检索结果-内蒙古大学图书馆

Merge-Weighted Dynamic Time Warping for Speech Recognition

Journal of Computer Science & Technology 2014年第6期29卷 1072-1082页

作者：张湘莉兰骆志刚李明 State Key Laboratory of Pathogen and Biosecurity Beijing Institute of Microbiology and Epidemiology Science and Technology on Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology David R.Cheriton School of Computer Science University of WaterlooWaterlooOntario N2L 3G1Canada ACM IEEE

Obtaining training material for rarely used English words and common given names from countries where English is not spoken is difficult due to excessive time, storage and cost factors. By considering personal privacy, language- independent （LI） with lightweight speaker-dependent （SD） automatic speech recognition （ASR） is a convenient option to solve tile problem. The dynamic time warping （DTW） algorithm is the state-of-the-art algorithm for small-footprint SD ASR for real-time applications with limited storage and small vocabularies. These applications include voice dialing on mobile devices, menu-driven recognition, and voice control on vehicles and robotics. However, traditional DTW has several lhnitations, such as high computational complexity, constraint induced coarse approximation, and inaccuracy problems. In this paper, we introduce the merge-weighted dynamic time warping （MWDTW） algorithm. This method defines a template confidence index for measuring the similarity between merged training data and testing data, while following the core DTW process. MWDTW is simple, efficient, and easy to implement. With extensive experiments on three representative SD speech recognition datasets, we demonstrate that our method outperforms DTW, DTW on merged speech data, the hidden Markov model （HMM） significantly, and is also six times faster than DTW overall.

关键词： merge-weighted dynamic time warping natural language processing speech recognition and synthesis tem-plate confidence index

来源：评论

学校读者我要写书评

暂无评论

A load balancing-supported constant degree DHT ID assignment method

引用

Tien Tzu Hsueh Pao/Acta Electronica Sinica 2010年第11期38卷 2649-2654页

作者： Wang, Xiao-Hai Peng, Yu-Xing Li, Dong-Sheng Key Laboratory of Science and Technology for Parallel and Distributed Processing National University of Defense Technology Changsha Hunan 410073 China

A Load Balancing-Supported ID assignment method is the foundation to implement and maintain DHT overlays, realized constant degree DHTs usually use simple pure centralized or distributed ID management strategies, which cannot resolve the contradiction between cost of maintaining topologies' information and topologies' balance. Analyzing the universal tree structures in the topologies, an ID Assignment method RFIDAM based on the internal structure Routing Forest is proposed, which regularly aggregates local balancing information to guide new nodes' joining for overall balance. The experimental results show, with low maintenance and routing message overhead, the system's loading balance is efficiently ensured with the length of IDs differ by at most 2.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Unified virtual memory support for deep CNN accelerator on soC FPGA 1

引用

15th International Conference on Algorithms and Architectures for parallel processing, ICA3PP 2015

作者： Xiao, Tao Qiao, Yuran Shen, Junzhong Yang, Qianming Wen, Mei College of Computer National University of Defense Technology Changsha410073 China National Key Laboratory of Parallel and Distributed Processing National University of Defense Technology Changsha410073 China

ISBN: (数字)9783319271194

ISBN: (纸本)9783319271187

Cooperation of CPU and hardware accelerator on SoC FPGA to accomplish computational intensive tasks, provides significant advantages in performance and energy efficiency. However, current operating systems provide little support for accelerators: the OS is unaware that a computational task can be executed either on a CPU core or an accelerator, and provides no assistance in efficient management of data sharing between CPU and accelerator on the DRAM, such as zero copy, data coherence. It’s also hard for current OS to allocate large contiguous physical memory space for accelerator. In this paper, we select the Xilinx ZYNQ as target and qualitatively analyze methods of sharing data. Besides using high-performance (HP) AXI interfaces of the ZYQN device, we develop a novel memory management system for FPGA-based accelerator. It provides a unified virtual space for CPU cores and accelerator so that they can access the same memory space in the operating systems user space. For a deep convolutional neural network task, our design gains up to speed-up of 5. 34x compared to traditional processoraccelerator cooperation. © Springer International Publishing Switzerland 2015.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Comparing performance of hierarchical identity-based signature schemes

Comparing performance of hierarchical identity-based signatu...

引用

作者： Chen, Peixin Wu, Yilun Su, Jinshu Wang, Xiaofeng College of Computer National University of Defense Technology Changsha410073 China National Key Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha410073 China

The key escrow problem and high computational cost are the two major problems that hinder the wider adoption of hierarchical identity-based signature (HIBS) scheme. HIBS schemes with either escrow-free (EF) or online/offline (OO) model have been proved secure in our previous work. However, there is no much EF or OO scheme that has been evaluated experimentally. In this letter, several EF/OO HIBS schemes are considered. We study the algorithmic complexity of the schemes both theoretically and experimentally. Scheme performance and practicability of EF and OO models are discussed. © Copyright 2016 The Institute of Electronics, Information and Communication Engineers.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

A novel L1 cache based on volatile STT-RAM 20th

A novel L1 cache based on volatile STT-RAM

引用

20th Annual Conference on Computer Engineering and Technology, NCCET 2016

作者： Hongguang, Zhang Minxuan, Zhang College of Computer National University of Defense Technology Changsha410073 China National Key Laboratory of Parallel and Distributed Processing National University of Defense Technology Changsha410073 China

ISBN: (纸本)9789811031588

Spin-transfer torque random access memory (STT-RAM) is one of the most promising substitutes for universal main memory and cache due to its excellent scalability, high density and low leakage power. Nevertheless, the current non-volatile STT-RAM cache architecture also has some drawbacks, such as long write latency and high write energy, which limit the application of STTRAM in the top level cache design. To solve these problems, we relax the retention time of STT-RAM to explore its different write performance, and propose a novel STT-RAM L1 cache architecture implemented with volatile STT-RAM as well as its related refresh scheme. The performance of proposed design is the same as SRAM L1 cache while its overall power consumption is only 63.8% of the latter one. © Springer Nature Singapore Pte Ltd. 2016.

关键词： Static random access storage

来源：评论

学校读者我要写书评

暂无评论

Using NMFAS to identify key biological pathways associated with human diseases

Using NMFAS to identify key biological pathways associated w...

引用

2012 IEEE 6th International Conference on Systems Biology, ISB 2012

作者： Guo, Hao Zhu, Yunping Li, Dong He, Fuchu Liu, Qijun State Key Laboratory of Proteomics Beijing Proteome Research Centre Beijing Institute of Radiation Medicine Beijing China National Laboratory for Parallel and Distributed Processing National University of Deference and Technology Changsha China

ISBN: (纸本)9781467343985

Gene expression microarray enables us to measure the gene expression levels for thousands of genes at the same time. Here, we constructed the non-negative matrix factorization analysis strategy (NMFAS) to dig the underlying biological pathways related with various diseases by factorizing the pathway expression matrix, which was extracted from microarray matrix using pathway membership information, into the product of row and column vectors. We defined row vector as the pathway activity and column vector as the gene contribution weight. Via comparing the pathway activity of two different sample groups, we can identify significantly expressed pathways. We applied this strategy on two different cases: smoking and type 2 diabetes (DM2). We found 152 differentially expressed pathways by the comparison of pathway activity between smoker and never smoker, including pathways that have been validated in literature, such as "O-Glycans biosynthesis" and "Glutathione metabolism". We also found important genes related to smoking phenotype, such as NQO, HSPA1A, ALDH3A1. As for DM2 analysis, our results suggested 9 pathways were significantly expressed, including typical pathways like "Oxidative phosphorylation" and "mTOR signaling pathway", and found genes like CAPNS1, APP, COX7A1, COX7B, which might play important roles in the cellular regulations of DM2. In conclusion, Our strategy can be efficiently used to integrate gene expression profiles and biological pathway information to identify the key processes underlying human disease and can identify gene pathways missed by alternative approaches. © 2012 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Implementation of encrypted data for outsourced database

Implementation of encrypted data for outsourced database

引用

2010 2nd International Conference on Computational Intelligence and Natural Computing, CINC 2010

作者： Wang, Zheng-Fei Tang, Ai-Guo Department of Computer Hunan Business College Changsha 410205 China National Key Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology Changsha 410073 China

ISBN: (纸本)9781424477036

Encryption technology has become an important mechanism of securing data stored in the outsourced database. However, it is a difficulty to query efficiently the encrypted data and many researchers take it into consideration. To solve the problem, an encrypted schema, based on the Postgresql DBMS, is proposed Through the security dictionary and the extended SQL, the approach implements the encrypted storage and efficiently query over the encrypted data in the outsourced databases. Results of experiments validate the efficiency and feasibility of our approach. ©2010 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Character feature learning for named entity recognition

Character feature learning for named entity recognition

引用

作者： Zeng, Ping Tan, Qingping Zhang, Haoyu Meng, Xiankai Zhang, Zhuo Xu, Jianjun Lei, Yan College of Computer National University of Defense Technology Changsha China National Key Laboratory for Parallel and Distributed Processing Changsha China School of Software Engineering Chongqing University Chongqing China

The deep neural named entity recognition model automatically learns and extracts the features of entities and solves the problem of the traditional model relying heavily on complex feature engineering and obscure professional knowledge. This issue has become a hot topic in recent years. Existing deep neural models only involve simple character learning and extraction methods, which limit their capability. To further explore the performance of deep neural models, we propose two character feature learning models based on convolution neural network and long short-term memory network. These two models consider the local semantic and position features of word characters. Experiments conducted on the CoNLL-2003 dataset show that the proposed models outperform traditional ones and demonstrate excellent performance. © Copyright 2018 The Institute of Electronics Information and Communication Engineers.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

CD-Sched: An Automated Scheduling Framework for Accelerating Neural Network Training on Shared Memory CPU-DSP Platforms 23

CD-Sched: An Automated Scheduling Framework for Accelerating...

引用

Proceedings of the 2023 International Conference on Power, Communication, Computing and Networking Technologies

作者： Yuanyuan Xiao Zhiquan Lai Dongsheng Li National Key Laboratory for Parallel and Distributed Processing National University of Defense Technology China National Key Laboratory of Parallel and Distributed Processing National University of Defense Technology China

ISBN: (纸本)9781450399951

DSP holds significant potential for important applications in Deep Neural Networks. However, there is currently a lack of research focused on shared-memory CPU-DSP heterogeneous chips. This paper proposes CD-Sched, an automated scheduling framework that aims to address this gap. By predicting the latency of operators on both CPU and DSP, CD-Sched automatically schedules the computation of operators to the appropriate computing device. This scheduling optimization accelerates the computation of individual operators and ultimately improves the overall training time of neural networks. In end-to-end training tasks, CD-Sched can significantly reduce the overall training time, with an average reduction of approximately 10.77%.

关键词： computation offloading

来源：评论

学校读者我要写书评

暂无评论

CRAWL: A Trace Routing Algorithm Based on Hybrid Two-Layer Topology 33rd

CRAWL: A Trace Routing Algorithm Based on Hybrid Two-Layer T...

引用

33rd International Conference on Advanced Information Networking and Applications, AINA 2019

作者： Zheng, Li-ming Long, Wen-feng Liu, Yu-Jia Sun, Wei-dong Department of Message Communication Armed Police Officer Academy Chengdu China National Key Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology Changsha China

ISBN: (纸本)9783030150341

Data distribution is a key technology for resources convergence and sharing in distributed environment. To better meet the requirement for real time data distribution in the dynamic network, a trace routing algorithm named CRAWL based on the hybrid two-layered topology is put forward. The algorithm contains an overlay topology named CBDLO, upper of which consists of multiple distributed balanced binary trees corresponding to different properties and the lower of which is an unstructured topology. CRAWL forwards the data on the lower unstructured topology in the form of random walk, so that the data can be sent to the corresponding upper topology entry. It also includes a matching algorithm named CDM for the parallel matching data properties on the upper distributed and balanced binary tree and transmitting the matched data to the nodes that are interested in the data. The experimental results show that the algorithm can effectively support large-scale data distribution in a dynamical network, reduce distribution overhead and matching delays. © 2019, Springer Nature Switzerland AG.

关键词： Routing algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：