JPS61215597A - Voice synthesizer - Google Patents

Voice synthesizer

Info

Publication number
JPS61215597A
JPS61215597A JP5731285A JP5731285A JPS61215597A JP S61215597 A JPS61215597 A JP S61215597A JP 5731285 A JP5731285 A JP 5731285A JP 5731285 A JP5731285 A JP 5731285A JP S61215597 A JPS61215597 A JP S61215597A
Authority
JP
Japan
Prior art keywords
circuit
speech
intonation
speech synthesis
accent
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
JP5731285A
Other languages
Japanese (ja)
Inventor
昭男 伊藤
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 JP5731285A priority Critical patent/JPS61215597A/en
Publication of JPS61215597A publication Critical patent/JPS61215597A/en
Pending legal-status Critical Current

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) [Abstract] 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、音声合成装置特に単語を編集して文章tg声
させる場合にアクセント及び抑揚をつけることを可能に
した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, and particularly to a speech synthesis device that makes it possible to add accents and intonation when editing words and making sentences into voices. .

〔従来の技術〕[Conventional technology]

従来この種の音声合成装置では、単語の音声データを格
納しておく記憶素子(ROMtたはRAM)とその格納
されているデータから音声を合成する音声合成回路と単
語を編集して文章を発声させる制御回路から構成されて
いた。
Conventionally, this type of speech synthesis device consists of a memory element (ROM or RAM) that stores speech data of words, a speech synthesis circuit that synthesizes speech from the stored data, and a speech synthesis circuit that synthesizes speech from the stored data, and edits words to produce sentences. It consisted of a control circuit to

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

上述した従来の音声合成装置は、単語を編集して文章を
発声させる場合記憶素子に記憶されている単語を選びだ
し順次各単語を発声させることにより文章としての意味
を持たせる手法となっているので各単語が音声データを
作成した時に用いた原音と同じアクセント及び抑揚で発
声される。このため単語を編集して文章とする場合いか
に各単語が明瞭であっても文章的なまとまシ感がなくな
り不自然なものとなってしまうという欠点がありた。ま
たこれを自然な合成音にするためには音声データ記憶素
子に同一の単語に対して色々なアクセント、抑揚の音声
データを記憶しておく必要が有り記憶容量が増加すると
いう欠点があった。
In the conventional speech synthesis device described above, when editing words and uttering a sentence, the method is to select the words stored in the memory element and utter each word in sequence to give it meaning as a sentence. Therefore, each word is pronounced with the same accent and intonation as the original sound used when creating the audio data. For this reason, when words are edited to form a sentence, no matter how clear each word is, there is a disadvantage that the sentence loses its sense of cohesion and becomes unnatural. Furthermore, in order to create a natural synthesized sound, it is necessary to store audio data of various accents and intonations for the same word in the audio data storage element, which has the disadvantage of increasing storage capacity.

〔問題点を解決するための手段〕[Means for solving problems]

本発明の音声合成装置は、波形符号化方式またはパラメ
ータ合成方式の音声合成手段と、多数のアクセント及び
抑揚のパターンを記憶する手段と音声合成手段から出力
される合成音を指定されたアクセント及び抑揚で再合成
する手段と全体の動作を制御する手段を有している。
The speech synthesis device of the present invention includes a speech synthesis means using a waveform encoding method or a parameter synthesis method, a means for storing a large number of accent and intonation patterns, and a synthesized sound output from the speech synthesis means using a specified accent and intonation. It has means for resynthesizing and means for controlling the overall operation.

〔実施例〕〔Example〕

次に本発明の実施例について図面を参照して説明する。 Next, embodiments of the present invention will be described with reference to the drawings.

図においである方式の音声合成回路1と音声データ記憶
素子2とアクセントのパターンを格納するアクセントパ
ターン記憶回路3と抑揚のパターンを格納する抑揚パタ
ーン記憶回路4と選択されたアクセント及び抑揚のパタ
ーンから合成音を再合成する再合成回路5と音声が実際
に出力される音声出力端子6と全体の動作を制御する制
御回路7t−含む。音声合成回路1は音声データ記憶素
子2よシ音声情報を引きだし合成音声を再合成回路5に
対し出力する。再合成回路5はアクセントパターン記憶
回路3と抑揚パターン記憶回路4よυアクセント及び抑
揚のパターンを引きだしその情報に基づき音声合成回路
1から入力された合成音にアクセント及び抑揚をつけ再
合成した後音声出力端子6に音声を出力する。制御回路
7は単語を編集する機能を持ち音声合成回路に単語を順
次発生させると同時に現在発生している文章のアクセン
ト及び抑揚のパターンを選択しその情報を再合成回路5
に送る機能を有する。
The figure shows a speech synthesis circuit 1, a speech data storage element 2, an accent pattern storage circuit 3 for storing accent patterns, an intonation pattern storage circuit 4 for storing intonation patterns, and selected accent and intonation patterns. It includes a resynthesizing circuit 5 for resynthesizing synthesized sounds, an audio output terminal 6 to which audio is actually output, and a control circuit 7t for controlling the overall operation. The speech synthesis circuit 1 extracts speech information from the speech data storage element 2 and outputs synthesized speech to the resynthesis circuit 5. The resynthesis circuit 5 extracts the υ accent and intonation patterns from the accent pattern storage circuit 3 and the intonation pattern storage circuit 4, adds accents and intonation to the synthesized sound input from the speech synthesis circuit 1 based on that information, and resynthesizes the resulting speech. Audio is output to the output terminal 6. The control circuit 7 has a function of editing words, and at the same time causes the speech synthesis circuit to sequentially generate words, it selects the accent and intonation pattern of the currently generated sentence, and the information is sent to the resynthesis circuit 5.
It has the function to send to.

〔発明の効果〕〔Effect of the invention〕

以上説明したように従来の単語を編集する機能を持った
音声合成装置にアクセントと抑揚をつけることができる
再合成回路を付加したことによシ自然な文章を発声でき
る効果がある。
As explained above, by adding a resynthesis circuit that can add accents and intonation to a conventional speech synthesizer that has the function of editing words, it is possible to produce natural sentences.

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

図は本発明の一実施例のブロック図である。 1・・・・・・音声合成回路、2・・・・・・音声デー
タ記憶素子、3・・・・・・アクセントパターン記憶回
路、4・・・・・・抑揚パターン記憶回路、5・・・・
・・再合成回路、6・・・・・・音声出力端子、7・・
・・・・制御回路。
The figure is a block diagram of one embodiment of the present invention. 1... Voice synthesis circuit, 2... Voice data storage element, 3... Accent pattern memory circuit, 4... Intonation pattern memory circuit, 5...・・・
...Resynthesis circuit, 6...Audio output terminal, 7...
...control circuit.

Claims (1)

【特許請求の範囲】[Claims] 波形符号化方式またはパラメータ合成方式で単語の編集
をする音声合成手段と、文章のアクセント及び抑揚を記
憶する記憶手段とを備えるとともに合成音を指定された
アクセント及び抑揚で再合成する手段を有する音声合成
装置。
A voice comprising a speech synthesis means for editing words using a waveform encoding method or a parameter synthesis method, a storage means for storing accents and intonations of sentences, and a means for resynthesizing synthesized sounds with specified accents and intonations. Synthesizer.
JP5731285A 1985-03-20 1985-03-20 Voice synthesizer Pending JPS61215597A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP5731285A JPS61215597A (en) 1985-03-20 1985-03-20 Voice synthesizer

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP5731285A JPS61215597A (en) 1985-03-20 1985-03-20 Voice synthesizer

Publications (1)

Publication Number Publication Date
JPS61215597A true JPS61215597A (en) 1986-09-25

Family

ID=13052044

Family Applications (1)

Application Number Title Priority Date Filing Date
JP5731285A Pending JPS61215597A (en) 1985-03-20 1985-03-20 Voice synthesizer

Country Status (1)

Country Link
JP (1) JPS61215597A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6449100A (en) * 1987-08-20 1989-02-23 Matsushita Electric Ind Co Ltd Voice processor

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6449100A (en) * 1987-08-20 1989-02-23 Matsushita Electric Ind Co Ltd Voice processor

Similar Documents

Publication Publication Date Title
KR100591655B1 (en) Voice synthesis method, voice synthesis apparatus, and computer readable medium
JPS62160495A (en) Voice synthesization system
JP3518898B2 (en) Speech synthesizer
JP3617603B2 (en) Audio information encoding method and generation method thereof
JPS6073589A (en) Voice synthesization system
JPS61215597A (en) Voice synthesizer
JP2894447B2 (en) Speech synthesizer using complex speech units
JPH08248993A (en) Controlling method of phoneme time length
JPH0642158B2 (en) Speech synthesizer
JP2577372B2 (en) Speech synthesis apparatus and method
JP2573586B2 (en) Rule-based speech synthesizer
JP2573585B2 (en) Speech spectrum pattern generator
JP3310217B2 (en) Speech synthesis method and apparatus
JP2844588B2 (en) Waveform editing type speech synthesizer
JP3515268B2 (en) Speech synthesizer
JPS60225198A (en) Voice synthesizer by rule
JPS6146997A (en) Voice reproduction system
JPS6325700A (en) Long vowel connection
JPH04243299A (en) Voice output device
JPH03160500A (en) Speech synthesizer
JPH0679231B2 (en) Speech synthesizer
JPS5897093A (en) Synthesization of voice
JPS63131195A (en) Voice synthesizer
JPS63110500A (en) Voice time length data generator
JPS63208099A (en) Voice synthesizer