JPS63118794A - Voice synthesizer - Google Patents
Voice synthesizerInfo
- Publication number
- JPS63118794A JPS63118794A JP26599886A JP26599886A JPS63118794A JP S63118794 A JPS63118794 A JP S63118794A JP 26599886 A JP26599886 A JP 26599886A JP 26599886 A JP26599886 A JP 26599886A JP S63118794 A JPS63118794 A JP S63118794A
- Authority
- JP
- Japan
- Prior art keywords
- processing section
- section
- text
- processing
- language 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
Links
- 230000015572 biosynthetic process Effects 0.000 claims description 18
- 238000003786 synthesis reaction Methods 0.000 claims description 18
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
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】
産業上の利用分野
本発明は、任意の文章を入力して音声に変換する音声合
成装置に関するものである。DETAILED DESCRIPTION OF THE INVENTION Field of Industrial Application The present invention relates to a speech synthesis device that inputs arbitrary text and converts it into speech.
従来の技術 従来の音声合成装置では、動作は以下のようになる。Conventional technology In a conventional speech synthesizer, the operation is as follows.
操作者は、音声で出力したいテキストを音声合成装置に
入力する。入力されたテキストは記号や数字、略号等を
話言葉に変換する（例えば１２３−＞ひやくにじゅうさ
ん）。次によみがなや発音記号の入った辞書を用いて発
音記号列とアクセント位置の情報に変換する。ここまで
の処理を言語処理と呼ぶ。次にこの発音記号列とアクセ
ント位置の情報から合成器用のパラメータを生成する。The operator inputs the text that he/she wishes to output as voice into the speech synthesis device. The input text converts symbols, numbers, abbreviations, etc. into spoken words (for example, 123->Hiyakuniju-san). Next, using a dictionary containing pronunciation symbols and phonetic symbols, the information is converted into a string of phonetic symbols and accent position information. The processing up to this point is called language processing. Next, parameters for the synthesizer are generated from this phonetic symbol string and accent position information.
この処理を音韻処理と呼ぶ。次に音韻処理で得られたパ
ラメータを基に音声を合成する。This process is called phonological processing. Next, speech is synthesized based on the parameters obtained through phoneme processing.
以上のような音声合成装置の場合、言語処理部と音韻処
理部は従属的な関係にあり、言語処理−音韻処理−合成
の順で処理が行われるので、例えば言語処理部が動作し
ている間音韻処理部はその処理の終了を待っている等無
駄な待ち時間がちシ処理に時間がかかる。In the case of the above-mentioned speech synthesis device, the language processing unit and the phonology processing unit are in a subordinate relationship, and processing is performed in the order of language processing - phonology processing - synthesis, so for example, when the language processing unit is operating The interphonological processing unit wastes time waiting for the processing to be completed, and the processing takes time.
発明が解決しようとする問題点
一般に音声合成装置では言語処理部と音韻処理部は片方
が処理している間もう片方は休止しており、処理の終了
を待っている等の無駄な待ち時間があり処理に時間がか
かる。Problems to be Solved by the Invention In general, in speech synthesis devices, one of the language processing section and the phonological processing section is inactive while the other is processing, resulting in wasted waiting time such as waiting for processing to finish. Yes, processing takes time.
本発明は、係る点に鑑み処理に無駄な待ち時間の入らな
い音声合成装置を提供することを目的とする。SUMMARY OF THE INVENTION In view of the above, an object of the present invention is to provide a speech synthesis device that does not involve unnecessary waiting time in processing.
問題点を解決するための手段
上記問題点を解決するための本発明の技術的な手段を以
下に示す。Means for Solving the Problems Technical means of the present invention for solving the above problems are shown below.
キーボード等からテキストを入力するテキスト入力部と
、上記入力部に接続されて入力されたテキストを発音記
号やアクセント位置等の情報に変換する言語処理部と、
上記言語処理部に接続されて上記言語処理部の出力であ
る発音記号列やアクセント位置等の情報を一時的に蓄え
る第一のバッファメモリと、上記第一のバックアメモリ
に接続され上記言語処理部の出力である発音記号列やア
クセント位置等の情報を受取力、音声合成に必要なパラ
メータを生成し、且つ上記言語処理部と並列に動作が可
能な音韻処理部と、上記音韻処理部に接続され上記音韻
処理部で生成されたパラメータを一時的に蓄える第二の
バッファメモリと、上記第二のバックアメモリに接続さ
れ幾上記音韻処理部で生成されたパラメータから音声を
合成する音声合成部とを用いて音声合成機能を果たすも
のである。a text input section for inputting text from a keyboard or the like; a language processing section connected to the input section for converting the input text into information such as phonetic symbols and accent positions;
a first buffer memory connected to the language processing section and temporarily storing information such as phonetic symbol strings and accent positions output from the language processing section; A phonological processing section that receives information such as phonetic symbol strings and accent positions output from the phonological processing section, generates parameters necessary for speech synthesis, and can operate in parallel with the language processing section, and is connected to the phonological processing section. a second buffer memory for temporarily storing the parameters generated by the phoneme processing section; and a speech synthesis section connected to the second backup memory for synthesizing speech from the parameters generated by the phoneme processing section. It performs the speech synthesis function using the .
作 用 この技術的手段による作用は次のようになる。For production The effect of this technical means is as follows.
即ち、言語処理部はあるテキストに対して必要な処理を
施しその結果を音韻処理部に送った後直ちに次のテキス
トの処理を開始出来る。同様に音韻処理部も言語処理部
に対して並列に処理が可能であり高速な処理が実現でき
る。That is, the language processing section can immediately start processing the next text after performing necessary processing on a certain text and sending the results to the phonological processing section. Similarly, the phoneme processing section can perform processing in parallel to the language processing section, and high-speed processing can be achieved.
実施例
図は本発明の実施例における音声合成装置の一構成例を
示すものである。同図において１はテキスト入力部、２
は言語処理部、３はバッファメモリ１．４は音韻処理部
、５はバッファメモリ２．６は合成部である。The embodiment diagram shows an example of the configuration of a speech synthesis device in an embodiment of the present invention. In the figure, 1 is a text input section, 2
3 is a language processing section, 3 is a buffer memory 1.4 is a phonological processing section, and 5 is a buffer memory 2.6 is a synthesis section.
上記のように構成された本発明の実施例の音声合成装置
について、以下、その動作を説明する。The operation of the speech synthesizer according to the embodiment of the present invention configured as described above will be described below.
操作者は音声出力したいテキストを入力部１に入力する
。入力されたテキストは、言語処理部２に入力される。The operator inputs into the input section 1 the text that he/she wishes to output aloud. The input text is input to the language processing section 2.
言語処理部２は入力テキストから発音記号列やアクセン
ト情報に変換し、これらの情報をバッファメモリ１に格
納し、次のテキストの処理を始める。The language processing unit 2 converts the input text into a phonetic symbol string and accent information, stores this information in the buffer memory 1, and starts processing the next text.
音韻処理部４はバッファメモリ１の情報を合成に必要な
パラメータに変換しバッファメモリ２に格納する。この
後、再びバックアメモリ１の次の情報を処理する。合成
部６は、バックアメモリ２の中の合成器用パラメータか
ら音声を合成する。The phoneme processing section 4 converts the information in the buffer memory 1 into parameters necessary for synthesis and stores them in the buffer memory 2. After this, the next information in the backup memory 1 is processed again. The synthesis unit 6 synthesizes speech from the synthesizer parameters in the backup memory 2.
発明の詳細
な説明したように本発明によれば、言語処理部と音韻処
理部が並列に動作可能であり各部の入力待ち時間が無く
なるので高速な音声合成処理が可能になりその実用的効
果は大である。DETAILED DESCRIPTION OF THE INVENTION According to the present invention, the language processing section and the phonological processing section can operate in parallel, eliminating input waiting time for each section, making it possible to perform high-speed speech synthesis processing, and its practical effects are as follows. It's large.
図は本発明における一実施例の音声合成装置のブロック
図を示したものである。
１・・・・・・テキスト入力部、２・・・・・・言語処
理部、３・・・・・・バッファメモリ１．４・・・・・
・音韻処理部、６・・・・・・バッファメモリ２．６・
・・・・・合成部。The figure shows a block diagram of a speech synthesizer according to an embodiment of the present invention. 1...Text input section, 2...Language processing section, 3...Buffer memory 1.4...
・Phonological processing unit, 6...Buffer memory 2.6・
...Synthesis department.
Claims (1)
、上記入力部に接続されて入力されたテキストを発音記
号やアクセント位置等の情報に変換する言語処理部と、
上記言語処理部に接続されて上記言語処理部の出力であ
る発音記号列やアクセント位置等の情報を一時的に蓄え
る第一のバッファメモリと、上記第一のバッファメモリ
に接続され上記言語処理部の出力である発音記号列やア
クセント位置等の情報を受取力、音声合成に必要なパラ
メータを生成し、且つ上記言語処理部と並列に動作が可
能な音韻処理部と、上記音韻処理部に接続され上記音韻
処理部で生成されたパラメータを一時的に蓄える第二の
バッファメモリと、上記第二のバッファメモリに接続さ
れ上記音韻処理部で生成されたパラメータから音声を合
成する音声合成部とを具備したことを特徴とする音声合
成装置。a text input section for inputting text from a keyboard or the like; a language processing section connected to the input section for converting the input text into information such as phonetic symbols and accent positions;
a first buffer memory connected to the language processing section and temporarily storing information such as phonetic symbol strings and accent positions output from the language processing section; A phonological processing section that receives information such as phonetic symbol strings and accent positions output from the phonological processing section, generates parameters necessary for speech synthesis, and can operate in parallel with the language processing section, and is connected to the phonological processing section. a second buffer memory that temporarily stores the parameters generated by the phoneme processing section; and a speech synthesis section that is connected to the second buffer memory and synthesizes speech from the parameters generated by the phoneme processing section. A speech synthesis device characterized by comprising:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP26599886A JPS63118794A (en) | 1986-11-07 | 1986-11-07 | Voice synthesizer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP26599886A JPS63118794A (en) | 1986-11-07 | 1986-11-07 | Voice synthesizer |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| JPS63118794A true JPS63118794A (en) | 1988-05-23 |
Family
ID=17424946
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP26599886A Pending JPS63118794A (en) | 1986-11-07 | 1986-11-07 | Voice synthesizer |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPS63118794A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0239300U (en) * | 1988-09-08 | 1990-03-15 |
-
1986
- 1986-11-07 JP JP26599886A patent/JPS63118794A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0239300U (en) * | 1988-09-08 | 1990-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JPS62160495A (en) | Voice synthesization system | |
| JP3518898B2 (en) | Speech synthesizer | |
| JPS6223888B2 (en) | ||
| JPS63118794A (en) | Voice synthesizer | |
| JPS5972494A (en) | Rule snthesization system | |
| JPH07200554A (en) | Sentence read-aloud device | |
| JP2002123281A (en) | Speech synthesizer | |
| JPH05281984A (en) | Method and device for synthesizing speech | |
| JP2536896B2 (en) | Speech synthesizer | |
| JP2584236B2 (en) | Rule speech synthesizer | |
| KR920009961B1 (en) | Unlimited korean language synthesis method and its circuit | |
| JPS62284398A (en) | Sentence-voice conversion system | |
| JPS6361299A (en) | Sentence-voice conversion | |
| JPH0229797A (en) | Text voice converting device | |
| JPH0667685A (en) | Speech synthesizing device | |
| JP2839488B2 (en) | Speech synthesizer | |
| JPH037999A (en) | Voice output device | |
| JPH02240699A (en) | Voice synthesizer | |
| JPH0229800A (en) | Voice synthesizing device | |
| JPS58168096A (en) | Multi-language voice synthesizer | |
| JPH0313597B2 (en) | ||
| JPH05210482A (en) | Method for managing sounding dictionary | |
| JPH0285899A (en) | Voice synthesizing device | |
| JPH07140999A (en) | Device and method for voice synthesis | |
| JPH10274998A (en) | Method and device for reading document aloud |