http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
환경음 분류와 위치 정보를 이용한 딥러닝 기반 음성 품질 향상 기법
강병휘,노동건 한국정보과학회 2023 정보과학회논문지 Vol.50 No.4
In the field of speech processing, deep learning has made great advances by improving the precision of speech recognition. One of advances, voice improvement, is a technique that can improve voice recognition by separating voice and noise from input mixed with speaking voice and noise. This is used in AI-speakers and smartphones to facilitate human-to-human communication and enable clean voice data collection for robots and text-to-speech. However, conventional speech enhancement techniques that use only a single model are not effective in eliminating noise that occurs specifically in each environment. To effectively eliminate environmental specific noise, this paper proposes a deep learning model that combines acoustic scene classification techniques with location information utilization techniques to enable optimal environmental-specific speech enhancements. As a result of the experiment, it is confirmed that this technique shows high voice quality improvement with low computational cost in various environments compared to the existing technique. 음성 처리 분야에서 딥러닝은 음성인식의 정밀도를 향상시켜 많은 발전을 이루었다. 그중 하나인 음성 향상은 말하는 음성과 잡음이 섞여있는 입력에서 음성과 잡음을 분리시켜 음성 품질을 향상시킬 수 있는 기법이다. 이는 AI-스피커, 스마트폰 등에 활용되어 사람 대 사람, 기계 대 인간과의 의사소통을 원활하게 하고 로봇이나 문자 음성 변환(Text-to-Speech) 등을 위한 깨끗한 음성 데이터 수집을 가능하게 한다. 하지만 단일 모델만을 사용한 기존 음성 향상 기법은 환경마다 특수적으로 발생하는 잡음 제거에 있어 효과적이지 못하다. 환경 특수적으로 발생할 수 있는 잡음을 효과적으로 제거하기 위해, 본 논문은 음향 장면 분류 기법과 위치 정보 활용 기술을 결합하여 최적의 환경별 음성 향상이 이루어 질 수 있게 하는 딥러닝 모델을 제안한다. 실험 결과 SNR 9 dB을 기준으로 하였을 때, 본 기법이 기존 딥러닝 모델 대비 PESQ 값은 평균 0.06 이상, STOI 값은 평균 0.015 이상의 향상된 품질을 보임을 확인하였다.
Rare Isotope Production and Experimental Systems of RAON
신택수,강병휘,김기동,김영진,권영관,박영호,추경호,윤종철 한국물리학회 2016 New Physics: Sae Mulli Vol.66 No.12
The rare isotope science project (RISP) of the Institute for Basic Science (IBS) has put tremendous efforts into carrying out the design and the development of the RAON heavy-ion accelerator facility, which will be built in the Sindong area of Daejeon by 2021. The heart of the RAON accelerator facility, which will be equipped with superconducting linear accelerator systems, is its capacity for producing rare isotope beams through rare isotope production systems using both the Isotope Separation On-Line (ISOL) and the In-Flight (IF) fragmentation separation methods. As beneficiaries of these rare isotope production systems, the RAON experimented systems, on which consist of include the KOrea Broad acceptance Recoil spectrometer and Apparatus (KOBRA) spectrometer for nuclear astrophysics, the Large Acceptance Multi-Purpose Spectrometer (LAMPS) for the symmetry energy of the equation of state and applied science facilities, all of which will utilize the various rare isotope beams for applications, are currently being developed. The status of the rare isotope production and the experimented systems of the RISP are briefly discussed.
최창일,강병휘,김용균,최일우,고도경,이종민,김기동 한국물리학회 2011 THE JOURNAL OF THE KOREAN PHYSICAL SOCIETY Vol.59 No.22
We performed two experiments of proton radiography by using protons generated by a femtosecond laser and by a Tandem Van de Graff accelerator to compare their image characteristics. In the laser experiment, the maximum energy of the protons was about 1.8 MeV, and they had a broad energy distribution. The protons in the accelerator experiment were monoenergetic with an energy of 1.8 MeV. In order to evaluate the radiography images, we used a step wedge phantom and a character-type phantom. A CR-39 solid state nuclear track detector (SSNTD) was used as a radiography screen. The radiography images were obtained by using an optical microscope. As a result of the comparison and evaluation of the two experiments’ radiography images, protons from the femtosecond laser were found to be more useful than protons from the accelerator. If good proton radiography images are to be obtained using CR-39, utilizing a certain proton energy distribution rather than monoenergetic protons is efficient.