A New Endpoint Detection Method Based on Chaotic System Features for Digital Isolated Word Recognition System

장한(Xian Zang),정길도(Kil To Chong) 大韓電子工學會 2009 電子工學會論文誌-SC (System and control) Vol.46 No.5

음성 인식 연구에서 잡음이 있는 상태에서 음성 발음상의 시작점과 종단점을 찾는 것은 매우 중요하다. 기존 음성인식 시스템의 오차는 대부분 참고템플릿의 시작점과 종단점을 왜란이나 잡음으로 인해 자동적으로 찾지 못했을 경우 발생한다. 따라서 음성 신호상에서 필요 없는 부분을 제거할 수 있는 방법이 필요하다. 기존의 음성 종단점을 찾는 방법으로는 시간도메인 측정방법, 미세시간 에너지 분석, 영교차율 방법이 있다. 위의 방법들은 저주파 신호 노이즈의 영향에 정밀성을 보장을 못한다. 따라서 본 논문에서는 시간영역상에서 리야프노프 지수를 이용한 종단점 인식 알고리즘을 제안하였다. 기존의 방법들과의 비교를 통해 제안한 방법의 성능 우수성을 보였으며, 시뮬레이션 및 실험을 통해 잡음환경에서도 음성종단 인식이 가능함을 보였다. In the research field of speech recognition, pinpointing the endpoints of speech utterance even with the presence of background noise is of great importance. These noise present during recording introduce disturbances which complicates matters since what we just want is to get the stationary parameters corresponding to each speech section. One major cause of error in automatic recognition of isolated words is the inaccurate detection of the beginning and end boundaries of the test and reference templates, thus the necessity to find an effective method in removing the unnecessary regions of a speech signal. The conventional methods for speech endpoint detection are based on two linear time-domain measurements: the short-time energy, and short-time zero-crossing rate. They perform well for clean speech but their precision is not guaranteed if there is noise present, since the high energy and zero-crossing rate of the noise is mistaken as a part of the speech uttered. This paper proposes a novel approach in finding an apparent threshold between noise and speech based on Lyapunov Exponents (LEs). This proposed method adopts the nonlinear features to analyze the chaos characteristics of the speech signal instead of depending on the unreliable factor-energy. The excellent performance of this approach compared with the conventional methods lies in the fact that it detects the endpoints as a nonlinearity of speech signal, which we believe is an important characteristic and has been neglected by the conventional methods. The proposed method extracts the features based only on the time-domain waveform of the speech signal illustrating its low complexity. Simulations done showed the effective performance of the proposed method in a noisy environment with an average recognition rate of up 92.85% for unspecified person.

A New Endpoint Detection Method Based on Chaotic System Features for Digital Isolated Word Recognition System

장한(Xian Zang),정길도(Kil To Chong) 대한전기학회 2009 정보 및 제어 심포지엄 논문집 Vol.2009 No.5

In the research of speech recognition, locating the beginning and end of a speech utterance in a background of noise is of great importance. Since the background noise presenting to record will introduce disturbance while we just want to get the stationary parameters to represent the corresponding speech section, in particular, a major source of error in automatic recognition system of isolated words is the inaccurate detection of beginning and ending boundaries of test and reference templates, thus we must find potent method to remove the unnecessary regions of a speech signal. The conventional methods for speech endpoint detection are based on two simple time-domain measurements - short-time energy, and short-time zero-crossing rate, which couldn't guarantee the precise results if in the low signal-to-noise ratio environments. This paper proposes a novel approach that finds the Lyapunov exponent of time-domain waveform. This proposed method has no use for obtaining the frequency-domain parameters for endpoint detection process, e.g. Mel-Scale Features, which have been introduced in other paper. Comparing with the conventional methods based on short-time energy and short-time zero-crossing rate, the novel approach based on time-domain Lyapunov Exponents (LEs) is low complexity and suitable for Digital Isolated Word Recognition System.

Digital Isolated Word Recognition System based on MFCC and DTW Algorithm

장한(Xian Zang),정길도(Kil To Chong) 대한전기학회 2008 대한전기학회 학술대회 논문집 Vol.2008 No.10

The most popular speech feature used in speech recognition today is the Mel-Frequency Cepstral Coefficients (MFCC) algorithm, which could reflect the perception characteristics of the human ear more accurately than other parameters. This paper adopts MFCC and its first order difference, which could reflect the dynamic character of speech signal, as synthetical parametric representation. Furthermore, we quote Dynamic Time Warping (DTW) algorithm 10 search match paths in the pattern recognition process. We use the software "Gold Wave" to record English digitals in the lab environments and the simulation results indicate the algorithm has higher recognition accuracy than others using LPCC, etc. as character parameters in the experiment for Digital Isolated Word Recognition (DIWR) system.

리아프노프 지수를 이용한 음성신호 종점 탐색 방법

장한(Xian Zang),김정연(Jeong Yeon Kim),정길도(Kil To Chong) 대한전자공학회 2009 電子工學會論文誌-SC (System and control) Vol.46 No.1

음성 인식 연구에서 잡음이 존재하는 음성 발음의 처음과 끝을 찾아내는 것은 매우 중요하다. 음성 종점 탐지를 위한 기존의 방식으로는 2개의 간단한 시간 영역 측정법인 단시간 에너지와 단시간 영점교차 비율 방법이 있다. 위의 방법들은 낮은 신호 대 잡음비의 환경에서는 정확한 결과를 보장 할 수 없기 때문에 본 논문에서는 시간 영역 파형의 리아프노프 지수를 이용하여 음성의 시작과 종점을 구별하는 새로운 접근법을 제시하였다. 제안한 방법은 Mel-Scale 특징 방법에서 요구되는 종점 탐지 과정을 위한 주파수 영역 매개변수를 얻는 과정이 필요 없기 때문에 보다 간단하다. 제안한 방법의 성능 검증을 위해 아라비아 숫자의 음성단어 분석에 적용해 보았으며, 결과를 통하여 제안한 방법이 인식률을 현저히 증가시킴을 확인하였다. In the research of speech recognition, locating the beginning and end of a speech utterance in a background of noise is of great importance. The conventional methods for speech endpoint detection are based on two simple time-domain measurements ? short-time energy, and short-time zero-crossing rate, which couldn’t guarantee the precise results if in the low signal-to-noise ratio environments. This paper proposes a novel approach that finds the Lyapunov exponent of time-domain waveform. This proposed method has no use for obtaining the frequency-domain parameters for endpoint detection process, e.g. Mel-Scale Features, which have been introduced in other paper. Accordingly, this algorithm is low complexity and suitable for Digital Isolated Word Recognition System.

Nonlinear Parameter based Endpoint Detection Algorithm for Isolated Word Recognition System with Neural Network

Xian Zang(장한),Kil-To Chong(정길도) 대한전자공학회 2010 대한전자공학회 학술대회 Vol.2010 No.6

청각 주파수 응답에 기반한 자동 모음 개시 지점 탐지

장한(Zang, Xian),김학태(Kim, Hag-Tae),정길도(Chong, Kil-To) 한국산학기술학회 2012 한국산학기술학회논문지 Vol.13 No.1

이 논문에서는 인간 청각 시스템에 기반한 모음 개시 지점 (VOP) 탐지 방법을 제시하였다. 이 방법을 통해 ‘지각의’ 주파수 범위, 즉 선형 음향 주파수에서의 Mel Scale을 보여준 후 일련의 삼각 Mel-weighted Filter Bank를 만 들어 인간의 청각 시스템에서 대역 필터링 기능을 시뮬레이션하였다. 이러한 비선형 임계 대역 Filter Bank는 데이터 차원수를 크게 감소시키고 비선형적으로 간격을 둔 Mel 스펙트럼에서 더욱 효과적으로 포먼트를 생성하기 위해 조파 들의 영향을 제거해준다. Mel 스펙트럼의 첨두 에너지 합은 각 프레임의 특징으로 추출하고 에너지 진폭이 급격히 상승하기 시작할 때의 특성은 Gabor 윈도우를 사용하여 VOP로 탐지한다. 실험 결과를 통해서 다른 종류의 자음들과 연결된 12개의 모음들을 포함하는 한 단어 데이터베이스에 대한 제안된 방법의 평균 정확도는 단시간 에너지와 zero-crossing 비율에 기반을 둔 다른 모음 탐지 방법들보다 높은 72.73% 이상임을 확인하였다. This paper presents a vowel onset point (VOP) detection method based on the human auditory system. This method maps the “perceptual” frequency scale, i.e. Mel scale onto a linear acoustic frequency, and then establishes a series of Triangular Mel-weighted Filter Bank simulate the function of band pass filtering in human ear. This nonlinear critical-band filter bank helps greatly reduce the data dimensionality, and eliminate the effect of harmonic waves to make the formants more prominent in the nonlinear spaced Mel spectrum. The sum of mel spectrum peaks energy is extracted as feature for each frame, and the instinct at which the energy amplitude starts rising sharply is detected as VOP, by convolving with Gabor window. For the single-word database which contains 12 vowels articulated with different kinds of consonants, the experimental results showed a good average detection rate of 72.73%, higher than other vowel detection methods based on short-time energy and zero-crossing rate.

Otsu's method for speech endpoint detection

고유(Yu Gao),장한(Xian Zang),정길도(Kil To Chong) 대한전기학회 2009 정보 및 제어 심포지엄 논문집 Vol.2009 No.5

This paper presents an algorithm, which is based on Otsu's method, for accurate and robust endpoint detection for speech recognition under noisy environments. The features are extracted in time domain, and then an optimal threshold is selected by minimizing the discriminant criterion, so as to maximize the separability of the speech part and environment part. The simulation results show that the method playa good performance in detection accuracy.