检索结果-南通市图书馆

Efficient decoding self-attention for end-to-end speech synthesis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2022年第7期23卷 1127-1138页

作者： Wei ZHAO Li XU College of Electrical Engineering Zhejiang UniversityHangzhou 310027China Institute of Robotics Zhejiang UniversityYuyao 315400China

Self-attention has been innovatively applied to text-to-speech(TTS)because of its parallel structure and superior strength in modeling sequential data.However,when used in end-to-end speech synthesis with an autoregressive decoding scheme,its inference speed becomes relatively low due to the quadratic complexity in sequence length.This problem becomes particularly severe on devices without graphics processing units(GPUs).To alleviate the dilemma,we propose an efficient decoding self-attention(EDSA)module as an alternative.Combined with a dynamic programming decoding procedure,TTS model inference can be effectively accelerated to have a linear computation complexity.We conduct studies on Mandarin and English datasets and find that our proposed model with EDSA can achieve 720%and 50%higher inference speed on the central processing unit(CPU)and GPU respectively,with almost the same performance.Thus,this method may make the deployment of such models easier when there are limited GPU resources.In addition,our model may perform better than the baseline Transformer TTS on out-of-domain utterances.

关键词： Efficient decoding end-to-end Self-attention Speech synthesis

A novel method for atomization energy prediction based on natural-parameter network

在线全文

学校读者我要写书评

暂无评论

Chinese Chemical Letters 2024年第1期35卷 505-509页

作者： Chaoqin Chu Qinkun Xiao Chaozheng He Chen Chen Lu Li Junyan Zhao Jinzhou Zheng Yinhuan Zhang School of Mechanical and Electrical Engineering Xi’an Technological UniversityXi’an 710021China School of Electrical and Information Engineering Xi’an Technological UniversityXi’an 710021China School of Materials Science and Chemical Engineering Xi’an Technological UniversityXi’an 710021China

Atomization energy(AE)is an important indicator for measuring material stability and reactivity,which refers to the energy change when a polyatomic molecule decomposes into its constituent atoms.Predicting AE based on the structural information of molecules has been a focus of researchers,but existing methods have limitations such as being time-consuming or requiring complex preprocessing and large amounts of training data.Deep learning(DL),a new branch of machine learning(ML),has shown promise in learning internal rules and hierarchical representations of sample data,making it a potential solution for AE prediction.To address this problem,we propose a natural-parameter network(NPN)approach for AE prediction.This method establishes a clearer statistical interpretation of the relationship between the network’s output and the given data.We use the Coulomb matrix(CM)method to represent each compound as a structural information matrix.Furthermore,we also designed an end-to-end predictive model.Experimental results demonstrate that our method achieves excellent performance on the QM7 and BC2P datasets,and the mean absolute error(MAE)obtained on the QM7 test set ranges from 0.2 kcal/mol to 3 kcal/mol.The optimal result of our method is approximately an order of magnitude higher than the accuracy of 3 kcal/mol in published works.Additionally,our approach significantly accelerates the prediction time.Overall,this study presents a promising approach to accelerate the process of predicting structures using DL,and provides a valuable contribution to the field of chemical energy prediction.

关键词： Structure prediction Atomization energy Deep learning Coulomb matrix NPN end-to-end

Redistribution of nerve strain enables end-to-end repair under tension without inhibiting nerve regeneration

在线全文

学校读者我要写书评

暂无评论

Neural Regeneration Research 2019年第7期14卷 1280-1288页

作者： Holly M.Howarth Turki Alaziz Brogan Nicolds Shawn O'Connor Sameer B.Shah Department of Bioengineering University of California Department of Orthopaedic Surgery University of California School of Exercise and Nutritional Sciences San Diego State University Research Service VA San Diego Healthcare System

end-to-end repair under no or low tension leads to improved outcomes for transected nerves with short gaps,compared to repairs with a graft.However,grafts are typically used to enable a tension-free repair for moderate to large gaps,as excessive tension can cause repairs to fail and catastrophically impede recovery.In this study,we tested the hypothesis that unloading the repair interface by redistributing tension away from the site of repair is a safe and feasible strategy for end-to-end repair of larger nerve gaps.Further,we tested the hypothesis that such an approach does not adversely affect structural and functional regeneration.In this study,we used a rat sciatic nerve injury model to compare the integrity of repair and several regenerative outcomes following end-to-end repairs of nerve gaps of increasing size.In addition,we proposed the use of a novel implantable device to safely repair end-to-end repair of larger nerve gaps by redistributing tension away from the repair interface.Our data suggest that redistriubution of tension away from the site of repair enables safe end-to-end repair of larger gap sizes.In addition,structural and functional measures of regeneration were equal or enhanced in nerves repaired under tension – with or without a tension redistribution device – compared to tension-free repairs.Provided that repair integrity is maintained,end-to-end repairs under tension should be considered as a reasonable surgical strategy.All animal experiments were performed under the approval of the Institutional Animal Care and Use Committee of University of California,San Diego(Protocol S11274).

关键词： tension biomechanics strain end-to-end repair peripheral nerve nerve regeneration

Joint CTC-Attention end-to-end Speech Recognition with a Triangle Recurrent Neural Net work Encoder

在线全文

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 2020年第1期25卷 70-75页

作者：朱涛程春玲 School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing 210023China

Traditional speech recognition model based on deep neural network(DNN)and hidden Markov model(HMM)is a complex and multi-module system.In other words,optimization goals may differ between modules in traditional model.Besides,additional language resources are required,such as pronunciation dictionary and language model.To eliminate the drawbacks of traditional model,we hereby propose an end-to-end speech recognition method,where connectionist temporal classification(CTC)and attention are integrated for decoding.In our model,the complex modules are replaced by a single deep network.Our model mainly consists of encoder and decoder.The encoder is constructed by bidirectional long short-term memory(BLSTM)with a triangular structure for feature extraction.The decoder based on CTC-attention decoding utilizes advanced features extracted by shared encoder for training and decoding.The experimental results on the Vox Forge dataset indicate that end-to-end method is superior to basic CTC and attention-based encoder-decoder decoding,and the character error rate(CER)is reduced to 12.9%without using any language model.

关键词： end-to-end connectionist temporal classification(CTC) att ent ion speech recognition

end-to-end verifiable electronic voting scheme of blockchain based on random linear block code

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High Technology Letters 2020年第1期26卷 25-33页

作者：刘霆 Cui Zhe Pu Hongquan Peng Xingyi Chengdu Institute of Computer Applications Chinese Academy of SciencesChengdu 610041P.R.China School of Computer and Control Engineering University of Chinese Academy of SciencesBeijing 100049P.R.China Guangxi Key Laboratory of Hybrid Computation and IC Design Analysis Nanning 530006P.R.China

Blockchain is an emerging decentralized technology of electronic voting.The current main consensus protocols are not flexible enough to manage the distributed blockchain nodes to achieve high efficiency of consensus.For practical implementation,the consensus based on random linear block code(RLBC)is proposed and applied to blockchain voting scheme.Along with achieving the record correctness and consistency among all nodes,the consensus method indicates the active and inactive consensus nodes.This ability can assist the management of consensus nodes and restrain the generating of chain forks.To achieve end-to-end verifiability,cast-or-audit and randomized partial checking(RPC)are used in the proposed scheme.The voter can verify the high probability of correctness in ballot encryption and decryption.The experiments illustrate that the efficiency of proposed consensus is suitable for blockchain.The proposed electronic voting scheme is adapted to practical implementation of voting.

关键词： random linear block code(RLBC) electronic voting(e-voting) blockchain consensus end-to-end verifiable

Data-driven engineering framework with AI algorithm of Ginkgo Folium tablets manufacturing

在线全文

学校读者我要写书评

暂无评论

Acta Pharmaceutica Sinica B 2023年第5期13卷 2188-2201页

作者： Lijuan Ma Jing Zhang Ling Lin Tuanjie Wang Chaofu Ma Xiaomeng Wang Mingshuang Li Yanjiang Qiao Yongxiang Wang Guimin Zhang Zhisheng Wu Beijing University of Chinese Medicine Engineering Research Center for Pharmaceutics of Chinese Materia Medica and New Drug DevelopmentMinistry of EducationBeijing 100029China Jiangsu Kanion Pharmaceutical Co. Ltd.State Key Laboratory of New Technology in Pharmaceutical Process of Traditional Chinese MedicineLianyungang 222001China Yangtze River Pharmaceutical(Group)Co. Ltd.State Pharmaceutical Engineering Technology Research Center of Traditional Chinese MedicineTaizhou 225321China Lunan Pharmaceutical Group Co. Ltd.State Key Laboratory of Generic Technology of Traditional Chinese MedicineLinyi 276005China

Smart manufacturing still remains critical challenges for pharmaceutical manufacturing.Here,an original data-driven engineering framework was proposed to tackle the challenges.Firstly,from sporadic indicators to five kinds of systematic quality characteristics,nearly 2,000,000 real-world data points were successively characterized from Ginkgo Folium tablet manufacturing.Then,from simplex to the multivariate system,the digital process capability diagnosis strategy was proposed by multivariate C_(pk)integrated Bootstrap-t.The C_(pk)of Ginkgo Folium extracts,granules,and tablets were discovered,which was 0.59,0.42,and 0.78,respectively,indicating a relatively weak process capability,especially in granulating.Furthermore,the quality traceability was discovered from unit to end-to-end analysis,which decreased from 2.17 to 1.73.This further proved that attention should be paid to granulating to improve the quality characteristic.In conclusion,this paper provided a data-driven engineering strategy empowering industrial innovation to face the challenge of smart pharmaceutical manufacturing.

关键词： Smart manufacturing Data-driven engineering Artificial intelligence Information fusion Process capability index end-to-end Quality traceability Real-world Ginkgo Folium products

Techniques for Avoiding Saccular Extended Obstruction at the Anastomotic Site of Functional end-to-end Anastomosis

在线全文

学校读者我要写书评

暂无评论

Surgical Science 2017年第7期8卷 305-311页

作者： Koichi Yoshida Kenichi Ietsugu Jyunpei Okamoto Saki Hayashi Yoshihide Asaumi Naohiro Ota Hiroyuki Sugawara Satoshi Tabata Masahiro Kaneki Mitsuaki Sakatoku Kaoru Kiyohara Department of Surgery Tonami General Hospital Toyama Japan

Saccular extended obstruction is generated when the anastomotic site of functional end-to-end anastomosis is extended saccularly and blocked by intestinal contents. This is a specific complication of functional end-to-end anastomosis. Saccular extended obstruction of the anastomotic site of func-tional end-to-end anastomosis causes postoperative intestinal obstruction. Saccular extended obstruction places a heavy burden on patients because surgery is necessary for treatment of intestinal obstruction due to saccular extended obstruction. However, saccular extended obstruction is not a commonly recognized complication. The greatest factor contributing to the development of saccular extended obstruction is an acute angle between the portions of the intestinal tract oral and aboral to the anastomotic site. When this angle approaches obtuse angle, preferably close to a straight line, stagnation of the intestinal contents does not occur at the anastomotic site of functional end-to-end anastomosis and saccular extended obstruction is avoided. For making the angle of anastomotic intestinal tracts obtuse or straight, it may be effective that the entry hole of stapling suture instrument creating the anastomotic stoma is closed perpendicular to the intestinal axis.

关键词： Functional end-to-end Anastomosis Stapling Anastomosis Anastomosis Postoperative Complication Intestinal Obstruction

Adaptive Cache Allocation with Prefetching Policy over end-to-end Data Processing

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 Signal and Information Processing 2017年第3期8卷 152-160页

作者： Hang Qin Li Zhu Computer School Yangtze University Jingzhou China Oujiang College Wenzhou University Chashan University Wenzhou China

With the speed gap between storage system access and processor computing, end-to-end data processing has become a bottleneck to improve the total performance of computer systems over the Internet. Based on the analysis of data processing behavior, an adaptive cache organization scheme is proposed with fast address calculation. This scheme can make full use of the characteristics of stack space data access, adopt fast address calculation strategy, and reduce the hit time of stack access. Adaptively, the stack cache can be turned off from beginning to end, when a stack overflow occurs to avoid the effect of stack switching on processor performance. Also, through the instruction cache and the failure behavior for the data cache, a prefetching policy is developed, which is combined with the data capture of the failover queue state. Finally, the proposed method can maintain the order of instruction and data access, which facilitates the extraction of prefetching in the end-to-end data processing.

关键词： end-to-end Data Processing Storage System Cache Prefetching

MILI:Multi-person inference from a low-resolution image

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Fundamental Research 2023年第3期3卷 434-441页

作者： Kun Li Yunke Liu Yu-Kun Lai Jingyu Yang Tianjin University Tianjin 300350China CardiffUniversity CardiffCF244AGUnited Kingdom

Existing multi-person reconstruction methods require the human bodies in the input image to occupy a considerable portion of the picture.However,low-resolution human objects are ubiquitous due to trade-offbetween the field of view and target distance given a limited camera resolution.In this paper,we propose an end-to-end multi-task framework for multi-person inference from a low-resolution image(MILI).To perceive more information from a low-resolution image,we use pair-wise images at high resolution and low resolution for training,and design a restoration network with a simple loss for better feature extraction from the low-resolution image.To address the occlusion problem in multi-person scenes,we propose an occlusion-aware mask prediction network to estimate the mask of each person during 3D mesh regression.Experimental results on both small-scale scenes and large-scale scenes demonstrate that our method outperforms the state-of-the-art methods both quantitatively and qualitatively.The code is available at http://***/faculty/likun/projects/MILI.

关键词： Multi-person reconstruction Low-resolution human objects end-to-end Multi-task learning Occlusion-aware prediction