KR100351590B1 - 음성 변환 방법 - Google Patents
음성 변환 방법 Download PDFInfo
- Publication number
- KR100351590B1 KR100351590B1 KR1020000078138A KR20000078138A KR100351590B1 KR 100351590 B1 KR100351590 B1 KR 100351590B1 KR 1020000078138 A KR1020000078138 A KR 1020000078138A KR 20000078138 A KR20000078138 A KR 20000078138A KR 100351590 B1 KR100351590 B1 KR 100351590B1
- Authority
- KR
- South Korea
- Prior art keywords
- target
- speaker
- source
- singer
- voice
- Prior art date
Links
Classifications
-
- 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
- G10L13/033—Voice editing, e.g. manipulating the voice of the synthesiser
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H1/00—Details of electrophonic musical instruments
- G10H1/0008—Associated control or indicating means
-
- 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
- G10L13/027—Concept to speech synthesisers; Generation of natural phrases from machine-based concepts
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H2250/00—Aspects of algorithms or signal processing methods without intrinsic musical character, yet specifically adapted for or used in electrophonic musical processing
- G10H2250/005—Algorithms for electrophonic musical instruments or musical processing, e.g. for automatic composition or resource allocation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Telephonic Communication Services (AREA)
Abstract
Description
Claims (4)
- 소스화자(source speaker)와 타겟화자(Target speaker)의 음성을 각각 디지털 신호로 변환하여 소정의 기억장치에 저장하는 데이터 생성과정과,변환함수를 적용하여 소스화자(source speaker)의 음색(timbre)을 타겟 화자(target speaker)의 음색으로 변환하는 변환학습과정과,타겟 화자(target speaker)의 음색(timbre)으로 변환된 신호를 소스 화자(source speaker)의 장단 및 고저 신호가 포함된 디지털 신호와 합성하여 타겟 화자(target speaker)의 음성으로 변환하는 매핑(mapping)과정을 포함하여 이루어지는 음성 변환 방법.
- 제 1 항에 있어서;상기 소스화자(source speaker)의 음성은 기계에 의해 구현되는 음성인 것을 특징으로 하는 음성 변환 방법.
- 타겟 싱어(target singer)가 부른 노래의 가사 부분과, 소스 싱어(source singer)의 노래중 반주부분과 가사부분을 분리하여 각각 디지털 신호로 변환하여 소정의 기억장치에 저장하는 데이터 생성과정과,변환함수를 적용하여 소스 싱어(source)의 음색(timbre)을 타겟 싱어(target singer)의 음색으로 변환하는 변환학습과정과,타겟 싱어(target singer)의 음색(timbre)으로 변환된 신호와 소스 싱어(source singer)가 부른 노래 중 분리되어 저장된 반주부분의 디지털 신호를 합성하여 타겟 싱어(target singer)의 노래로 변환하는 매핑(mapping)과정을 포함하는 음성 변환 방법.
- 제 3 항에 있어서; 상기 변환학습과정은,데이터 생성과정을 통해 추출된 소스 싱어(source singer)와 타겟 싱어(target singer)의 디지털 신호(Signal)를 분석(Analysis)하여 시간축정합법(Dynamic Time Warping) 알고리즘(Algorithm)을 이용하여 시간정렬된 스펙트럴 엔벌로프(Spectral envelope)를 생성하는 제 1 단계와,시간정렬된 소스(source)와 타겟(target) 스펙트럴(Spectral) 엔벌로프(envelope)를 EM(Expectation maximization) 알고리즘에 의해 추정된 GMM(Gaussian Mixture Model)의 파라미터(parameter)를 이용하여 최적화(least square)하는 제 2 단계를 포함하여 이루어지는 것을 특징으로 하는 음성 변환 방법.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020000078138A KR100351590B1 (ko) | 2000-12-19 | 2000-12-19 | 음성 변환 방법 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020000078138A KR100351590B1 (ko) | 2000-12-19 | 2000-12-19 | 음성 변환 방법 |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20020049061A KR20020049061A (ko) | 2002-06-26 |
KR100351590B1 true KR100351590B1 (ko) | 2002-09-05 |
Family
ID=27683045
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020000078138A KR100351590B1 (ko) | 2000-12-19 | 2000-12-19 | 음성 변환 방법 |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR100351590B1 (ko) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11646044B2 (en) * | 2018-03-09 | 2023-05-09 | Yamaha Corporation | Sound processing method, sound processing apparatus, and recording medium |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20020026228A (ko) * | 2002-03-02 | 2002-04-06 | 백수곤 | 실시간 음성 변환 |
TWI265718B (en) * | 2003-05-29 | 2006-11-01 | Yamaha Corp | Speech and music reproduction apparatus |
CN106571145A (zh) * | 2015-10-08 | 2017-04-19 | 重庆邮电大学 | 一种语音模仿方法和装置 |
CN108320741A (zh) * | 2018-01-15 | 2018-07-24 | 珠海格力电器股份有限公司 | 智能设备的声音控制方法、装置、存储介质和处理器 |
CN112331222B (zh) * | 2020-09-23 | 2024-07-26 | 北京捷通华声科技股份有限公司 | 一种转换歌曲音色的方法、系统、设备及存储介质 |
CN112382269B (zh) * | 2020-11-13 | 2024-08-30 | 北京有竹居网络技术有限公司 | 音频合成方法、装置、设备以及存储介质 |
CN112382274B (zh) * | 2020-11-13 | 2024-08-30 | 北京有竹居网络技术有限公司 | 音频合成方法、装置、设备以及存储介质 |
-
2000
- 2000-12-19 KR KR1020000078138A patent/KR100351590B1/ko not_active IP Right Cessation
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11646044B2 (en) * | 2018-03-09 | 2023-05-09 | Yamaha Corporation | Sound processing method, sound processing apparatus, and recording medium |
Also Published As
Publication number | Publication date |
---|---|
KR20020049061A (ko) | 2002-06-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5665780B2 (ja) | 音声合成装置、方法およびプログラム | |
US8005677B2 (en) | Source-dependent text-to-speech system | |
Shinoda et al. | A structural Bayes approach to speaker adaptation | |
Nakamura et al. | Differences between acoustic characteristics of spontaneous and read speech and their effects on speech recognition performance | |
CN100371926C (zh) | 通过响应输入语句而输出应答语句的交互对话装置和方法 | |
US5970453A (en) | Method and system for synthesizing speech | |
US9123337B2 (en) | Indexing digitized speech with words represented in the digitized speech | |
US7062435B2 (en) | Apparatus, method and computer readable memory medium for speech recognition using dynamic programming | |
Rudnicky et al. | Survey of current speech technology | |
Welling et al. | Speaker adaptive modeling by vocal tract normalization | |
EP2523442A1 (en) | A mass-scale, user-independent, device-independent, voice message to text conversion system | |
US20050114137A1 (en) | Intonation generation method, speech synthesis apparatus using the method and voice server | |
US6671668B2 (en) | Speech recognition system including manner discrimination | |
KR100351590B1 (ko) | 음성 변환 방법 | |
Hain et al. | The development of the AMI system for the transcription of speech in meetings | |
US11335321B2 (en) | Building a text-to-speech system from a small amount of speech data | |
Shih et al. | A statistical multidimensional humming transcription using phone level hidden Markov models for query by humming systems | |
Verma et al. | Using viseme based acoustic models for speech driven lip synthesis | |
Furui | Robust methods in automatic speech recognition and understanding. | |
KR101890303B1 (ko) | 가창 음성 생성 방법 및 그에 따른 장치 | |
CN116469369A (zh) | 虚拟声音合成方法、装置及相关设备 | |
Jiang et al. | A robust compensation strategy for extraneous acoustic variations in spontaneous speech recognition | |
KR20220069776A (ko) | 자동음성인식을 위한 음성 데이터 생성 방법 | |
Ogbureke et al. | Improving initial boundary estimation for HMM-based automatic phonetic segmentation. | |
Wan et al. | Cluster adaptive training of average voice models |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
PA0109 | Patent application |
Patent event code: PA01091R01D Comment text: Patent Application Patent event date: 20001219 |
|
PA0201 | Request for examination | ||
PG1501 | Laying open of application | ||
E701 | Decision to grant or registration of patent right | ||
PE0701 | Decision of registration |
Patent event code: PE07011S01D Comment text: Decision to Grant Registration Patent event date: 20020723 |
|
GRNT | Written decision to grant | ||
PR0701 | Registration of establishment |
Comment text: Registration of Establishment Patent event date: 20020823 Patent event code: PR07011E01D |
|
PR1002 | Payment of registration fee |
Payment date: 20020826 End annual number: 3 Start annual number: 1 |
|
PG1601 | Publication of registration | ||
FPAY | Annual fee payment |
Payment date: 20050824 Year of fee payment: 4 |
|
PR1001 | Payment of annual fee |
Payment date: 20050824 Start annual number: 4 End annual number: 4 |
|
LAPS | Lapse due to unpaid annual fee | ||
PC1903 | Unpaid annual fee |