JPS59177644A - Input device of japanese language information - Google Patents

Abstract

PURPOSE:To make the input operation easy by operating an auxiliary input part in interlocking with a voice input by pronouncing to input a signal which distinguishes between a code, a mode, a function, etc. and displaying them to perform Kana (Japanese syllabary)-Kanji (Chinese character) conversion. CONSTITUTION:A kana syllable which the operator pronounces is converted to an audio signal by a voice input part 1 and is compared with preliminarily stored voice patterns in a voice recognizing part 3 to output a Kana character signal of the pattern coiciding with this audio signal. An auxiliary input part 2 is operated in interlocking with pronouncing to input distinguishing information of a code, a mode, a function, or the like. A control part 4 retrieves Kana character information from the voice recognizing part 3 with an incorporated memory 4a and displays this information on a display device 7 as Kana characters as they are or after converting it to a signal indicating a code, a mode, a function, or the like and uses a dictionary file 6 to convert Kana characters of Kanji by a Kana-Kanji converting part 5. Homonymous Kanjis are selected by designating a number. The result is printed out by a printing part 8. Thus, the input operation is made easy.

Description

DETAILED DESCRIPTION OF THE INVENTION (Technical Field) The present invention relates to a linguistic information input device, and particularly to a device capable of inputting Japanese information using kana syllables.

(Prior Art) There has been a major problem with inputting information in linguistic information processing, especially in Japanese information processing.

Japanese information includes mixed characters such as hiragana, katakana, and kanji9
It is characterized by an extremely large number of words.

For inputting Japanese information, there are full character array keyboard inputs traditionally used on Japanese typewriters, Ben-touch type tablet keyboard input, multi-level character array keyboard input, associative code input, etc. It has the drawbacks that it requires memorization, special training, complicated operation, and time-consuming operation, making it unsuitable for amateurs.

To solve this problem, a so-called kana-kanji conversion technology has been developed that inputs kana characters and then converts them into kanji.

This is input using a kana keyboard, which reduces the burden of special training on the operator, but it is difficult to input from a free position.

In order to solve this problem, a method of inputting using kana voice has been devised, but codes (letters, numbers, symbols, etc.), modes (
(Katakana mode, Hiragana mode, proper noun mode, etc.)
There is a drawback that character type information indicating ``character type'' and control information indicating functions (registration, deletion, search, etc.) cannot be input using the normal reading method.

(Object of the Invention) The purpose of the present invention is to reduce the burden on the operator by using a kana voice input method that anyone can easily input without requiring special training, and by using character types that indicate codes, modes, etc. An object of the present invention is to provide a Japanese information input device capable of inputting information and control information indicating functions by voice.

(Structure of the Invention) To achieve the above object, the present invention includes a voice input section that converts uttered kana syllables into voice signals, and a voice signal converted by the voice input section that is recognized and outputs a kana character signal. an auxiliary input unit that inputs auxiliary information for identifying the code, mode, and function of the uttered kana syllable; and an auxiliary input unit that inputs auxiliary information input from the auxiliary input unit to output from the voice recognition unit. The code indicated by the kana character signal,
It is equipped with a control section that identifies modes, functions, etc., and outputs corresponding character type information, information, or control information.

(Example) Next, an example of the present invention will be described with reference to the drawings. 1st
The figure is a block diagram showing one embodiment of the present invention.

1 is an audio input section consisting of a microphone; 2 is an auxiliary input section that is operated in conjunction with vocalization to input auxiliary information for identifying codes, modes, functions, etc.; and 3 is an audio signal output from the audio input section 1 by vocalization. 4 is a memo IJ that stores the data shown in Tables 1 and 2.
5 is a kana-kanji converter, and 6 is a kana-kanji converter.
A dictionary file is used for kanji conversion, 7 is a display section, and 8 is a print section.

The operation of the embodiment of the above configuration will be explained.

First, the kana syllables uttered by the operator are converted into voice signals via the voice input unit 1, and compared with the voice patterns stored in advance in the voice recognition unit 3. The kana characters corresponding to the matched sounds and turns are converted into kana character signals. Output as .

In conjunction with the utterance, the auxiliary input section 2 is operated to input desired auxiliary information among the auxiliary information for identifying codes, modes, functions, etc. The input auxiliary information and the kana character signal output from the voice recognition section 3 are supplied to the control section 4. Control unit 4
identifies the kana character signal according to the auxiliary information, converts it into a signal indicating the kana character format, code, mode, or function, and outputs it to the display section 7. The display unit 7 displays input kana characters, codes, characters indicating modes or functions. Further, the kana characters, codes, and modes identified by the control unit 4 based on the auxiliary information are supplied to the kana-kanji conversion unit 5 in the order identified based on the auxiliary information. Kana
The kanji conversion unit 5 uses the dictionary file 6 to convert kana character strings into kanji/kana mixed sentences, code strings into codes, and mode strings according to the mode. The converted sentence converted in this manner is displayed on the display section 7. For example, if a homonym exists in the converted sentence, the operator selects and sets the numbered homonym displayed on the display section 7 by specifying the number. Corrections and additions can be made by speaking again and operating the auxiliary input section 2 to obtain the desired converted sentence. The obtained kanji/kana mixed sentence is printed by the printing unit 8. FIG. 2 is a diagram showing a specific example of the auxiliary input section used in this embodiment.

9 is the content information of the first table and the first one that instructs to move the cursor to the left.
key, 10 is a second key for instructing the content information in Table 2 and carmol right movement, 11 is from the control unit 4 to the Kanji-Kanji conversion unit 5
The third key 12, which instructs the supply of Hekana characters, codes, and mode strings and the execution of the operations of each function, is used when an undesired Kana character, code, mode, or function is identified based on the uttered Kana syllable and auxiliary information. This is the fourth key for instructing the display unit 2 to delete (clear) a Shikana character, code, mode, or function, and to complete the operation of the function when the function has already been executed. Inputs of codes, modes, functions, etc. are made in correspondence as shown in Tables 1 and 2. It is desirable that the correspondence between the contents of Tables 1 and 2 and the kana syllables be easy for the operator to remember, be familiar with, and easily identify. do not have.

The memory 4a of the control unit 4 that stores the data shown in Tables 1 and 2 stores, for each table, a table arranged in alphabetical order for each number of kana syllables and an index for searching the table.

Table 2. Figures 3 and 4 are 70mm diagrams for explaining the operation of the above embodiment.
- A diagram showing a chart and an input method.

In steps 13 to 15, auxiliary information in the auxiliary input section 2 is determined. If the third key 11 is operated in step]3, processing according to the input string is executed in step 3o. That is, when the input string is a function, the function is executed, and when the input string is a kana character, code, or mode, the input string is supplied to the kana-kanji converter 5.

If the third key 11 is not operated in step 13, step 14. If the K advance fourth key 12 is operated, inputs such as characters, codes, mode functions, etc. will be deleted (cleared) in step 29, and if each function has already been executed, this function will be deleted. complete the process.

If the fourth key 12 is not operated in step 14, the process proceeds to step 15, and if the first key 9 or the second key 10 is operated, the kana characters input in step 16 are displayed in the first table and the second table. Set 1 to register F, which indicates a comparison with the memory 4a that stores the indicated data, and set 1 to register T, which indicates whether it is a comparison with the first table or the second table (when the first key 9 is pressed).
Also, (d 2 (when the second gear is 10) is stored.

If key 9 or key 10 is not operated in STEP 015, proceed to STETSUNO 017 and register F, KO.
Store.

Next, in step 18, if kana characters have been input, the contents of register F are determined by the stencil 019. When the register F is 1, in step 20, 1 is added to the register N, which is the number of kana characters input. Also, the input kana characters are stored according to register N. In step 19, if the register F is kaO, it is not a comparison with the memory 4a which stores the data shown in Tables 1 and 2, so the process goes to step 31 and outputs the input kana characters. Step 1
If no kana characters have been input in step 8 or if step 2° is completed, the process advances to step 21, and if register F is 1, the above steps can be repeated. When the register F is 0, the process proceeds to step 22, and when the register T is 0, the above steps are repeated. If the register T is not 0, the process goes to step 23; if the register N is 0, the process goes to step 24; if the register N is not 0, the process goes to step 32.

In step 24, a table to be referred to is selected according to the contents of register T. When the register T is 1, the first table in the memory 4a storing the data shown in the first table and the second table is selected in step 25. In step 20, the table is searched using the input number of kana characters stored in register N and the first kana character among the stored kana characters. According to the index, the kana syllables in the corresponding table are matched with the stored kana characters. Do the following. In step 26, when the register T is not [] in step 24, the second table of the memo I) 4a is selected which stores the data shown in the first table and the second table. The rest is the same as Stesono 025.

When steps 25 and 26 are completed, the process goes to step 27, stores O in register T and register N, and outputs the content corresponding to the matched kana syllable.

Similarly to step 24, the stencil 32 also selects the cursor movement direction in accordance with the register T. When the register T is 1, the stencil 33 stores O in the register T and moves the cursor to the left. Stesono 34 is executed when register T is not 1 in Stesono 32, stores O in register T, and moves the kernel to the right.

Stesono'27, 29. , 30, 31, 33. Upon completion of 3/1, the process advances to step 28. Step 28 displays information on the display unit 7 according to each step, and returns to step 13 to repeat the above steps.

How an input character string is processed according to the above-described flowchart will be explained using a more specific example.

Now, A and a can be easily processed. Assume that a manuscript sentence ``'' is inputted. The operator utters kana syllables in response to this manuscript sentence. If necessary, in conjunction with the utterance, auxiliary information is inputted by key operations on the auxiliary input section 2.

For example, for the kana syllable ``'° 工'' for A'', press the first key 9 to open (turn on) the utterance.The kana syllable for ``°'a'' is pronounced the same as ``A''. presses the second key IO to open (turn on) the utterance. Similarly, the kana syllables ``'te'', '', corresponding to ° and '' are pressed.

The first key 9 is turned on to open the utterance for the kana syllable °'mall' for ''.

Since "Pakankun" is written in katakana, the kana syllable baka ""yu""power" which indicates katakana mode (the mode indicating katakana notation is displayed as "El" on the display section 7) is used before and after '°kankun'. The second key 10 is vocally opened (turned on) in response to "".

The control unit 4 supplies kana characters, codes, and mode strings to the kana-kanji conversion unit 5 when the third key 1 of the auxiliary input unit 2 is input, but it supplies them when “l, +111°” etc. are identified in advance. If this is done, there will be no need to operate the third key 11, which is not to say that the burden on the operator will be reduced.

For example, the kana syllable ``2'' for ``in the original sentence'' is incorrectly recognized as ゛mi'' by the speech recognition section 3, and when the kana character signal ``mi'' is output to the control section 4, ゛mi'' is displayed on the display section 7. .

When the operator confirms that the input is not the desired one, he can delete (clear) the displayed string by operating the key 12.

Similarly, when deleting (clearing) or correcting any kana character code or mode for the input kana character, code, or mode string, operate the ] key 9 or the second key 10 without speaking. When deleting (clearing) the cursor by instructing the cursor movement to the left or right by the number of operations, the fourth key 12 is operated.

Also, when making corrections, it can be done by uttering a kana syllable or by operating the first key 9 or second key 10 in conjunction with the utterance.

Control information for functions (registration, deletion, search, etc.) can be reversely input by operating the second gear lθ in conjunction with vocalization. When executing the identified function, the third key 1 is operated. The executed function can be easily completed by operating the fourth key J2.

In the second embodiment shown in FIG. 5, the auxiliary input section 2 in FIG. 1 is replaced with a numeric keypad, and an input switching key is provided on the kana keyboard, so that it can be used by switching the input of a part of the numeric key. 35 is the input information of a part of the numeric key. 36 is a fifth key that instructs "'0" or the content information of Table 1 by switching the input switching key 35; 37 is a 5th key that instructs "'0" by switching the input switching key 35; ``Also, the 6th key'' indicates the content information of table d.
138 is a seventh button which instructs the display section 7 to delete (clear) the shikana character and mode when an undesired kana character or mode is identified by switching the input switching key 35 or by the uttered kana syllable and auxiliary information. key, and other keys (conversion, cursor movement keys, etc.) are assumed to be implemented on a kana keyboard with a numeric keypad. The operation is exactly the same as that of the embodiment shown in FIGS. 1 to 4, so a description thereof will be omitted.
In this embodiment, as mentioned above, the input information of a part of the numeric keypad can be switched by the input switching key 35, so it is necessary to specially provide the auxiliary input section 2 in a Japanese information processing device having a kana keyboard with a numeric keypad. You can enter Japanese information without having to use it. It also has the feature of being able to operate a kana keyboard if necessary.

(Effects of the Invention) As explained in detail above, the Japanese information input device of the present invention uses kana voice input to input character type information indicating codes and modes, and control information indicating functions, and uses approximately four hands. Because it can be input by fixing it to the key and operating it, anyone can input not only Shikana characters but also symbols, modes, functions, etc. using the normal reading method with simple rules and easy operations without the need for special training. It is effective, and as a result, you can expect an improvement in input speed.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing one embodiment of the present invention, FIG. 2 is a diagram showing an auxiliary input section used in the present invention, FIG. 3 is a flowchart for explaining the present invention in detail, and FIG. The figure shows an input method according to an embodiment of the present invention, and FIG. 5 shows a second embodiment of the auxiliary input section of the present invention. 1. Voice input section, 2. Auxiliary input section, 3. Voice recognition section, 4. Control section, 5. Kana-kanji conversion section, 6.
・Dictionary file, 7...display section, 8...-print section, 9
...1st key, 10...2nd key, 11...3rd key
key, 12...4th key, 35...input switching key,
36...5th key, 37...6th key, 38...7th key. Patent applicant Oki Electric Industry Co., Ltd.

Claims (1)

[Claims]! 1. A voice input section that converts the generated kana syllables into voice signals, and a voice recognition section that recognizes the voice signals converted by the voice input section and outputs a kana character signal. an auxiliary input section for inputting auxiliary information for identifying the code, mode, and function of the originally drawn kana syllable, and an auxiliary information inputted from the auxiliary input section to output the speech recognition section. What is claimed is: 1. A Japanese language information input device comprising a control section that identifies the code, mode, function, etc. indicated by a kana character signal, and outputs corresponding character type information or control information. 2. The auxiliary input section is equipped with a numeric part of a general keyboard or a numeric key part of a keyboard with a numeric keypad and an input changeover switch, and by changing the input changeover switch to voice input, the numeric part of the general keyboard can be input. 2. The Japanese information input device according to claim 1, wherein the Japanese language information input device uses the part or the numeral part as an auxiliary input part for voice input.