• Journal of the Korea Computer Industry Society
• /
• v.5 no.2
• /
• pp.269-274
• /
• 2004

Noisy speech recognition is one of most important problems in speech recognition. In this paper, a method which efficiently removes the mixed noise with speech, is proposed. The proposed method is based on the ICA to separate the mixed noise. ICA(Independent component analysis) is a signal processing technique, whose goal is to express a set of random variables as linear combinations of components that are statistically as independent from each other as possible.

• Journal of KIISE:Information Networking
• /
• v.30 no.1
• /
• pp.24-29
• /
• 2003

In this paper, a new method for the mixed image separation is presented using the independent component analysis, the innovation process, and the expectation-maximization. In general, the independent component analysis (ICA) is one of the widely used statistical signal processing schemes, which represents the information from observations as a set of random variables in the from of linear combinations of another statistically independent component variables. In various useful applications, ICA provides a more meaningful representation of the data than the principal component analysis through the transformation of the data to be quasi-orthogonal to each other. which can be utilized in linear projection.. However, it has been known that ICA does not establish good performance in source separation by itself. Thus, in order to overcome this limitation, there have been many techniques that are designed to reinforce the good properties of ICA, which improves the mixed image separation. Unfortunately, the innovation process still needs to be studied since it yields inconsistent innovation process that is attached to the ICA, the expectation and maximization process is added. The results presented in this paper show that the proposed improves the image separation as presented in experiments.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.6
• /
• pp.353-359
• /
• 2011

This paper proposes a vocal enhancement technique for improving the performance of vocal pitch detection in polyphonic music signal. The proposed vocal enhancement technique predicts an accompaniment signal from the input signal and generates an accompaniment replica signal according to the vocal power. Then, it removes the accompaniment replica signal from the input signal, resulting in a vocal-enhanced signal. The performance of the proposed method was measured by applying the same vocal pitch extraction method to the original and the vocal-enhanced signal, and the vocal pitch detection accuracy was increased by 7.1 % point in average.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06c
• /
• pp.185-188
• /
• 1998

실제의 음성 인식 및 음성 통신 등의 음성 처리 시스템에서는 음성 신호를 손상시키는 배경 잡음 신호의 존재로 그 성능이 많이 저하된다. 특히 차량 내와 같은 잡음이 극심한 상황에서는 전처리 부분에서 이러한 잡음을 제거시켜 주어야한다. 본 연구는 자동차 내의 배경 잡음에 의해 손상된 음성에서 배경 잡음을 주파수 차감에 의하여 제거시킨다. 특히 음성 정보의 손실이 적은 잡음 추정 방법으로 가중치를 이용하여 잡음을 추정하는 가중치 주파수 차감법을 이용하였다. 이러한 가중치 주파수 차감법 사용의 전제 조건은 잡음의 변화가 완만한 경우에 적당하다. 그러나 실제적인 상황에서 배경잡음신호의 변화가 큰 경우가 존재한다. 이러한 이유에서 본 연구는 잡은 추정시 잡음 추정값을 이용하여 추정 잡음 경계값을 적응적으로 변화하는 차감법을 제안한다. 이러한 방법은 추정된 잡음 신호의 변화율을 이용하여 경계값을 상황에 따라 적응적으로 변화시키는 방법이다. 모의 실험에 의하여 고정적인 경계값을 갖는 가중치 주파수 차감법에 비해 제안한 적응적 경계값을 갖는 가중치 주파수 차감법의 출력 SNR이 증가함을 확인하였고, 음성 인식 시스템에 정용한 인식 실험에서도 성능이 향상됨을 확인하였다.

• Proceedings of the KOSOMBE Conference
• /
• v.1985 no.06
• /
• pp.20-21
• /
• 1985

본 연구에서는 다중채널의 방대한 생체 신호 정보량을 전화회선을 이용하여, 효율적으로 전송하기 위한 생체 신호 데이터 전송 시스템을 설계한다. 특히 생체 신호 데이터를 신속하게 전송하기 위하여 가변어장 data frame을 사용하였고, 생체 신호 전처리 unit와의 interface 등을 검토하였다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.38 no.4
• /
• pp.31-36
• /
• 2001

In this paper we propose a method of pattern classification of the hand movement using EMG signals through Self-organizing feature map. Self-organizing feature map is an artificial neural network which organizes its output neuron through learning and therefore it can classify input patterns. The raw EMG signals become direct input to the Self-organizing feature map. The simulation and experiment results showed the effectiveness of the classification of EMG signal using the Self-organizing feature map.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2011.06a
• /
• pp.319-320
• /
• 2011

이 연구에서는 국토해양부 해양교통시설과 위성항법중앙사무소가 운영하고 있는 DGNSS 기준국의 신호수신환경을 파악하기 위해 관측자료의 TEQC 품질평가와 현장조사를 병행하였다. TEQC는 GPS 수신기로 관측한 원시자료를 RINEX형식으로 변환 편집하고, 관측자료의 품질을 점검하는데 이용하는 GPS 전처리 소프트웨어이다. TEQC 품질점검 기능을 통해 GPS 관측자료의 데이터수신율, L1과 L2 신호의 의사거리 다중경로오차, 사이클슬립에 관한 지수를 산출하였고, 이를 현장조사결과와 상호 비교하였다. 장기 관측 자료의 TEQC 품질지수 결과를 통하여 시간변화에 따른 관측소의 주변환경 및 장비변화 시점을 간접적으로 확인하였다.

• Proceedings of the Korean Society of Developmental Biology Conference
• /
• 2001.08a
• /
• pp.45-47
• /
• 2001

생쥐 착상전 초기배아에서 insulin과 tumor necrosis factor $\alpha$ (TNF$\alpha$)에 의한 배아의 형태 발생, 세포증식, apoptosis 및 MAPK활성의 변화를 조사하였다. Insulin에 의해 형태발생 및 포배당 세포수가 증가되었으며 TNF $\alpha$ 처리시 유의하게 감소하였다. TNT$\alpha$ 전처리시 insulin에 의한 발생 및 세포수 증가 촉진효과가 상쇄되었으며 TNF$\alpha$는 배아내 caspase-3의 활성을 증가시켰다. Insulin은 단시간내에 포배에서 mitogen activated protein kinase (MAPK or Erk1/2)의 활성을 증가시켰다. TNF$\alpha$는 포배내 MAPK의 활성을 감소시켰다. Insulin 처리 전 TNF $\alpha$를 전처리한 경우 insulin에 의한 MAPK 활성의 증가가 상쇄되었다. 배발생을 촉진하는 인슐린 신호전달 과정은 MAPK cascade를 경유하며 TNF $\alpha$를 경유한 신호전달과 Crosstalk이 존재하는 것으로 사료된다.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.42 no.8
• /
• pp.1242-1248
• /
• 2013

This study was performed to determine the effects of pretreatment (NT: non-treatment, BTS: boiling treatment with 3% sodium chloride, DTG: dipping treatment in glycerol) and drying methods (sun drying, hot air drying, and cold air drying) on the physicochemical properties and antioxidant activities of dried jujube (Zizyphus jujuba Mill.) fruits. Our results show that moisture content is lower (P<0.05) with DTG, and that moisture content is lower with hot air drying compared to other drying methods. The bulk density was highest with BTS. The soluble solids content was highest with DTG. Additionally, the soluble solids content were highest in the following order: hot air drying> cold air drying> sun drying. The titratable acidity of hot air drying was highest of all the drying methods. The titratable acidity was higher with NT and DTG, and the brix and acid ratio of sun drying was higher than other drying methods. Among the drying methods, BTS showed the best browning-retarding effect, whereas boiling treatment affected quality and color. The total polyphenol content from hot air drying and NT or DTG treatment was relatively higher than the content from BTS. The flavonoid content was highest with BTS, and all dried jujube showed relatively high antioxidant activities. The sensory evaluation results indicated that the organoleptic scores for overall preference were higher in the NT and DTG treatment groups. These results suggest that pretreatment and drying methods affect the quality of dried jujube fruit, and show that glycerol treatment with hot air drying can be applied to the production of high quality dried jujube.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.2
• /
• pp.137-142
• /
• 2010

Although multi-model speech recognizer has been shown to be quite successful in noisy speech recognition, the results were based on general speech front-ends which do not take into account noise adaptation techniques. In this paper, for the accurate evaluation of the multi-model based speech recognizer, we adopted a quite noise-robust speech front-end, AFE, which was proposed by the ETSI for the noisy DSR environment. For the performance comparison, the MTR which is known to give good results in the DSR environment has been used. Also, we modified the structure of the multi-model based speech recognizer to improve the recognition performance. N reference HMMs which are most similar to the input noisy speech are used as the acoustic models for recognition to cope with the errors in the selection of the reference HMMs and the noise signal variability. In addition, multiple SNR levels are used to train each of the reference HMMs to improve the robustness of the acoustic models. From the experimental results on the Aurora 2 databases, we could see better recognition rates using the modified multi-model based speech recognizer compared with the previous method.