JPH11272662A - Voice information processor, its method and medium storing its control program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To execute document processing nearly without destroying the format of a document by automatically identifying whether attached voice information is a voice command or a voice text and giving document processing to it to improve the operability of document processing. SOLUTION: A display part 306 displays a previously obtained document and a voice attaching position instructing part 301 instructs a position to attach voice information in the document. A voice input part 302 inputs voice information including the voice command or a voice text to the attaching position. A voice information attaching part 303 displays that voice information is attached, and stores them in a voice information storage part 304. A voice information retrieving part 305 retrieves voice information corresponding to the attaching position from the part 304 and a voice information recognizing part 308 identifies the voice command or the voice text from voice information. A voice information processing part 309 executes document processing previously set as the voice command or the voice text based on the identifying result of the part 308.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice information processing apparatus and method for processing a document by voice input, and a medium storing a control program thereof, which is applied to a word processor, a personal computer and various information processing terminals.

[0002]

2. Description of the Related Art In recent years, speech recognition technology has become capable of recognizing speech with a considerable accuracy with a simple response. In addition to displaying characters and images on a display and operating electronic devices by key input, Many devices for operating electronic devices by voice input have been proposed.

[0003] For example, according to the description of Japanese Patent Application Laid-Open No. 9-222985, there has been proposed a voice operation device for operating an electronic device such as a CD player by voice. If this voice operation device is applied to, for example, electronic devices in a car,
Since the electronic device can be operated only by voice, eyes and hands can be concentrated on the driving operation, so that there is an effect that the driver can drive safely.

According to Japanese Patent Application Laid-Open No. H8-255047, if a user is not satisfied with the pronunciation of a particular word by attaching a user-specific pronunciation feature to a text file, the user can add the word to himself / herself. Methods and systems have been proposed for annotation of voice control systems that can be replaced with pronunciations. The method and system has the effect that each time a particular word is encountered, it is pronounced correctly.

Further, according to the description of Japanese Patent Application Laid-Open No. 9-62289, by using difference feature data between individual voice data and standard voice data, differences in characteristics due to age, gender, individual differences in speech, and the like can be eliminated. Regardless, a speech recognition apparatus and a speech recognition processing method that recognize an unspecified speaker's voice at an extremely high recognition rate and perform a response or a specific operation corresponding to the recognition result have been proposed. If this voice recognition device and method are applied to, for example, a vending machine, the voice of an unspecified speaker is recognized at a high recognition rate, so that there is an effect that unnecessary button operations can be reduced.

According to Japanese Patent Application Laid-Open No. 5-27790, the type of a user is determined from voice input, and a response message suitable for the user's gender, urgency, maturity, etc. Has been proposed. If this voice input device is applied to, for example, a CD device such as a bank, a CD operation is guided by a response message corresponding to the type of the user, and the waiting time of the user can be reduced.

[0007]

The conventional voice recognition technology recognizes a voice command of a specific speaker or an unspecified speaker from voice and operates according to the recognized voice command. However, the voice input can be used not only to operate the apparatus as a voice command but also as a voice memo (voice text) attached to a document to be displayed, printed and transmitted. For example, when text data such as e-mail is received by a communicable information processing terminal, a person who is unfamiliar with key operations can take in the received text data and attach a comment, or operate by voice input. Workability is better. In addition, when inputting a voice including a document processing command or text to the apparatus, a processing function corresponding to the voice by identifying the voice command or the voice text from the input voice is required.

The present invention has been made in consideration of the above circumstances. For example, if voice information including voice commands or voice text related to document processing is specified at any position in a document and attached, the attached Provided are a voice information processing apparatus and method capable of automatically identifying a voice command or a voice text with respect to the generated voice information and performing document processing, and a medium storing a control program therefor.

[0009]

A display unit for displaying a document obtained in advance, a voice attachment position indicating unit for indicating a position to attach voice information in the document, and at least a voice command or a voice text at the attachment position. A voice input unit for inputting any of the voice information, a voice information attachment unit for displaying a notation indicating that the voice information is attached to the attachment position and storing them in a voice information storage unit; A voice information search unit that searches for voice information corresponding to the voice information from the voice information storage unit; a voice information identification unit that identifies a voice command or a voice text from the searched voice information; A voice information processing unit for executing a document process preset as a voice command or voice text Boric processing apparatus.

In the present invention, the display unit is an LCD.
(Liquid crystal display), a plasma display, or the like. The voice attachment position indicating unit can be configured by an input device such as a keyboard, a mouse, a pen, and a tablet. The audio input unit can be configured with a microphone, an amplifier, a filter, and the like. Further, the audio information attachment unit, the audio information search unit, the audio information identification unit, and the audio information processing unit may be configured by a computer including a CPU, a ROM, a RAM, and an I / O port. The voice information storage unit is R
It can be constituted by a storage device such as an AM, a floppy disk, a hard disk, or the like.

According to the present invention, if voice information including a voice command or voice text related to document processing is indicated at an arbitrary position in a document and attached, whether the voice command or voice text is attached to the attached voice information is determined. Automatic identification and document processing. For this reason, the workability of the document processing is improved, and the document processing can be performed without substantially changing the format of the document.

A voice command table storing voice commands corresponding to the voice information; and a command processing table storing document processing contents corresponding to the voice commands, wherein the voice information identifying unit stores the voice command table in the voice command table. When identifying the voice command from the voice information based on, the voice information processing unit deletes the attached notation,
The document processing content corresponding to the voice command may be extracted and executed based on the command processing table. Note that the voice command table and the command processing table can be configured by a memory such as a ROM and a floppy disk. According to the above configuration, when the voice information is recognized as a voice command, the attached notation is deleted, and the content of the document processing indicated by the voice command can be automatically extracted and executed.

The voice command table further includes an attribute command table storing an attribute command indicating an attribute of the voice command, wherein the command processing table stores the processing content corresponding to the attribute command and the voice command corresponding to the voice information. May be stored. The attribute command table can be configured by a memory such as a ROM and a floppy disk. According to the configuration, it is possible to automatically extract and execute the content of the document processing specified by the attribute command. For this reason, by associating the attribute command with the partial document processing, the content of the partial document processing can be automatically extracted and executed.

A print unit for printing a document, wherein when the voice information identification unit identifies the voice information as a voice command for processing the destination name and the attached sentence, the voice information processing unit outputs the destination name and the attached text May be configured to be output to the printing unit. The printing unit can be constituted by a thermal printer or a laser printer.
According to the configuration, it is possible to print a document to which an address and an attached text are automatically added.

[0015] The apparatus further includes a communication unit capable of transmitting and receiving a document by connecting to an external terminal, wherein the voice information identification unit includes:
When the voice information is identified as a voice command for address and attachment processing, the audio information processing unit may output a document to which the address and the attachment are added to the communication unit. Note that the communication unit can be configured with a communication interface such as a modem and RS232C. According to the configuration, it is possible to transmit and receive a document to which an address and an attached text are automatically added.

When the voice information identification unit identifies the voice information as a voice command designating document deletion processing, the voice information processing unit is configured to delete a document area specified by the voice command. Is also good. According to the configuration, it is possible to delete the area of the document specified by the voice.

When the voice information identification unit identifies the voice information as a voice command specifying a ruled line processing for a deleted portion of the document, the voice information processing unit determines that the line information is processed for a deleted portion of the document specified by the voice command. May be configured. According to the configuration, it is possible to clearly indicate that the deleted portion of the document specified by voice is deleted by performing ruled line processing.

When the voice information identification unit identifies the voice information as a voice command designating document deletion processing and format change processing, the voice information processing unit deletes a document area specified by the voice command. The format of the document may be changed. According to the configuration, it is possible to delete the area of the document specified by the voice and prevent the format from being destroyed by the deletion.

When the voice information identifying section identifies the voice information as a voice command designating the emphasis processing of the document, the voice information processing section is configured to emphasize the area of the document specified by the voice command. You may. As the emphasis processing, for example, the print density may be increased or the character size may be increased to emphasize. According to the above configuration, the region of the document specified by the voice is emphasized, so that the user can carefully check the emphasized portion.

When the voice information identifying section identifies the voice information as a voice command designating the weak processing of the document, the voice information processing section performs the weak processing on the area of the document specified by the voice command. You may comprise. As the low-tone processing, for example, the low-density printing may be performed or the character size may be reduced to perform the low-tone processing. According to the above configuration, since the area of the document specified by the sound is subjected to the attenuating process, the user can carefully check the attenuated portion.

When the voice information identifying section identifies the voice information as a voice command for inserting a specific character string,
The voice information processing unit may be configured to insert a specific character string into an area of a document specified by a voice command. The specific character string is, for example, a character string often used for additional writing such as [important] and [reference]. According to the above configuration, since the specific character string is inserted into the area of the document specified by the voice, the user can carefully check the document area having the specific character string.

When the voice information identifying unit identifies the voice information as a voice text, the voice information processing unit
A configuration may be adopted in which audio text is attached to the attachment position of the document. According to the above configuration, since the voice text is attached to the attachment position of the document specified by voice, the voice text can be directly attached to the document as a voice memo without conversion.

According to another aspect of the present invention, a document obtained in advance is displayed on a display unit, a position at which voice information is to be attached in the document is indicated, and at least one of a voice command and a voice text is provided at the attachment position. Is input by a voice input unit, a notation indicating that the voice information is attached to the attachment position is displayed and stored in a voice information storage unit, and the voice information corresponding to the attachment position is displayed. Speech information characterized by retrieving from a speech information storage unit, identifying a speech command or speech text from the retrieved speech information, and executing document processing preset as a speech command or speech text based on the identification result. A processing method is provided.

Further, according to another aspect of the present invention, a display unit for displaying a previously acquired document, a voice attachment position designating unit for designating a position to attach audio information in the document, And a voice input unit for inputting voice information including either a voice command or a voice text. A medium storing a program for controlling a voice information processing device by a computer, wherein the voice information is attached to the computer. The notation indicating that the position is attached is displayed and stored in the voice information storage unit, and the voice information corresponding to the attached position is searched from the voice information storage unit. Identify the text and set it in advance as a voice command or voice text based on the identification result of the voice information Medium storing a voice information processing apparatus control program for executing the document processing which is provided.

The control program stored in the storage medium is transferred to the RA of the apparatus having no voice information processing function of the present invention.
By installing the information processing device in a memory such as a floppy disk or the like, various information processing devices can be applied as the voice information processing device of the present invention.

[0026]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail based on an embodiment shown in the drawings. The present invention is not limited by this.

FIG. 1 is a block diagram showing a hardware configuration of a voice information processing apparatus according to the present invention. In FIG. 1, reference numeral 1 denotes a CPU of a computer that controls each unit of the audio information processing apparatus of the present invention by a control program. The CPU 1 functions as each unit shown in FIG. 3 by the control program shown in FIG. Reference numeral 2 denotes a ROM that stores a control program of the CPU 1, various data, and the like, and also functions as a voice command table and an attribute command table. Reference numeral 3 denotes a buffer that temporarily stores control data of the CPU 1 and a RAM that functions as an audio information storage unit that stores audio information.

Reference numeral 4 denotes an LCD (Liquid Crystal Display) for displaying various display data, which functions as a display unit. Reference numeral 5 denotes a display controller that controls display data and the LCD 4 according to an instruction from the CPU 1. Reference numeral 6 denotes a tablet integrated with the display screen of the LCD 4. Reference numeral 7 denotes a pen for inputting coordinate data to the tablet 6, and functions as a voice attachment position indicating unit. Reference numeral 8 controls the tablet 6 and the pen 7, respectively, and stores coordinate data input to the tablet 6 in the CPU.
1 shows a coordinate input controller to be transferred.

Reference numeral 9 denotes a microphone for inputting voice, which functions as a voice input unit. Reference numeral 10 denotes an audio input controller that converts analog audio data input by the microphone 9 into digital audio data and transfers the digital audio data to the CPU 1. 11
Denotes a voice recognition table which is constituted by a ROM and stores code data for recognizing digital voice data and converting it into code data. Reference numeral 13 denotes an audio output controller that converts digital audio data into analog audio data and outputs the converted audio data through the speaker 12.

Reference numeral 14 denotes a storage medium which is constituted by an IC card, FD (floppy disk), CD-ROM, MD, or the like, and stores a control program of the present invention. Reference numeral 15 denotes a storage medium controller that controls input and output of information between the storage medium 14 and the RAM 3. The storage medium controller 15
A control program for implementing the present invention can be read from the storage medium 14 and installed in the RAM 3 as needed.

Reference numeral 16 denotes a printer including a thermal printer, a laser printer, and the like. Reference numeral 17 denotes a printing unit 16 and a print controller that controls print data. 18
Denotes a modem for communication connection with another information processing terminal on a communication line. Reference numeral 19 denotes a communication controller (communication unit) for controlling the modem 18 and communication data. Reference numeral 20 denotes a bus for transferring addresses, control program data, voice data (voice commands, voice texts) and the like.

FIG. 2 is a diagram showing a control program stored in the storage medium of this embodiment. As shown in FIG. 2, in the storage medium 14, the CPU 1 stores a voice information attachment program for attaching voice information (voice data) to an attachment position designated in a document, and a voice for searching for voice information corresponding to the attachment position. Each program stores an information search program, a voice information recognition program for recognizing attached voice information, a voice information identification program for determining whether voice information is a voice command or voice text, and an information processing program. In addition, the storage medium 14 stores each controller and R shown in FIG.
Various data such as a program for controlling the OM 2 and the RAM 3 and a voice recognition table are also included.

According to the above configuration, the display unit 4 for displaying a previously acquired document, the voice attachment position instructing unit 7 for designating a position to attach audio information in the document, and at least a voice command or a voice at the attachment position. An audio information processing apparatus having an audio input unit 9 for inputting audio information including any of texts is displayed on a computer 1 by displaying a notation indicating that the audio information is attached to the attachment position. The information is stored in the information storage unit 3, the voice information corresponding to the attachment position is searched from the voice information storage unit 3, a voice command or a voice text is identified from the searched voice information, and based on the identification result of the voice information. A control program for executing document processing preset as a voice command or voice text is stored in the storage medium 1.
4 may be stored. Therefore, by installing the control program stored in the storage medium 14 into various information processing terminals on the market, the audio information processing apparatus of the present invention can be realized.

FIG. 3 is a block diagram showing a functional configuration of the voice information processing apparatus according to the present invention. In FIG. 3, reference numeral 301 denotes a voice attachment position indicating unit (pen 7), 302 denotes a voice input unit (microphone 9), 303 denotes a voice information attachment unit (CPU 1), 30
4 is a voice information storage unit (RAM3), 305 is a voice information search unit (CPU1), 306 is a display unit (LCD4), 30
7 is a voice information recognition unit (CPU1), 308 is a voice information identification unit (CPU1), and 309 is a voice information processing unit (CPU1).
1) and 310 are voice command tables (ROM2), 3
Reference numeral 11 denotes an attribute command table (ROM2), and reference numeral 312 denotes a command processing table (ROM2).

The functional configuration of FIG. 3 is shown in FIGS.
This will be described with reference to FIG. FIG. 4 is a diagram showing a processing screen of audio information attached to a document in this embodiment. FIG.
(A) shows a processing screen for determining a position where sound information is to be attached (inserted) in a displayed document by the sound attachment position indicating unit 301 composed of a pen. FIG. 4B shows a processing screen for specifying the attachment position by moving the cursor.

The operation of attaching the voice information is performed by using the pen 7, but can also be performed by operating the cursor keys including the mouse and the keyboard. As described above, the attachment position in the document to which the audio information is attached is determined, and then the audio is input by the audio input unit 302 such as the microphone 9, and the audio information attachment unit 303 is input.
To attach the audio information to the attachment position of the document.

FIG. 4C shows a processing screen on which an icon [sound] indicating that the audio information has been attached is displayed.
The audio information attached to the attachment position of the document by the audio information attachment unit 303 is stored in the audio information storage unit 304 in association with the attachment position.

FIG. 5 is a view showing a display example of a document to which voice information is attached in this embodiment and its text data. FIG. 5A shows a display example of a document to which audio information is attached. “Delete two characters” shown in FIG. 5A indicates that it is voice information (voice command). FIG. 5 (b)
Indicates text data (code data) of a document to which audio information is attached. A voice identifier (5555H) and a pointer are inserted into the text data at the position where the voice information is attached. The voice information attachment unit 303 stores the input voice information as text data in the voice information storage unit 304 in association with the position indicated by the pointer.

FIG. 6 is a diagram showing a voice command table according to this embodiment. The voice command table 310 is for identifying whether the voice information (voice data) recognized by the voice information recognition unit 307 is a voice command (control command) by the voice information identification unit 308.
When voice data is included in the voice command table 310, it is processed as a voice command, and when voice data is not included, it is processed as voice text (voice memo).

FIG. 7 is a view showing an attribute command table according to this embodiment. When the voice data identified by the voice information identification unit 308 is a voice command (control command), the attribute command table 311 is used to further identify whether the voice command is a whole processing command or a partial selection processing command. Things. When the attribute command table 311 includes a voice command, the voice information processing unit 309 processes the command as a partial selection processing command.

FIG. 8 is a diagram showing a command processing table according to this embodiment. The command processing table 312 defines processing contents of a voice command in which a control command and an attribute command are effectively combined. FIG. 9 is a diagram illustrating an example of a recognition result of a voice command and code data thereof according to the present embodiment. The recognized voice command and the processing content are temporarily stored in the voice information storage unit 304 by the voice information processing unit 309.

The audio information search unit 305 searches the audio data stored in the audio information storage unit 304 for an audio data identifier, and searches for audio information based on the audio data identifier. The voice information recognition unit 307 recognizes the searched voice information by using the voice recognition table 11 and converts it into code data. The voice information identification unit 308 identifies whether the voice information (code data) is a voice text (voice memo) or a voice command by using the voice command table 310 and the attribute command table 311. Treated as text. For example, as shown in FIG. 31, [this is realized by speech recognition] is processed as speech text,
Inserted into the document. The voice information identification unit 308 identifies the control command as a more detailed voice command by the attribute command table, and is applied by the voice information processing unit 309 to editing processing such as deletion.

Referring now to the flowcharts of FIGS. 10 to 22, FIGS. 23 to 32 show a document to which sound information (1) to (10) is attached and a document processed based on the sound information in this embodiment. This will be described with reference to FIG.

FIG. 10 is a flowchart showing the procedure of the voice information recognition processing and voice information processing of this embodiment. FIG.
At 0, the audio data stored in the audio information storage unit 304 exists in the document data at the position indicated by the pointer of the audio identifier in the document data, as shown in FIG. It is checked whether a voice data identifier exists in the document data (S100).
1). If there is no voice data identifier, no voice data is included, and the process ends without any processing. If there is a voice data identifier, the voice data is recognized (S100).
2) The recognition result is stored in the voice information storage unit 304 in a format converted into a code. FIG. 6 shows the stored code data.
It is checked whether or not there is a control command of the voice command table (S1003). For example, it is checked whether or not the recognition result includes a code string “Sakuju”.

If the control command is not included in the recognition result, it is identified as a voice text (S1005), and the voice data is code-converted as a voice text and inserted into a document (S1007). This shows a case where voice data is attached to the document in FIG. 31A, and FIG.
Shows a state in which the voice data is converted into voice text and inserted into the document.

If a control command is included in S1003, it is identified as a voice command (S1004), the content of the voice command is analyzed, and a corresponding command process is performed (S1006). If the voice command is processed, the voice command becomes unnecessary, so the voice data is cut (S1008). This indicates, as shown in FIG. 32, text data including a voice command of “print”,
The voice command is cut, and only the text data is printed.

FIG. 11 is a flow chart showing the procedure of the voice command identification processing of this embodiment. An attribute command is extracted from the voice data from the attribute command table of FIG. 7 (S1101). Next, control commands are extracted from the voice data from the voice command table of FIG. 6 (S110).
2) From the combination of control command and attribute command,
The processing target and the processing content are extracted from the command processing table of FIG.

FIG. 12 is a flowchart showing the procedure of the voice command identification process and the command process (1) of this embodiment. In FIG. 12, it is determined whether the voice data is a voice text or a voice command (S1201). If the voice data is a voice text (voice memo), the voice data is converted into text data and a paste process is performed on the document (S120).
6). Here, it is analyzed whether the voice command is a command for instructing overall processing or a command for instructing processing in a specified range.

If the voice data is a voice command, it is checked whether or not there is a voice identifier at the head of the document (S1202). If there is no voice data identifier, the command is a partial processing command because it is not an entire processing command (S1205). If there is a voice identifier at the beginning of the sentence, it is determined whether or not the recognized voice data has an attribute command (S1203). If there is an attribute command, processing corresponding to the partial processing command is performed (S1205). If there is no attribute command, processing corresponding to the entire processing command is performed (S1204).

FIG. 13 is a flowchart showing the procedure of the voice command identification process and the command process (2) of this embodiment. In FIG. 13, when the voice data is a voice command for the entire process, the entire process according to the type of the command is performed. For example, when the voice command is a command of [Print], it is checked whether the process is a print process (S1301).
Since the printing process is performed and there is no attribute command, the entire process is performed, and the document is printed (S1302). If it is not a print process, it is further checked whether the process is an attachment to a mail address (S1
303), in the case of mail address attachment processing, the mail address is attached to the head of the document (S1304) (see FIG. 23).

FIG. 14 is a flowchart showing the procedure of the voice command identification process and the command process (3) of this embodiment. Next, in FIG. 14, when the voice data is a voice command of a partial process, a partial process corresponding to the type of the command is performed. For example, it is checked whether the process is a deletion process (S
1401) In the case of the deletion process, it is checked whether a format change is involved (S1402).
The designated part is deleted (S1403) (see FIG. 24).

If the format is changed, the designated portion is deleted and the format is changed (S1404) (FIG. 26).
reference). Next, a check is made to see if the process explicitly specifies the deleted portion (S14).
05) If it is the process of specifying the deleted portion, a process of specifying the deleted portion by drawing a double line is performed (S14).
06) (see FIG. 25).

Next, it is checked whether the process is the emphasis process (S1407). If the process is the emphasis process, the emphasis process is performed by making the character string a double-width character (S1408) (see FIG. 27). It is checked whether the process is a weak tone process (S1409), and in the case of the weak tone process, the halftone process is performed by making the character half-width (S1410) (see FIG. 28).
It is checked whether the process is a specific expression providing process (S1411). In the case of the specific expression providing process, the specific expression providing process is performed by, for example, providing a specific expression “important” (S1412) (see FIG. 29).

FIG. 15 is a detailed flowchart showing the command processing (print processing) in S1302 of FIG. FIG.
In step 5, the input document is converted into print data on the RAM 3 (S1501). The converted print data is printed (S1502). For example, FIG.
As shown in (b), the voice command “print” disappears and is printed.

FIG. 16 is a detailed flowchart showing the command processing (mail address attachment processing) in S1304 of FIG. In FIG. 16, a document having a mail address is created (S1601), and the created document is added to the head of the body (S1502). For example, FIG.
As shown in (b), since it is a command of [Attach mail address], a document "I am always taking care of A." is attached to the beginning of the sentence.

FIG. 17 is a detailed flowchart showing the command processing (deletion processing) in S1403 of FIG. FIG.
In step 7, an address indicating a designated portion on the memory is obtained (S1701), and a deletion bit (flag) indicating that the code data corresponding to the address is deleted for a certain number of characters is set (S1702). In this command processing, if the delete bit is set, it is as if the characters that are not deleted in display / print are cut and cut. For example, as shown in (a) and (b) of FIG. 24, the command processing has the attribute of [2 characters], so that the specified portion is deleted, and a deletion bit for two characters is set.

FIG. 18 is a detailed flowchart showing the command processing (deletion / format change processing) in S1404 of FIG. In FIG. 18, an address indicating a designated portion on a memory is obtained (S1801), and a deletion bit indicating that the code data corresponding to the address is deleted for a certain number of characters is set (S1802). next,
The format of the portion that needs to be changed is changed (S1803). For example, as shown in (a) and (b) of FIG. 26, when one line is deleted, the number assigned to the head of the line is also changed.

FIG. 19 is a detailed flowchart showing the command processing (deleted part explicit processing) in S1406 of FIG. In FIG. 19, an address indicating a designated portion on the memory is obtained (S1901), and a double line bit indicating that a double line is added for a certain number of characters is set for the code data corresponding to the address (S1901). S1902). For example, as shown in (a) and (b) of FIG. 25, when the process of specifying the deleted portion is performed, a process of specifying the deleted portion and leaving the deleted portion is performed by drawing a double line.

FIG. 20 is a detailed flowchart showing the command processing (emphasis processing) in S1408 of FIG. FIG.
At 0, an address indicating a designated portion on the memory is obtained (S2001), and a double-width bit is set in the code data corresponding to the address to indicate that the double-width is set for a certain number of characters (S2002). For example, FIG.
As shown in (b), since the command processing is an emphasis processing, the emphasis processing is performed by making the character string a double-width character. For emphasis, it is possible to change not only double-width characters but also character colors and fonts.

FIG. 21 is a detailed flowchart showing the command processing (weak processing) in S1410 of FIG. FIG.
In step 1, an address indicating a designated portion on the memory is obtained (S2101), and a half-width bit is set in the code data corresponding to the address to indicate that the half-width is set for a certain number of characters (S2102). For example, FIG.
As shown in (b), since the command processing is a low-tone processing, the low-tone processing is performed by reducing the character string to half-width. It is also possible to change the color of characters and the typeface in addition to half-width characters.

FIG. 22 is a detailed flowchart showing the command processing (added data insertion processing) in S1412 of FIG. In FIG. 22, additional data is determined by voice input (S2201). An address indicating a specified portion on the memory is obtained (S2202), and the specific assignment data is inserted into a position corresponding to the address (S2203). For example,
As shown in (a) and (b) of FIG. 29, the command processing is the processing of adding the character notation “important” because the processing is the insertion data insertion processing. Also, FIG.
As shown in (b), a process of giving a character notation “reference” is performed.

[0062]

According to the present invention, if voice information including voice commands or voice text related to document processing is indicated at an arbitrary position in a document and attached, a voice command or voice text is attached to the attached voice information. Can be automatically identified and document processing can be performed. For this reason, the workability of the document processing is improved, and the document processing can be performed without substantially changing the format of the document.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a hardware configuration of a speech information processing apparatus according to the present invention.

FIG. 2 is a diagram showing a control program stored in a storage medium of the embodiment.

FIG. 3 is a block diagram illustrating a functional configuration of a voice information processing apparatus according to the present invention.

FIG. 4 is a diagram showing a processing screen of audio information attached to a document in the embodiment.

FIG. 5 is a diagram illustrating a display example of a document to which audio information is attached and text data thereof according to the embodiment.

FIG. 6 is a diagram illustrating a voice command table according to the present embodiment.

FIG. 7 is a diagram illustrating an attribute command table according to the embodiment.

FIG. 8 is a diagram illustrating a command processing table according to the present embodiment.

FIG. 9 is a diagram illustrating an example of a voice command recognition result and code data thereof according to the present embodiment.

FIG. 10 is a flowchart illustrating a procedure of voice information recognition processing and voice information processing according to the present embodiment.

FIG. 11 is a flowchart illustrating a procedure of a voice command identification process according to the embodiment;

FIG. 12 is a flowchart illustrating a voice command identification process and a procedure of the command process (1) according to the embodiment;

FIG. 13 is a flowchart illustrating a procedure of voice command identification processing and command processing (2) according to the present embodiment.

FIG. 14 is a flowchart illustrating a procedure of voice command identification processing and command processing (3) according to the present embodiment.

FIG. 15 is a detailed flowchart showing a command process (print process) in S1302 of FIG.

FIG. 16 is a detailed flowchart showing a command process (mail address attachment process) in S1304 of FIG. 13;

FIG. 17 is a detailed flowchart showing the command processing (deletion processing) in S1403 of FIG.

FIG. 18 shows a command processing (deletion /
9 is a detailed flowchart illustrating format change processing).

FIG. 19 is a detailed flowchart showing the command processing (deleted part explicit processing) in S1406 of FIG.

FIG. 20 is a detailed flowchart showing a command process (emphasis process) in S1408 of FIG. 14;

FIG. 21 is a detailed flowchart showing the command processing (weak processing) in S1410 of FIG.

FIG. 22 is a detailed flowchart showing a command process (added data insertion process) in S1412 of FIG.

FIG. 23 is a diagram showing a document to which audio information (1) is attached and a document processed based on the audio information in the embodiment.

FIG. 24 is a diagram showing a document to which audio information (2) is attached and a document processed based on the audio information in the embodiment.

FIG. 25 is a diagram showing a document to which audio information (3) is attached and a document processed based on the audio information in the embodiment.

FIG. 26 is a diagram showing a document to which audio information (4) is attached and a document processed based on the audio information in the embodiment.

FIG. 27 is a diagram showing a document to which audio information (5) is attached and a document processed based on the audio information in the embodiment.

FIG. 28 is a diagram showing a document to which audio information (6) is attached and a document processed based on the audio information in the embodiment.

FIG. 29 is a diagram illustrating a document to which audio information (7) is attached and a document processed based on the audio information in the embodiment.

FIG. 30 is a diagram showing a document to which audio information (8) is attached and a document processed based on the audio information in the embodiment.

FIG. 31 is a diagram showing a document to which audio information (9) is attached and a document processed based on the audio information in the embodiment.

FIG. 32 is a diagram showing a document to which audio information (10) is attached and a document processed based on the audio information in the embodiment.

[Explanation of symbols]

 1 CPU 2 ROM 3 RAM 4 LCD 5 Display controller 6 Tablet 7 Pen 8 Coordinate input controller 9 Microphone 10 Voice input controller 11 Voice recognition table 12 Speaker 13 Voice output controller 14 Storage medium 15 Storage medium controller 16 Printer 17 Printer controller 18 Modem 19 Communication controller 20 bus

Claims (14)

[Claims] A display unit for displaying a document obtained in advance;
A voice attachment position indicating unit that indicates a position to which voice information is to be attached in the document; a voice input unit that inputs voice information including at least one of a voice command and a voice text at the attachment position; A voice information attachment unit that displays a notation indicating that it is attached to a position and stores them in a voice information storage unit, and a voice information search unit that searches the voice information storage unit for voice information corresponding to the attached position, A voice information identification unit that identifies a voice command or a voice text from the searched voice information, and a voice information processing unit that executes a document process that is preset as a voice command or a voice text based on the identification result by the voice information identification unit. A voice information processing apparatus comprising: 2. A voice command table storing voice commands corresponding to the voice information, and a command processing table storing document processing contents corresponding to the voice commands, wherein the voice information identifying unit includes the voice command. When the voice command is identified from the voice information based on the table, the voice information processing unit deletes the attached notation and extracts and executes the document processing content corresponding to the voice command based on the command processing table. The voice information processing apparatus according to claim 1, wherein 3. An attribute command table storing attribute commands indicating attributes of voice commands of the voice command table, wherein the command processing table stores processing contents corresponding to the attribute commands. Item 3. The audio information processing device according to Item 2. 4. A printing unit for printing a document, wherein when the voice information identification unit identifies the voice information as a voice command for address processing and attached sentence processing, the voice information processing unit outputs The voice information processing apparatus according to claim 1, wherein the document to which the attached text is added is output to the printing unit. 5. A communication unit capable of transmitting and receiving a document by connecting to an external terminal, wherein the voice information identification unit identifies the voice information as a voice command for address processing and attached text processing. The voice information processing apparatus according to claim 1, wherein the voice information processing unit outputs a document to which a destination name and an attached text are added to the communication unit. 6. When the voice information identification unit identifies the voice information as a voice command designating document deletion processing, the voice information processing unit deletes a document area specified by the voice command. The voice information processing apparatus according to claim 1, wherein: 7. When the voice information identification unit identifies the voice information as a voice command designating ruled line processing in a deleted portion of the document, the voice information processing unit determines whether the voice information has been deleted in the document deleted portion specified by the voice command. 2. The audio information processing apparatus according to claim 1, wherein rule processing is performed. 8. When the voice information identification unit identifies the voice information as a voice command that simultaneously specifies a document deletion process and a format change process, the voice information processing unit determines a region of the document specified by the voice command. 2. The method according to claim 1, wherein the format of the document is changed by deleting the file.
An audio information processing apparatus according to claim 1. 9. When the voice information identification unit identifies the voice information as a voice command designating a document emphasizing process, the voice information processing unit emphasizes a region of the document specified by the voice command. Claim 1 characterized by the following:
An audio information processing apparatus according to claim 1. 10. When the voice information identification unit identifies the voice information as a voice command designating the weak processing of the document, the voice information processing unit performs the weak processing on the area of the document specified by the voice command. The voice information processing apparatus according to claim 1, wherein 11. When the voice information identification unit identifies the voice information as a voice command for a specific character string insertion process, the voice information processing unit stores the specific character string in a document area specified by the voice command. 2. The audio information processing apparatus according to claim 1, wherein an insertion process is performed. 12. The speech information processing unit according to claim 1, wherein when the speech information identification unit identifies the speech information as speech text, the speech information processing unit attaches the speech text to a document attachment position. Audio information processing device. 13. A document obtained in advance is displayed on a display unit,
Indicating a position to attach audio information in the document, inputting audio information including at least one of a voice command and an audio text to the attachment position by an audio input unit, and attaching the audio information to the attachment position. Displaying the notations shown and storing them in the voice information storage unit, searching the voice information storage unit for voice information corresponding to the attached position, identifying a voice command or voice text from the searched voice information, A voice information processing method, wherein a document process preset as a voice command or voice text is executed based on the identification result. 14. A display unit for displaying a document obtained in advance, a voice attachment position indicating unit for indicating a position to attach audio information in the document, and at least one of a voice command and a voice text at the attachment position. A medium storing a program for controlling a voice information processing apparatus having a voice input unit for inputting voice information by a computer, wherein the computer displays a notation indicating that the voice information is attached to the attachment position. And store them in a voice information storage unit, and search the voice information storage unit for voice information corresponding to the attachment position,
A medium storing a voice information processing device control program for causing a voice command or a voice text to be identified from the searched voice information, and executing a document process preset as a voice command or a voice text based on the identification result of the voice information.