JPS61177575A - Forming device of japanese document - Google Patents

Abstract

PURPOSE:To deal with voicing with a long vowel only by registering one kind of Japanese rendering for one KANJI (Chinese character) by providing a long vowel character conversion part which searches for a KANA (Japanese syllabary) character 'o' following the KANA character of the 'o' series of KANA and adds 'u' to the KANA character 'o' as a speech recognition result. CONSTITUTION:When 'sotou' is voiced with a long vowel, a speech recognition part 1 outputs 'sotou' to an input buffer 2. Then, the two-pronged tree generating part 31 of the long vowel character conversion part 3 searches for the KANA character 'o' in the KANA character string which follows the KANA character of the 'o' series and generates a two-pronged tree wherein a character 'u' is added to the KANA character 'u' as a speech recognition candidate in a two-pronged tree buffer 32. A two-pronged tree tracing part 33 traces the tree in order to generate and store character candidates 'soto', 'sotou', 'suto', and 'soutou' in a character string candidate buffer 34 temporarily and a display part character decision part 35 sends them to an independent word retrieval part 4 successively. In such a case, when the 'sotou' is sent a KANJI code 'sutou' is read out of an independent word dictionary 50 and displayed on a display part 7.

Description

DETAILED DESCRIPTION OF THE INVENTION Field of the Invention The present invention relates to a Japanese text creation device that creates Japanese texts by voice input.

2. Prior Art Conventional Japanese text creation devices include, for example, ``Prototype Japanese word processor with voice input that recognizes 101 monosyllables,'' 9th Nikkei Electronics, ppee-68.
Shown on June 6, 1983.

FIG. 6 shows a configuration diagram of this conventional Japanese text creation device, in which 1 is a speech recognition section, 2 is a buffer for temporarily storing the recognition results obtained from the speech recognition section 1, and 3 is a buffer 2. An independent word search section 61 searches for a kanji corresponding to an independent word in a temporarily stored kana string; 61 is an independent word dictionary in which readings of independent words and kanji are registered as pairs; 6 is an independent word dictionary 61
Kanji code read from or input buffer 2
A display buffer 7 temporarily stores display kana characters corresponding to the kana character string temporarily stored in the kana character string, and 7 is a display section that displays the contents of the display buffer 6.

The operation of the conventional Japanese text creation device configured as described above will be explained below.

Let's consider the case of creating the Japanese sentence ``equivalent'' using voice input. Unlike keyboard input, in the case of voice input, "Soutou""
It may also be "Sootou", "Sootou", "Sootou". Also, considering the ease of vocalization, “So-to-”
'' or, if a monosyllabic utterance is made, it is desired to be able to pronounce it as a long vowel, such as ``sootoo''. Therefore, independent word dictionary 51
``Soutou'', ``Sootou'', ``Soutou'', ``
The four readings of ``sootoo'' are associated with the kanji code ``equivalent''.

When you pronounce "equivalent" as a long vowel, the speech recognition unit 1 will say "equivalent" as a long vowel.
An independent word search unit 4 outputs “Sootoo” to the input buffer 2.
searches whether the independent word part "sootoo" in the input buffer 2 is registered as a reading in the independent word dictionary 51. If the reading is found, the kanji code corresponding to the reading is stored in the display buffer 6. The display unit 7 displays the contents of the display buffer 6 "equivalent j".

Similarly, ``Soutou'' and ``Sootou.''

Even if it recognizes ``souto'', the kanji for ``equivalent'' is displayed.

Problems to be Solved by the Invention However, with the above configuration, in order to cope with the pronunciation that becomes a long vowel, it is necessary to prepare multiple readings of one kanji and register them in the independent word dictionary. This has the problem of an increase in size, ie, an increase in cost.

In view of this, an object of the present invention is to provide a Japanese text creation device that can deal with long vowel pronunciations by simply registering one type of pronunciation for one kanji.

Means for Solving the Problems The present invention provides long vowel character conversion that searches for the kana character "o" following the kana character in the "o" stage and adds "u" to the kana character "o" as a speech recognition candidate. This is a Japanese sentence creation device with a section.

Effects of the present invention With the above-described configuration, even if a place that should be recognized as "u" in writing due to long vowel pronunciation is recognized as "o", the possibility of "u" is recognized in the long vowel character converter. Because it also considers the following, Japanese sentences can be created without increasing the size of the independent word dictionary.

Embodiment FIG. 1 shows a block diagram of a Japanese sentence creation device of the present invention. In Figure 1, step 3 searches for the kana character "o" following the kana character in the "o" stage in the kana character string temporarily stored in the input buffer 2, and uses the kana character "u" as a speech recognition candidate. ” long vowel character conversion unit added to 5
o is an independent word dictionary composed of Japanese independent words or mainly composed of Japanese independent words.

FIG. 2 is a block diagram of the long vowel conversion unit 3 in an embodiment of the Japanese sentence creation device of the present invention.

In Fig. 2, 31 searches the kana character string in input buffer 2 for the kana character ``o'' that follows the ``o'' row, and searches for the ``o'' and ``o'' characters.
The binary tree creation unit 31 creates the binary tree by relating the two types of kana characters ``u'' and the one type of kana characters in the input order for other kana characters. A binary tree buffer to be created, 33 is a binary tree tracing unit that generates a string that traces the binary tree on the binary tree buffer 32 created by the binary tree creation unit 31, and 34 is a binary tree tracing unit 33. A display character determination unit that sequentially sends the kana character string candidates in the kana character string candidate buffer 35 which temporarily stores the generated kana character string, and the kana character string candidates in the ephemeral character string candidate buffer 34 to the independent word search unit 4; 4 When a kanji code corresponding to a kana character string is returned, that kanji code is output to the display buffer 6, and the kana character string sent to the independent word search unit 4 is not registered in the independent word dictionary 60. Therefore, when no kanji code is returned from the independent word search unit 4, the next kana character string in the buffer 34 for kana character string candidates is sent to the independent word search unit 4, and all kana character string candidates are independent. If the corresponding kanji code cannot be obtained even after sending it to the word search section 4, the kana character string in the input buffer 7 is sent to the display buffer 6.

The operation of the Japanese text creation device of this embodiment configured as described above will be described below.

Let us consider the case of creating the Japanese sentence ``equivalent'' using voice input. Say “
When the full-length vowel is uttered, the speech recognition unit 1 outputs "sootoo" to the full-length speech buffer 2. Then, the long vowel conversion unit 3 generates kana character string candidates through the following process.

For this explanation, the configuration of the binary tree buffer 32 is
As shown in the figure. In FIG. 3, the binary tree buffer 32'
It is expressed as i tr・6[). Each element of the binary tree buffer 32 is composed of three pieces of data. 32 & ephemeral characters indicate the connection relationship between 32b, 320 ephemeral characters, and kana characters. 32! L.

32b, each Boolean t of 320, each h tree[], k
ana.

tree['], 16ft, tr4H5[':1.
Let's express it as right.

Then, the binary tree creation unit 31 performs processing according to the flowchart shown in FIG. Note that an explanation of each variable in FIG. 4 is shown in Table 1.

Referring to Table 1 and FIG. 4, the processing of the binary tree creation unit 31 when "sootoo" is temporarily stored in the input buffer 2 will be described.

First, the length 4 of "Sootoo" is assigned to i.

31! In L, 1nbuf (41 is "o", 1nb
Since the vowel of uf[:s] ("to") is "o", proceed to Y.

In 31b, "o" and "u" are registered in tree[1] and tree(2), respectively, and the indenter 32b and gentleman 320iθ are made.

310 is p6ert, plight is "o", "
Each index 1 of traa[) that registered ``U''.
Substitute 2. When processing flows to 31& again, 1nbu
Since f[3] is "to" and not "o", the process moves to 31d. Then, "to" is registered in tree[3], and the index value 1 of tree[1], in which "o" is registered in indenter tree[3] and 1ef, is set to Kimiko tree.
[31, tres registered “u” for right
s(Substitute the index value 2 of 2:1.

Similarly, the remaining kana characters in input buffer 2 are 1nbur[
2] (rOJ), 1nbufl:1:](r
When processing is also performed for the binary tree 32, the binary tree shown in FIG. 6 is generated in the binary tree buffer 32. The binary tree tracing unit 33 traces this binary tree sequentially from the left to generate all kana character string candidates and temporarily stores them in the kana character string candidate buffer 34. That is, ■ ``Sooto'' ■ ``Sooto'' ■ ``Sooto'' ■ ``Sooto'' are temporarily stored in the kana character string candidate buffer.

The character determination section of the display section sequentially selects the independent word search section 4 from ■ to ■.
When the independent word search unit 4 returns a kanji code, the kanji code is sent to the display buffer 6. If no kanji code is returned even after sending all the kana character string candidates to the independent word search section, it is assumed that a recognition error has occurred or that the correct independent word has not been obtained, and the contents of input buffer 2 are The kana characters are sent as they are to the display buffer 6, and the kana characters are displayed on the display section 7. In the case of the above example, ■ When "Soutou" is sent to the independent word search section 4, the kanji code "equivalent" is read out from the independent word dictionary 50, so that the kanji is displayed on the display section 7.

As described above, according to this embodiment, by providing the long vowel conversion unit 6 that adds "uj" as a recognition candidate to the kana character "o" following the kana character in the "o" stage, the independent word dictionary is It is possible to correspond to long vowel pronunciation without registering the pronunciation of the long vowel notation.

As described in detail, according to the present invention, it is possible to cope with long vowel pronunciation without registering the pronunciation of the long vowel notation in the independent word dictionary, thereby increasing the memory cost for the independent word dictionary. It is possible to realize a Japanese sentence creation device that is easy to use and has high operability.
Its practical effects are significant.

[Brief explanation of drawings]

FIG. 1 is a block diagram of the Japanese text creation device of the present invention;
FIG. 2 is a block diagram of the long vowel conversion unit in the Japanese sentence creation device in an embodiment of the present invention, and FIG. 3 is a binary tree buffer in the Japanese sentence creation device in an embodiment of the present invention. FIG. 4 is a processing flowchart of the binary tree creation section of the Japanese text creation device in an embodiment of the present invention, and FIG. 5 is a data structure diagram of the Japanese text creation device in an embodiment of the present invention. FIG. 6 is an explanatory diagram showing a binary tree generated by the binary text generation section when the input speech "Too" is recognized. FIG. 6 is a configuration diagram of a conventional Japanese sentence generation device. 1...Speech recognition unit, 2...Input buffer, 3...Long vowel conversion unit, 4...
- Independent word search unit, 60゛...Independent word dictionary of the Japanese sentence creation device of the present invention, 61...Independent word dictionary of the conventional Japanese sentence creation device, 6... ...display buffer, 7...display section, 31...binary tree creation section, 32...°...binary tree buffer, 33...
. . . Binary tree tracing section, 34 . . . Kana character string candidate buffer, 35 . . . Display character determination section. Name of agent: Patent attorney Toshio Nakao and 1 other person No. 1
Figure 2 Figure 3 Figure 4 Figure 5 Figure 6

Claims (1)

[Claims] a speech recognition means for recognizing Japanese speech and outputting the recognition result as a code corresponding to kana characters; an input buffer for temporarily storing the kana character string obtained from the speech recognition means;
Find the kana character "o" that follows the kana character in the "o" stage in the character string temporarily stored in the input buffer and output the character "u".
a long vowel character conversion unit that creates a kana character string candidate to be added to the kana character “O” as a speech recognition candidate; an independent word dictionary comprising at least Japanese independent words; and the long vowel character conversion unit. an independent word dictionary search unit that searches the independent word dictionary with the kana character string candidates created by the independent word dictionary; and a display that displays the kana character string output from the voice recognition means or the kanji character searched by the independent word search unit. A Japanese sentence creation device characterized by comprising a section.