http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
이차 볼테라 시스템 인식을 위한 효율적인 적응 디지탈 필터링 알고리즘
황영수,차일환,윤대희,Hwang, Y.S.,Mathews, V.J.,Cha, I.W.,Youn, D.H. 한국음향학회 1988 韓國音響學會誌 Vol.7 No.4
본 연구는 이차 볼테라 필터 계수를 연속적으로 변화시키기 위하여 sequential regression (SER) 방법을 이용한 적응 비선형 디지탈 필터링 알고리즘에 대하여 서술하였다. 일반적으로 SER 방법은 Wiener 필터 이론을 볼테라필터에 직접 적용시킬때 생기는 큰 행렬을 역변환시키기 위하여 사용되었다. 그러나, 본 연구에서는 입력신호가 가우시안일 경우, 최소 자승해를 구하기 위하여 SER 방법을 이용하였다. 이 알고리즘에서, 역변환시킬 행렬의 크기는 일반적 접근 방법보다 작게 되기때문에, 일반적 비선형 시스템 인식 기술보다 본 연구에서 제시한 방법의 계산량이 적다. 본 연구에서 제안한 알고리즘의 성능을 검토하기 위하여 시뮬레이션 결과를 구했다. This paper introduces an adaptive nonlinear filtering algorithm that uses the sequential regression(SER) method to update the second order Volterra filter coefficients in a recursive way. Conventionally, the SER method has been used to invert large matrices which result from direct application of Wiener filter theory to the Volterra filter. However, the algorithm proposed in this paper uses the SER approach to update the least squares solution which is derived for Gaussian input signals. In such an algorithm, the size of the matrix to be inverted is smaller than that of conventional approaches, and hence the proposed method is computationally simpler than conventional nonlinear system identification techniques. Simulation results are presented to demonstrate the performance of the proposed algorithm.
주파수 영역 적응 디지탈 필터를 이용한 Magnitude-Squared Coherence 함수 추정
김도년,차일환,윤대희,Kim, D.N.,Cha, I.W.,Youn, D.H. 한국음향학회 1988 韓國音響學會誌 Vol.7 No.2
한 쌍의 주파수 영역 적응 디지탈 필터를 이용하여 두 신호간의 magnitude squared coherence(MSC) 함수를 추정하는 방법을 제안하였다. 이와 같은 방법은 시간 영역에서 한 쌍의 적응디지탈 필터를 이용하는 LMS-MSC(least mean square-MSC)알고리즘에 비하여 적은 양의 계산으로 MSC 함수를 구할 수 있다. MSC함수 추정을 위하여 대표적인 주파수 영역 적응 필터링 알고리즘인 CFLMS(constrained frequency-domain LMS)와 UFLMS (unconstrained frequency-domain LMS)알고리즘을 사용하였으며, 컴퓨터 시뮬레이션을 통하여 LMS-MSC 알고리즘과 성능을 비교하였다. It is proposed to use a pair of frequency-domain adaptive digital filters to estimate the magnitude squared coherence (MSC) functions of two signals. Such a method requires less computations than the LMS-MSC algorithm in which the least mean square (LMS) algorithm is applied in the time domain to compute the coefficients of a pair of adaptive digital filters. The frequency-domain adaptive digital filtering algorithms considered in this paper include the constrained frequency domain LMS (CFLMS) and the unconstrained frequency domain LMS (UFLMS) algorithms. The performance of the proposed methods are compared with those of the LMS-MSC algorithm.
음소를 이용한 한국어 음성 신호의 분석과 인식에 관한 연구
김영일,황영수,윤대희,차일환,Kim Y. I.,Hwang Y. S.,Youn D. H.,Cha I. W. 한국음향학회 1989 韓國音響學會誌 Vol.8 No.5
본 연구는 한국어를 음소변로 분리하여 인식하는 실험에 관한 연구이다. 한국어 단음 545개를 자음 음소, 모음 음소, 받침 음소로 분리하여 선형 예측 계수로 인식한 결과, 각각 $87.3(\%), 91.0(\%), 91.7(\%)$의 인식률을 얻었고, 이 음소들을 결합한 단음에서는 $71.4(\%)$의 인식률을 얻었다. 음소 분리 및 음소 인식은 Itakura-Saito 거리 측정을 이용하였다. In this paper, Korean language recognition using the phoneme is studied. The experiment is carried out by dividing 545 isolated words into phonemes. Using linear prediction coefficients the recognition rate of consonants, vowels, and end-consonants are $87.3(\%), 91.0(\%), 91.7(\%)$, respectively. Recognition rate of isolated words combined with the phonemes is $71.4(\%)$. Itakura-saito distortion measure is used to phoneme segmentation and phoneme recognition.
자동차 환경에서 Oak DSP 코어 기반 음성 인식 시스템 실시간 구현
우경호,양태영,이충용,윤대희,차일환 한국음성과학회 1999 음성과학 Vol.6 No.1
This paper presents a real-time implementation of a speaker independent speech recognition system based on discrete hidden markov model(DHMM0). This system is developed for a car navigation system to design on-chip VLSI system of speech recognition which is used by fixed point Oak DSP core of DSP GROUP LTD. We analyze recognition procedure with C language to implement fixed point real-time algorithms. Based on the analyses, we improve the algorithms which are possible to operate in real-time, and can verity the recognition result at the same time as speech ends, by processing all recognition routines within a frame. A car noise is the colored noise concentrated haavily on the low frequency segment under 400 Hz. For the noise robust processing, the high pass filtering and the liftering on the distance measure of feature vectors are applied to the recognition system. Recognition experiments on the twelve isolated command words were performed. The recognition rates of the baseline recognizer were 98.68 % in a stopping situation and 80.7 % in a running situation. Using the noise processing methods, the recognition rates were enhanced to 89.04% in running situation. Keyword : speech recognition, real-time implementation, fixed point Oak DSP
심리 음향 켑스트럼 평균 차감법을 이용한 이동 전화망에서의 음질 평가
윤종진,박상욱,박영철,윤대희,차일환 한국음성과학회 1999 음성과학 Vol.6 No.1
For the set up, management and repair of a mobile communication system, continuous estimation of speech quality is required. Speech quality measurement can be conducted by listerner's judgement in a subjective test such as MOS (Mean Opinion Score) test. However, this method is laborious, expensive and time-consuming, it is advisable to predict subjective speech quality via objective measures. This paper presents a robust objective speech quality measure,PLP-CMS (Perceptual Linear Predictive-Cepstral Mean Subtraction), which can predict subjective speech quality in mobile communication systems. PLP-CMS has a high correlation with subjective quality owing PLP (Perceptual Linear Predictive) analysis and shows a robust performance not being influenced by PSTN (Public Switched Telephone Network) channel effects due to CMS (Cepstral Mean Subtraction). To prove the performance of out proposed algorithm, we carried out subjective and objective quality estimation on speech samples which are variously distorted in a real mobile communication system. As a result, we demonstrated that PLP-CMS has a higher correlation with subjective quality than PSQM (Perceptual Speech Quality Measure) and PLP-CD (Perceptual Linear Predictive-Cepstral Distance). Keyword: PLP-CMS, MOS, speech quality measure, channel effect