JPH07219586A - Information processing method and device - Google Patents

Abstract

(57) [Summary] [Purpose] The recognition of commands by voice is switched in response to changes in the state of the application by inputting commands, and command input other than voice is also supported. [Structure] A command receiving unit 15 that receives a voice and a command input by another method, and a voice recognition dictionary switching unit 12 that switches a dictionary used for voice recognition according to the command received here.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an information processing method and apparatus for operating an application on a computer by inputting a command by voice.

[0002]

2. Description of the Related Art Conventionally, in this type of information processing method, since the words and sentences that can be recognized by voice are limited, a dictionary defining voice commands corresponding to commands to applications on a computer is prepared, and this voice command is used. I was trying to recognize only the voice. Then, in accordance with the recognized voice command, a corresponding application command is generated.

Here, since the number of voice commands that can be effectively voice-recognized is limited, attention is paid to the fact that the application command to be used differs depending on the state of the application. Was prepared to reduce the number of voice commands targeted for voice recognition. For example, when each layer of the hierarchical menu is set as a state and a corresponding menu is selected by inputting a voice command, next, switching to a dictionary including voice commands corresponding to the submenu is performed.

For example, consider the top menu 51 of the editor application shown in FIG. When each menu is selected by mouse clicking, the specified operation is performed. When the menu 501 is selected, the submenu 61 shown in FIG. 6 is displayed and only this submenu can be selected. When each of the sub menus 611, 612, and 613 is selected, the document is opened, saved, and closed, and the top menu 51 is returned to. Similarly, when the menu 502 is selected, the submenu 62 is displayed and each submenu is selected. When the menu 503 is selected, the application ends. Here, one letter of the alphabet at the right end of each menu is a letter indicating that, when the letter is sent, the same effect as when the menu is selected by mouse click is exerted. For example, when the top menu 51 is displayed and the character “d” input by the keyboard is sent, the menu 501 is selected and the submenu 61 is displayed.

When the above menu selection is performed by a voice command, in the conventional information processing method, for example, a dictionary shown in FIG. 7 is prepared. The dictionary 71 is a voice recognition dictionary in a state of waiting for selection of the top menu. Here, 701 is a dictionary number that identifies the dictionary. Dictionary 7
The dictionary number of 1 is 1. The remaining lines correspond to one voice command line by line. The column 751 describes the name of the voice command. A column 752 describes how to read a voice command, and voice recognition is performed using this information. Column 753 describes the characters to be sent to the application when a voice command is input. Row 754
Describes the dictionary number of the voice recognition dictionary to be used next when the voice command is input. First, when the top menu is on standby, the dictionary 71 is used as the voice recognition dictionary. When a voice command is input, voice recognition is performed using the reading information in column 752 of the voice recognition dictionary, and the characters described in column 753 of the voice command, which is the recognition result, are transmitted to the application, so that the voice command is converted. The same processing is performed as when the corresponding menu is selected. Then, by making the dictionary of the dictionary number described in the column 754 the next voice recognition dictionary, the voice command that can be recognized is changed according to the state of the application.

[0006]

However, in the above-mentioned conventional example, since the voice recognition dictionary is switched only by the result of voice command input, the state of the application is changed by the user directly selecting the menu by clicking the mouse. Even if the voice recognition dictionary changes, the voice recognition dictionary is not switched, so that there is a drawback that the state of the application and the voice command that can be recognized cannot be consistent.

[0007]

In order to solve the above problems, the information processing method of the present invention accepts a voice command input and a command input other than voice input, and a voice recognition dictionary is used for the voice command input. Voice recognition of voice commands using, when performing the processing according to the both commands,
A voice recognition dictionary is prepared for each state, and the voice recognition dictionary used for voice recognition is switched according to a change in the state due to both the voice command input and the command input other than the voice input.

If the application for processing and the application for receiving voice input are different,
Upon receiving a voice command input, voice-recognizing a voice command using the voice recognition dictionary, and transmitting the command to another application based on the voice recognition result,
A voice recognition dictionary is prepared for each state of the application, and the change of the state of the application by the voice command input and the change of the state of the application by the command input to the application by another method are received from the application, and the change in the state of the application is received. Accordingly, we decided to switch the voice recognition dictionary used for voice recognition.

[0009]

Embodiments of the present invention will now be described in detail with reference to the drawings.

FIG. 1 is a block diagram showing a basic configuration of a method according to an embodiment of the present invention. In the figure, 11 is a voice recognition dictionary holding unit for holding a voice recognition dictionary prepared for each state of an application. A voice recognition switching unit 12 switches a dictionary used for voice recognition from the voice recognition dictionaries held in the voice recognition dictionary holding unit 11. Reference numeral 13 is a voice command receiving unit that receives a voice command input. Reference numeral 14 recognizes the voice command accepted by the voice command accepting unit 13 using the voice recognition dictionary switched by the voice recognition dictionary switching unit 12,
A voice recognition unit that generates a command for an application according to the result. Reference numeral 15 is a command receiving unit that receives the command generated by the voice recognition unit 14. The command accepting unit also accepts direct command input from the user using the keyboard and mouse. Even if any command is input, the voice recognition dictionary switching unit 12
To the received command. Reference numeral 16 is a command execution unit that performs various processes according to the command received by the command reception unit 15.

The method will be described below with reference to the flow chart shown in FIG. First, in step S21, the voice recognition dictionary to be used first is set. Then, the process proceeds to step S22. In step S22, the voice command receiving unit 13 checks whether or not the voice command is received. If not, the process proceeds to step S25. If accepted, the process proceeds to step S23. In step S23, the voice command accepted by the voice command accepting unit 13 is recognized using the voice recognition dictionary switched by the voice recognition dictionary switching unit 12. Then, the process proceeds to step S24.
In step S24, a command for the application is generated based on the recognition result in step S23.
Then, the process proceeds to step S25. In step S25, it is checked whether or not the command receiving unit 15 has received the command to the application including the direct input from the user. If not received, the process returns to step S22. If accepted, the process proceeds to step S26. In step S26, various processes are performed according to the command received by the command receiving unit 15. Then, the process proceeds to step S27. Step S2
At 7, the voice recognition dictionary is switched according to the command received by the command receiving unit 15. Then, the process returns to step S22.

The above operation will be described by taking as an example the case where the dictionary shown in FIG. 7 is used as the voice recognition dictionary for the application having the menus shown in FIGS. The dictionary 71 is first set as the voice recognition dictionary in S21. Then, steps S22 and S25 are alternately repeated until a voice command is input or the menu is clicked with the mouse. Here, when the voice command "Henshu" is input, the control moves to step S23, and voice recognition is performed. Result of speech recognition "Edit"
When is recognized as a voice command, the command character “e” corresponding to “edit” is generated by referring to the dictionary 71 and sent to the command receiving unit 15 in step S24. As a result, the command accepting unit accepts the command meaning to select the menu 502, and the process proceeds to step S26, and the process of displaying the submenu 62 is performed. Then, in step S27, the dictionary number 3 to be moved when the "edit" command, which is the name of the menu 502, is searched from the dictionary 71, and the voice recognition dictionary is switched to the dictionary 73. As a result, the voice command corresponding to the sub menu 62 can be recognized. The dictionary 71 is first set as the voice recognition dictionary in S21. Then, until a voice command is input or the menu is clicked with the mouse, step S
22 and step S25 are alternately repeated. Next, in this state, the user clicks the menu 621 by clicking the mouse.
If is selected, the process proceeds to step S26, and the cutting process and the process of displaying the top menu are performed. Then, in step S27, the menu 621 is selected from the dictionary 73.
When the "cut" command, which is the name of the dictionary, is searched, the dictionary number 1 to be moved is searched, and the voice recognition dictionary is set to the dictionary 71.
Switch to. As a result, the voice command corresponding to the top menu 51 can be recognized. In this way, the recognized voice command can be changed according to the state of the application even in the case of command input by mouse click instead of voice command input.

In this embodiment, the command generated according to the voice recognition result is transmitted to another application without receiving and executing the command, and the name of the executed command is received from the other application. Then, when the voice recognition dictionary is switched, it becomes an embodiment of the information processing information of claim 2. A block diagram and a flow chart in this case are shown in FIGS.

In this embodiment, the case where the menu command is the operation target has been described, but the present invention is not limited to this, and an arbitrary command for an application may be the operation target.

In this embodiment, the case where the character is sent as a command from the recognition result of the voice command has been described, but the present invention is not limited to this, and the processing function may be directly called.

In the present embodiment, the case where the voice recognition dictionary is switched using the name of the accepted command has been described, but the present invention is not limited to this, and the corresponding voice commands such as numbers given to both sides can be used. Any identifiable information may be used.

In the present embodiment, the case where the voice recognition dictionary is switched after the command of the application is accepted regardless of the type of the command input by the user has been described, but the present invention is not limited to this, and the voice command is not limited to this. In the case of input, switching processing of the voice recognition dictionary may be performed directly from the recognition result.

In this embodiment, the case of alternately checking the presence / absence of acceptance of a voice command and other commands has been described. However, the present invention is not limited to this, and even if the number of checks is increased. Good.

In the present embodiment, the case where the processing of accepting the voice command and other commands is handled in the same flow has been described, but the present invention is not limited to this, and parallel processing may be performed.

In this embodiment, the description has been given of the case where the name, reading, generated character, and switching dictionary number of the voice command are described in the voice recognition dictionary, but the present invention is not limited to this, and voice recognition such as a phoneme string is performed. Any format may be used as long as it has the information necessary for the above and the information that can generate the command of the application.

In the present embodiment, the case where the information for selecting the next voice recognition dictionary is described for each voice command has been described, but the present invention is not limited to this, and the state of the application is named. Any method may be used as long as the change in the state of the application is reflected in switching the voice recognition dictionary, such as searching a voice recognition dictionary to be used next with the name.

[0022]

As described above, according to the present invention,
Voice command input and command input other than voice input are accepted, and for voice command input, voice commands are voice-recognized using a voice recognition dictionary. A recognition dictionary is prepared, and the voice recognition dictionary used for voice recognition is switched according to a change in the state due to both the voice command input and the command input other than the voice input, so that the user can directly click the mouse to open the menu. Even if the state of the application changes by inputting a command other than the voice command such as selection, the voice command according to the state of the application can be recognized.

Even when the application for processing is different from the application for accepting voice input, the voice command input is accepted, the voice command is voice-recognized using the voice recognition dictionary, and another voice command is selected based on the voice recognition result. When sending a command to the application, a voice recognition dictionary is prepared for each state of the application, and the change of the state of the application by the voice command input and the change of the application state by the command input to the application by another method are performed. Since the voice recognition dictionary used for voice recognition is switched according to the state change of the application received from the application, the same effect can be obtained.

[Brief description of drawings]

FIG. 1 is a block diagram showing a basic configuration of an embodiment of an information processing method according to the present invention.

FIG. 2 is a flowchart showing an outline of an information processing method according to an embodiment of the present invention.

FIG. 3 is a block diagram showing the basic configuration of another embodiment of the information processing method according to the present invention.

FIG. 4 is a flowchart showing an outline of an information processing method according to another embodiment of the present invention.

FIG. 5 is a diagram showing a top menu of an application.

FIG. 6 is a diagram showing a submenu of an application.

FIG. 7 is a diagram showing the contents of a voice recognition dictionary.

Claims (4)

[Claims] 1. An information processing method for recognizing an input voice by using a voice recognition dictionary prepared for each state, which accepts a command input other than voice and responds to a change in the state according to the received command. And a voice recognition dictionary used for the voice recognition is switched. 2. Information processing for receiving a voice command input, voice-recognizing a voice command using a voice recognition dictionary, and transmitting a command based on a voice recognition result, the voice recognition dictionary for each state of the application. An information processing method characterized by receiving a state change caused by the voice command input and a state change caused by a command input by another method, and switching a voice recognition dictionary used for voice recognition according to the state change. . 3. An information processing apparatus having an input means for inputting voice, a recognition means for recognizing the input voice using a voice recognition dictionary prepared for each state, and accepting command input other than voice. An information processing apparatus, comprising: a command receiving unit; and a switching unit that switches a voice recognition dictionary used for the voice recognition according to a change in a state according to the received command. 4. A voice command accepting means for accepting a voice command input, a recognizing means for recognizing the accepted voice command using a voice recognition dictionary, and a command transmitting means for transmitting a command based on the result of the recognition. An information processing apparatus having: a receiving unit that receives a state change due to the voice command input and a state change due to another command input method; and voice recognition used for the voice recognition according to the received state change. An information processing apparatus comprising: a switching unit that switches a dictionary.