KR970056663A - 114 Information for improving voice data naturalness - Google Patents

114 Information for improving voice data naturalness Download PDF

Info

Publication number
KR970056663A
KR970056663A KR1019950055859A KR19950055859A KR970056663A KR 970056663 A KR970056663 A KR 970056663A KR 1019950055859 A KR1019950055859 A KR 1019950055859A KR 19950055859 A KR19950055859 A KR 19950055859A KR 970056663 A KR970056663 A KR 970056663A
Authority
KR
South Korea
Prior art keywords
sound
environment
generating
naturalness
voices
Prior art date
Application number
KR1019950055859A
Other languages
Korean (ko)
Other versions
KR0175464B1 (en
Inventor
한민수
김상훈
지민제
Original Assignee
양승택
한국전자통신연구원
이준
한국전기통신공사
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 양승택, 한국전자통신연구원, 이준, 한국전기통신공사 filed Critical 양승택
Priority to KR1019950055859A priority Critical patent/KR0175464B1/en
Publication of KR970056663A publication Critical patent/KR970056663A/en
Application granted granted Critical
Publication of KR0175464B1 publication Critical patent/KR0175464B1/en

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
    • H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
    • H04M3/4931—Directory assistance systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • G10L13/02—Methods for producing synthetic speech; Speech synthesisers
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2201/00—Electronic components, circuits, software, systems or apparatus used in telephone systems
    • H04M2201/39—Electronic components, circuits, software, systems or apparatus used in telephone systems using speech synthesis

Landscapes

  • Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Machine Translation (AREA)
  • Telephone Function (AREA)

Abstract

본 발명은 114 안내음성의 자연성 개선 방법에 관한 것으로서, 114 안내 시스템에 있어서, 중복되는 음성 단위를 추출하는 제1단계; 상기 제1단계후 유사음운 환경을 이용하여 그룹화 하는 제2단계; 상기 제2단계후 음운환경이 경음화된 음성 단위를 생성하는 제3단계; 및 상기 제3단계후 114 안내 문장을 이루는 기타 음성 단위를 생성되는 제4단계를 구비하여 종래 114 안내음성의 대표적 부자연스런 부분(네 : [숫자음]+[국에],[숫자음]+[번입니다])을 개선하고 중복되는 음성단위(예 : 천, 백, 십, 국에, 번)를 따로 저장하여 메모리 사용량을 줄일 수 있는 효과가 있다.The present invention relates to a method for improving the naturalness of voices in 114 voices, comprising: a first step of extracting overlapping voice units; A second step of grouping using a similar phonetic environment after the first step; A third step of generating a sound unit in which the phonological environment is sounded after the second step; And a fourth step of generating other voice units constituting the 114 guide sentences after the third step, including representative unnatural parts of the conventional 114 guide voices (eg: [number] + [count], [number]] + It is possible to reduce memory usage by improving [Burn]) and storing redundant voice units (eg, thousand, hundred, ten, station, bun) separately.

Description

114 안내용 음성데이타 자연성 개선 방법114 Information for improving voice data naturalness

본 내용은 요부공개 건이므로 전문내용을 수록하지 않았음Since this is an open matter, no full text was included.

제1도는 본 발명이 적용되는 하드웨어의 기본 구성도1 is a basic configuration of hardware to which the present invention is applied

제2도는 본 발명에 사용되는 음운환경 및 음절위치를 고려한 음성 데이타 제작법의 흐름도2 is a flowchart of a method for producing speech data in consideration of phonological environment and syllable location used in the present invention.

Claims (4)

114 안내 시스템에 있어서, 중복되는 음성 단위를 추출하는 제1단계; 상기 제1단계후 유사음운 환경을 이용하여 그룹화 하는 제2단계; 상기 제2단계후 음운환경이 경음화된 음성 단위를 생성하는 제3단계; 및 상기 제3단계후 114 안내 문장을 이루는 기타 음성 단위를 생성되는 제4단계를 구비하고 있는 것을 특징으로 하는 음성 데이타 자연성 개선 방법.114. A guide system, comprising: a first step of extracting overlapping speech units; A second step of grouping using a similar phonetic environment after the first step; A third step of generating a sound unit in which the phonological environment is sounded after the second step; And a fourth step of generating other voice units constituting the 114 guide sentences after the third step. 제1항에 있어서, 상기 제1단계에서의 음성단위는 [천, 백, 십, 국, 번]으로 추출되는 것을 특징으로 하는 음성 데이타 자연성 개선 방법.The method of claim 1, wherein the voice unit in the first step is extracted as [thousand, hundred, ten, station, number]. 제2항에 있어서, 제2단계의 유사음운환경은 파찰음, 마찰음, 양순파열음, 및 연구개파열음 등에 의해 분류되는 것을 특징으로 하는 음성 데이타 자연성 개선 방법.3. The method of claim 2, wherein the quasi-phonological environment of the second stage is classified into a streaking sound, a rubbing sound, a sheep rupture sound, and a rupture sound. 제3항에 있어서, 상기 제2단계에서 동일한 음운 환경에 대해서 음절위치에 의한 숫자음의 영향을 고려하는 제5단계를 더 구비하고 있는 것을 특징으로 하는 음성 데이타 자연성 개선 방법.4. The method of claim 3, further comprising a fifth step of considering the influence of the number sound due to the syllable position on the same phonetic environment in the second step. ※ 참고사항 : 최초출원 내용에 의하여 공개하는 것임.※ Note: The disclosure is based on the initial application.
KR1019950055859A 1995-12-23 1995-12-23 How to make voice data for phone number guide KR0175464B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1019950055859A KR0175464B1 (en) 1995-12-23 1995-12-23 How to make voice data for phone number guide

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1019950055859A KR0175464B1 (en) 1995-12-23 1995-12-23 How to make voice data for phone number guide

Publications (2)

Publication Number Publication Date
KR970056663A true KR970056663A (en) 1997-07-31
KR0175464B1 KR0175464B1 (en) 1999-04-01

Family

ID=19444022

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1019950055859A KR0175464B1 (en) 1995-12-23 1995-12-23 How to make voice data for phone number guide

Country Status (1)

Country Link
KR (1) KR0175464B1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20010011281A (en) * 1999-07-27 2001-02-15 서평원 Announcement Broadcasting Storage Method In Voice Offer Unit
KR100430305B1 (en) * 2001-07-21 2004-05-04 엘지전자 주식회사 Voice Message Change Device And Method Of Voice Data Service Board

Also Published As

Publication number Publication date
KR0175464B1 (en) 1999-04-01

Similar Documents

Publication Publication Date Title
US5774854A (en) Text to speech system
US7565291B2 (en) Synthesis-based pre-selection of suitable units for concatenative speech
US8566099B2 (en) Tabulating triphone sequences by 5-phoneme contexts for speech synthesis
Elshafei et al. Techniques for high quality Arabic speech synthesis
KR970037209A (en) Voice output device (SPEECH SYNTHSIZER)
Hirose et al. Synthesizing dialogue speech of Japanese based on the quantitative analysis of prosodic features
EP0786132B1 (en) A method and device for preparing and using diphones for multilingual text-to-speech generating
Wolters A diphone-based text-to-speech system for Scottish Gaelic
KR970056663A (en) 114 Information for improving voice data naturalness
Chen et al. A Mandarin Text-to-Speech System
Henton Challenges and rewards in using parametric or concatenative speech synthesis
Maghbouleh A logistic regression model for detecting prominences
JPH08248993A (en) Controlling method of phoneme time length
JPS6014360B2 (en) voice response device
KR100387232B1 (en) Apparatus and method for generating korean prosody
Tatham et al. Speech synthesis in dialogue systems
Hande A review on speech synthesis an artificial voice production
Khudoyberdiev The Algorithms of Tajik Speech Synthesis by Syllable
Eady et al. Pitch assignment rules for speech synthesis by word concatenation
Orhan et al. A concatenative Turkish text-to-speech system and evaluation process
El-Imam Speech synthesis by concatenating sub-syllabic sound units
Keller Quality improvement of (wireless) phone-based teleservices using advanced speech synthesis techniques
Venkatagiri Digital speech technology: An overview
Abramson et al. Stop voicing, intonation, and the F contour
Bruce On the phonetics of rhythm: Evidence from Swedish

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 20031030

Year of fee payment: 6

LAPS Lapse due to unpaid annual fee