• 음성과학
• /
• 제11권2호
• /
• pp.247-257
• /
• 2004

There has been many research efforts to overcome the problems of speech recognition in the noisy conditions. Among them, the model-based compensation methods such as the parallel model combination (PMC) and vector Taylor series (VTS) have been found to perform efficiently compared with the previous speech enhancement methods or the feature-based approaches. In this paper, a data-driven model compensation approach that adapts the HMM(hidden Markv model) parameters for the noisy speech recognition is proposed. Instead of assuming some statistical approximations as in the conventional model-based methods such as the PMC, the statistics necessary for the HMM parameter adaptation is directly estimated by using the Baum-Welch algorithm. The proposed method has shown improved results compared with the PMC for the noisy speech recognition.

• 말소리와 음성과학
• /
• 제4권4호
• /
• pp.79-86
• /
• 2012

In the two-band excitation (TBE) model, maximum voiced frequency (MVF) is the most important feature of the excitation parameter because the synthetic speech quality depends on MVF. Thus, this paper proposes an enhanced MVF estimation scheme based on the peak picking method. In the proposed scheme, the local peak and the peak lobe are picked from the spectrum of a linear predictive residual signal. The normalized distance between neighboring peak lobes is calculated and utilized as a feature to estimate MVF. Experimental results of both objective and subjective tests show that the proposed scheme improves synthetic speech quality compared with that of the conventional one.

• 말소리와 음성과학
• /
• 제2권1호
• /
• pp.87-95
• /
• 2010

In this paper, we address issues associated with mixed-lingual text-to-speech based on context-dependent HMMs, where there are multiple sets of HMMs corresponding to each individual language. In particular, we propose smoothing techniques of synthesis parameters at the boundaries between different languages to obtain more natural quality of speech. In other words, mel-frequency cepstral coefficients (MFCCs) at the language boundaries are smoothed by applying several linear and nonlinear approximation techniques. It is shown from an informal listening test that synthesized speech smoothed by a modified version of linear least square approximation (MLLSA) and a quadratic interpolation (QI) method is preferred than that without using any smoothing technique.

• 대한음성학회지:말소리
• /
• 제47호
• /
• pp.131-140
• /
• 2003

We propose a new method of generating client models for HMM based text-dependent speaker verification system with only a small amount of training data. To make a client model, statistical methods such as segmental K-means algorithm are widely used, but they do not guarantee the quality or reliability of a model when only limited data are avaliable. In this paper, we propose a blind speech segmentation based on level building DTW algorithm as an alternative method to make a client model with limited data. In addition, considering the fact that voiced sounds have much more speaker-specific information than unvoiced sounds and energy of the former is higher than that of the latter, we also propose a new score evaluation method using the observation probability raised to the power of weighting factor estimated from the normalized log energy. Our experiment shows that the proposed methods are superior to conventional HMM based speaker verification system.

• Journal of Welding and Joining
• /
• 제20권6호
• /
• pp.45-45
• /
• 2002

This study is a middle report on the development of intelligent spot welding monitoring technology applicable to the production line. An intelligent algorithm has been developed to predict the quality of welding in real time. We examined whether it is effective or not through the In-Line and the Off-Line tests. The purpose of the present study is to provide a reliable solution which can prevent welding defects in production site. In this study, the process variables, which were monitored in the primary circuit of the welding, are used to estimate the weld quality by Hidden Markov Model(HMM). The primary dynamic resistance patterns are recognized and the quality is estimated in probability method during the welding. We expect that the algorithm proposed in the present study is feasible to the applied in the production sites for the purpose of in-process real time quality monitoring of spot welding.

• Journal of Welding and Joining
• /
• 제20권6호
• /
• pp.769-775
• /
• 2002

This study is a middle report on the development of intelligent spot welding monitoring technology applicable to the production line. An intelligent algorithm has been developed to predict the quality of welding in real time. We examined whether it is effective or not through the In-Line and the Off-Line tests. The purpose of the present study is to provide a reliable solution which can prevent welding defects in production site. In this study, the process variables, which were monitored in the primary circuit of the welding, are used to estimate the weld quality by Hidden Markov Model(HMM). The primary dynamic resistance patterns are recognized and the quality is estimated in probability method during the welding. We expect that the algorithm proposed in the present study is feasible to the applied in the production sites for the purpose of in-process real time quality monitoring of spot welding.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2014년도 추계학술대회 논문집
• /
• pp.833-834
• /
• 2014

In recent years, a pattern recognition method has been widely used by researchers for fault diagnoses of mechanical systems. A pattern recognition method determines the soundness of a mechanical system by detecting variations in the system's vibration characteristics. Hidden Markov model has recently been used as pattern recognition methods in various fields. In this study, a HMM method for the fault diagnosis of a mechanical system is introduced, and a rotating machine with mass unbalance is selected for fault diagnosis. Moreover, a diagnosis procedure to identity the size of a defect is proposed in this study.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 가을 학술발표논문집 Vol.32 No.2 (2)
• /
• pp.898-900
• /
• 2005

강인한 행동 인식을 하기 위해서는 연속적인 전신 제스처 입력에서부터 의미 있는 부분만을 분할하는 기술이 필요하다. 하지만 의미 없는 행동을 정의하고, 모델링 하기 어렵기 때문에, 연속적인 행동에서 중요한 행동만을 분할한다는 것은 어려운 문제이다. 본 논문에서는 연속적인 전신 행동의 입력으로부터 의미있는 부분을 분할하고, 동시에 인식하는 방법을 제안한다. 의미 없는 행동을 제거하고, 의미 있는 행동만을 적출하기 위해 garbage 모델을 제안한다. 이 garbage 모델에 의해 의미 있는 부분만 HMM의 입력으로 사용되어지며, 학습되어진 HMM 중에서 가장 높은 확률 값을 가지는 모델을 선택하여. 행동으로 인식한다. 제안된 방법은 20명의 3D motion capture data와 Principal Component Analysis를 이용하여 생성된 80개의 행동 데이터를 이용하여 평가하였으며, 의미 있는 행동과, 의미 없는 행동을 포함하는 연속적인 제스처 입력열에 대해 $98.3\%$의 인식률과 $94.8\%$의 적출률을 얻었다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2001년도 가을 학술발표논문집 Vol.28 No.2 (2)
• /
• pp.34-36
• /
• 2001

본 논문에서는 모델 기반의 잡음 보상 방법인 PMC (parallel model combination)를 온라인상에서 적용하는 방법에 관해 논한다. PMC는 파라미터 보상시 미리 계산된 잡음 모델을 필요로 하며 파라미터 보상에 많은 연산을 요구하므로 온라인으로 모델 파라미터를 보상하기가 어렵다. 본 논문에서는 이러한 문제를 해결하기 위해 기존에 제안된 온라인 모델 보상 방법을 살펴보고, 기존 방법에서 보상 시간 문제로 제외한 PMC의 공분산 보상을 비교적 적은 연산량으로 수행하여 인식성능을 더욱 향상시켰다. 고립 숫자음 인식시스템에 백색 잡음을 SNR 0, 5, 10 dB로 가산한 평가 자료로 실험한 결과, 제안한 방식은 PMC를 적용한 경우에 비해 모델 적응 시간은 적게 걸리면서도 기존의 온라인 모델 보상 방법에 비해 평균 10%의 인식률 향상을 보였다.

• Genomics & Informatics
• /
• 제13권4호
• /
• pp.152-155
• /
• 2015

Recently, the Encyclopedia of DNA Elements (ENCODE) Analysis Working Group converted data from ChIP-seq analyses from the Broad Histone track into 15 corresponding chromatic maps that label sequences with different kinds of histone modifications in promoter regions. Here, we publish a frequency profile of the three ChromHMM promoter states, at 200-bp intervals, with particular reference to the existence of sequence patterns of promoter elements, GC-richness, and transcription starting sites. Through detailed and diligent analysis of promoter regions, researchers will be able to uncover new and significant information about transcription initiation and gene function.