JPS58108594A - Re-registration of voice input - Google Patents
Re-registration of voice inputInfo
- Publication number
- JPS58108594A JPS58108594A JP56208705A JP20870581A JPS58108594A JP S58108594 A JPS58108594 A JP S58108594A JP 56208705 A JP56208705 A JP 56208705A JP 20870581 A JP20870581 A JP 20870581A JP S58108594 A JPS58108594 A JP S58108594A
- Authority
- JP
- Japan
- Prior art keywords
- voice
- voice input
- registration
- input
- registered
- 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.)
- Pending
Links
Abstract
(57)【要約】本公報は電子出願前の出願データであるた
め要約のデータは記録されません。(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.
Description
【発明の詳細な説明】
α）発明の技術分野
本発明は音声入力装置のディスプレイ表示装置に表示さ
れる類似度順の文字を登録するに際し同時に行うようＫ
した音声入力再登録方法に関するものである、
（２）技術の背景
近年バーツナμコンピュータが各企業事務所に採用され
、その利用度はめざましいものである、この利用度は特
定のオペレータから一般事務員にまで拡大する方向をと
っているう従ってこの現象が進行すればするほど操作は
何人でも出来るようにせざるを得なくなり、音声を利用
して情報を入力するということが行われている。この目
的のために音声入力装置が用いられるまでに至っている
。Detailed Description of the Invention α) Technical Field of the Invention The present invention provides a method for simultaneously registering characters in order of similarity displayed on a display device of a voice input device.
(2) Technical background In recent years, Vertuna μ computers have been adopted in corporate offices, and their usage is remarkable.This usage ranges from specific operators to general office workers. As this phenomenon progresses, it becomes necessary to allow any number of people to operate it, and information is input using voice. Voice input devices have come to be used for this purpose.
音声入力装置は取扱者の音声を登録しておき、入力する
音声と比較して近似せるものを音声信号とするといった
方法を採用しているのが一般である、従って誤認識の少
ない音声登録方法が要望されている、
（８）従来技術と問題点
従来音声入力装置に廟いられる音声登録データは一語即
ち一文字分互に登録されるのが一般である。従って習熟
度の高いオペレータが音声再登録を行っても文字自体に
非常に類似度の高いものは登録上区別するのに困難であ
り、その分誤認織となり作業性を阻害するといった欠点
があった。The voice input device generally registers the user's voice, compares it with the input voice, and uses a voice signal that approximates it.Therefore, this voice registration method has fewer misrecognitions. (8) Prior Art and Problems The voice registration data stored in conventional voice input devices is generally registered one word, that is, one character. Therefore, even if a highly skilled operator re-registers the voice, it is difficult to distinguish between characters that are very similar in character during registration, resulting in misidentification and hindering work efficiency. .
（４）発明の目的
本発明は上記従来の欠点に鑑み、１Ｉｌｉ！認識の少な
い音声入ノー録方法を提供することを目的とするもので
ある。(4) Purpose of the Invention The present invention has been made in view of the above-mentioned drawbacks of the conventional art. The purpose of this invention is to provide a voice input/no recording method that requires less recognition.
（５）発明の構成
そしてこの目的は本発明によれば音声登録データを再作
成するに際し類似度の高い文字を同時に再登録するよう
Ｋするととくよって達成されろう（６）発明の実施例
以下本発明の実施例を図面によって詳述する。(5) Structure of the invention This object is achieved by, according to the present invention, re-registering characters with a high degree of similarity at the same time when re-creating voice registration data. Embodiments of the invention will be described in detail with reference to the drawings.
第１図は本発明による音−人メ５録方法を示すブロック
図であるつ
同図において、ｌはマイク、２は音声入力部、８は音声
パラメータ抽呂部、４はＤＰマツチング部、６は音声登
録部、６は順位決定部、７はＣＰＵ８はディスプレイ表
示装置をそれぞれ示す、マイクｌより入力された音声は
音声入力部２にて増幅され〜勺変換を行われ音声パラメ
ータ抽出部８に入力されろう音声バフメータ抽出部８は
音声パラメータをＤＰマツチング部鳴に送出する。一方
音声登録部６に予め格納され九音声登録データもＤＰ−
ｔツチング部４に入力され、ＤＰマツチング部６が類似
度検定をして順位決定部６に入力する。FIG. 1 is a block diagram showing a sound-to-person recording method according to the present invention. In the figure, 1 is a microphone, 2 is an audio input section, 8 is an audio parameter extraction section, 4 is a DP matching section, and 6 6 is a voice registration unit, 6 is a ranking determination unit, and 7 is a CPU 8 is a display device.The voice input from the microphone 1 is amplified by the voice input unit 2, subjected to amplification conversion, and sent to the voice parameter extraction unit 8. The input audio buff meter extraction section 8 sends the audio parameters to the DP matching section. On the other hand, the nine voice registration data stored in advance in the voice registration section 6 are also DP-
The data is input to the matching section 4, the DP matching section 6 performs a similarity test, and the result is input to the ranking determining section 6.
順位決定結果に基づいてＣＰＵ７はその順序をディスプ
レイ表示装置８に表示する。その表示状態は第２図（ａ
）に示すようになっている。即ち１Ａ′という音声入力
を入力し認識後の状態は第一候補文字として例えばＡ′
、第二候補文字としてＡ、第三候補文字としてＮ、第四
候補文字としてＡ等のように表示される。本発明による
と以上のように表示された場合″Ａ′を再登録する場合
に同時にＡ′。Based on the ranking determination result, the CPU 7 displays the order on the display device 8. The display state is shown in Figure 2 (a
) as shown. In other words, the voice input 1A' is input, and the state after recognition is, for example, A' as the first candidate character.
, A as the second candidate character, N as the third candidate character, A as the fourth candidate character, etc. According to the present invention, in the case where "A" is displayed as described above, when "A" is re-registered, A' is displayed at the same time.
Ａ′、 Ａ″″も再登録するのである。勿論かくするこ
とにより音声入力装置はＡ、に、 Ａ’、 Ｘ’″の紛
わしい文字の区別を行い次回に１Ａ′を音声入力すると
第２図（′ｂ）に示すように表示されることとなる、以
上は１Ａ′について述べたが勿論瞑認識を発生する文字
は何であっても差支えない、
（７）発明の効果
以上、詳細に説明したように、本発明の音声入ノ薔録方
法によると予め誤認識を発生し易い文字を区別して登録
が行われ誤認識の少ない音声入力の登録となり音声入力
装置運用上の効率向上上効果大なるもつであるうA' and A'''' are also re-registered. Of course, by doing this, the voice input device distinguishes between the confusing characters A, A', and X''', and the next time you input 1A' by voice, it will be displayed as shown in Figure 2 ('b). (7) Effects of the Invention As explained in detail above, although the above description has been made regarding 1A', any character that generates meditative recognition may be used. According to this method, characters that are likely to be misrecognized are distinguished in advance and registered, and voice input with fewer misrecognitions is registered, which is highly effective in improving the efficiency of voice input device operation.
プリッタ図、第２図は本発明のディスプレイ表示装置の
表示状態を示す模式図である。
図面において、６は音声登録部、８はディスプレイ表示
装置をそれぞれ示す、
第１図
（Ｑ） ｔｂ）The printer diagram and FIG. 2 are schematic diagrams showing the display state of the display device of the present invention. In the drawings, 6 indicates a voice registration unit, and 8 indicates a display device, Fig. 1 (Q) tb)
Claims (1)
し、その類似度１［Ｋ従ってディスプレイ表示装置に文
学を表示する音声入力装置において、前記音声登録デー
タを再作成するに際し前記類似度の高い文字を同時に再
登録するようにしたことを特徴とする音声入力再登録方
法。The voice is recognized by comparing voice registration data and voice input data, and the degree of similarity thereof is 1 [K. Therefore, in a voice input device that displays literature on a display device, when recreating the voice registration data, the degree of similarity is 1 [K]. A voice input re-registration method characterized in that characters are re-registered at the same time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP56208705A JPS58108594A (en) | 1981-12-22 | 1981-12-22 | Re-registration of voice input |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP56208705A JPS58108594A (en) | 1981-12-22 | 1981-12-22 | Re-registration of voice input |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| JPS58108594A true JPS58108594A (en) | 1983-06-28 |
Family
ID=16560707
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP56208705A Pending JPS58108594A (en) | 1981-12-22 | 1981-12-22 | Re-registration of voice input |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPS58108594A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH01206398A (en) * | 1988-02-12 | 1989-08-18 | Fujitsu Ltd | Voice recognizing device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS5396703A (en) * | 1977-02-04 | 1978-08-24 | Fujitsu Ltd | Voice input device |
| JPS5614381A (en) * | 1979-07-13 | 1981-02-12 | Nec Corp | Pattern recognizing system |
| JPS56156900A (en) * | 1980-05-09 | 1981-12-03 | Tokyo Shibaura Electric Co | Voice recognizing device |
-
1981
- 1981-12-22 JP JP56208705A patent/JPS58108594A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS5396703A (en) * | 1977-02-04 | 1978-08-24 | Fujitsu Ltd | Voice input device |
| JPS5614381A (en) * | 1979-07-13 | 1981-02-12 | Nec Corp | Pattern recognizing system |
| JPS56156900A (en) * | 1980-05-09 | 1981-12-03 | Tokyo Shibaura Electric Co | Voice recognizing device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH01206398A (en) * | 1988-02-12 | 1989-08-18 | Fujitsu Ltd | Voice recognizing device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104078044B (en) | The method and apparatus of mobile terminal and recording search thereof | |
| US20070016419A1 (en) | Selective security masking within recorded speech utilizing speech recognition techniques | |
| EP0085209A1 (en) | Audio response terminal for use with data processing systems | |
| JPS59161786A (en) | Recognition of hand written character | |
| CN109660936A (en) | A kind of face and mobile device identification number mapping method, system and readable storage medium storing program for executing | |
| JPS58108594A (en) | Re-registration of voice input | |
| JP3678360B2 (en) | Kanji character string specifying apparatus and method using voice input | |
| KR100513038B1 (en) | Storing Method of Audible Data in Enhanced Multi-Channel Automatic Speech Recognition System | |
| WO2016197755A1 (en) | Audio data processing method and terminal | |
| JPS58108593A (en) | Registration of voice | |
| JPS59170895A (en) | Monosyllable inputting system | |
| JPS58108596A (en) | Voice registration system | |
| JPS60205594A (en) | Recognition results display system | |
| JPS62173496A (en) | Reference pattern registering circuit | |
| JPS60662U (en) | character recognition device | |
| CN110990535A (en) | Method for recording meeting based on dot matrix paper pen technology | |
| JPS5968792A (en) | Voice recognition equipment | |
| JPS62221254A (en) | Retrieval device for telephone ic card talk-available time | |
| JPS5814284A (en) | On-line character collecting system | |
| JPS6086686A (en) | Character recognizing device | |
| JPS59219798A (en) | Voice recognition equipment | |
| JPS6073697A (en) | Preparation of phoneme dictionary | |
| JPS58111097A (en) | Voice recognition system | |
| JPS608897A (en) | Voice recognition equipment | |
| JPS595294A (en) | Voice recognition equipment |