JP2000099076A - Performance environment setting device utilizing voice recognition, and method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To set automatically intrinsic application performance environment for each user by relaxing troublesomeness of selection of application and input for specifying a user. SOLUTION: This device is provided with a voice input section 11 inputting a voice, a word discriminating section 12 discriminating a specific word from an inputted voice, a speaker discriminating section 13 discriminating a specific user from an inputted voice, an environment information selecting section 14 selecting an application program and intrinsic environment for user based on a discriminated result obtained from the speaker discriminating section 13, and an application program performing section 17 performing an application program based on selected environment information. Therefore, an application program desired by a user is specified by a voice, while a user is specified by discriminating a speaker, and an application program is performed under operation environment of an intrinsic application program for a user.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to a method and an apparatus for executing an application program by voice input.

[0002]

2. Description of the Related Art With the advancement of computer systems in recent years, technologies for identifying words by voice and technologies for identifying speakers by voice have made great strides. Also,
Since voice can be used, one of the factors that hinders the spread of the computer environment, such as so-called computer allergies, which dislikes the input itself from a keyboard or the like, has been eliminated, and many people are using computer systems. . However, under the present circumstances, when a plurality of people jointly use a plurality of application programs existing in one computer system, an application desired to be used is selected with a pointing device such as a keyboard or a mouse to identify a user. Is performed by inputting a user registration name and a password associated therewith with a keyboard or the like.

[0003]

However, when the application is frequently switched or the user changes at a considerable frequency, it is often rather troublesome to select an application or input an identifier by such a method.
In other words, it is conceivable that smooth operation may be hindered by erroneous operation of the mouse or the like, erroneous key strokes, or forgetting of a password. Further, each time the user changes, it may be necessary to set individual execution environments.

According to the present invention, when such an application is switched or the user changes, the application is selected and the user is identified by using the voice recognition technology, thereby selecting the application and identifying the user. The purpose of the present invention is to reduce the trouble of inputting with a keyboard, a mouse, or the like, and to automatically set an execution environment of an application program unique to each user.

[0005]

In order to solve the above-mentioned problems, an execution environment setting apparatus utilizing voice recognition according to the present invention is characterized in that a voice input unit for inputting voice and a voice input from the voice input unit are specified. A word identification unit that identifies the word of the speaker, a speaker identification unit that identifies a specific user from the voice input from the voice input unit, an identification result obtained from the word identification unit,
An environment information selection unit that selects an application program and user-specific environment information based on the identification result obtained from the speaker identification unit; and one or more environment information storage units that store user environment information for each application program. An environment information management unit that has an environment information storage unit and manages the entirety of the application information and the environment information; an application program execution unit that executes the application program based on the environment information selected by the environment information selection unit; And an execution result output unit that outputs an execution result.The application program is identified by word identification by voice, and at the same time, the user is identified by speaker identification by voice. Can do And wherein the door.

With this configuration, the application program execution section can automatically execute the application program in an operating environment unique to the user without performing any manual operation for identifying the user. .

It is preferable that the execution environment setting device utilizing voice recognition according to the present invention has an identification result confirmation unit for confirming the identified user and the application program. This is because when an incorrect user is identified, the recognition operation can be performed again.

The execution environment setting apparatus utilizing speech recognition according to the present invention executes the application program after copying the specified user's environment information to the environment information management section before executing the application program. It is preferable that the environment information management unit detects the end of the application program, and after the execution of the application program ends, the environment information of the environment information management unit is copied back as the specified user's environment information. This is so that even an application program that is not adapted to be used by a plurality of users can be executed in an environment unique to each user.

Further, the execution environment setting apparatus utilizing speech recognition according to the present invention preferably includes a speaker registration unit which can register or delete a new speaker. This is in order to flexibly respond to changes in the user.

In the execution environment setting apparatus utilizing voice recognition according to the present invention, an environment information management unit registers a new application program in an application information list or deletes unnecessary application programs from the application information list. Preferably, an application registration unit is provided. This is in order to flexibly respond to changes in the application program.

Further, the execution environment setting apparatus utilizing speech recognition according to the present invention includes a speaker identification result holding unit for storing a history of identification results obtained from the speaker identification unit in the information selection unit, and a word identification unit. It is preferable to judge the user based on the contents of the speaker identification result holding unit at the time when the identification result is obtained in the step (a). This is because a plurality of speaker recognition results are stored, so that erroneous recognition of the speaker can be prevented.

Next, in order to solve the above-mentioned problems, an execution environment setting method utilizing speech recognition according to the present invention comprises the steps of: inputting a voice; identifying a specific word from the input voice; Identifying a specific user from the input voice, selecting an application program and user-specific environment information based on the word identification result and the user identification result, and identifying the application program and user-specific environment information. A step of executing the application program based on the environment information selected in the step of selecting the environment information; and a step of outputting an execution result of the application program. Users are identified by speaker identification, and user-specific application programs are identified. Characterized in that the application can run programs under production environment.

With this configuration, the application program execution section can automatically execute the application program in an operating environment unique to the user without performing any manual operation for identifying the user. .

Next, a computer-readable recording medium storing a program to be executed by a computer according to the present invention includes a step of inputting a voice, a step of identifying a specific word from the input voice, and a step of inputting a voice. A step of identifying a specific user from voice; a step of selecting environment information specific to the application program and the user based on the identification result of the word and the identification result of the user; and environment information specific to the application program and the user Selecting an application program based on the environment information selected in the step of selecting an application program, and outputting an execution result of the application program. Used by identification Identify characterized by their ability to execute an application program under the user-specific application program production environment.

With this configuration, by loading and executing the program on the computer, the application program execution unit does not perform any manual operation for identifying the user, and operates under the operating environment unique to the user. An execution environment setting device by voice identification that can automatically execute an application program can be realized.

[0016]

FIG. 1 shows an execution environment setting apparatus utilizing speech recognition according to an embodiment of the present invention.
This will be described with reference to FIG. FIG. 1 is a configuration diagram of an execution environment setting device utilizing voice recognition according to an embodiment of the present invention.

In FIG. 1, reference numeral 11 denotes a voice input unit;
Is a word identification unit, 13 is a speaker identification unit, 14 is an information selection unit, 15 is a speaker registration unit, 16 is an information management unit, and 17 is an information management unit.
Indicates an application program execution unit, and 18 indicates an execution result output unit.

First, information input by the user through an information input medium such as a keyboard is input by voice from the voice input unit 11. The audio input medium is not particularly limited as long as it is an audio input device such as a microphone. Further, since the voice input itself is analog data, it is necessary to convert it into digital data using an A / D converter or the like so that it can be handled by a computer.

Next, based on the voice data input from the voice input unit 11, the word identification unit 12 identifies the application name to be executed. At the same time, the speaker identification unit 13
, A user who has input a voice from the voice input unit 11 is identified based on a voice feature pattern or the like. The two identification results are notified to the environment information selection unit 14 to obtain environment information unique to the user.

In the environment information selecting section 14, the word identifying section 12
Application name and speaker identification section 13
Based on the user name that is the identification result of the above, the environment information necessary when the user uses the application can be acquired from the environment information management unit 16. At the same time, for the application, accompanying information such as a command line to be executed can be acquired as application information.

In the environment information management unit 16, there are a plurality of environment information storage units for each application name (APPL1, APPL2, etc. in FIG. 1). It has an ID list for managing user IDs and has an environment information file corresponding to each user ID. The user ID and the environment information have a one-to-one correspondence. Therefore, when the application name and the user (user ID) are specified, one piece of environment information to be used is specified.

The application program execution unit 17 is notified of the application information and the environment information, the application program execution unit 17 executes the application program, and outputs the execution result to the execution result output unit 18. The execution result output unit 18 may be a screen display output such as a CRT display or a liquid crystal display device, or may be a sound output for synthesizing and outputting a sound.

As described above, according to the present embodiment, not only a word is identified by a voice input to identify an application, but also a user is identified at the same time, whereby the user associated with the specific application is identified. It is possible to acquire unique environment information, and to automatically start the application program based on the user-specific environment information when the application program is executed.

Next, a case where the execution environment setting apparatus utilizing speech recognition according to the embodiment of the present invention has an identification result confirmation unit 26 will be described with reference to FIG. FIG. 2 is a flowchart of a process in the identification result confirmation unit 26 in the execution environment setting device utilizing the speech recognition according to the embodiment of the present invention.

In FIG. 2, the word identifying section 12 and the speaker identifying section 13 are simultaneously executed based on the input voice. The application name recognized by the word identification unit 12 and the user name recognized by the speaker identification unit 13 are notified to the identification result confirmation unit 26. In addition, the identification result of the word identification section is displayed on the CRT display 25. The display output is not limited to a CRT display, but may be another display device such as a liquid crystal display device.

Next, the identification result confirmation section 26 checks the notified identification result against a word name list (application name list) and a speaker name list (user name list) registered in advance. (Step S21). As a result, a word name and a speaker name that can be determined to be the same as or closest to the identification result notified in each list are represented by C.
The display is output to the RT display 25.

Then, by checking the displayed collation result, a confirmation screen for inputting whether or not the collation result matches the result conscious of the user is displayed and output to the CRT display 25 ( (Step S22), and enters a state of waiting for input from the user (Step S23).

The user uses the input medium 27 such as a keyboard or a mouse to input whether or not the identification result matches the consciousness (step S24). If they match, the identification result, that is, the application name to be executed and the speaker name are notified to the environment information selecting unit 14. If they do not match, input the voice again and repeat until a correct recognition result is obtained.

As described above, according to the present embodiment, it is possible to prevent the processing from proceeding in a state in which the voice recognition is not accurate, and to prevent a meaningless application from starting.

Next, processing performed by the application program execution unit 17 in the execution environment setting device utilizing speech recognition according to the embodiment of the present invention will be described with reference to FIGS. FIG. 3 and FIG. 4 are process schematic diagrams of the application program execution unit in the execution environment setting device utilizing voice recognition according to the third embodiment of the present invention.

In FIG. 3, when the application name and the user name (speaker name) are specified, and the corresponding environment information file name is notified to the application program execution unit 17, the application program 18 corresponding to the information is executed. It is started automatically. In this case, the environment information file selected by the environment information selecting unit 14 is copied as specific environment information when executing the application program. This makes it possible to execute the application program under an environment corresponding to the user, regardless of the state of the environment before the execution of the application program.

As shown in FIG. 4, when the upper management unit 16 detects the end of the execution of the application, the copied specific environment information is re-read by the environment information management unit 1.
Copy back to the environment information storage unit in 6. By performing such processing, after terminating the application,
Regardless of who runs which application on the same terminal, when the user executes the application again, it is possible to execute the application under the same environment as when the application was terminated this time.

As described above, according to the present embodiment, a case where a plurality of users use the same application on the same terminal and a case where the application program is a program which does not correspond to a plurality of uses. Even so, when each user uses the application, it becomes possible to execute the application program again in the same usage environment as when he or she used it last time.

Next, a description will be given of a specific example of processing in the environment information management unit 16 of the execution environment setting device utilizing voice recognition according to the embodiment of the present invention with reference to FIGS. FIGS. 5 and 6 show the information storage state in the environment information management unit 16 at the time of new user registration in the execution environment setting device utilizing voice recognition according to the embodiment of the present invention.

FIG. 5 shows the information storage state in the environment information management unit 16 before the notification of the new user registration. First, the application information list includes an application name and an application ID to be identified by voice recognition.
(Hereinafter referred to as “A-ID”), and the name of the environment information storage unit in which the initial environment information and the environment information are stored in addition to the execution command at the time of execution.

The environment information storage unit has an ID list and an environment information file for each application. The speaker ID (hereinafter, “S”) indicating the user is included in the ID list.
-ID ". ) And the name of the environment information file in which the environment information is stored. The environment information storage unit includes as many environment information files as the number of S-IDs registered in the ID list.

Now, as a new user, S-ID =
Assuming that the registration of the user of “3” has been notified, FIG.
The information shown in the colored frame is added. That is,
No addition is made to the application information list, but “3” is added as a new S-ID to the ID list of the environment information storage unit, and the environment information file corresponding to S-ID = “3” is stored in the application information list. Is automatically generated based on the initial environment information. That is, the environment information “APP-A3.CFG” is a copy of the initial environment information “Data A”, and the environment information “APP-B.
3. “CFG” is generated as a copy of the initial environment information “Data B”.

FIG. 7 is a diagram showing how the environment information selecting section actually selects the application information and the environment information file name. In FIG. 7, for example, if the word identification unit 12 identifies A-ID = “2” and the speaker identification unit 13 identifies S-ID = “1”, the application name is determined from the application information list. Is "A
PP-B ”and the environment information file name is“ APP-B1.CF ”from the ID list of the environment information storage unit.
G ".

5 and 6, the application “APP”
The execution command line of “-B” is “APP-B-con
f %% ”. Here, assuming that “%%” means replacement with the environment information file name, the actual execution command line is “APP-B-co
nf APP-B1. CFG ".

Next, a description will be given, with reference to FIG. 8, of the execution environment setting apparatus utilizing speech recognition according to the embodiment of the present invention, in the case where the environment information selecting section 14 has a speaker identification result holding section 81. I do. FIG. 8 is a processing flowchart in the environment information selecting unit 14 in the execution environment setting device utilizing voice recognition according to the embodiment of the present invention.

First, the A-ID is specified in the word identification section 12, and then the S-ID is specified in the speaker identification section 13. The identification result for the same speaker is stored in the speaker identification result holding unit 81 as an S-ID history. The generation of the history is not particularly limited, but is preferably around 10 generations in consideration of the determination time and the like. However, the present invention is not limited to this, and any number of generations may be stored as long as the information processing resources allow.

Next, the value held most frequently among the S-IDs stored in the speaker identification result storage unit 81 at the timing when the A-ID is notified is defined as the S-ID. Here, if the value of the S-ID is “0 (zero)”, it means that the S-ID has not been recognized, and thus is not included in the S-ID count. However, the newest recognition result, S
If the -ID and the specified S-ID are different, the voice input should be performed once more to confirm again. Conversely, if the S-ID that is the newest recognition result matches the specified S-ID, the process proceeds to the next process assuming that the S-ID represents a correct user.

Next, an execution environment setting apparatus utilizing speech recognition according to an embodiment of the present invention will be described with reference to the drawings. FIG. 9 shows a speaker registration unit 15 in an execution environment setting device utilizing voice recognition according to an embodiment of the present invention.
The processing block diagram of FIG.

In FIG. 9, in the speaker registration section 15, the user first inputs his / her name into an information input medium 94 such as a keyboard.
Enter from. For example, the operation of keying in “TARO” corresponds to this.

Next, in order to register the feature pattern of the voice, an arbitrary word is input from the voice input unit such as a microphone in the voice input unit 11 for about 10 seconds. The input audio data is converted into digital data by an A / D converter 91 and stored in an audio data buffer 92. The audio data buffer 92 is facilitated by a certain fixed capacity. When the audio data buffer 92 is full of audio data, old data is replaced with new data in order. By doing so, it is possible to know the feature pattern of the voice based on the latest voice data.

Then, in order to confirm whether the application name can be recognized based on the feature pattern of the voice,
The designated application name is input from the voice input unit 11 again, and is collated with the word list of the word identification unit 12,
CRT display 9 displays the recognized application name
3 is displayed. If the recognized application name is correct, the input user name (speaker name) and the acquired voice feature pattern are registered in the speaker list of the speaker identification unit 13,
The user is registered in the environment information management unit 16 as a new user.

A series of processes will be described from the viewpoint of display on the CRT display 93. FIG. 10 to FIG. 14 show the transition of the screen of the new registration process in the speaker registration unit. First, FIG.
A name entry is required, such as 0. Next, as shown in FIG. 11, "TAR" is input from an information input medium 94 such as a keyboard.
Key in "O".

Further, as shown in FIG. 12, a new user “TARO” is input from a voice input medium such as a microphone.
In order to register the voice feature pattern, an arbitrary word is input for about 10 seconds. As in the example of the screen, it is preferable that the remaining time for input is displayed, and the character of “Recording” is inverted or changed in color during recording so that it can be visually confirmed.

After the voice feature pattern has been registered, an application name frequently used as "word processor" is input from a voice input medium such as a microphone in order to test whether or not voice recognition can be accurately performed using the pattern. I do. The result of actual recognition is also displayed at the same time.

Finally, as shown in FIG. 14, a screen for confirming whether or not the recognition has been made correctly is displayed. If the recognition has been made correctly, that is, if "YES" is input, the user who has input the data is displayed. The name (speaker name) and the acquired voice pattern are registered in the speaker list of the speaker identification unit 13 and registered as a new user in the environment information management unit 16. If it is not correctly recognized, that is, if "NO" is input, voice input is performed once again to confirm again.

FIG. 15 shows the flow of the above processing.
Shown in In FIG. 15, first, a user name and voice for user registration are input (step S151), and a new S-
An ID is automatically generated (step S152). For example, S
-If the ID is of a form designated by a serial number, a new S-ID is obtained by adding "1" to the latest registered S-ID.

Then, the generated S-ID, the input user name (speaker name) and the feature pattern of the voice are registered in the speaker identification unit 13 (step S153). Information about the user is registered in a speaker list in the speaker identification unit 13. When a new user is registered in the speaker registration unit 13, the speaker registration unit 13 notifies the environment information management unit 16 of the registration (step S154).

The environment information management unit 16 adds the user name (speaker name) and S-ID to all the environment information storage units and updates the ID list file to add the added environment unique to the user. Add an information file. Finally, the S-ID of the added user is stored in the S-ID storage unit of the speaker registration unit 13 (step S155), and the registration of one user is completed.

FIG. 16 shows the contents stored in the environment information management unit 16 when two users are registered. In FIG. 16, “WORD” which is word processing software is used as the application name.
PROC "and" HYOKEISA "as spreadsheet software
N "are registered in the application information list, and the respective environment information storage units" WORDPROC-EN "are registered.
V and HYOUKEISAN-ENV, the environment information files corresponding to the S-IDs of the two users are registered. Note that “NULL” in the initial environment information means that the data is empty. In this example, WORDPROC is used.
Uses an environment information file whose data is empty as an initial information file.

FIG. 17 shows the initial environment information “HY-DAT”.
A shows an example of the content of "A". The first line is a description that specifies that the key for reading data is set to the “F1” key, and the second line is a description that specifies that the key for reading data is set to the “F2” key. . in this way,
Information on the use environment is designated as initial environment information, and environment information customized to be easy for the user to use is used as user-specific environment information, for example, HYOUKE.
ISAN2. What is necessary is just to save like CFG.

Next, FIG. 18 is a block diagram showing processing up to the execution of an application program in the execution environment setting device utilizing voice recognition according to one embodiment of the present invention.

In FIG. 18, first, in the voice input unit 11, a user inputs a name of an application desired to be used from a voice input medium such as a microphone. The input audio data is converted into digital data by an A / D converter 91 and temporarily stored in an audio data buffer 92.

Next, the input speech data is converted to a word
2 and to the speaker identification unit 13. First, the word identification unit 1
In 2, the A-ID is obtained by collating with the word list. FIG. 19 shows an example of the contents of the word list. In the word list, pronunciation words and application names can correspond to N: 1. This is because, in many cases, the same application is called differently depending on the user. In the example of FIG. 19, a plurality of pronunciation words are registered for the same A-ID “1”.

Then, the speaker identification section 13 obtains the S-ID by collating with the speaker list. FIG. 20 shows an example of the contents of the speaker list. A-ID and S obtained respectively
-ID is transferred to the information selection unit 14.

The information selection unit 14 acquires application information and environment information from the environment information management unit 16 using the acquired A-ID and S-ID as search keys. Specifically, application information corresponding to the A-ID obtained by searching the application information file is obtained,
The environment information storage unit corresponding to each application is accessed, and the ID list file is searched using the S-ID as a search key to obtain the acquired S-ID-specific environment information. The obtained application information and environment information are transferred to the application program execution unit 17.

The processing up to this point will be described from the viewpoint of screen display. 21 to 24 show the flow of screen display of the execution unit. First, FIG. 21 shows an image of the initial screen. Although information corresponding to the contents of the word list is displayed at the top of the screen, it is not particularly necessary to display the information.

Next, when the user registered under the name "TARO" wants to start "WORDPROC",
The user “TARO” may speak “word processor”. Then, when "TARO" starts speaking "word...", The speaker identifying unit 13 first recognizes that the user is "TARO" as shown in FIG.

When "TARO" finishes speaking "..processor", the word identification unit 12 recognizes that the application name is "WORDPROC" as shown in FIG. When the user name and the application name can be specified, the application program execution unit 1
7, the application "WORDPROC" is automatically activated as shown in FIG.

The application program execution unit 17 is notified of the application information of the application “WORDPROC” and the name of the environment information file for the user “TARO”. In the execution command line of the application information, "WORDPROC %%" is described, and the environment file name at the time of execution is automatically set in "%%". For example, if the environment information file name is "WOR
DPROC1. In the case of "CFG", the application "WFG" is actually described by a command line description "WORDPROC WORDPROC1.CFG".
"ORDPROC" is activated.

Also, the application “WORDPRO”
If "C" is a use that can save the last saved document file name in the environment information file at the end of the application and can automatically read the document file when the application is next started, as shown in FIG. Environment information can be stored as information unique to the user “TARO”. FIG. 25 shows that the last saved file is “TARO.
WDP "is environment information indicating that the application is stored at the end of the application.
The next operation can be started from the last file saved last time.

Next, a description will be given of a processing flow of a program for realizing the execution environment setting device utilizing the speech recognition according to the embodiment of the present invention. FIG. 26 shows a flow chart of a process of a program for realizing the execution environment setting device utilizing the speech recognition according to the embodiment of the present invention. Since the registration unit has been described above, only the execution unit will be described here.

In FIG. 26, first, the name of the application to be executed is input by voice (step S261). next,
The word identification unit 13 identifies the A-ID by collating with the word list (step S262). In addition, the speaker identification unit 12 checks S against the
-ID identification is performed (step S263).

Then, the identified A-ID and S-ID
Is notified to the environment information selection unit 14, and the environment information selection unit 14 acquires the application information and the environment information from the environment information management unit 16 (step S264). In this case, the application information is obtained from the application information list in the environment information management unit 16, and the environment information is obtained from the ID of the environment information storage unit.
Get as environment information file name from the list.

The acquired application information and environment information file names are stored in the application program execution unit 17.
Is notified to reconstruct the actual execution command line,
The application program is started under the environment specified based on the environment information unique to the user (step S26)
6).

A recording medium storing a program for realizing an execution environment setting device utilizing voice recognition according to the embodiment of the present invention is a CD-ROM or a floppy disk as shown in the example of the recording medium shown in FIG. Etc. as well as other storage devices provided at the end of a communication line or a recording medium such as a hard disk or RAM of a computer. When the program is executed, the program is loaded and stored in the main memory. Executed in

Further, a recording medium for recording environment information data and the like generated by the execution environment setting device utilizing speech recognition according to the embodiment of the present invention is, as shown in the example of the recording medium shown in FIG. Not only a portable recording medium such as a CD-ROM and a floppy disk, but also any other storage device provided at the end of a communication line or a recording medium such as a hard disk or a RAM of a computer may be used. It is read by a computer when using an execution environment setting device utilizing recognition.

[0072]

As described above, according to the execution environment setting method and apparatus utilizing speech recognition according to the present invention, it is possible to construct a system for automatically starting a plurality of application programs utilizing a speech recognition function. It is possible to reduce the manual work of the user at the time of starting the application program, and to automatically set the environment unique to each user.

[Brief description of the drawings]

FIG. 1 is a configuration diagram of an execution environment setting device utilizing voice recognition according to a first embodiment of the present invention;

FIG. 2 is a processing flowchart of an identification result confirmation unit in the execution environment setting device utilizing voice recognition according to the second embodiment of the present invention;

FIG. 3 is a schematic processing diagram of an application execution unit in an execution environment setting device utilizing voice recognition according to a third embodiment of the present invention;

FIG. 4 is a schematic processing diagram of an application execution unit in an execution environment setting device utilizing voice recognition according to a third embodiment of the present invention;

FIG. 5 is a view showing an example of information included in an information management unit before notification.

FIG. 6 is an exemplary diagram of information included in an information management unit after notification.

FIG. 7 is an exemplary diagram of an information selection process in an execution unit.

FIG. 8 is an exemplary diagram of an information selection process in an execution unit.

FIG. 9 is a configuration diagram of an execution environment setting device utilizing speech recognition according to an embodiment of the present invention (registration unit);

FIG. 10 is an exemplary diagram of a speaker registration unit input procedure screen

FIG. 11 is an exemplary diagram of a speaker registration unit input procedure screen

FIG. 12 is an exemplary diagram of a speaker registration unit input procedure screen

FIG. 13 is an exemplary diagram of a speaker registration section input procedure screen

FIG. 14 is an exemplary diagram of a speaker registration unit input procedure screen

FIG. 15 is a processing flowchart of a speaker registration unit.

FIG. 16 is an exemplary diagram of information included in an information management unit when two speakers are registered;

FIG. 17 is a diagram showing an example of initial environment information.

FIG. 18 is a configuration diagram (executing unit) of an execution environment setting device utilizing voice recognition according to an embodiment of the present invention;

FIG. 19 is a diagram showing an example of a word list.

FIG. 20 is an exemplary diagram of a speaker list.

FIG. 21 is a view showing an example of an information recognition screen in the execution unit.

FIG. 22 is an exemplary diagram of an information recognition screen in the execution unit.

FIG. 23 is an exemplary diagram of an information recognition screen in the execution unit.

FIG. 24 is an exemplary diagram of an information recognition screen in the execution unit.

FIG. 25 is an exemplary diagram of an environment information file.

FIG. 26 is a flowchart of processing in an execution environment setting device utilizing voice recognition according to an embodiment of the present invention (execution unit)

FIG. 27 is an exemplary diagram of a recording medium.

[Explanation of symbols]

Reference Signs List 11 voice input unit 12 word identification unit 13 speaker identification unit 14 information selection unit 15 speaker registration unit 16 information management unit 17 application program execution unit 18 execution result output unit 25, 93 CRT display 26 identification result confirmation unit 27, 94 input Mechanism 81 Speaker identification result holding unit 91 A / D converter 92 Audio data buffer 271 Line destination storage device 272 Portable recording medium such as CD-ROM or floppy disk 272-1 CD-ROM 272-2 Floppy disk 273 Computer 274 Recording media such as RAM / hard disk on computer

Claims (8)

[Claims] A voice input unit for inputting a voice; a word identification unit for identifying a specific word from the voice input from the voice input unit; and a specific user from the voice input from the voice input unit. A speaker identification unit to be identified; environment information for selecting an application program and the user-specific environment information based on the identification result obtained from the word identification unit and the identification result obtained from the speaker identification unit; A selection unit, an environment information management unit that has one or a plurality of environment information storage units that store the environment information of the user for each application program, and manages the entire application information and environment information; An application program execution unit that executes the application program based on the environment information selected by the selection unit; An execution result output unit that outputs an execution result of the application program, wherein the application program is identified by word identification by voice, and the user is identified by speaker identification by voice, and the application program operating environment unique to the user is provided. An execution environment setting device utilizing speech recognition, wherein the execution environment setting device is capable of executing the application program below. 2. The execution environment setting device utilizing speech recognition according to claim 1, further comprising an identification result confirmation unit for confirming the identified user and the application program. 3. The method according to claim 1, wherein the environment information of the user specified by the environment information management unit is copied before the execution of the application program, and the application program is executed. 2. The execution environment setting apparatus utilizing voice recognition according to claim 1, wherein a unit detects the environment information and copies the environment information of the environment information management unit back as the environment information of the specified user after the execution of the application program is completed. 4. The execution environment setting device utilizing speech recognition according to claim 1, further comprising a speaker registration unit capable of registering or deleting a new speaker. 5. The speech recognition according to claim 1, wherein said environment information management unit includes an application registration unit for registering a new application program in an application information list or deleting an unnecessary application program from an application information list. Execution environment setting device utilizing 6. A speaker identification result holding unit for storing a history of identification results obtained from the speaker identification unit in the information selection unit, wherein the speaker at the time when the word identification unit outputs an identification result. The execution environment setting device utilizing voice recognition according to claim 1, wherein the user is determined based on the contents of the identification result holding unit. 7. A step of inputting a voice, a step of identifying a specific word from the input voice, a step of identifying a specific user from the input voice, and a result of word identification and identification of the user. A step of selecting an application program and the user-specific environment information based on the result; anda step of selecting the application program based on the environment information selected in the step of selecting the application program and the user-specific environment information. Executing, and outputting an execution result of the application program.At the same time, the application program is identified by word identification by voice, and the user is identified by speaker identification by voice. Under the application program operating environment, the application program An execution environment setting method utilizing voice recognition characterized by being able to execute programs. 8. A step of inputting a voice, a step of identifying a specific word from the input voice, a step of identifying a specific user from the input voice, a word identification result and user identification. Selecting an application program and the user-specific environment information based on the result; andselecting the application program based on the environment information selected in the step of selecting the application program and the user-specific environment information. Executing, and outputting an execution result of the application program.Specifying the application program by voice word identification, and simultaneously identifying the user by voice speaker identification, Under application program operating environment A computer-readable recording medium recording a program to be executed by a computer, wherein the program is capable of executing the application program.