positions
Anything will have exactly the same effect.

[Procedure Amendment 8]

[Document name to be amended] Statement

[Correction target item name] 0041

[Correction method] Change

[Correction content]

[0041]

As described above, according to the present invention, the function selector is not a linguistic concept but a symbol image concept display device.
In Displays, detected by the speech recognition device when uttering words representing the symbol image concept represents the symbol image concept uttered by the image operation command conversion circuit that detects the output
Since the words are converted into operation commands and transmitted to the control device, and the function selector on the screen of the display device is selected by the control device, the symbol image type of the function selector can be identified just by looking at the screen. Moreover, since this symbol image can be input by voice, it is not necessary to read the characters on the screen, and the number of spoken words can be small, which is an effect that the function can be selected intuitively and easily.

[Procedure Amendment 9]

[Document name to be amended] Statement

[Correction target item name] 0042

[Correction method] Change

[Correction content]

[0042] In addition, according to this invention, the color of the function selector
Displayed on the screen of every bill Ete display device and shapes, detected by the speech recognition device by saying the name of the color and shape, convert the operation instruction the detection output by the symbol image operation command conversion circuit,
The controller selects the function selector corresponding to the color or shape on the screen based on the operation command.Therefore, the number of spoken words is small, and the controlled device can be selected easily. There is an effect that the controlled device can be selected intuitively and easily without reading.

[Procedure Amendment 10]

[Document name to be amended] Statement

[Correction target item name] 0043

[Correction method] Change

[Correction content]

[0043] Furthermore, according to this invention, to display by changing the position of the function selector on the screen of the display device, Say the name of the position, detected by the speech recognition apparatus, the symbol image of the detection output Converted into motion command by motion command conversion circuit,
Based on the output, the controller selects the function selector corresponding to the position on the screen, so you can easily select the controlled device with a small number of uttered words and simplify the selection operation. can do.

[Procedure Amendment 11]

[Document name to be corrected] Drawing

[Name of item to be corrected] Figure 6

[Correction method] Change

[Correction content]

[Figure 6]

[Procedure Amendment 12]

[Document name to be corrected] Drawing

[Name of item to be corrected] Figure 7

[Correction method] Change

[Correction content]

[Figure 7]

Claims (3)

[Claims] 1. A display device for color-coding and displaying function selectors of a controlled device on a screen, and a voice recognition device for recognizing a voice when a color name of the function selector displayed on the display device is uttered. And a symbol image operation instruction conversion circuit that converts the uttered color name recognized by the voice recognition device into an operation instruction, and an operation instruction output from the symbol image operation instruction conversion circuit, and displays the display. A voice input function selection device comprising: a control device that selects a function selector corresponding to a color on the screen of the device and controls the controlled device to execute this function. 2. A display device for changing the shape of the function selector of the controlled device on the screen, and a voice recognition device for detecting that the name of the displayed shape of the function selector is detected.
A symbol image operation command conversion circuit for converting the uttered form name recognized by the voice recognition device into an operation command, and a screen of the display device that receives an operation command output from the symbol image operation command conversion circuit. A voice input function selection device comprising: a function selector for selecting the function selector corresponding to the above form, and a control device for controlling the controlled device to execute this function. 3. A display device for changing the position of the function selector of the controlled device on the screen and a voice recognition device for detecting that the name of the position of the function selector displayed on the display device is uttered. And a symbol image operation instruction conversion circuit for converting the result recognized by the voice recognition device into an operation instruction of the name of the uttered position, and an operation instruction output from the symbol image operation instruction conversion circuit, A voice input function selecting device comprising: a control device that selects a function selector corresponding to a position on the screen and controls the controlled device to execute this function.