http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
결정적/확률적 요소로의 음성 분해와 심리음향 모델 기반 잡음 제거 기법
조석환(Seokhwan Jo),유창동(Chang D. Yoo) 대한전자공학회 2007 대한전자공학회 학술대회 Vol.2007 No.7
A speech enhancement algorithm based on both a decomposition of speech into deterministic and stochastic components and a psychoacoustic model is proposed. Noisy speech is decomposed into deterministic and stochastic components, and then each component is enhanced preserving its individual characteristics. A psychoacoustic model is taken into account when enhancing the stochastic component. Simulation results show that the proposed algorithm performs better than some of the more popular algorithms.
심리음향적 제약조건 최적화에 기반한 잡음 제거 기법 문제 설정 및 고찰
조석환(Seokhwan Jo),유창동(Chang D. Yoo) 대한전자공학회 2010 대한전자공학회 학술대회 Vol.2010 No.6
This paper considers a speech enhancement based on the psychoacoustically constrained optimization problem. In this paper, four constrained optimization problems are set using the masking threshold of the clean speech, and these problems and their solutions are considered. Experimental results show that the performance of the algorithms considered in this paper.
윈도우 길이가 하모닉 구조 모델을 이용한 멜로디 피치 추출에 미치는 영향 분석
주시현(Sihyun Joo),조석환(Seokhwan Jo),유창동(Chang D. Yoo) 대한전자공학회 2010 대한전자공학회 학술대회 Vol.2010 No.6
This paper considers a melody extraction algorithm using a harmonic structure model and analyzes an effect of window length on the melody extraction. The algorithm estimates a melody pitch of each frame based on the melody definition that melody is a dominant single pitch sequence of a polyphonic audio. The algorithm performs short time Fourier transform (STFT) to find the dominant pitch sequence. However, the length of window for the STFT affects the melody extraction result because time-frequency resolution depends on the window length. Therefore, the relation between the window length for STFT and melody extraction is analyzed.