http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Comparison of Observation Confidence Estimators for Robust Speaker Verification
Xinjie Ma,Tan Dat Trinh,Jin Young Kim 한국정보기술학회 2017 한국정보기술학회논문지 Vol.15 No.7
In this paper, we first explore a modified adaptive Gaussian mixture model (MAGMM) by investigating the confidence value of observation vectors to deal with noise conditions problem. The observation confidence values are estimated by using the frame SNR values calculated between the input noisy speech and the enhanced speech, and the sigmoid function. We compare three speech enhancement techniques, minimum mean square error logarithm shorttime spectral amplitude (MMSE log-STSA), low-rank matrix recovery (LRR) and multiple low-rank representation (MLRR), for observation confidence computation. Furthermore, we also consider the effect of the use of observation confidence value in the GMM-supervector (GSV) and i-vector approaches which are considers as input feature vectors for the Support vector machine (SVM). To verify the accuracy of the speaker system, we use utterances from a Korean drama “You came from the stars.” The experimental results show that our proposed approaches achieve better performance than the baseline systems under noisy environments.
Tan Dat Trinh,Xinjie Ma,Hak-Jae Lee(이학재),Jin Young Kim(김진영),Seung-Ho Choi(최승호) 한국정보기술학회 2016 한국정보기술학회논문지 Vol.14 No.10
In this paper, we propose a new method to detect cheering events in basketball audio streams by combining short time Fourier transform (STFT) bin strengths, adaptive Gaussian mixture model (GMM) and low rank matrix recovery (LRR) approach. First, we apply the STFT and then calculate pre-defined frequency bins based on a specific frequency range of cheering sounds. An adaptive GMM model is used as a classifier to detect cheering events. In addition, we also propose to apply a post processing approach based on the LRR and power spectral density (PSD) within specified frequency interval to reduce false alarms and to improve the performance of the system. The experimental results on Korean basketball audio database demonstrate that our proposed method can outperform other well-known methods and achieve high accuracy. Specifically, recall rate, precision rate and F value are, respectively, 92.38%, 91.29% and 91.83%.
Improved Running Gaussian Average for Background Subtraction in Thermal Imagery
Tan Dat Trinh,Xinjie Ma,Jin Young Kim 한국정보기술학회 2017 한국정보기술학회논문지 Vol.15 No.7
In this paper, we propose a new method for background subtraction in thermal videos by improving the running Gaussian average technique (RGA). First, we propose a new background modeling even in the presence of moving objects in scene using region-based robust principle component analysis (RPCA). To enhance the performance or reduce computation cost of the RGA, we incorporate selectivity and random spatial subsampling techniques into background updating scheme. In addition, we also propose a new technique to deal with intensity sudden change problem by detecting corrupted frame based on skewness value of histogram followed by intensity enhancement using histogram matching method. Finally, we reduce number of ROI regions for human detection step by using a candidate extraction using morphology operator. Experiment results with our thermal database confirm that the proposed method significantly outperforms the baseline RGA and frame difference methods. Specially, the recall rate, precision rate and F value of the proposed method are 82.02%, 75.08% and 73.20% in comparison to 76.12%, 42.80% and 39.64%, of the baseline RGA, respectively.
Yingqin Wei,Baojuan Hou,Haiyan Fang,Xinjie Sun,Feng Ma 고려인삼학회 2020 Journal of Ginseng Research Vol.44 No.1
Background: Salting-out extraction (SOE) had been developed as a special branch of aqueous two-phasesystem recently. So far as we know, few reports involved in extracting ginsenosides with SOE because ofthe lower recovery caused by the unique solubility and surface activity of ginsenosides. A new SOEmethod for rapid pretreatment of ginsenosides from the enzymatic hydrolysates of Panax quinquefoliumwas established in this article. Methods: The SOE system comprising ethanol and sodium carbonate was selected to extract ginsenosidesfrom the enzymatic hydrolysates of Panax quinquefolium, and HPLC was applied to analyze theginsenosides. Results: The optimized extraction conditions were as follows: the aqueous two-phase extraction systemcomprising ethanol, sodium carbonate, ethanol concentration of 41.51%, and the mass percent of sodiumcarbonate of 7.9% in the extraction system under the experimental condition. Extraction time had minorinfluence on extraction efficiency of ginsenosides. The results also showed that the extraction efficienciesof three ginsenosides were all more than 90.0% only in a single step. Conclusion: The proposed method had been successfully applied to determine ginsenosides in enzymatichydrolysate and demonstrated as a powerful technique for separating and purifying ginsenosides incomplex samples.
Wei, Yingqin,Hou, Baojuan,Fang, Haiyan,Sun, Xinjie,Ma, Feng The Korean Society of Ginseng 2020 Journal of Ginseng Research Vol.44 No.1
Background: Salting-out extraction (SOE) had been developed as a special branch of aqueous two-phase system recently. So far as we know, few reports involved in extracting ginsenosides with SOE because of the lower recovery caused by the unique solubility and surface activity of ginsenosides. A new SOE method for rapid pretreatment of ginsenosides from the enzymatic hydrolysates of Panax quinquefolium was established in this article. Methods: The SOE system comprising ethanol and sodium carbonate was selected to extract ginsenosides from the enzymatic hydrolysates of Panax quinquefolium, and HPLC was applied to analyze the ginsenosides. Results: The optimized extraction conditions were as follows: the aqueous two-phase extraction system comprising ethanol, sodium carbonate, ethanol concentration of 41.51%, and the mass percent of sodium carbonate of 7.9% in the extraction system under the experimental condition. Extraction time had minor influence on extraction efficiency of ginsenosides. The results also showed that the extraction efficiencies of three ginsenosides were all more than 90.0% only in a single step. Conclusion: The proposed method had been successfully applied to determine ginsenosides in enzymatic hydrolysate and demonstrated as a powerful technique for separating and purifying ginsenosides in complex samples.