检索结果-南通市图书馆

Monaural voiced speech segregation based on elaborate harmonic grouping strategies

在线全文

学校读者我要写书评

暂无评论

Science china(Information Sciences) 2011年第12期54卷 2491-2500页

作者： LIU WenJu 1 , ZHANG XueLiang 1 , JIANG Wei 1 , LI Peng 2 & XU Bo 2 1 national laboratory of pattern recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, china 2 Digital Media Content Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, china national laboratory of pattern recognition Institute of Automation Chinese Academy of Sciences Beijing China Digital Media Content Technology Research Center Institute of Automation Chinese Academy of Sciences Beijing China

In this paper, an enhanced algorithm based on several elaborate harmonic grouping strategies for monaural voiced speech segregation is proposed. Main achievements of the proposed algorithm lie in three aspects. Firstly, the algorithm classifies the time-frequency (T-F) units into resolved and unresolved ones by carrier-to-envelope energy ratio, which leads to more accurate classification results than by cross-channel correlation. Secondly, resolved T-F units are grouped together according to minimum amplitude principle, which has been verified to exist in human perception, as well as the harmonic principle. Finally, "enhanced" envelope autocorrelation function is employed to detect amplitude modulation rates, which helps a lot in reducing half-frequency error in grouping of unresolved units. Systematic evaluation and comparison show that performance of separation is greatly improved by the proposed algorithm. Specifically, signal-to-noise ratio (SNR) is improved by 0.96 dB compared with that of previous method. Besides, our algorithm is also effective in improving the PESQ score and subjective perception score.

关键词： computational auditory scene analysis voiced speech separation harmonistic principle minimum amplitude principle elaborate harmonic grouping strategies

A TENSOR ANALYSIS METHOD FOR ESTIMATING 3-D MOTION PARAMETERS

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Electronics(china) 1992年第3期9卷 209-217页

作者：李象霖陈小平 Graduate School USTC Academia SinicaNational Pattern Recognition LaboratoryBeijing 100039

By using the center projection image sequence to estimate 3-D motion parameters,one needs to know the corresponding relationship between the feature of motion object in spaceand the projection coordinate on image *** order to avoid using the relationship of featurecorrespondence,the tensor analysis method in the affine transformation system is presented,andthe simulation data of experimental results are given.

关键词： Signal processing Image sequence analysis 3-D motion analysis Tensor analysis method

3D virtual reconstruction of the Pleistocene cheetah skull from the Tangshan, Nanjing, china

在线全文

学校读者我要写书评

暂无评论

Progress in Natural Science:Materials International 2007年第1期17卷 74-79页

作者： DONG Wei, HOU Xinwen, LIU Jinyi, FANG Yingsan, JIN Changzhu and ZHU Qizhi ( Institute of Vertebrate Paleontology and Paleoanthropology, Chinese Academy of Sciences, Beijing 100044, china State Key laboratory of pattern recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100080, china Nanjing Provincial Museum, Nanjing 210016, china Radiology Department, Renmin Hospital, Peking University, Beijing 100044, china) Institute of Vertebrate Paleontology and Paleoanthropology Chinese Academy of Sciences Beijing 100044 China State Key laboratory of pattern recognition Institute of Automation Chinese Academy of Sciences Beijing 100080 China Nanjing Provincial Museum Nanjing 210016 China Radiology Department Renmin Hospital Peking University Beijing 100044 China

The development of computer tomography and image processing has made it possible to establish virtual 3D reconstruction and non-invasive dissection of fossil specimens. We used these methods to reconstruct a virtual 3D skull of a Pleistocene cheetah skull from the Tuozi cave, Tangshan, Nanjing, and virtually dissected it for anatomic studies, and measured the volumes of different parts of the endocranium. The endocranium of the cheetah skull has showed that its frontal sinus is beehive-like, the frontal lobe of cerebra is relatively large but the temporal lobe is relatively small, its cerebral sulcus and gyrus are more complicated than those of the domestic cat, similar to those of the domestic dog, but simpler than those of giant panda, pig, cattle and horse. The technology of virtual 3D reconstruction and non-invasive dissection of fossil specimens can extend the morphological study from the exterior to the interior, and it can also help to study fragile specimens and virtually backup rare and precious specimens.

关键词： CT imaging 3D reconstruction cheetah skull early Pleistocene Tangshan Nanjing.

Modeling of Accent Perception in Chinese Spontaneous Speech

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Modeling of Accent Perception in Chinese Spontaneous Speech

Approximate computation of Madaline sensitivity based on discrete stochastic technique

第六届全国现代语音学学术会议

作者： Tao Jianhua national laboratory of pattern recognition Institute of Automation,Chinese Academy of Sciences,Beijing,china,100080

The accent was proved to be the essential links between linguistics and acoustics, and behaves as an important parameter for prosody processing and unit selection in speech synthesis system. In the paper, some acoustical measurements are carried out on FO, duration, silence in order to disclose the relationship between accent and corresponding acoustical parameters. The normalized acoustic parameters are induced to facilitate the accent detecting. Based on this, a model is proposed to predict accent in spontaneous speech. The method is proved to be very successful and has been used to label accent automatically for our large corpus. Further listening tests also show that the labelling results reaches 86% accurate rate, which is nearly the same as the agreement of hand labelling results. Furthermore, different native’s evaluations are also compared in the paper.

关键词：

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Science china(Information Sciences) 2010年第12期53卷 2399-2414页

作者： ZHONG ShuiMing , ZENG XiaoQin, LIU HuiYi & XU Yan Institute of pattern recognition and Intelligent System, College of Computer and Information Engineering, Hohai University, Nanjing 210098, china Institute of pattern recognition and Intelligent System College of Computer and Information Engineering Hohai University Nanjing China

The computation of the sensitivity of a Madaline’s output to its parameter perturbation is system- atically discussed. Firstly, according to the discrete feature of Adalines, a method based on discrete stochastic technique is proposed, which derives some analytical formulas for the computation of Adalines’ sensitivity. The method can theoretically solve some problems that are unsolvable by the existing methods based on continu- ous stochastic techniques, release some unpractical constraints, and make it available to theoretically analyze the approximation error of Adalines’ sensitivity. Secondly, on the basis of the sensitivity of Adalines and the structural characteristics of Madalines, a new selection strategy depending on a type of dedication degree for computing Madalines’ sensitivity is proposed, which is superior to current popular way of simply averaging in both precision and complexity. The proposed formulas and algorithm have the advantages of simplicity, low computational complexity, small approximation error, and high generality, as have been verified by a great amount of experimental simulations.

关键词： Adaline Madaline feedforward networks sensitivity parameter perturbation stochastic discrete technique

中国非儿童癌症患者脓毒血症流行情况及地域分布:一项全国横断面研究

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science Bulletin 2024年第11期69卷 1637-1641页

作者：陆斌胥洋李娜周月阳马旭东陈燕董润周翔代敏陈宏达翁利杜斌中国国家重症医学质控中心和中国重症医学临床试验组 Center for Prevention and Early Intervention National Infrastructures for Translational MedicineInstitute of Clinical MedicinePeking Union Medical College HospitalChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijing 100730China Department of Cancer Epidemiology National Cancer Center/National Clinical Research Center for Cancer/Cancer HospitalChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijing 100021China Department of Pharmacy Administration and Clinical Pharmacy School of Pharmaceutical SciencesPeking University Health Science CenterBeijing 100191China Department of Medical Epidemiology and Biostatistics Karolinska InstitutetStockholm 17177Sweden Department of Medical Administration National Health Commission of the People’s Republic of ChinaBeijing 100044China Medical Intensive Care Unit State Key Laboratory of Complex Severe and Rare DiseasesPeking Union Medical College HospitalChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijing 100730China Intensive Care Unit State Key Laboratory of Complex Severe and Rare DiseasesPeking Union Medical College HospitalChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijing 100730China 不详

Cancer poses a major public health burden worldwide,with approximately 18,094,716 newly diagnosed cases and 9,894,402 cancer-related deaths in 2020[1].Infections such as sepsis are among the leading causes of death in... 详细信息

关键词：脓毒血症横断面研究 death 地域分布

Multi-feature Based Chinese-English Named Entity Extraction from Comparable Corpora

在线全文

学校读者我要写书评

暂无评论

Multi-feature Based Chinese-English Named Entity Extraction ...

Study on the Medical Image Distributed Dynamic Processing Method

第20届亚太地区语言、信息和计算国际会议

作者： Min Lu, Jun Zhao national laboratory of pattern recognition. Institute of Automation, Chinese Academy of Sciences, Beijing, 100080, china

Bilingual Named Entity Extraction is important to some cross language information processes such as machine translation (MT), cross-lingual information retrieval (CLIR), etc. A lot of previous work extracted bilingual Named Entities from parallel corpus. Here we propose a multi-feature based method to extract bilingual Named Entities from comparable corpus. We first recognize the Chinese and English Named Entities respectively from the Chinese and English part of the comparable corpus. Then all the feature scores are calculated for every possible pair of Chinese and English Named Entities. At last we combine these feature scores together and decide which pairs are mutual translations. For translation score calculation, we didn't use the formula of IBM model I like previous approach. In stead, we used a modified edit distance to take the order of words into consideration. Experiment shows that the F-score of this method increased by 11 %. And with the multi-feature integration strategy encouraging results are obtained.

关键词： Multi-feature Based Chinese-English Named Entity Extraction from Comparable Corpora

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2003年第4期14卷 69-76页

作者： Zhang Quanhai & Shi PengfeiInstitute of Image Processing and pattern recognition, Shanghai Jiaotong University, Shanghai 200030, P. R. china Institute of Image Processing and pattern recognition Shanghai Jiaotong University Shanghai 200030 P.R. China

To meet the challenge of implementing rapidly advanced, time-consuming medical image processing algorithms, it is necessary to develop a medical image processing technology to process a 2D or 3D medical image dynamically on the web. But in a premier system, only static image processing can be provided with the limitation of web technology. The development of Java and CORBA (common object request broker architecture) overcomes the shortcoming of the web static application and makes the dynamic processing of medical images on the web available. To develop an open solution of distributed computing, we integrate the Java, and web with the CORBA and present a web-based medical image dynamic processing methed, which adopts Java technology as the language to program application and components of the web and utilies the CORBA architecture to cope with heterogeneous property of a complex distributed system. The method also provides a platform-independent, transparent processing architecture to implement the advanced image routines and enable users to access large dataset and resources according to the requirements of medical applications. The experiment in this paper shows that the medical image dynamic processing method implemented on the web by using Java and the CORBA is feasible.

关键词： medical image dynamic processing based on web distributed computing interoperation CORBA.

Multimodality Image Registration Using Parallel Genetic Algorithms and Multi-start Simplex Method

在线全文

学校读者我要写书评

暂无评论

Multimodality Image Registration Using Parallel Genetic Algo...