JP2002351653A - Device and method for processing voice - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enhance usability of printing systems especially for beginners and differently abled persons by performing an information processing such as printing by using voice. SOLUTION: In the case of controlling the information processing on the basis of recognition and synthesis of the voice, messages for voice processing regarding various kinds of information processing are displayed, a desired message for voice processing is selected among a plurality of displayed messages for voice processing, a voice message is created by synthesizing the voice of the selected message for voice processing and the synthesized voice message is vocally outputted for confirmation.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention is applicable to print control in a printing system including, for example, an information processing apparatus such as a host computer, a printer, and the like.
The present invention relates to an audio processing device and an audio processing method.

[0002]

2. Description of the Related Art Conventionally, in a printing system including an information processing apparatus and a printer, when printing a specific document, a user sets various parameters related to printing in order to control printing. It is necessary to set the print mode, print paper, and printer cartridge.

In order to set these various parameters, a user reads a graphic and a text message displayed on a screen by a printer driver, recognizes a selection item, and uses a keyboard, a mouse, or another input device to specify a specific item. Items were selected and various parameters were set.

[0004]

However, in the related art, there are the following disadvantages (1) to (4) regarding the setting of various parameters relating to information processing such as printing. (1) In a case where, for example, print processing is performed as information processing, a series of operation procedures of setting specific parameters using a keyboard and a mouse in accordance with graphics displayed on a screen when setting various parameters relating to printing are described. , The user needs to learn. As a result, there is a problem that a novice user who has never used a keyboard and a mouse is very difficult to use. (2) A novice user may not be able to select an appropriate selection item using only graphics and text generally displayed on a screen. Further, when the amount of graphic and text information displayed on the screen is increased, there is a problem that the screen becomes cumbersome for a skilled user. (3) When setting various parameters related to printing, the user must visually operate the keyboard and mouse with his / her hand, and thus cannot be used by visually impaired persons and physically handicapped persons. There's a problem. (4) If a voice message is missed when setting various parameters relating to printing, the printing process is interrupted, and there is a problem that it is very difficult to use.

Accordingly, an object of the present invention is to provide a voice processing apparatus capable of improving the usability of a user such as a beginner or a physically handicapped person by performing information processing such as printing using voice. And a voice processing method.

[0006]

SUMMARY OF THE INVENTION The present invention is an apparatus for performing information processing based on speech recognition and synthesis, comprising: display means for displaying a voice processing message relating to various information processing; Selecting means for selecting a desired voice processing message from the plurality of voice processing messages, voice synthesizing means for generating a voice message by voice synthesizing the selected voice processing message, and By providing a confirmation output means for outputting a voice message as a voice for confirmation,
Construct an audio processing device.

Here, if there is no response from the outside even after a certain period of time has passed since the voice message was confirmed and output,
Means for notifying detailed information pertaining to the information processing, or after confirming and outputting the voice message, even if a certain time has passed,
If there is no response from the outside, a means for raising the volume and notifying the voice message again may be further provided.

Means for inputting voice information and performing voice recognition; means for determining whether or not the voice information recognized as voice is valid corresponding to the voice processing message selected by the selecting means; Means for executing predetermined information processing corresponding to the selected voice processing message, when the determination is made valid according to the determination result.

In executing the predetermined information processing,
Means for notifying the occurrence of an error in the predetermined information processing, means for notifying an error recovery method of the predetermined information processing, or means for executing processing for recovering the error in the predetermined information processing by voice It may be further provided.

[0010] The present invention is a method for performing information processing based on speech recognition and synthesis, comprising the steps of displaying a message for voice processing relating to various information processing, and displaying the plurality of displayed messages for voice processing. Selecting a desired voice processing message from among the following; generating a voice message by voice-synthesizing the selected voice processing message; and converting the synthesized voice message to voice for confirmation. And outputting the audio data, thereby providing an audio processing method.

The present invention is a program for performing information processing control based on speech recognition and synthesis. The program is recorded on a computer-readable recording medium, and performs various types of audio processing related to information processing. Displaying a voice message, selecting a desired voice processing message from the plurality of displayed voice processing messages, and generating a voice message by voice-synthesizing the selected voice processing message. And a step of outputting the synthesized voice message as voice for confirmation, thereby providing a voice processing control program.

[0012] Here, if there is no response from the outside after a certain period of time has elapsed after the confirmation output of the voice message,
Notifying detailed information pertaining to the information processing, or increasing the volume and notifying the voice message again; inputting voice information and performing voice recognition; and Determining whether or not the message is valid according to the voice processing message, and performing a predetermined information process corresponding to the selected voice processing message when the voice processing message is valid according to the determination result. You may have.

[0013] The present invention is a medium in which a computer is recorded with a program for performing information processing control based on speech recognition and synthesis, and the control program transmits to a computer a voice processing message relating to various information processing. Displaying, selecting a desired voice processing message from the plurality of displayed voice processing messages, and generating a voice message by voice-synthesizing the selected voice processing message; A medium in which a voice processing control program is recorded is provided by outputting the voice message as voice for confirmation.

[0014]

DESCRIPTION OF THE PREFERRED EMBODIMENTS [Overview] First, an overview of the present invention will be described.

FIG. 1 is a flowchart showing a simplified control of information processing based on speech recognition / synthesis according to the present invention.

In step S1, a message for voice processing relating to various information processing is displayed. For example, a selection item of a printing parameter related to the printing process is displayed.

In step S2, a desired voice processing message is selected from the displayed plurality of voice processing messages. Thereby, predetermined parameters are set.

In step S3, a voice message is created by performing voice synthesis on the selected voice processing message.

In step S4, the synthesized voice message is output as voice for confirmation.

In step S5, after confirming and outputting the voice message, it is checked whether a predetermined time has elapsed. If the predetermined time has elapsed, the process proceeds to step S6, and if not, the process proceeds to step S7.

In step S6, if there is no response from the outside after a lapse of a predetermined time, the user is notified of detailed information relating to predetermined information processing, or the volume is increased and a voice message is notified again. .

Thus, for example, in a printing system provided with a print control method in which the user can set various parameters collectively by voice, even if a certain time elapses after notifying the user of the voice message, When there is no reaction from, it is possible to activate Help, provide detailed information to the user, increase the volume, and notify the user of the voice message again.

In step S7, speech information is input from outside to perform speech recognition.

In step S8, it is determined whether or not the recognized voice information is valid corresponding to the selected voice processing message.

In step S9, if the result is determined to be valid, predetermined information processing corresponding to the selected voice processing message is executed.

[Specific Example] Next, a specific example will be described.

<System Configuration> FIG. 2 shows an external configuration of a printing system as an information processing system according to the present invention.

The printing system has a print control function of notifying the user of various parameter selection items by voice and allowing the user to collectively set various parameters by voice.

Reference numeral 101 denotes a host computer as an information processing device. 102 is a printer. In this example, the devices constituting the printing system are connected by a USB (Universal Serial Bus) cable, but the connection form may be an IEEE 1284 interface or the like, and is not limited to USB. Absent. Detailed description of the USB standard, IEEE1284 standard, and the like will be omitted.

(Host Computer) FIG. 3 shows the internal configuration of the host computer 101.

An AC adapter (rated voltage 2
0 [V], 54 [W]) 201 and a nickel-metal hydride secondary battery (rated voltage 12 [V], 2700 [mA / h]) 20
And 2. The power supply unit 203, the power management IC 204, the CPU 205, the BIOS 206, the L
CD 207, video controller (VGAC) 208,
Video memory (VRAM) 209, hard disk
Drive (HDD) 210, hard disk controller (HDC) 211, DMA controller (DMA
C) 212, port (PORT) 213, floating point processor (FPU) 214, real-time clock (R)
TC) 215, keyboard controller (KBC) 21
6, keyboard 217, system main memory 218,
Floppy (registered trademark) disk controller (F
DC) 219, floppy disk drive (FD)
D) 220, interrupt controller (IRQC) 22
1. Built-in serial interface (SIO) 222 and the like.

The USB I / F is provided through a USB port included in the port 513. A speaker 224 and a microphone 225 are connected to the sound source board 223.

Although the configuration of the host computer 101 has been described above, the present invention is not limited to this configuration.

(Printer) FIG. 4 shows the internal configuration of the printer 102.

The printer 102 includes a panel unit 110,
It is roughly divided into a printer control unit 120, an interface unit 130, and a power supply unit 140. Hereinafter, the configuration of each unit will be described.

Reference numeral 301 denotes a power switch, 302 denotes a cartridge replacement switch, and 303 denotes a reset switch.

Reference numeral 304 denotes an LE which lights green when the power is turned on.
D is an LED that lights up in orange when an error occurs. The LED 304 alone can be lit in two colors, green and orange.

Reference numeral 310 denotes an operation of the power switch 301
This is a signal line to be transmitted to the PU 317. Since this signal line is transmitted to the MPU 317 as the interrupt signal 313, the MPU 317 performs processing with priority.

Reference numeral 311 denotes an address bus. 312
Are printer control gate array 314, MPU 317,
An address bus and a data bus for connecting the ROM 316. The ROM 316 stores a program describing the operation and processing of the MPU 317.

Reference numeral 314 denotes a printer control gate array, which has a control function such as a switch, an LED, an interface, and a memory. Microphone 339, speaker 3
The printer control gate array 314 also manages the management of 40 and the like.

An RA 315 provides a storage area for temporarily storing data and the like when the MPU 317 performs processing.
M.

Reference numeral 318 denotes a signal line for transmitting a signal for controlling the stepping motor. Reference numeral 319 denotes a carriage motor (CR) that moves a carriage that is a support for the ink cartridge. Reference numeral 320 denotes a feed motor (LF) for feeding print paper.

Reference numeral 322 denotes an ink cartridge. The ink cartridge 322 has a structure in which the ink itself and a head for discharging the ink are integrated. Also, an ID indicating the type of the ink cartridge 32 itself is recorded.

Reference numeral 321 denotes a control line for controlling the head in the ink cartridge 322 and reading the ID.

Reference numeral 306 denotes a commercial power supply provided to ordinary households. 307 is a DC 5
This is an AC adapter for converting into a V signal line 308 and a DC 24 V signal line 309. DC 5V signal line 308
It is used to operate a potential component such as the PU 317.
The DC 24 V signal line 309 is used for driving the motors 319 and 320 and the like and the head in the ink cartridge 322.

323 is an interface controller 3
27 and an interface controller signal for connecting the printer control gate array 314. This sets the interface operation mode to the printer control gate array 31.
4 is used to detect.

Reference numeral 324 denotes a data bus for sending data received from the host computer 101 by the interface controller 327, which is an interface gate array, to the printer control gate array 314. The interface controller 327 includes the Centronics connector 3
The switching from the data from the MPU 29 to the data from the USB MPU 338 is performed. This switching is performed by the analog switch 325.

The interface controller 327 is designed to always give priority to data from the USB MPU 338. That is, when print data is sent to both the Centronics interface 329 and the USB B type connector 335, the USB side is always given priority and data from the Centronics side is not received. This switching is performed using the statuses of the signal line 326 and the signal line 330 from the Centronics interface 329.

328 is a data signal line from the Centronics interface 329. Reference numeral 331 denotes a flash memory in which a program of the USB MPU 338 for controlling the USB interface 338 is stored.
The USB has A type and B type connectors, and the personal computer 101 or an upstream device has a B type connector.
A type connector 335 is connected. In addition, a downstream device is connected through an A-type connector 334. 3
36 is a signal line to the A type connector 334.
337 is a signal line to the B type connector 335.

Although the configuration of the printer 102 has been described above, the present invention is not limited to this configuration.

<System Operation> Next, a printing control method using voice in an information processing system in which the host computer 101 and the printer 102 are connected will be described.

(Flow of Print Control) FIG. 5 shows an example of software configuration related to print control using sound in the present system.

Reference numeral 400 denotes an application program which creates a print document, notifies the printer driver 401 that printing processing is to be started, and transfers image data of the print document to the printer driver.

Reference numeral 401 denotes a printer driver, which is device driver software having a function of controlling a specific printer and printing (printing) image data generated by specific application software.

Reference numeral 402 denotes a USB port monitor, which provides an application programming interface (API) used by the printer driver to control the printer. Specific U as API
USB port control commands such as an SB port open command, a specific USB port close command, a data write command to a specific USB port, and a data read command from a specific USB port are prepared. When the printer driver 409 calls the API, the USB port monitor 402 interprets the command of the called API,
The API command is converted and passed to a USB port driver 403 described later.

Reference numeral 403 denotes a USB port driver.
After interpreting the control command received from the USB port monitor 402, the command is further converted and passed to a USB common driver 404 described later.

Reference numeral 404 denotes a USB common driver.
In response to a control command received from the SB port driver 403, the USB port of the host computer 101 is directly controlled to transmit and receive data to and from the USB printer 405.

Reference numeral 406 denotes a voice recognition program which converts the voice data received from the voice control program 410 into
Analysis is performed using the voice recognition database 408. The speech recognition database 408 is a database in which information necessary for speech information processing is registered. This database can be prepared in plurals or can be registered later by the user.

For example, the speech recognition program 406 extracts character string data registered in the speech recognition database 408, one-to-one with the received speech data, and transfers the character string data to the printer driver 401. I do.

Reference numeral 407 denotes a speech synthesis program which creates speech data to be output to the speaker 224 using the speech synthesis database 409. The speech synthesis database 409 is a database in which information on printing, information on the printer itself, and the like are registered as speech data. This database can be prepared in plurals or can be registered later by the user.

Reference numeral 410 denotes a sound source control program, which controls the sound source board 223 to take in audio data input from the microphone 225, converts the data into appropriate input digital data, and delivers the digital data to a voice recognition program 406 described later. Further, the sound source control program 406 converts the sound data generated by the sound synthesis program 407 into appropriate sound data, and then controls the sound source board 223 to output the sound data from the speaker 224.

The sound source board 223 records the sound data input from the microphone 225, and
Hand over to 0. Further, the sound source board 223 outputs the audio data received from the sound source control program 410 to the speaker 224.

Reference numeral 414 denotes a printer driver Help, which is software having a function of providing “detailed information” on a printer control method using a specific printer driver.

The detailed information includes detailed descriptions of various print parameter items, presentation of manufacturer recommended values of various print parameters, and the like.

The printer driver Help displays detailed information on a graphic and text screen, and
Provided by voice message output.

The printer driver Help has a function of providing detailed information on a specific item when activated by designating a specific keyword. For example, when the printer driver specifies the keyword “print data type” and starts the printer driver Help, the printer driver Help prints the print data Hel.
p provides detailed information on the type of print data.

Each of the above software programs is developed in the system main memory 218 of the host computer 101 and executed by the CPU 205.

The configuration of the software in this embodiment has been described above. However, the configuration of the software is not limited to this, as long as the configuration allows voice recognition processing, voice synthesis processing, and printing processing.

(Speech Recognition Processing) FIG. 6 is a flowchart showing a speech recognition processing procedure in the information processing system in which the host computer 101 and the printer 102 are connected.

If the specific software requires the input of voice commands and data, in step S501, the sound source control program controls the sound source board to enable the microphone, and outputs words spoken by the user to the microphone. Take in as.

In step S502, the received voice data is transferred to a voice recognition program.

In step S503, the speech recognition program analyzes speech data using a speech model and a recognition grammar.

Thereafter, in step S 504, a language matching the voice data is searched for with reference to the voice database and the language knowledge database.

In step S505, the voice recognition program notifies the software that has requested voice recognition of the result of voice recognition.

In general, there are two methods of speech recognition: discrete word recognition and dictation.

Discrete word recognition means that a plurality of discrete words are registered / stored in advance, and it is determined whether or not voice data representing the input word matches the registered data.
This is a speech recognition method for each word.

A dictation is a sentence-based speech recognition method in which sentence sample data is registered / stored in advance and input speech data is sequentially converted to text sentence data while referring to the registered data. It is.

(Speech Synthesis Processing) FIG. 7 is a flowchart showing a speech synthesis processing procedure in the information processing system in which the host computer 101 and the printer 102 are connected.

If the specific software requires speech synthesis, the software transfers the text data to the speech synthesis program in step S601.

In step S602, the speech synthesis program analyzes the transferred text data using the language analysis dictionary, and performs language processing for adding linguistic information such as phrase relations, readings, and accents to the text data. Do.

In step S603, the speech synthesis program generates speech waveform data corresponding to the transferred text data using the speech segment dictionary and the prosody parameters.

Then, in step S604, the generated sound waveform data is transferred to the sound source control program.

In step S605, the sound source control program controls the sound source board 223 and
4, the transferred voice waveform data is transferred to the speaker 224, and the synthesized sound is transferred to the speaker 22.
4 to output.

The speech recognition and speech synthesis processing has been described above with reference to FIGS. 6 and 7. However, the present invention is not limited to this, and another method may be used.

<Example of Document Printing Processing> Next, a method of printing a document in an information processing system in which the host computer 101 and the printer 102 are connected will be described with reference to FIGS.

(Printer Driver Screen 1) FIG. 8 shows a print data selection request printer driver screen 1 displayed on the display device by the printer driver.

An agent character 701 is realized by a 3D graphic animation that operates in synchronization with a voice message.

Reference numeral 702 denotes a balloon for displaying a voice message text attached to the agent character.
In this example, the print data selection request voice message is displayed in text.

Reference numeral 703 denotes a selectable print data display dialog box. In this example, as print data that can be selected, 1. Photo, and 2. Ch
art, and 3. Composite and
4. Four types of Text are prepared.

In FIG. 8, the notification of the print data that can be selected is performed by voice and graphic.
Selection of print data can be performed by voice, click operation with a mouse, and key input with a keyboard.

(Printer Driver Screen 2) FIG. 9 is a print paper selection request printer driver screen 2 displayed on the display device by the printer driver.

Reference numeral 801 denotes an agent character, which is realized by a 3D graphic animation that operates in synchronization with a voice message.

Reference numeral 802 denotes a balloon for displaying a voice message text attached to the agent character.
In this example, the paper selection request voice message is displayed in text.

Reference numeral 803 denotes a selectable print paper display dialog box. In this example, as print paper that can be selected, 1. 1. Glossy Photo Paper, and High Resolution Paper
r, and 3. Other types are prepared.

In FIG. 9, the notification of the print paper that can be selected is made by voice and graphic, and the print paper can be selected by voice, click operation by mouse, and key input by keyboard. It is possible.

(Printer Driver Screen 3) FIG. 10 is a printer driver selection request printer driver screen 3 displayed on the display device by the printer driver.

Reference numeral 901 denotes an agent character, which is realized by a 3D graphic animation that operates in synchronization with a voice message.

Reference numeral 902 denotes a balloon for displaying a voice message text attached to the agent character.
In this example, the printer cartridge selection request voice message is displayed in text.

Reference numeral 903 denotes a selectable dialog box for displaying a printer cartridge. In this example, the selectable printer cartridge is 1. Photo / Co
lor (BC-32 / BC-31), and 2. Bl
ack / Color (BC-30 / BC-31), 2
Types are available.

In FIG. 10, the notification of the selectable printer cartridge is made by voice and graphic, and the selection of the printer cartridge is made by voice, click operation by mouse, and key input by keyboard. It is possible.

(Printer Driver Screen 4) FIG. 11 shows a printer driver screen 4 for requesting print parameter confirmation displayed on the display device by the printer driver.

An agent character 1001 is realized by a 3D graphic animation that operates in synchronization with a voice message.

Reference numeral 1002 denotes a balloon for displaying a voice message text attached to the agent character. In this example, the print parameter confirmation request voice message is displayed in text.

Reference numeral 1003 denotes a dialog box for displaying a selected print parameter for requesting confirmation. In this example, the print parameters required for confirmation are 1. 1. the type of print data, and 2. the type of printing paper, and Three types of print cartridges are prepared.

In FIG. 11, the notification of the confirmation request item is
The confirmation notification is performed by voice and graphic, and the confirmation notification can be performed by voice, click operation by mouse, and key input by keyboard.

(Printer Driver Screen 5) FIG. 12 shows a printer driver screen 5 for notifying a print error occurrence and recovery method, which is displayed on the display device by the printer driver.

Reference numeral 1101 denotes an agent character, which is realized by a 3D graphic animation that operates in synchronization with a voice message.

Reference numeral 1102 denotes a balloon for displaying a voice message text attached to the agent character. In this example, a paper jam error notification voice message is displayed in text.

Reference numeral 1103 denotes a print error notification dialog box.

In FIG. 12, the notification of the printing error occurrence and error recovery method is performed by voice and graphic, and the error recovery instruction is performed by voice, click operation by mouse, and key input by keyboard. Is possible.

(Screen for requesting reselection of printing paper by printer driver) FIG. 13 shows the state after the printer driver Help is started.
9 is a help display & printer driver print paper reselection request screen displayed on the display device.

This screen has a configuration in which a help screen is added to the printer paper selection request printer driver screen 2.

Reference numeral 1701 denotes an agent character, which is realized by a 3D graphic animation that operates in synchronization with a voice message.

Reference numeral 1702 denotes a balloon for displaying a voice message text attached to the agent character. In this example, the paper selection request voice message is displayed in text.

Reference numeral 1703 denotes a selectable print paper display dialog box. In this example, as print paper that can be selected, 1. Glossy Photo Paper,
And 2. High Resolution Pap
er, and 3. Other types are prepared.

Reference numeral 1704 denotes a dialog box for displaying detailed information on the type of printing paper provided by the printer driver Help.

In FIG. 13, notification of selectable printing paper and notification of detailed information of the printer driver Help are performed by voice and graphic. Selection of printing paper is performed by voice and mouse click operation. Also, it can be performed by key input using a keyboard.

In FIGS. 8 to 13 described above, when various parameters are selected by voice, one voice command used to select one item is defined in advance.

For example, in this example, “1.
The voice command for selecting “o” is a voice command that pronounces “photo.” “2. High Reso
The voice command for selecting “lution Paper” is a voice command that pronounces “high resolution”.
0 "2. Black / Color (BC-30 / BC
The voice command for selecting “−31)” is a voice command that pronounces “black”.

In another example, a plurality of commands can be defined in advance as voice commands for selecting one item by selecting various parameters.

For example, as the voice command for selecting “1. Photo” in FIG.
Can be defined in advance. "2. High Resolution" in FIG.
It is also possible to define in advance two voice commands that pronounce “Ni” or “Koihinoshi” as voice commands for selecting “n Paper”.

The predefined voice command is registered and stored in association with the specified software, and becomes a valid voice command for the specified software.

For example, in this example, “1.
The voice command that pronounces “photo” that selects “o” is registered and stored in association with the printer driver.If the printer driver requests the input of a voice command and data, the voice command that pronounces “photo” Is a valid voice command for the printer driver.

Further, in this example, the printer driver Help detailed information regarding the type of printing paper has been described with reference to FIG. 13, but the help detailed information is provided in the same manner as for other print parameter selections. .

(Flow of Original Printing Process) FIGS. 14 to 18
9 is a flowchart showing a flow of a document printing process.

(Print Data Selection Processing) FIG. 14 is a flowchart showing print data selection processing.

Host computer 101 and printer 10
When the user prints the document using a specific application in the information processing system connected to the application 2, the user selects the “print” command from the command menu of the specific application in step S1201 in FIG. I do.

In step S1202, the printer driver is started, and the print data selection request printer driver screen 1 is displayed on the display device.

In step S1203, the printer driver reads the print data selection request message information with reference to an arbitrary voice notification message database.

In step S1204, the read print data selection request message information is transferred to the voice synthesis program, and the voice print data selection request message is voice-synthesized.

In step S1205, the speech synthesis program outputs the synthesized speech message from the speaker.

In step S1206, the printer driver sets a timer to measure the elapsed time.

The user refers to the voice message output from the speaker and the graphic information and text information on the printer driver screen 1 displayed on the display to determine the type of print data to be selected.

In step S1207, the printer driver determines whether a print data item has been selected by the user. For example, when using voice for parameter selection, it is determined whether a voice command has been input from a microphone.

If the print data item has not been selected, the printer driver proceeds to step S1208.
, It is checked whether or not a designated time has elapsed since the notification of the voice message to the user. The designated time is a time preset in the printer driver, for example, 3
0 seconds.

If it is determined in step S1208 that the designated time has not elapsed, the process returns to step S1207.
Then, it waits until a print data item is selected.

On the other hand, if the designated time has elapsed in step S1208, the process advances to step S1209, where the printer driver specifies the keyword "print data type" and activates the printer driver Help. Then, the printer driver Help becomes He
A screen for requesting print data reselection is displayed, and detailed information on the type of print data, for example, a detailed description of each print data item is displayed on the screen in graphics and text.
Output from the speaker as a voice message.

Thereafter, the process returns to step S1205, and the speech synthesis program outputs a print data selection request voice message from the speaker, and requests the user again to select print data.

Also, in this example, this step S1208
In, the following processing may be executed. That is, as a modified example of step S1208, if the designated time has elapsed, the process proceeds to step S1209, and the printer driver increases the speaker output volume.

Thereafter, the process returns to step S1205, and the voice synthesizing program outputs the synthesized voice message at a higher volume from the speaker, and requests the user to select print data again.

After the processing in step S1208,
Proceed to the following process.

In step S1207, when a voice command is input from the microphone by the user,
The process proceeds to step S1210.

At this time, the user is speaking the print data selection voice command into the microphone. For example, the user pronounces “photo”. Then, in step S1210, the voice recognition program voice-recognizes the voice command input from the microphone, and notifies the printer driver that the voice command has been input.
Transfer information related to the input voice command.

In step S1211, the printer driver refers to the voice recognition command database.

In step S1212, it is determined whether the input voice command is a valid voice command in response to the print data selection request. For example, if the user correctly pronounces "photo", it is determined as a valid voice command, but if the user pronounces "phone", it is determined as an invalid voice command.

Here, if the voice command is an invalid command, the process proceeds to step S1213, where the printer driver transfers the command error notification voice message information to the voice synthesis program and causes the command error notification voice message to be voice-synthesized. . Then, the process returns to step S1205, and the voice synthesis program outputs the synthesized voice message from the speaker, and then waits for the next voice command to be input from the microphone.

On the other hand, if it is determined in step S1212 that the voice command is a valid command, the process proceeds to step S1214, and in accordance with the input voice command,
Execute print data selection processing.

For example, when the input voice command is “photo”, the type of print data is “1.
The process of selecting "to" is executed. Thereafter, the print data selection process is terminated, and the process proceeds to the following process.

(Print Paper Selection Processing) Next, print paper selection processing is started.

FIG. 15 is a flowchart showing the printing paper selection process.

In step S1301, the printer driver sets the printer driver selection request printer driver screen 2
Is displayed on the display device.

In step S1302, the printer driver reads the print paper selection request message information with reference to an arbitrary voice notification message database.

In step S1303, the read print paper selection request message information is transferred to the voice synthesis program, and the voice print paper request message is voice-synthesized.

At step S1304, the speech synthesis program outputs the synthesized speech message from the speaker.

In step S1305, the printer driver sets a timer to measure the elapsed time.

The user refers to the voice message output from the speaker and the graphics information and text information on the printer driver screen 2 displayed on the display, and determines the type of printing paper to be selected.

In step S1306, the printer driver determines whether the user has selected a print paper selection item. For example, when using voice for parameter selection, it is determined whether a voice command has been input from a microphone.

If the print paper item has not been selected, the printer driver checks in step S1307 if a specified time has elapsed since the notification of the voice message to the user.

The designated time is a time preset in the printer driver, for example, 30 seconds.

If it is determined in step S1307 that the specified time has not elapsed, the process returns to step S1306.
Then, it waits until a print data item is selected.

On the other hand, if the specified time has elapsed in step S1307, the process advances to step S1308, where the printer driver starts the printer driver Help by designating the keyword "print paper type". Then, the printer driver Help becomes H in FIG.
Displays an elp display & printer driver print paper reselection request screen, and displays detailed information on the type of print paper, for example, a detailed description of each print paper item and the presentation of manufacturer recommended values on the screen in graphic and text format. Output from the speaker as a voice message.

Thereafter, the process returns to step S1304, and the speech synthesis program outputs a print paper selection request voice message from the speaker, and requests the user again to select a print paper.

In the present example, this step S1307
In, the following processing may be executed. That is, as a modified example of step S1307, if the designated time has elapsed, the process proceeds to step S1308, and the printer driver increases the volume of the speaker. Thereafter, the process returns to step S1304, and the voice synthesis program outputs the synthesized voice message at a higher volume from the speaker, and requests the user to select a print sheet again.

After the processing in step S1307,
Proceed to the following process.

In step S1306, when a voice command is input from the microphone by the user,
The process proceeds to step S1309.

At this time, the user is speaking the print paper selection voice command into the microphone. For example, the user pronounces “high res”.

Then, in step S1309, the voice recognition program voice-recognizes the voice command input from the microphone, notifies the printer driver that the voice command has been input, and outputs information related to the input voice command. Forward.

In step S1310, the printer driver refers to the voice recognition command database, and in step S1311, determines whether the input voice command is a valid voice command in response to the print paper selection request. For example, if the user pronounces “high res” correctly, it is determined as a valid voice command,
When pronounced "high leg", it is determined as an invalid voice command.

Here, if the voice command is an invalid command, the process proceeds to step S1312, where the printer driver transfers the command error notification voice message information to the voice synthesis program, and causes the command error notification voice message to be voice-synthesized. Then, the process proceeds to step S1.
Returning to 304, the voice synthesis program outputs the synthesized voice message from the speaker, and then waits for the next voice command to be input from the microphone.

On the other hand, if the voice command is a valid command in step S1311, the process advances to step S1313 to execute print paper selection processing according to the input voice command. For example, if the input voice command is “high resolution”, “2. High Resolution Paper” is used as the type of printing paper.
Is performed. Thereafter, the printing paper selection processing is terminated, and the processing proceeds to the following processing.

(Printer Cartridge Selection Processing)
The printer cartridge selection process starts.

FIG. 16 is a flowchart showing a printer cartridge selection process.

In step S1401, the printer driver displays a printer cartridge selection request printer driver screen 3 on the display device.

In step S1402, the printer driver reads printer cartridge selection request message information with reference to an arbitrary voice notification message database.

In step S1403, the read printer cartridge selection request message information is transferred to the voice synthesis program, and the voice printer cartridge selection request message is voice-synthesized.

In step S1404, the speech synthesis program outputs the synthesized speech message from the speaker.

In step S1405, the printer driver sets a timer for measuring the elapsed time.

The user refers to the voice message output from the speaker and the graphics information and text information on the printer driver screen 3 displayed on the display, and determines the type of the printer cartridge to be selected.

In step S1406, the printer driver determines whether the user has selected a printer cartridge item.

If it is determined in step S1407 that the printer cartridge item has not been selected, the printer driver checks whether or not the designated time has elapsed after notifying the user of the voice message.

The designated time is a time preset in the printer driver, for example, 30 seconds.

If it is determined in step S1407 that the designated time has not elapsed, the process returns to step S1406.
Then, it waits for the selection of the printer cartridge item.

On the other hand, if the specified time has elapsed in step S1407, the process advances to step S1408, where the printer driver specifies the keyword "printer cartridge type" and prints the printer driver H
Start elp. Then, the printer driver Help
Displays a help display & printer driver printer parameter reselection request screen, and displays detailed information on the type of printer cartridge, for example, a detailed description of each printer cartridge, and a printer cartridge recommended by the manufacturer in a graphic and text form. And output from the speaker as a voice message.

Thereafter, the process returns to step S1404, and the voice synthesis program outputs a printer cartridge selection request voice message from the speaker, and requests the user again to select a printer cartridge.

Also, in this example, this step S1407
In, the following processing may be executed. That is, as a modified example of step S1407, if the designated time has elapsed, the process proceeds to step S1408, and the printer driver increases the speaker output volume. After that, the process returns to step S1404, and the voice synthesis program outputs the synthesized voice message at a higher volume from the speaker, and requests the user to select a printer cartridge again.

After the processing in step S1407,
Proceed to the following process.

In step S1406, when a voice command is input from the microphone by the user,
The process proceeds to step S1409.

At this time, the user is speaking the printer cartridge selection voice command into the microphone. For example, the user pronounces "black".

Then, in step S1409, the voice recognition program voice-recognizes the voice command input from the microphone, notifies the printer driver that the voice command has been input, and also outputs information related to the input voice command. Forward.

In step S1410, the printer driver refers to the voice recognition command database.

In step S1411, it is determined whether the input voice command is a valid voice command for the printer cartridge selection request. For example, if the user pronounces "black" correctly, it is determined as a valid voice command, but if the user pronounces "block", it is determined as an invalid voice command.

If the voice command is an invalid command, the process advances to step S1409 to cause the printer driver to synthesize a command error voice notification message by voice. Then, the process returns to step S1404,
The voice synthesis program outputs the synthesized voice message from the speaker, and then waits for the next voice command to be input from the microphone.

On the other hand, if it is determined in step S1411 that the voice command is a valid command, the process proceeds to step S1414, and in accordance with the input voice command,
Printer cartridge selection processing is executed. For example,
If the input voice command is "black", the type of printer cartridge is "2. Black / Col".
or (BC-30 / BC-31) "is executed. Thereafter, the printer cartridge selecting process is terminated, and the process proceeds to the following process.

(Printer Cartridge Selection Processing)
The print parameter confirmation processing starts.

FIG. 17 is a flowchart showing the print parameter confirmation processing.

In step S1501, the printer driver displays a printer parameter confirmation request printer driver screen 4 on the display device.

In step S1502, the printer driver reads print parameter confirmation request message information with reference to an arbitrary voice notification message database.

In step S1503, the read print parameter confirmation request message information is transferred to the voice synthesis program, and the voice print parameter confirmation request message is voice-synthesized.

In step S1504, the speech synthesis program outputs the synthesized speech message from the speaker.

[0200] In step S1505, the printer driver sets a timer to measure the elapsed time.

The user refers to the voice message output from the speaker and the graphics information and text information on the printer driver screen 4 displayed on the display, and confirms the print parameters.

In step S1506, the printer driver determines whether the print parameters have been confirmed by the user. For example, if a voice is used to confirm print parameters, it is determined whether a voice command has been input from a microphone.

If the print parameters have not been confirmed, the printer driver proceeds to step S15.
At 07, it is checked whether a specified time has elapsed since the notification of the voice message to the user.

The designated time is a time preset in the printer driver, for example, 30 seconds.

If the designated time has not elapsed in step S1507, the process returns to step S1506, and
Then, it waits until the print parameters are confirmed.

On the other hand, if the designated time has elapsed in step S1507, the process advances to step S1508, where the printer driver determines "print parameter confirmation".
Printer driver Hel
Start p. Then, the printer driver Help
Help display & printer driver Displays a print parameter reconfirmation request screen, displays detailed information on print parameter confirmation on the screen in graphics and text, and outputs it from the speaker as a voice message.

Thereafter, the process returns to step S1504, and the speech synthesis program outputs a print parameter confirmation request voice message from the speaker, and requests the user to confirm the print parameters again.

Also, in this example, this step S1507
In, the following processing may be executed. That is, as a modified example of step S1507, if a predetermined time has elapsed, the process proceeds to step S1508, and the printer driver increases the speaker output volume. Thereafter, the process returns to step S1504, and the speech synthesis program
The synthesized voice message is output from the speaker at a higher volume, and the user is requested to confirm the print parameters again.

After the processing in step S1507,
Proceed to the following process.

In step S1506, when a voice command is input from the microphone by the user,
The process proceeds to step S1509.

At this time, the user is speaking the print parameter confirmation command into the microphone. Then, in step S1509, the voice recognition program recognizes the voice command input from the microphone, notifies the printer driver that the voice command has been input, and transfers information related to the input voice command.

In step S1510, the printer driver refers to a voice recognition command database.

[0213] In step S1511, the input voice command responds to the print parameter confirmation request.
Determine if the command is valid.

Here, if the voice command is an invalid command, the process proceeds to step S1512, where the printer driver transfers the command error notification voice message information to the voice synthesis program and causes the command error notification voice message to be voice synthesized. .

Then, the process returns to step S1504, where the speech synthesis program outputs the synthesized speech message from the speaker, and then waits for the next speech command to be input from the microphone.

On the other hand, if the voice command is a valid command, the process proceeds to 1513, where print parameter confirmation processing is executed according to the input voice command.

When the print parameter confirmation processing ends, the printer driver starts the printing processing in step S1514.

That is, image data of a document is rendered to generate print data, and then the generated print data is sent to the printer 102. As a result, the following print processing is executed.

(Print Process) FIG. 18 is a flowchart showing the print process.

[0220] In step S1601, the printer driver monitors the status of the printer 102 and checks whether a printing error has occurred.

If a printing error has occurred in step S1601, the process advances to step S1602.

In step S1602, the printer driver displays an error notification printer driver screen 5.

In step S1603, a print error occurrence & error recovery method notification message information is read with reference to an arbitrary voice notification message database.

In step S1604, the read print error occurrence & error recovery method notification message information is transferred to the voice synthesis program, and the voice print error occurrence & error recovery method notification message is voice-synthesized.

[0225] In step S1605, the speech synthesis program outputs the synthesized speech message from the speaker.

In step S1606, the printer driver sets a timer to measure the elapsed time.

The user refers to the voice message output from the speaker and the graphic information and text information on the printer driver screen 5 displayed on the display, and executes error recovery of the printer.

In step S1607, the printer driver determines whether the user has selected a print error return command. For example, when using a voice for the print error return command, it is determined whether the voice command has been input from the microphone.

If the print error return command has not been selected, the printer driver proceeds to step S16.
At 08, it is checked whether or not the designated time has elapsed since the notification of the voice message to the user. The designated time is a time preset in the printer driver, for example, 30 seconds.

If it is determined in step S1608 that the designated time has not elapsed, the process advances to step S1609,
The printer driver starts the printer drive Help by designating the keyword “print error”. Then, the printer drive Help displays a help display & printer drive print error notification screen, and displays detailed information on the print error, for example, a detailed description on the cause of the print error and a method of restoring the print error in graphics and text. To display on the screen and output from the speaker as a voice message.

Thereafter, the process returns to step S1605, and the voice synthesizing program outputs a voice print error occurrence / error recovery method notification message from the speaker, and again executes the print error recovery process to the user, and outputs the print error recovery command. Request to select

Also, in this example, this step S1608
In, the following processing may be executed. That is, as a modified example of step S1608, if the designated time has not elapsed, the process proceeds to step S1609, and the printer driver increases the speaker output volume. afterwards,
The process returns to step S1605, and the voice synthesis program outputs the synthesized voice message at a higher volume from the speaker, and requests the user to select a print error recovery command again.

After the processing in step S1608,
Proceed to the following process.

On the other hand, in step S1607, if a voice command has been input from the microphone by the user, the process proceeds to step S1610.

At this time, the user is speaking into the microphone the voice command for recovering the printing error from the printer drive.

In step S1610, the voice recognition program voice-recognizes the voice command input from the microphone, notifies the printer driver that the voice command has been input, and transfers information related to the input voice command. .

In step S1611, the printer driver refers to the voice recognition command database.

In step S1612, it is determined whether the input voice command is a valid voice command for error recovery processing.

Here, if the voice command is an invalid command, the process proceeds to step S1613, where the printer driver transfers the command error notification voice message information to the voice synthesis program and causes the command error notification voice message to be voice synthesized. .

[0240] Then, the process returns to step S1605, and the speech synthesis program outputs the synthesized speech message from the speaker, and then waits for the next speech command to be input from the microphone.

On the other hand, if the voice command is a valid command, the process proceeds to step S1614, and the printing process is restarted according to the input voice command. Then, the process proceeds to step S1615.

If no printing error has occurred in step S1601, step S1615
Proceed to.

Then, in step S1615, the printer driver sends the print data to the printer.

In step S1616, the printer driver determines whether the print data to be sent to the printer 102 is
Check if it still remains. If print data remains, the process returns to step S1601 to repeat the above process until all print data is sent to the printer 102.

If no print data remains in step S1616, all print processing ends.

The method of printing a document in the information processing system has been described above. However, if voice recognition processing and voice synthesis processing are used in the course of printing processing, the procedure of this example differs from that of the printing processing. It may be.

The present invention can be applied to a system including a plurality of devices (for example, a host computer, an interface device, a reader, and a printer).
The present invention may be applied to an apparatus including one device (for example, a small image processing device such as a PDA (personal information management) device, a copying machine, and a facsimile device).

It is needless to say that the present invention can be applied to a case where the present invention is achieved by supplying a program to a system or an apparatus. Then, a storage medium storing a program represented by software for achieving the present invention is supplied to a system or an apparatus, and the computer (or CPU or M) of the system or the apparatus is supplied.
PU) can read and execute the program code stored in the storage medium, so that the effects of the present invention can be enjoyed.

In this case, the program code itself read from the storage medium realizes the function of the above-described embodiment, and the storage medium storing the program code constitutes the present invention.

As a storage medium for supplying the program code, for example, a floppy disk, hard disk, optical disk, magneto-optical disk, CD-ROM, CD
-R, magnetic tape, nonvolatile memory card (IC memory card), ROM (mask ROM, flash EEP)
ROM etc.) can be used.

When the computer executes the readout program codes, not only the functions of the above-described embodiments are realized, but also the OS (Operating System) running on the computer based on the instructions of the program codes. ) May perform some or all of the actual processing, and the processing may realize the functions of the above-described embodiments.

Further, after the program code read from the storage medium is written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer, based on the instruction of the program code, It goes without saying that the CPU included in the function expansion board or the function expansion unit performs part or all of the actual processing, and the processing realizes the functions of the above-described embodiments.

[0253]

As described above, according to the present invention,
In information processing control based on speech recognition and synthesis,
A voice message is created by displaying a voice processing message related to various information processing, selecting a desired voice processing message from the displayed plurality of voice processing messages, and voice-synthesizing the selected voice processing message. However, since the synthesized voice message is output as voice for confirmation, even if the user is a beginner,
When setting various parameters related to printing, a series of operation procedures of setting specific parameters using a keyboard and a mouse according to a graphic displayed on a screen can be easily used without learning, and the user can use the system easily. Can be improved,
In particular, it is possible to obtain a user interface that can be used for visually impaired persons and physically handicapped persons who cannot operate a mouse / keyboard.

Further, according to the present invention, if there is no response from the outside even after a certain period of time has elapsed after confirming and outputting the voice message, detailed information relating to the information processing is notified, and further, voice information is input. The voice recognition is performed to determine whether or not the recognized voice information is valid for the selected voice processing message. If the voice information is determined to be valid based on the determination result, a predetermined value corresponding to the selected voice processing message is determined. For example, after notifying the user of the voice message, if there is no reaction from the user even after a certain time elapses, the user cannot take the reaction due to lack of information. Judge
It is possible to start the printer driver Help and execute a print control process having a means for providing detailed print information, thereby further improving the usability of the user.

Further, according to the present invention, after a voice message is confirmed and output, if there is no response from outside even after a certain period of time, the volume is increased and the voice message is notified again,
Further, voice information is input and voice recognition is performed, and it is determined whether or not the recognized voice information is valid for the selected voice processing message. For example, after executing a predetermined information processing corresponding to the message for the user, after notifying the user of the voice message, if there is no reaction from the user even after a certain period of time, the volume is increased and the voice message is reproduced again. The user can be notified, and even if the user misses the voice message, the printing process can be smoothly continued, thereby further improving the usability of the user.

[Brief description of the drawings]

FIG. 1 is a flowchart illustrating an example of information processing by voice according to an embodiment of the present invention.

FIG. 2 is a perspective view illustrating an external configuration of an information processing system according to the present invention configured by connecting a serial printer to a host computer.

FIG. 3 is a block diagram illustrating an internal configuration of a host computer.

FIG. 4 is a block diagram illustrating an internal configuration of the printer.

FIG. 5 is a block diagram showing a configuration of software.

FIG. 6 is a flowchart illustrating a procedure of a voice recognition process.

FIG. 7 is a flowchart illustrating a procedure of a speech synthesis process.

FIG. 8 is an explanatory diagram showing a print data selection request print driver screen 1;

FIG. 9 is an explanatory view showing a printer driver screen 2 for a print paper selection request.

FIG. 10 is an explanatory diagram showing a printer cartridge selection request printer driver screen 3;

FIG. 11 is an explanatory diagram showing a printer driver screen 4 for a print parameter confirmation request.

FIG. 12 is an explanatory diagram showing a printer error notification printer driver screen 5;

FIG. 13 is a help display & printer driver print paper reselection request screen.

FIG. 14 is an original printing process (print data selection process).
It is a flowchart which shows the flow of.

FIG. 15 is a flowchart illustrating a flow of a document printing process (print paper selection process).

FIG. 16 is a flowchart illustrating a flow of a document printing process (printer cartridge selection process).

FIG. 17 is a flowchart illustrating a flow of a document printing process (print parameter confirmation process).

FIG. 18 is a flowchart illustrating a flow of a document printing process (printing process).

[Explanation of symbols]

Reference Signs List 101 host computer (information processing device) 102 printer device 201 AC adapter 202 nickel-metal hydride secondary battery 203 power supply unit 204 power management IC 205 CPU 206 BIOS 207 LCD 208 video controller (VGAC) 209 video memory (VRAM) 210 hard disk Drive (HDD) 211 Hard Disk Controller (HDC) 212 DMA Controller (DMAC) 213 Port (PORT) 214 Floating Point Processor (FPU) 215 Real Time Clock (RTC) 216 Keyboard Controller (KBC) 217 Keyboard 218 System Main Memory 219 Floppy disk controller (FD
C) 220 Floppy disk drive (FDD) 221 Interrupt controller (IRQC) 222 Serial interface (SIO) 223 Sound source board 224 Speaker 225 Microphone 301 Power switch 302 Cartridge exchange switch 303 Reset switch 304 LED 305 Error LED 306 Commercial power supply 307 AC Adapter 308 5 V DC 309 24 V DC 310 Signal line for transmitting operation of power switch to MPU 312 Address bus and data bus 313 Interrupt signal 314 Printer control gate array 315 RAM 316 ROM 317 MPU 318 Signals for controlling the step motor Signal lines to be transmitted 319 Carriage motor 320 Feed motor 321 Control of head and reading of ID Control line 322 Ink cartridge 323 Interface control signal line 324 Data bus 325 Analog switch 326 Signal line from Centronics interface 327 Interface controller 328 Signal line from Centronics interface 329 Centronics connector 330 Signal line 331 Flash memory 334 USB A type connector 335 USB B type connector 336 USB A type connector signal line 337 USB B type connector signal line 338 USB MPU 339 Microphone 340 Speaker 401 Printer driver 402 USB port monitor 403 USB port driver 404 USB common driver 405 USB printer device 406 Voice recognition Program 407 Audio Synthesis program 408 speech recognition database 409 speech synthesis database 410 sound source control program 411 sound source board 412 microphone 413 speaker 701 agent character 702 balloon for displaying voice message text 703 selectable print data display dialog box 801 agent character 802 voice message text display Balloon 803 for printing paper display dialog box 901 agent character 902 balloon for displaying voice message text 903 dialog box for displaying printer cartridge 1001 agent character 1002 balloon for displaying voice message text 1003 dialog box for displaying selected print parameters 1101 age DOO character 1102 voice message text display of the balloon 1103 print error notification dialog box 1701 Agent character 1702 voice message text balloon 1703 selectable printing paper display dialog box 1704 print sheet type regarding detailed information display dialog box for display

Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat II (Reference) G10L 15/00 G10L 3/00 561D 15/22 551P 15/28 571H (72) Inventor Daisuke Inoue 3 Shimomaruko, Ota-ku, Tokyo (30) Inventor Masaru Makida 3-30-2 Shimomaruko, Ota-ku, Tokyo F-term (reference) 5-3015 Canon KK01 LL05 LL06

Claims (18)

[Claims] 1. An apparatus for performing information processing based on speech recognition and synthesis, comprising: a display unit for displaying a voice processing message relating to various information processing; and a display unit for displaying the plurality of displayed voice processing messages. From inside
Selecting means for selecting a desired voice processing message; voice synthesizing means for generating a voice message by voice synthesizing the selected voice processing message; converting the synthesized voice message into voice for confirmation An audio processing device comprising: a confirmation output means for outputting. 2. The information processing apparatus according to claim 1, further comprising a notification unit configured to notify the detailed information related to the information processing when there is no response from outside even after a predetermined time has elapsed after confirming and outputting the voice message. Item 1. The audio processing device according to Item 1. 3. A notifying means for raising the volume and notifying the voice message again when there is no response from outside even after a certain time has passed after confirming and outputting the voice message. Item 1. The audio processing device according to Item 1. 4. A voice recognition unit for performing voice recognition by inputting voice information, and determining whether the voice information recognized by the voice is valid according to the voice processing message selected by the selection unit. 2. The apparatus according to claim 1, further comprising: a discriminating means for discriminating; and a processing control means for executing predetermined information processing corresponding to the selected voice processing message, when the discrimination result indicates that the message is valid. 4. The audio processing device according to any one of claims 3 to 3. 5. The voice processing apparatus according to claim 4, wherein said processing control means further comprises means for notifying the occurrence of the predetermined information processing error by voice. 6. The apparatus according to claim 4, wherein said processing control means further comprises means for notifying an error recovery method of said predetermined information processing by voice.
An audio processing device according to claim 1. 7. The voice processing device according to claim 4, wherein said processing control means further comprises means for executing a process of recovering the error of the predetermined information processing by voice. 8. A method for performing information processing based on speech recognition and synthesis, comprising: displaying a voice processing message relating to various information processing; and displaying a plurality of voice processing messages among the plurality of displayed voice processing messages. From
Selecting a desired voice processing message; generating a voice message by voice-synthesizing the selected voice processing message; and outputting the synthesized voice message as voice for confirmation An audio processing method comprising: 9. The method according to claim 1, further comprising the step of notifying detailed information relating to the information processing when there is no response from outside even after a predetermined time has passed after the confirmation output of the voice message. 8. The voice processing method according to 8. 10. The method according to claim 1, further comprising the step of increasing the volume and notifying the voice message again when there is no response from the outside even after a predetermined time has passed after the voice message is confirmed and output. 8. The voice processing method according to 8. 11. A step of performing voice recognition by inputting voice information; and determining whether the voice information recognized as voice is valid corresponding to the selected voice processing message. 11. The method according to claim 8, further comprising a step of executing predetermined information processing corresponding to the selected voice processing message when the determination is made valid according to the determination result. 12. Audio processing method. 12. The audio processing method according to claim 11, further comprising, when executing the predetermined information processing, notifying an occurrence of an error in the information processing by voice. 13. The audio processing method according to claim 11, further comprising, when executing the predetermined information processing, a step of notifying an error recovery method of the information processing by voice. 14. The method according to claim 11, further comprising the step of executing a process of recovering an error in the information processing by voice when executing the predetermined information processing.
The described speech processing method. 15. A program for controlling information processing based on speech recognition and synthesis, the program being recorded on a computer-readable recording medium, and a voice processing message relating to various information processing. Displaying a voice message; selecting a desired voice processing message from the plurality of displayed voice processing messages; and generating a voice message by voice-synthesizing the selected voice processing message. And a step of outputting the synthesized voice message as a voice for confirmation and outputting the voice message. 16. After confirming and outputting the voice message, if there is no response from the outside even after a certain period of time, detailed information relating to the information processing is notified, or the volume is increased and the voice message is reproduced again. Notifying; inputting voice information to perform voice recognition; determining whether the recognized voice information is valid corresponding to the selected voice processing message; 16. The non-transitory computer-readable storage medium according to claim 15, further comprising a step of executing predetermined information processing corresponding to the selected one of the voice processing messages when the result is determined to be valid. 17. A medium recording a program for performing information processing control based on speech recognition and synthesis by a computer, the control program causing the computer to display voice processing messages related to various information processing. , From the displayed plurality of voice processing messages,
A desired voice processing message is selected, a voice message is created by voice-synthesizing the selected voice processing message, and the synthesized voice message is output as voice for confirmation. A medium on which an audio processing control program is recorded. 18. After confirming and outputting the voice message, if there is no response from the outside even after a certain period of time, detailed information relating to the information processing is notified, or the volume is increased and the voice message is reproduced again. Notifying, and further, inputting voice information and causing voice recognition to be performed, determining whether the voice information recognized as voice is valid corresponding to the selected voice processing message, and determining the determination result. 18. The medium according to claim 17, wherein, when enabled, predetermined information processing corresponding to the selected voice processing message is executed.