JPS6311696B2 - - Google Patents
Info
- Publication number
- JPS6311696B2 JPS6311696B2 JP57079598A JP7959882A JPS6311696B2 JP S6311696 B2 JPS6311696 B2 JP S6311696B2 JP 57079598 A JP57079598 A JP 57079598A JP 7959882 A JP7959882 A JP 7959882A JP S6311696 B2 JPS6311696 B2 JP S6311696B2
- Authority
- JP
- Japan
- Prior art keywords
- syllable
- candidates
- phrase
- candidate
- voice input
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Document Processing Apparatus (AREA)
Description
【発明の詳細な説明】
本発明は音節単位に発声した音声入力に基いて
１文節１ブロツクとして言語的処理を行ない、文
書を作成するようにした日本語文書処理装置に係
り、音節単位の認識の不確実さを１文節に対応し
た音節候補と文節候補をそれぞれ表示させること
により補正し、もつて文書作成の効率化を図つた
ものである。DETAILED DESCRIPTION OF THE INVENTION The present invention relates to a Japanese document processing device that creates a document by performing linguistic processing on each phrase as one block based on voice input uttered in units of syllables. The uncertainty of the text is corrected by displaying syllable candidates and phrase candidates corresponding to one phrase, thereby improving the efficiency of document creation.
以下本発明を説明すると、第１図は本発明に係
る音声入力式日本語文書処理装置のブロツクダイ
アグラムであり、第２図は本発明の要旨に係る処
理フローを説明するためのフローチヤートを示し
ている。第１図によれば１は音節認識部であり、
マイクロフオン等を介して入力された音声に対し
110音節の標準パターンとマツチングを取り、１
文節を単位として音節候補列を出力する。例え
ば、「おんせい（音声）」という入力に対して、
「お」については“お”と“ほ”が候補に上り、
「せ」については“せ”と“え”，「い」について
は“い”と“き”が候補に上つたとした時、その
類似度から１おんせき，２おんせい，３ほんせ
い，４おんえい，５ほんせき，という順序で候補
が得られる。この候補の数は処理速度の実用的な
値から適当な数に定める。 To explain the present invention below, FIG. 1 is a block diagram of a voice input type Japanese document processing device according to the present invention, and FIG. 2 is a flowchart for explaining the processing flow according to the gist of the present invention. ing. According to FIG. 1, 1 is a syllable recognition unit,
For audio input via a microphone etc.
Matching with the standard pattern of 110 syllables, 1
Outputs a syllable candidate string in units of phrases. For example, for the input "Onsei (voice)",
Regarding “o”, “o” and “ho” are candidates.
Assuming that "se" and "e" are candidates for "se", and "i" and "ki" are candidates for "i", based on their similarity, 1 onseki, 2 onsei, 3 honsei, Candidates are obtained in the order of 4 on-ei, 5 on-ei, and so on. The number of candidates is determined to be an appropriate number based on a practical value of processing speed.
これらの音節候補はコントローラ２を介して音
節候補メモリ３に転送され、ここに一時記憶され
る。このコントローラ２は第２図の処理フローを
制御する手段であり、各装置が接続される。音声
入力後その処理フローに従いキーボード６（第３
図に平面図を示す。）に配列された変換／次候補
キー６ａを操作するとコントローラ２により先の
音節認識で得られた音節候補メモリーに記憶され
た音節候補例について辞書５とのマツチングを取
る。これは単なる単語としてのマツチングではな
く、接頭，接尾，語尾変化，助詞等の接続を含め
た処理により文法的に合致したものを選び出すよ
うになつている。また、この処理において各音節
候補列に合致する漢字候補（複数の場合もある。）
も選ぶ。即ち、
１ おんせき ×
２ おんせい 〇 音声
３ ほんせい 〇 本性，本姓
４ おんえい ×
５ ほんせき 〇 本籍
このように、辞書照合により文法的に正しいと
された音節候補２，３，５およびその音節候補に
対する漢字変換を行なつた（漢字のない場合もあ
る。）文節候補はそれぞれメモリ３，４に一時記
憶され表示装置７で、例えば第４図に示す如く音
節候補が上段，対応の文節候補が下段に表示され
る。ここで、候補が複数個ある場合にはまず第１
候補を表示する。この順序づけは、音節候補につ
いては音節認識における類似度（組合せを考慮し
て）によつてもよいが、自立語の最も長いものか
ら（使用頻度による）とか、最も近い時点で使わ
れた文節を何個か記憶しておき、その中に含まれ
るものを最優先とする方法もある。文節候補につ
いては最後の方式を合せた優先方法を採用してい
る。 These syllable candidates are transferred to the syllable candidate memory 3 via the controller 2 and temporarily stored there. This controller 2 is means for controlling the processing flow shown in FIG. 2, and is connected to each device. After voice input, follow the processing flow on the keyboard 6 (3rd
The plan view is shown in the figure. ), the controller 2 matches the syllable candidate examples stored in the syllable candidate memory obtained in the previous syllable recognition with the dictionary 5. This does not simply match words, but uses processing that includes prefixes, suffixes, inflections, particle connections, etc. to select grammatically matching words. In addition, in this process, kanji candidates (there may be more than one) that match each syllable candidate string.
Also choose. That is, 1 Onseki × 2 Onsei 〇 Voice 3 Honsei 〇 Honseki, real family name 4 Onei × 5 Honseki 〇 Domicile In this way, syllable candidates 2, 3, and 5 that were determined to be grammatically correct by dictionary comparison and their The phrase candidates for which kanji conversion has been performed for the syllable candidates (in some cases, there are no kanji) are temporarily stored in the memories 3 and 4, respectively, and displayed on the display device 7. For example, as shown in FIG. Candidates are displayed at the bottom. Here, if there are multiple candidates, first
Show suggestions. This ordering may be based on the similarity in syllable recognition (taking into account combinations) for syllable candidates, but it may also be based on the longest independent word (based on frequency of use), or the most recently used phrase. There is also a method of memorizing several items and giving top priority to those included in them. For phrase candidates, a priority method that combines the last method is used.
また、第４図の表示例でも示しているように、
音節候補，文節候補とも前に数字を付し候補数を
表わしている。その場合、音節認識の結果に適当
な候補がない時には数字は“０”として第１認識
結果を音節候補として表示する。例えば第１候補
が“おんせき”で他の候補も全て辞書照合により
不適当とされた場合。 Also, as shown in the display example in Figure 4,
Both syllable candidates and bunsetsu candidates are preceded by numbers to indicate the number of candidates. In this case, if there are no suitable candidates in the syllable recognition results, the number is set to "0" and the first recognition result is displayed as the syllable candidate. For example, if the first candidate is "onseki" and all other candidates are determined to be inappropriate by dictionary comparison.
このように辞書照合によつて表示された音節候
補・文節候補がともに所期の入力しようとしたも
のであれば、処理フローは確定キーの操作とな
り、そのキー操作によつて１文節処理が終了とな
る。しかし、表示された第１候補が意図したもの
でない場合、例えば「おんせい」の例をとれば、
その音節候補の第１位として“ほんせい”が表示
された時変換／次候補キーを操作し、音節次候補
を音節候補メモリ３から呼び出し表示させ、この
操作を“おんせい”が表示されるまで繰り返し、
“おんせい”が表示された時点で確定キーを操作
する。また「ほんせい（本姓）」を入力しようと
した場合、＜音節候補＞３ほんせい＜文節候補＞
２本性，と表示された時には、次の処理フローと
して文節次候補キーの操作が必要であり、該キー
操作により文節候補メモリ４から次候補の“本
姓”が呼び出され表示が＜文節候補＞１本姓と切
換わる。数字が“１”の時は次候補がないことを
示すもので、もう一度文節次候補キー６ｃを操作
するとは表示が元に戻り、＜文節候補＞２本性と
なる。 If both the syllable candidates and bunsetsu candidates displayed by the dictionary check are the ones you intended to input, the processing flow will be the operation of the confirm key, and one bunsetsu processing will be completed by that key operation. becomes. However, if the first candidate displayed is not the one you intended, for example, if we take the example of "Onsei",
When "honsei" is displayed as the first syllable candidate, operate the conversion/next candidate key to call up and display the next syllable candidate from syllable candidate memory 3, and when this operation is performed, "honsei" will be displayed. Repeat until
Operate the confirmation key when "ONSEI" is displayed. Also, if you try to enter "honsei (real name)", <syllable candidate> 3 honsei <phrase candidate>
When ``Dual nature'' is displayed, the next processing flow requires operation of the phrase next candidate key, which calls up the next candidate "real name" from the phrase candidate memory 4, and the display changes to <Phrase candidate>1. Switch to real surname. When the number is "1", it indicates that there is no next candidate, and when the phrase next candidate key 6c is operated again, the display returns to the original, and the phrase becomes dual.
然しながら、もし、音節候補中に所期の入力す
べきものがない時は文節取消キー６ｄを操作して
コントローラ２に処理フローのやり直しを指示
し、再度最初から音声入力させるか、あるいは修
正キー６ｅを操作後カーソルキー６ｆとかなキー
６ｇとを適宜操作して音節候補を所望のものに修
正する。そして、変換／次候補キー６ａを操作す
ると処理フローは辞書照合に入り、正しい音節が
選択された状態で音節候補および対応の文節候補
が表示される。 However, if there is no desired syllable to be input among the syllable candidates, operate the phrase cancel key 6d to instruct the controller 2 to restart the processing flow and input the voice again from the beginning, or press the correction key 6e. After the operation, the cursor key 6f and kana key 6g are operated as appropriate to modify the syllable candidates to desired ones. Then, when the conversion/next candidate key 6a is operated, the processing flow enters dictionary matching, and syllable candidates and corresponding phrase candidates are displayed with the correct syllable selected.
以上のように、本発明の音声入力式日本語文書
処理装置によれば、音節単位に発声した音声入力
を認識し、１文節を１ブロツクとして辞書照合処
理し、類似度から音節候補列を得、音節候補に対
応した文節候補を音節候補と並列表示させるよう
にしたものであるから、音節候補列を認識するこ
とで音節単位での認識の不確実さを補正すること
ができ、しかも文書として入力したい音節候補お
よび文節候補の判別が迅速に行なえる。 As described above, according to the voice input type Japanese document processing device of the present invention, voice input uttered in units of syllables is recognized, one phrase is treated as one block, and dictionary matching processing is performed to obtain a string of syllable candidates based on similarity. , the phrase candidates corresponding to the syllable candidates are displayed in parallel with the syllable candidates, so by recognizing the syllable candidate string, it is possible to correct the uncertainty of recognition in syllable units. Syllable candidates and phrase candidates to be input can be quickly determined.
第１図は本発明に係る音声入力式日本語文書処
理装置のブロツク図、第２図はその処理フローを
説明するフローチヤート、第３図はキーボードの
平面図、第４図は表示例を示す表示説明図であ
る。
１…音節認識部、２…コントローラ、３…音節
候補メモリ、４…文節候補メモリ、５…辞書、６
…キーボード、７…表示装置。
Fig. 1 is a block diagram of the voice input type Japanese document processing device according to the present invention, Fig. 2 is a flowchart explaining its processing flow, Fig. 3 is a plan view of the keyboard, and Fig. 4 shows an example of display. It is a display explanatory diagram. DESCRIPTION OF SYMBOLS 1...Syllable recognition unit, 2...Controller, 3...Syllable candidate memory, 4...Passage candidate memory, 5...Dictionary, 6
...Keyboard, 7...Display device.
Claims (1)
節１ブロツクとして認識結果を音節候補とそれに
対応した文節候補とにより表示する手段を備えた
ことを特徴とする音声入力式日本語文書処理装
置。 ２ 上記手段は音節単位に発声した音声入力を認
識し、１文節１ブロツクとして認識結果を音節候
補とそれに対応した文節候補とにより表示し、且
つ該表示内容を次候補の呼出し指示毎に切替表示
をするように構成したことを特徴とする特許請求
の範囲第１項記載の音声入力式日本語文書処理装
置。[Scope of Claims] 1. A voice input method characterized by comprising a means for recognizing voice input uttered in units of syllables and displaying the recognition results as syllable candidates and corresponding phrase candidates as one phrase and one block. Japanese document processing device. 2 The above means recognizes voice input uttered in units of syllables, displays the recognition result as a syllable candidate and a corresponding phrase candidate, with each phrase as one block, and switches and displays the display contents each time the next candidate is called. A voice input type Japanese document processing device according to claim 1, characterized in that the device is configured to perform the following.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP57079598A JPS58195955A (en) | 1982-05-11 | 1982-05-11 | Japanese language document processor of voice inputting system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP57079598A JPS58195955A (en) | 1982-05-11 | 1982-05-11 | Japanese language document processor of voice inputting system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPS58195955A JPS58195955A (en) | 1983-11-15 |
| JPS6311696B2 true JPS6311696B2 (en) | 1988-03-15 |
Family
ID=13694433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP57079598A Granted JPS58195955A (en) | 1982-05-11 | 1982-05-11 | Japanese language document processor of voice inputting system |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPS58195955A (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6121526A (en) * | 1984-07-10 | 1986-01-30 | Nippon Signal Co Ltd:The | Voice recognition input device |
| JP2708771B2 (en) * | 1988-04-15 | 1998-02-04 | 富士通株式会社 | Voice recognition method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS5396703A (en) * | 1977-02-04 | 1978-08-24 | Fujitsu Ltd | Voice input device |
| JPS53147405A (en) * | 1977-05-27 | 1978-12-22 | Fujitsu Ltd | Audio input unit |
| JPS562041A (en) * | 1979-06-20 | 1981-01-10 | Fujitsu Ltd | Audio input system |
| JPS56162142A (en) * | 1980-05-19 | 1981-12-12 | Nippon Telegr & Teleph Corp <Ntt> | Character input device of voice input and display selection type |
-
1982
- 1982-05-11 JP JP57079598A patent/JPS58195955A/en active Granted
Also Published As
| Publication number | Publication date |
|---|---|
| JPS58195955A (en) | 1983-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JPS58132800A (en) | Voice responder | |
| JPS6311696B2 (en) | ||
| JPS6049932B2 (en) | Japanese information processing method | |
| JPS5821287B2 (en) | Kana-Kanji conversion device | |
| JPS634206B2 (en) | ||
| JPH033260B2 (en) | ||
| JP3377684B2 (en) | Search device by voice recognition | |
| US6327560B1 (en) | Chinese character conversion apparatus with no need to input tone symbols | |
| JPH10124085A (en) | Voice recognition device and recognition method | |
| JPS62117060A (en) | Character/voice input conversion system | |
| JPS61122781A (en) | Speech word processor | |
| JPH03217900A (en) | Text voice synthesizing device | |
| JPS5818730A (en) | character processing device | |
| KR100305446B1 (en) | Voice data base building method | |
| KR20040008546A (en) | revision method of continuation voice recognition system | |
| JP4797307B2 (en) | Speech recognition apparatus and speech recognition method | |
| JPS6211732B2 (en) | ||
| JPH0319005Y2 (en) | ||
| JPH01191199A (en) | Voice input device | |
| JPS5864548A (en) | Japanese voice processing system | |
| JPS58186836A (en) | Voice input data processor | |
| JP2001282287A (en) | Voice recognition device | |
| MATSUOKA et al. | Spoken word recognition system for unlimited adult male speakers | |
| JPH0314359B2 (en) | ||
| JPS63259686A (en) | voice input device |