• 한국컴퓨터정보학회논문지
• /
• 제20권5호
• /
• pp.53-63
• /
• 2015

노래음 합성이란 주어진 가사와 악보를 이용하여 컴퓨터에서 노래음을 생성하는 것이다. 텍스트/음성 변환기에 널리 사용된 HMM 기반 음성합성기는 최근 노래음 합성에도 적용되고 있다. 그러나 기존의 구현방법에는 대용량의 노래음 데이터베이스 수집과 학습이 필요하여 구현에 어려움이 있다. 또한 기존의 상용 노래음 합성시스템은 피아노 롤 방식의 악보 표현방식을 사용하고 있어 일반인에게는 익숙하지 않으므로 읽기 쉬운 표준 악보형식의 사용자 인터페이스를 지원하여 노래 학습의 편의성을 향상시킬 필요가 있다. 이 문제를 해결하기 위하여 본 논문에서는 기존 낭독형 음성합성기의 HMM 모델을 이용하고 노래음에 적합한 피치값과 지속시간 제어방법을 적용하여 HMM 모델 파라미터 값을 변화시킴으로서 노래음을 생성하는 방법을 제안한다. 그리고 음표와 가사를 입력하기 위한 MusicXML 기반의 악보편집기를 전단으로, HMM 기반의 텍스트/음성 변환 합성기를 합성기 후단으로서 사용하여 노래음 합성시스템을 구현하는 방법을 제안한다. 본 논문에서 제안하는 방법을 이용하여 합성된 노래음을 평가하였으며 평가결과 활용 가능성을 확인하였다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2004년도 추계학술대회 논문집
• /
• pp.1270-1273
• /
• 2004

The mechanism design is synthesis of suitable mechanism which can be output motions about input motions. That has generally two steps which are the type synthesis and the dimensional synthesis. And required mechanism analysis step for confirming middle or final result. The type synthesis is definition of mechanism type which required aim and the dimensional synthesis is calculation of dimension about defined type mechanism. The type synthesis of mechanism is included qualitative design field which isn't defined systematic design method. especially, the most difficult step for mechanism design automation. In this paper proposed the component modular design method which is figured mechanism types automate with component modules using component modular approach. And develop CAD(Computer Aided Program) program for application.

• 소음진동
• /
• 제7권5호
• /
• pp.737-746
• /
• 1997

The substructure synthesis method is used for making it easy to analyze vibration systems generally in vibration field. In the past, this method has been to be used mainly because of shortage of computer memory and CPU time. But recently this method is used for analyzing complex structure or identifying the characteristics of systems precisely. The purpose of this study is to develop acoustic substructure synthesis method that can be applied to acoustic modal analysis of complex acoustic systems. Acoustic modal analysis method to be introduced here is a method that analyze acoustic natural mode shape of the complex acoustic system by the principle of CMS(component mode synthesis method). This paper describes the acoustic modal analysis of the acoustic finite element model of simple expansion pipe by acoustic substructure synthesis method. The resutls of acoustic modal analysis analyzed by Acoustic substructure synthesis method and the results by FEM(finite element method) shows good agreement.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2005년도 International Meeting on Information Displayvol.II
• /
• pp.1087-1090
• /
• 2005

We have investigated the synthesis and field emission properties of high-quality double-walled carbon nanotubes (DWCNTs) using a catalytic chemical vapor deposition method and a hydrogen arc discharge method. The produced carbon materials using a catalytic CVD method indicated high-purity DWCNT bundles free of amorphous carbon covering on the surface. By adopting a hydrogen arc discharge method, we could obtained high-purity DWCNTs in large-scale. DWCNTs showed low turn-on voltage and higher emission stability compared with SWCNTs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.713-725
• /
• 2022

Mostly, artificial intelligence does not show any definite change in emotions. For this reason, it is hard to demonstrate empathy in communication with humans. If frequency modification is applied to neutral emotions, or if a different emotional frequency is added to them, it is possible to develop artificial intelligence with emotions. This study proposes the emotion conversion using the Generative Adversarial Network (GAN) based voice frequency synthesis. The proposed method extracts a frequency from speech data of twenty-four actors and actresses. In other words, it extracts voice features of their different emotions, preserves linguistic features, and converts emotions only. After that, it generates a frequency in variational auto-encoding Wasserstein generative adversarial network (VAW-GAN) in order to make prosody and preserve linguistic information. That makes it possible to learn speech features in parallel. Finally, it corrects a frequency by employing Amplitude Scaling. With the use of the spectral conversion of logarithmic scale, it is converted into a frequency in consideration of human hearing features. Accordingly, the proposed technique provides the emotion conversion of speeches in order to express emotions in line with artificially generated voices or speeches.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.126-126
• /
• 2000

In this paper, we provide an approach of controller synthesis for input-saturated linear systems by a linear parameter varying (LPV) framework. Using directly the saturation nonlinearity as scheduling parameters, we propose an LPV-stabilizer with parameter-dependent dynamic state-feedback controller concept. Especially, the synthesis conditions are formulated in terms of linear matrix inequalities (LMIs) that can be solved very efficiency.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제68차 하계학술대회논문집 31권2호
• /
• pp.575-576
• /
• 2023

본 논문에서는 텍스처 합성할 때 방향을 고려하여 합성의 품질의 개선시킬 수 있는 방법을 제안한다. 또한 고정된 회전 각도가 아닌, 다양한 각도를 자동으로 샘플링하여 효율적으로 예제 이미지를 생성할 수 있도록 하였고, 이를 통해 합성 경계간의 차이를 자연스럽게 완화시킬 수 있는 결과를 실험을 통해 보여준다.

• Journal of Advanced Marine Engineering and Technology
• /
• 제24권1호
• /
• pp.82-87
• /
• 2000

The component mode synthesis method(CMS) used for vibration analysis has demerit that error becomes larger, as degree of natural frequency grows higher. The reason of error occurrence is that Guyan's static reduction is used and the number of modes taken in each component is deficient. This paper proposes the substructure synthesis method using dynamic reduction to solve the problem from the component mode synthesis method. Computer simulation for the proposed method. FEM and the component mode synthesis method(CMS) on a rectrangular plate has been carried out to prove the avilability of the proposed method.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2014년도 추계학술대회 논문집
• /
• pp.464-466
• /
• 2014

The mechanism synthesis methods, graphical, analytical and computer-aided technique have been proposed for selecting and scaling mechanical system. According to developing computation tools, mechanism could be synthesized much faster and more correct than previous analytical ways by improved techniques. In this paper, the improved synthesis method is proposed to solve body guidance synthesis problem. To perform the mechanism synthesis for body guidance, a planar linkage is modeled as a set of free three bushings located in design space. The values of bushing stiffness and x, y position of bushings yielding a desired functional requirement related to input motion are found by using an optimization technique.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 FIFTH WESTERN PACIFIC REGIONAL ACOUSTICS CONFERENCE SEOUL KOREA
• /
• pp.1098-1103
• /
• 1994

In this paper, we design and implement the Korean speech synthesis by rule system. This system is applied the multiband excitation signal on voiced sounds. The multiband excitation signal is obtained by mixing impluse spectrum and which noise spectrum. We find that the quality of synthesized speech is improved using this application. Also, we classify the voiced sounds by cepstral euclidian distance measure for reducing overhead memory. The representative excitation signal of the same group's voiced sounds is used as excitation signal on synthesis. This method does not affect the quality of synthesized speech. As the result of experiment, this method eliminates the "buzziness" of synthesized speech and reduces the spectral distortion of synthesized speech.ed speech.