检索结果-南通市图书馆

Emotional Vietnamese Speech Synthesis Using Style-Transfer Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第2期44卷 1263-1278页

作者： Thanh X.Le An T.Le quang H.nguyen School of Information and Communication Technology Hanoi University of Science and TechnologyHanoi10000Vietnam

In recent years,speech synthesis systems have allowed for the produc-tion of very high-quality ***,research in this domain is now turning to the problem of integrating emotions into ***,the method of con-structing a speech synthesizer for each emotion has some ***,this method often requires an emotional-speech data set with many *** data sets are very time-intensive and labor-intensive to ***,training each of these models requires computers with large computational capabilities and a lot of effort and time for model *** addition,each model for each emotion failed to take advantage of data sets of other *** this paper,we propose a new method to synthesize emotional speech in which the latent expressions of emotions are learned from a small data set of professional actors through a Flow-tron *** addition,we provide a new method to build a speech corpus that is scalable and whose quality is easy to ***,to produce a high-quality speech synthesis model,we used this data set to train the Tacotron 2 *** used it as a pre-trained model to train the Flowtron *** applied this method to synthesize Vietnamese speech with sadness and *** opi-nion score(MOS)assessment results show that MOS is 3.61 for sadness and 3.95 for *** conclusion,the proposed method proves to be more effec-tive for a high degree of automation and fast emotional sentence generation,using a small emotional-speech data set.

关键词： Emotional speech synthesis ﬂowtron speech synthesis style transfer vietnamese speech

Adaptive data fusion framework for modeling of non-uniform aerodynamic data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2023年第7期36卷 316-336页

作者： Vinh PHAM Maxim TYAN tuan Anh nguyen Chi-Ho LEE L.V.Thang nguyen Jae-Woo LEE Department of Aerospace Information Engineering Konkuk UniversitySeoul 05029Republic of Korea Konkuk Aerospace Design-Airworthiness Institute Konkuk UniversitySeoul 05029Republic of Korea

Multi-fidelity Data Fusion(MDF)frameworks have emerged as a prominent approach to producing economical but accurate surrogate models for aerodynamic data modeling by integrating data with different fidelity ***,most existing MDF frameworks assume a uniform data structure between sampling data sources;thus,producing an accurate solution at the required level,for cases of non-uniform data structures is *** address this challenge,an Adaptive Multi-fidelity Data Fusion(AMDF)framework is proposed to produce a composite surrogate model which can efficiently model multi-fidelity data featuring non-uniform ***,the design space of the input data with non-uniform data structures is decomposed into subdomains containing simplified ***,different MDF frameworks and a rule-based selection process are adopted to construct multiple local models for the subdomain *** the other hand,the Enhanced Local Fidelity Modeling(ELFM)method is proposed to combine the generated local models into a unique and continuous global ***,the resulting model inherits the features of local models and approximates a complete database for the whole design *** validation of the proposed framework is performed to demonstrate its approximation capabilities in(A)four multi-dimensional analytical problems and(B)a practical engineering case study of constructing an F16C fighter aircraft’s aerodynamic *** comparisons of the generated models using the proposed AMDF framework and conventional MDF approaches using a single global modeling algorithm are performed to reveal the adaptability of the proposed approach for fusing multi-fidelity data featuring non-uniform ***,the results indicated that the proposed framework outperforms the state-of-the-art MDF approach in the cases of non-uniform data.

关键词： Aerodynamic modeling Data fusion Diverse data structure Multi-fidelity data Multi-fidelity surrogate modeling

Integrating Machine Learning and Evidential Reasoning for User Profiling and Recommendation

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science and Systems Engineering 2023年第4期32卷 393-412页

作者： Toan nguyen Mau quang-Hung Le Duc-Vinh Vo Duy Doan Van-Nam Huynh University of Information Technology Ho Chi Minh CityVietnam Vietnam National University Ho Chi Minh CityVietnam Department of Information Technology Quy Nhon UniversityQuy NhonVietnam Ho Chi Minh City University of Banking Ho Chi Minh CityVietnam School of Knowledge Science Japan Advanced Institute of Science and TechnologyIshikawaJapan

User profiles representing users’preferences and interests play an important role in many applications of personalized *** the rapid growth of social platforms,there is a critical need for efficient solutions to learn user profiles from the information they shared on social platforms so as to improve the quality of recommendation *** problem of user profile learning is significantly challenging due to difficulty in handling data from multiple sources,in different formats and often associated with *** this paper,we introduce an integrated approach that combines advanced Machine Learning techniques with evidential reasoning based on Dempster-Shafer theory of evidence for user profiling and *** developed methods for user profile learning and multi-criteria collaborative filtering are demonstrated with experimental results and analysis that show the effectiveness and practicality of the integrated approach.A proposal for extending multi-criteria recommendation systems by incorporating user profiles learned from different sources of data into the recommendation process so as to provide better recommendation capabilities is also highlighted.

关键词： Machine learning Dempster-Shafer theory of evidence user profiles personalized recommendation preferences

On the speed of convergence of Picard iterations of backward stochastic differential equations

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Probability, Uncertainty and Quantitative Risk 2022年第2期7卷 133-150页

作者： Martin Hutzenthaler Thomas Kruse tuan Anh nguyen Faculty of Mathematics University of Duisburg-EssenThea-Leymann-Str.9EssenNordrhein-Westfalen 45127Germany Institute of Mathematics University of GiessenArndtstraβe 2Giessen 35392Germany

It is a well-established fact in the scientific literature that Picard iterations of backward stochastic differential equations with globally Lipschitz continuous nonlinearities converge at least exponentially fast to the *** this paper we prove that this convergence is in fact at least square-root factorially *** show for one example that no higher convergence speed is possible in ***,if the nonlinearity is zindependent,then the convergence is even factorially *** we reveal a phase transition in the speed of convergence of Picard iterations of backward stochastic differential equations.

关键词： Backward stochastic differential equation Picard iteration A priori estimate Semilinear parabolic partial differential equation

Target tracking method of Siamese networks based on the broad learning system

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2023年第3期8卷 1043-1057页

作者： Dan Zhang C.L.Philip Chen Tieshan Li Yi Zuo nguyen quang Duy Navigation College Dalian Maritime UniversityDalianChina Innovation and Entrepreneurship Education College Dalian Minzu UniversityDalianChina Computer Science and Engineering College South China University of TechnologyGuangzhouChina Department of Computer and Information Science Faculty of Science and TechnologyUniversity of MacaoMacaoChina School of Automation Engineering University of Electronic Science and Technology of ChinaChengduChina Faculty of Navigation Vietnam Maritime UniversityHaiphongVietnam

Target tracking has a wide range of applications in intelligent transportation,real‐time monitoring,human‐computer interaction and other ***,in the tracking process,the target is prone to deformation,occlusion,loss,scale variation,background clutter,illumination variation,etc.,which bring great challenges to realize accurate and real‐time *** based on Siamese networks promotes the application of deep learning in the field of target tracking,ensuring both accuracy and real‐time ***,due to its offline training,it is difficult to deal with the fast motion,serious occlusion,loss and deformation of the target during ***,it is very helpful to improve the performance of the Siamese networks by learning new features of the target quickly and updating the target position in time *** broad learning system(BLS)has a simple network structure,high learning efficiency,and strong feature learning *** at the problems of Siamese networks and the characteristics of BLS,a target tracking method based on BLS is *** method combines offline training with fast online learning of new features,which not only adopts the powerful feature representation ability of deep learning,but also skillfully uses the BLS for re‐learning and re‐*** broad re‐learning information is used for re‐detection when the target tracking appears serious occlusion and so on,so as to change the selection of the Siamese networks search area,solve the problem that the search range cannot meet the fast motion of the target,and improve the *** results show that the proposed method achieves good results on three challenging datasets and improves the performance of the basic algorithm in difficult scenarios.

关键词： broad learning system siamese network target tracking

STRONG CONVERGENCE OF AN INERTIAL EXTRAGRADIENT METHOD WITH AN ADAPTIVE NONDECREASING STEP SIZE FOR SOLVING VARIATIONAL INEQUALITIES

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mathematica Scientia 2022年第2期42卷 795-812页

作者： nguyen Xuan LINH Duong Viet THONG Prasit CHOLAMJIAK Pham Anh tuan Luong Van LONG Department of Mathematics Mathematics Falcuty of Information TechnologyNational University of Civil Engineering Division of Applied Mathematics Thu Dau Mot UniversityBinh Duong ProvinceVietnam School of Science University of PhayaoPhayao 56000Thailand Paculty of Mathematical Economics National Economics UniversityHanoi CityVietnam

In this work,we investigate a classical pseudomonotone and Lipschitz continuous variational inequality in the setting of Hilbert space,and present a projection-type approximation method for solving this *** method requires only to compute one projection onto the feasible set per iteration and without any linesearch procedure or additional projections as well as does not need to the prior knowledge of the Lipschitz constant and the sequentially weakly continuity of the variational inequality mapping.A strong convergence is established for the proposed method to a solution of a variational inequality problem under certain mild ***,we give some numerical experiments illustrating the performance of the proposed method for variational inequality problems.

关键词： Inertial method Tseng’s extragradient viscosity method variational inequality problem pseudomonotone mapping strong convergence

Assessing Asian Economies Renewable Energy Consumption Efficiency Using DEA with Undesirable Output

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2022年第10期43卷 347-362页

作者： Chia-Nan Wang Ngoc-Ai-Thy nguyen Thanh-tuan Dang Jing-Wein Wang Department of Industrial Engineering and Management National Kaohsiung University of Science and TechnologyKaohsiung80778Taiwan Department of Logistics and Supply Chain Management Hong Bang International UniversityHo Chi Minh723000Vietnam Institute of Photonics Engineering National Kaohsiung University of Science and TechnologyKaohsiung80778Taiwan

Along with vast non-fossil potential and significant expertise,there is a question of whether Asian nations are attaining efficient consumption and exploitation of renewable *** this perspective,the paper aims to evaluate the efficiency of 14 potential Asia countries in renewable energy consumption during the six-year periods(2014-2019).In analyzing the performance of the renewable energy sector,the data envelopment analysis(DEA)with an undesirable output model approach has been widely utilized to measure the efficiency of peer units compared with the best practice *** consider four inputs and two outputs to a DEA-based efficiency *** force,total energy consumption,share of renewable energy,and total renewable energy capacity are *** outputs consist of CO_(2)emissions as an undesirable output and gross domestic product as a desirable *** results show that United Arab Emirates,Saudi Arabia,Japan,and South Korea consistently outperform in the evaluation,achieving perfect efficiency scores during the research *** is found to have the lowest average efficiency of renewable energy utilization.

关键词： Asia renewable energy efficiency frontier data envelopment analysis bad output

The future of COVID-19 vaccination rates for children

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Asian Pacific Journal of Tropical Medicine 2022年第9期15卷 381-382页

作者： Giao Huynh Kimberly H.nguyen Han Thi Ngoc nguyen tuan Diep Tran Pham Le An Faculty of Public Health University of Medicine and Pharmacy at Ho Chi Minh CityHo Chi Minh CityVietnam Department of Public Health and Community Medicine Tufts University School of MedicineBostonMAUSA Infection Control Department University Medical Center Ho Chi Minh CityHo Chi Minh CityVietnam Faculty of Medicine University of Medicine and Pharmacy at Ho Chi Minh CityHo Chi Minh CityVietnam Family Medicine Training Center University of Medicine and Pharmacy at Ho Chi Minh CityHo Chi Minh CityVietnam

The COVID-19 pandemic has been ongoing for over two years since the first case was reported in the end of January *** has successfully controlled the pandemic through its vaccination campaign,targeted messages and applications of various public health interventions including social distancing,quarantining,masking,and hand washing,which have made some significant achievements in reducing hospitalizations and deaths[1].

关键词： vaccination targeted COV

A novel approach for synthesis of hierarchical mesoporous Nd2O3 nanomaterials

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Rare Earths 2017年第7期35卷 677-682页

作者： Le Huu Trinh Dinh quang Khieu Hoang Thai Long Tran Thai Hoa Duong tuan quang nguyen Duc Cuong College of Sciences Hue University 77 Nguyen Hue Hue City Viet Nam Faculty of Hospitality and Tourism Hue University 22 Lam Hoang Hue CityViet Nam College of Education Hue University 34 Le LoL Hue City Viet Nam

A novel route to the fabrication of hierarchical mesoporous Nd_2O_3 nanostructures including nanospheres and nanoporous network was described. Their structure and morphology evolution of the as-synthesized materials were determined by various techniques such as scanning electron microscopy, transmission electron microscopy, high-resolution transmission electron microscopy, X-ray diffraction, energy-dispersive X-ray spectroscopy, Fourier transforminfrared spectra, nitrogen adsorption/desorption isotherm, and a formation mechanism was proposed. The results revealed that the Nd_2O_3 nanospheres had the diameter of 300 nm, which were composed of small primary nanoparticles（NPs） with the size of 10 nm. The nanoporous structure also formed the NPs of ca. 10 nm which were connected with each other to form a three-dimensional（3D） texture. This simple and mild approach to fabricate hierarchical mesoporous Nd_2O_3 nanostructures could be easily scaled up and potentially extended to synthesize other oxide hierarchical structures.

关键词： Nd2O3 hierarchical nanostructures nanospheres nanoporous network rare earths