JPS6352264A - Translation system for chinese sentence - Google Patents

Translation system for chinese sentence

Info

Publication number
JPS6352264A
JPS6352264A JP61193940A JP19394086A JPS6352264A JP S6352264 A JPS6352264 A JP S6352264A JP 61193940 A JP61193940 A JP 61193940A JP 19394086 A JP19394086 A JP 19394086A JP S6352264 A JPS6352264 A JP S6352264A
Authority
JP
Japan
Prior art keywords
chinese
japanese
file
words
information processing
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
Application number
JP61193940A
Other languages
Japanese (ja)
Inventor
Tadao Takahashi
忠雄 高橋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to JP61193940A priority Critical patent/JPS6352264A/en
Publication of JPS6352264A publication Critical patent/JPS6352264A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • G10L25/15Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being formant information

Abstract

PURPOSE:To increase the translating speed of Chinese sentences by recognizing a Chinese sentence in voices, analyzing the recognized voices to convert the Chinese words into Japanese words and correcting these converted Japanese words into correct ones in terms of the Japanese grammar. CONSTITUTION:The voice input of Chinese words into the voice coding data by a Chinese word voice recognizing device. Then the phonetic symbols and four tones are analyzed based on said voice coding data by an information processing system 2 and a standard pattern file 3. These analyzed phonetic symbols and the four tones are translated into Japanese words via the system 2 and a Chinese language dictionary file 4. Then the translated Japanese words are normalized by the system 2 and a Japanese grammar file 5. Thus a Japanese sentence is obtained.

Description

【発明の詳細な説明】 〔産業上の利用分野〕 本発明は、中国語音声入力を日本語文章へ変換および翻
訳して出力する中国語翻訳システムに関するものである
DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a Chinese translation system that converts and translates a Chinese audio input into a Japanese sentence and outputs the translated text.

(従来の技術〕 従来、この種の翻訳は、日本語文章の音声入力から英語
文章への変換および翻訳システムが開発されつつあるが
、中国語文章の音声入力から日本語文章への変換および
翻訳を行なう中国語翻訳システムはなかった。
(Prior art) Conventionally, for this type of translation, systems for converting and translating voice input of Japanese sentences into English sentences are being developed, but systems for converting and translating voice input of Chinese sentences into Japanese sentences are being developed. There was no Chinese translation system that could do this.

〔発明が解決しようとする問題点〕[Problem that the invention seeks to solve]

上述したように、中国語音声認識装置と中国語翻訳方式
とを組み合わせた情報処理システムがなかったため、中
国語文章の音声入力による中国語の翻訳ができず、中国
語の翻訳に長時間を要するという問題があった。
As mentioned above, because there was no information processing system that combined a Chinese speech recognition device and a Chinese translation method, it was not possible to translate Chinese text by voice input, and it took a long time to translate the Chinese text. There was a problem.

L問題点を解決するための手段〕 このような問題点を解決するために本発明は、中国語を
音声認識するための中国語音声認識装置と、この中国語
音声認識装置からの出力を入力し翻訳作業を行なう情報
処理システムと、この情報処理システムの出力を入力し
作成された日本語文章を出力する日本語処理装置と、中
国語の音声を解析する標準パターンファイルと、中国語
から日本語へ変換するための中国語辞書ファイルと、日
本語文を作成するための日本語文法ファイルとをシステ
ムに設けるようにしたものである。
Means for Solving Problems L] In order to solve these problems, the present invention provides a Chinese speech recognition device for recognizing Chinese speech, and an input device for inputting the output from this Chinese speech recognition device. An information processing system that performs translation work, a Japanese processing device that inputs the output of this information processing system and outputs Japanese sentences created, a standard pattern file that analyzes Chinese speech, and a The system is provided with a Chinese dictionary file for converting into words and a Japanese grammar file for creating Japanese sentences.

〔作用〕[Effect]

本発明においては、中国語翻訳を高速に行なうことがで
きる。
In the present invention, Chinese translation can be performed at high speed.

〔実施例〕〔Example〕

図は本発明に係わる中国語翻訳システムの一実施例を示
す系統図である。図において、1は中国語を音声認識す
るための中国語音声認識装置、2は中国語音声認識装置
1からの出力を入力し翻訳作業を行なう情報処理システ
ム、3は発音記号・声調(四声)・論理アドレス・漢字
の音声符号化データ等から成り中国語の音声を解析する
標準パターンファイル、4は中国語から日本語へ変換す
るための中国語辞書ファイル、5は日本語文を作成する
ための日本語文法ファイル、6は情報処理システム2の
出力を人力し作成された日本語文章を表示装置に表示す
る日本語処理装置である。
The figure is a system diagram showing an embodiment of the Chinese translation system according to the present invention. In the figure, 1 is a Chinese speech recognition device for recognizing Chinese speech, 2 is an information processing system that inputs the output from the Chinese speech recognition device 1 and performs translation work, and 3 is a phonetic symbol/tone (four-tone )・Standard pattern file for analyzing Chinese speech consisting of logical addresses, kanji audio encoded data, etc. 4 is a Chinese dictionary file for converting from Chinese to Japanese, 5 is for creating Japanese sentences 6 is a Japanese language processing device that manually processes the output of the information processing system 2 and displays the created Japanese sentences on a display device.

まず、中国語音声認識装置1は、中国語の音声入力を音
声符号化データへ変換する。次に、情報処理システム2
と標準パターンファイル3は、上記音声符号化データか
ら、発音記号(1合音)と四声との解析を行なう。この
解析された断音と四声から、情報処理システム2と中国
語辞書ファイル4とを用いて、日本語に1訳する。次に
、翻訳された日本語を情報処理システム2と日本語文法
ファイル5とを用いて正規化法し、日本語文章を作成す
る。
First, the Chinese speech recognition device 1 converts Chinese speech input into speech encoded data. Next, information processing system 2
The standard pattern file 3 analyzes the phonetic symbols (one tone) and four tones from the audio encoded data. Based on the analyzed tones and four tones, the information processing system 2 and the Chinese dictionary file 4 are used to translate them into Japanese. Next, the translated Japanese is normalized using the information processing system 2 and the Japanese grammar file 5 to create a Japanese sentence.

なお、日本語文法ファイルを使用しての日本語の正規化
法は、例えば「情報処理VOL、26NO,10,日本
情報処理学会、昭和60年10月発行」に記載されてい
る。
The Japanese language normalization method using a Japanese grammar file is described, for example, in "Information Processing Vol. 26, No. 10, Information Processing Society of Japan, Published October 1985."

次に、本システムを使用して中国語文の音声入力から日
本語文へ変換および翻訳する具体例について説明する。
Next, a specific example of converting and translating a Chinese sentence voice input into a Japanese sentence using this system will be described.

例えば「勺了祝大家身体健康、千杯」という中国語文を
中国語音声認識装置1に単語単位に音声で話すと、標準
パターンファイル3によって 声と四声に変換される。
For example, when the Chinese sentence ``Congratulations on your health and well-being, 1,000 cups'' is spoken word by word to the Chinese speech recognition device 1, the standard pattern file 3 converts it into four tones and four tones.

まず、“カ了”と発声するとWE I 4ΔLE4に変
換され、次にWE I 4ΔLE4のf7を音と四声が
、中国語辞書ファイル4にて、日本語の“のために”と
“接続詞”とに翻訳される。以後、同じように単語単位
に発声すると表のように翻訳される。
First, when you say "KARYO", it is converted to WE I 4ΔLE4, and then the f7 of WE I 4ΔLE4 is the sound and the four tones are converted into the Japanese "for" and "conjunction" in Chinese dictionary file 4. It is translated into . From now on, if you say each word in the same way, it will be translated as shown in the table.

従って、翻訳された日本語は、「のために(接)祝す(
他動)皆さん(氏名)体く名)健康(名・形動)乾杯(
名・自動)」となる。これを日本語文法ファイル5を使
用して正規化すると、“皆さン体健康のために祝す、乾
杯。′となる。この文に日本語文法ファイル5の規則に
従って助詞を追加すると、“皆さんの体の健康のために
祝す、乾杯。”となる。この文は書き言葉であり、日本
語文法ファイル5を使用して話し言葉に変換すると、“
皆さんの健康を祝し、乾杯。”となり、この文を日本語
処理装置6に出力する。この日本語文は、日本語処理装
置6において、CRT等の表示装置に表示されたり、プ
リンタ等で打ち出されたりする。
Therefore, the translated Japanese is ``for (encounter) congratulations (for)
Passive) Everyone (name) Health (noun/adjective) Cheers (
name/automatic)". If we normalize this using Japanese Grammar File 5, it becomes ``A toast to everyone's health.'' If we add particles to this sentence according to the rules of Japanese Grammar File 5, we get `` A toast to everyone's health. ”.This sentence is a written word, and when converted into a spoken word using Japanese Grammar File 5, it becomes “
Cheers to everyone's health. ", and this sentence is output to the Japanese language processing device 6. In the Japanese language processing device 6, this Japanese sentence is displayed on a display device such as a CRT or printed out on a printer or the like.

〔発明の効果〕〔Effect of the invention〕

以上説明したように本発明は、中国語の文章を音声認識
し、認識した音声を解析し、この解析結果により中国語
を日本語へ変換し、変換された日本語を正しい文法の日
本語文とすることにより、中国語の)属音と四声をキー
ボードから入力する必要がなくなり、このキーボードか
らの入力に比較して約2.5倍〜6倍の翻訳の高速化を
図れる効果がある。
As explained above, the present invention performs speech recognition on Chinese sentences, analyzes the recognized speech, converts Chinese into Japanese based on the analysis results, and converts the converted Japanese into Japanese sentences with correct grammar. By doing so, it is no longer necessary to input the Chinese (subjective sounds) and the four tones from the keyboard, which has the effect of speeding up the translation by about 2.5 to 6 times compared to inputting from the keyboard.

【図面の簡単な説明】[Brief explanation of drawings]

図は本発明に係わる中国語翻訳システムの一実施例を示
す系統図である。 1・・・中国語音声認識装置、2・・・情報処理システ
ム、3・・・標準パターンファイル、4・・・中国語辞
書ファイル、5・・・日本語文法ファイル、6・・・日
本語処理装置。
The figure is a system diagram showing an embodiment of the Chinese translation system according to the present invention. 1... Chinese speech recognition device, 2... Information processing system, 3... Standard pattern file, 4... Chinese dictionary file, 5... Japanese grammar file, 6... Japanese Processing equipment.

Claims (1)

【特許請求の範囲】[Claims] 中国語を音声認識するための中国語音声認識装置と、こ
の中国語音声認識装置からの出力を入力し日本語への翻
訳作業を行なう情報処理システムと、この情報処理シス
テムの出力を入力し作成された日本語文章を表示装置に
表示する日本語処理装置と、中国語の音声を解析する標
準パターンファイルと、中国語から日本語へ変換するた
めの中国語辞書ファイルと、日本語文を作成するための
日本語文法ファイルとを備え、中国語の音声入力を日本
語文章へ変換することを特徴とする中国語翻訳システム
Created by inputting a Chinese speech recognition device for recognizing Chinese speech, an information processing system that inputs the output from this Chinese speech recognition device and performs translation work into Japanese, and inputs the output of this information processing system. A Japanese processing device that displays Japanese sentences on a display device, a standard pattern file that analyzes Chinese audio, a Chinese dictionary file that converts from Chinese to Japanese, and creates Japanese sentences. A Chinese translation system that is equipped with a Japanese grammar file for converting Chinese audio input into Japanese sentences.
JP61193940A 1986-08-21 1986-08-21 Translation system for chinese sentence Pending JPS6352264A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP61193940A JPS6352264A (en) 1986-08-21 1986-08-21 Translation system for chinese sentence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP61193940A JPS6352264A (en) 1986-08-21 1986-08-21 Translation system for chinese sentence

Publications (1)

Publication Number Publication Date
JPS6352264A true JPS6352264A (en) 1988-03-05

Family

ID=16316272

Family Applications (1)

Application Number Title Priority Date Filing Date
JP61193940A Pending JPS6352264A (en) 1986-08-21 1986-08-21 Translation system for chinese sentence

Country Status (1)

Country Link
JP (1) JPS6352264A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009069276A (en) * 2007-09-11 2009-04-02 National Institute Of Information & Communication Technology Speech recognition device, automatic translation device, speech recognition method, program and data structure

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009069276A (en) * 2007-09-11 2009-04-02 National Institute Of Information & Communication Technology Speech recognition device, automatic translation device, speech recognition method, program and data structure

Similar Documents

Publication Publication Date Title
US6085162A (en) Translation system and method in which words are translated by a specialized dictionary and then a general dictionary
US7124082B2 (en) Phonetic speech-to-text-to-speech system and method
US20070088547A1 (en) Phonetic speech-to-text-to-speech system and method
JPH07129594A (en) Automatic interpretation system
CN113409761B (en) Speech synthesis method, speech synthesis device, electronic device, and computer-readable storage medium
JPS6352264A (en) Translation system for chinese sentence
JP2002132282A (en) Electronic text reading aloud system
JP2000352990A (en) Foreign language voice synthesis apparatus
JP2658476B2 (en) Document Braille device
US20220189462A1 (en) Method of training a speech recognition model of an extended language by speech in a source language
JPH03196198A (en) Sound regulation synthesizer
JPS60188995A (en) Sentence enunciation
PATKAR ENGLISH TO AHIRANI LANGUAGE MODEL GENERATION USING HIDDEN MARKOV MODEL AND RECURRENT NEURAL NETWORK FOR TEXT TO SPEECH TRANSLATION
JPH04195586A (en) Machine translation device based upon chinese voice input
JP2888847B2 (en) Text-to-speech apparatus and method, and language processing apparatus and method
JPS6079400A (en) Arbitrary voice synthesization system
JPH02308194A (en) Foreign language learning device
JPH09281993A (en) Phonetic symbol forming device
JPH07160685A (en) Device for reading out sentence
JPS6235120Y2 (en)
JPS62100831A (en) Character input device
JPH10143192A (en) Method and device for character conversion and display of speech
JPS59218547A (en) Kanji input device using speech recognition
JPS6310264A (en) Chinese-japanese translation system
JPH04342297A (en) Information device