[go: up one dir, main page]

KR960018879A - Synthesis method of voiced and unvoiced consonants of Korean synthesizer - Google Patents

Synthesis method of voiced and unvoiced consonants of Korean synthesizer Download PDF

Info

Publication number
KR960018879A
KR960018879A KR1019940029839A KR19940029839A KR960018879A KR 960018879 A KR960018879 A KR 960018879A KR 1019940029839 A KR1019940029839 A KR 1019940029839A KR 19940029839 A KR19940029839 A KR 19940029839A KR 960018879 A KR960018879 A KR 960018879A
Authority
KR
South Korea
Prior art keywords
consonant
vowel
korean
voiced
unvoiced
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.)
Withdrawn
Application number
KR1019940029839A
Other languages
Korean (ko)
Inventor
이병수
Original Assignee
이헌조
엘지전자 주식회사
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 이헌조, 엘지전자 주식회사 filed Critical 이헌조
Priority to KR1019940029839A priority Critical patent/KR960018879A/en
Publication of KR960018879A publication Critical patent/KR960018879A/en
Withdrawn legal-status Critical Current

Links

Landscapes

  • Document Processing Apparatus (AREA)

Abstract

본 발명은 켑스트럼 방법(Cepstrum Method)에 의한 스펙트럼 엔벨로프로부터 얻어진 한국어 기본 데이타의 시메트릭 파형을 가지고 한국어를 합성하는 한국어 합성기술에 관한 것으로 자음을 중심으로 모음의 안정구간에서 자른 한국어의 기본 데이타를 켑스트럼 방법으로 분석하여 스펙트럼 엔벨로프로부터 얻어진 시메트릭파형으로 한국어를 합성하는 한국어 합성방법에 있어서, 상기 기본 데이타는 자음+모음(초성), 단모음+자음(종성), 단모음+자음+모음, 단모음+유성자음+무성자음의 4가지 종류로 이루어지도록 함으로써 유성자음과 무성자음의 연속된 음절에 대해 합성에 필요한 데이타량을 크게 늘리지 않고도 자연스러운 합성음을 얻을 수 있도록 한 것이다.The present invention relates to a Korean synthesis technique for synthesizing Korean with symmetrical waveforms of Korean basic data obtained from the spectral envelope by the Cepstrum Method. In the Korean synthesis method for synthesizing Korean by the symmetric waveform obtained from the spectral envelope, the basic data is consonant + vowel (cho), single vowel + consonant (single), single vowel + consonant + vowel, It is composed of four kinds of short vowel + voiced consonant + unvoiced consonant so that natural synthesized sound can be obtained without increasing the amount of data needed for synthesis for continuous syllables of voiced and unvoiced consonants.

Description

한국어 합성장치의 유성자음과 무성자음의 합성방법Synthesis method of voiced and unvoiced consonants of Korean synthesizer

본 내용은 요부공개 건이므로 전문내용을 수록하지 않았음As this is a public information case, the full text was not included.

제3도는 일반적인 기본 데이타로부터 음성을 합성하는 방법을 설명하기 위한 도면.3 is a diagram for explaining a method of synthesizing speech from general basic data.

제4도는 본 발명에 따른 VC1C2형태의 기본 데이타 생성방법을 설명하기 위한 도면.4 is a view for explaining a basic data generation method of the VC1C2 form according to the present invention.

Claims (2)

자음을 중심으로 모음의 안정구간에서 자른 한국어의 기본 데이타크를 켑스트럼 방법으로 분석하여 스펙트럼 엔벨로프로부터 얻어진 시메트릭 파형으로 한국어를 합성하는 한국어 합성방법에 있어서, 상기 기본 데이타는 자음+모음(초성), 단모음+자음(종성), 단모음+자음+모음, 단모음+유성자음+무성자음의 4가지 종류로 이루어짐을 특징으로 하는 한국어 합성장치의 유성자음과 무성자음의 합성방법.In the Korean synthesis method of synthesizing Korean with symmetric waveforms obtained from the spectral envelope by analyzing the Korean basic datak cut in the vowel stability section centered on the consonant, the basic data is consonant + vowel ), A method of synthesizing the voiced and unvoiced consonants of the Korean synthesizer, characterized by consisting of four types: short vowel + consonant (single), short vowel + consonant + vowel, short vowel + voiced consonant + unvoiced consonant. 제1항에 있어서, 상기 기본 데이타종 단모음+유성자음+무성자음형태의 기본 데이타와 단모음+자음+모음의 형태의 기본 데이타중 모음 데이타를 연속적으로 합성하여 단모음+유성자음+무성자음+모음형태의 음성을 합성하는 것을 특징으로 하는 한국어 합성장치의 유성자음과 무성자음의 합성방법.The method of claim 1, wherein the basic data type of the short vowel + voiced consonant + unvoiced consonant and the vowel data of the short vowel + consonant + vowel form are synthesized continuously to form a short vowel + voiced consonant + unvoiced consonant + vowel form Method for synthesizing voiced and unvoiced consonants of the Korean synthesizer, characterized in that for synthesizing the voice of the. ※ 참고사항 : 최초출원 내용에 의하여 공개하는 것임.※ Note: The disclosure is based on the initial application.
KR1019940029839A 1994-11-14 1994-11-14 Synthesis method of voiced and unvoiced consonants of Korean synthesizer Withdrawn KR960018879A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1019940029839A KR960018879A (en) 1994-11-14 1994-11-14 Synthesis method of voiced and unvoiced consonants of Korean synthesizer

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1019940029839A KR960018879A (en) 1994-11-14 1994-11-14 Synthesis method of voiced and unvoiced consonants of Korean synthesizer

Publications (1)

Publication Number Publication Date
KR960018879A true KR960018879A (en) 1996-06-17

Family

ID=66687532

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1019940029839A Withdrawn KR960018879A (en) 1994-11-14 1994-11-14 Synthesis method of voiced and unvoiced consonants of Korean synthesizer

Country Status (1)

Country Link
KR (1) KR960018879A (en)

Similar Documents

Publication Publication Date Title
Caspers et al. Effects of time pressure on the phonetic realization of the Dutch accent-lending pitch rise and fall
US8219398B2 (en) Computerized speech synthesizer for synthesizing speech from text
Bhaskararao Salient phonetic features of Indian languages in speech technology
KR870007477A (en) Rule synthesis speech synthesis system
US6829577B1 (en) Generating non-stationary additive noise for addition to synthesized speech
Kumar et al. Significance of durational knowledge for speech synthesis system in an Indian language
KR960018879A (en) Synthesis method of voiced and unvoiced consonants of Korean synthesizer
Lukaszewicz et al. Microphonemic method of speech synthesis
Waghmare et al. Analysis of pitch and duration in speech synthesis using PSOLA
Code Observations in the Art of Speech: Paul Lansky's Six Fantasies
Pongweni An acoustic study of the qualitative and pitch effect of breathy-voice on Shona vowels
RU2298234C2 (en) Method for compilation phoneme synthesis of russian speech and device for realization of said method
KR970003093B1 (en) Synthesis unit drawing-up method for high quality korean text to speech transformation
Verma et al. Comparative analysis of Hindi retroflex and dental CV syllables and their synthesis
Saravari et al. A demisyllable approach to speech synthesis of Thai A tone language
Datta et al. Epoch Synchronous Overlap Add (ESOLA)
Karjalainen Review of speech synthesis technology
Eady et al. Pitch assignment rules for speech synthesis by word concatenation
KR100202539B1 (en) Voice synthetic method
JPS59155899A (en) Voice synthesization system
Rashid et al. Diphone preparation for Bangla text to speech synthesis
Rischel Invariance in the linguistic expression, with digressions into music
JPH01321496A (en) Speech synthesizing device
JPS60153099A (en) Rule type voice synthesizer
KR970060042A (en) Speech synthesis method

Legal Events

Date Code Title Description
PA0109 Patent application

Patent event code: PA01091R01D

Comment text: Patent Application

Patent event date: 19941114

PG1501 Laying open of application
PC1203 Withdrawal of no request for examination
WITN Application deemed withdrawn, e.g. because no request for examination was filed or no examination fee was paid