云南高校图书馆联盟文献共享服务平台- CONNECTIONIST

CONNECTIONIST: 作品数：12被引量：26H指数：2; 导出分析报告; 相关作者：孙维祥王薇俞立军许满武张莉更多>>; 相关机构：南京大学浙江师范大学西南大学广东外语外贸大学更多>>; 相关期刊：《Journal of Beijing Institute of Technology》《计算机应用研究》《Computer Systems Science & Engineering》《China Communications》更多>>; 相关基金：国家自然科学基金国家高技术研究发展计划更多>>

A Novel Re-weighted CTC Loss for Data Imbalance in Speech Keyword Spotting被引量：1: 《Chinese Journal of Electronics》2023年第3期465-473,共9页LAN Xiaotian HE Qianhua YAN Haikang LI Yanxiong; supported by the National Natural Science Foundation of China(61571192);Guangdong Basic and Applied Basic Research Foundation(2021A1515011454).; Speech keyword spotting system is a critical component of human-computer interfaces.And connectionist temporal classifier(CTC)has been proven to be an effective tool for that task.However,the standard training process...; 关键词：Speech keyword spotting Connectionist temporal classifier Data imbalance Sample importance re-weighting

Continuous Sign Language Recognition Based on Spatial-Temporal Graph Attention Network被引量：2: 《Computer Modeling in Engineering & Sciences》2023年第3期1653-1670,共18页Qi Guo Shujun Zhang Hui Li; supported by the Key Research&Development Plan Project of Shandong Province,China(No.2017GGX10127).; Continuous sign language recognition(CSLR)is challenging due to the complexity of video background,hand gesture variability,and temporal modeling difficulties.This work proposes a CSLR method based on a spatialtempora...; 关键词：Continuous sign language recognition graph attention network bidirectional long short-term memory connectionist temporal classification

An Efficient Hybrid Model for Arabic Text Recognition: 《Computers, Materials & Continua》2023年第2期2871-2888,共18页Hicham Lamtougui Hicham El Moubtahij Hassan Fouadi Khalid Satori; In recent years,Deep Learning models have become indispensable in several fields such as computer vision,automatic object recognition,and automatic natural language processing.The implementation of a robust and effici...; 关键词：Deep learning arabic handwritten text recognition convolutional neural network(CNN) bidirectional long-term memory(BLSTM) connectionist temporal classification(CTC)

Network Traffic Prediction Using Radial Kernelized-Tversky Indexes-Based Multilayer Classifier: 《Computer Systems Science & Engineering》2022年第3期851-863,共13页M.Govindarajan V.Chandrasekaran S.Anitha; Accurate cellular network traffic prediction is a crucial task to access Internet services for various devices at any time.With the use of mobile devices,communication services generate numerous data for every moment....; 关键词：Cellular network traffic prediction connectionist Tversky multilayer deep structure learning attribute selection classification radial kernelized long short-term memory

HLR-Net: A Hybrid Lip-Reading Model Based on Deep Convolutional Neural Networks被引量：2: 《Computers, Materials & Continua》2021年第8期1531-1549,共19页Amany M.Sarhan Nada M.Elshennawy Dina M.Ibrahim; Lip reading is typically regarded as visually interpreting the speaker’s lip movements during the speaking.This is a task of decoding the text from the speaker’s mouth movement.This paper proposes a lip-reading mode...; 关键词：LIP-READING visual speech recognition deep neural network connectionist temporal classification

Joint CTC-Attention End-to-End Speech Recognition with a Triangle Recurrent Neural Net work Encoder被引量：2: 《Journal of Shanghai Jiaotong university(Science)》2020年第1期70-75,共6页ZHU Tao CHENG Chunling; 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....; 关键词：END-TO-END CONNECTIONIST temporal classification(CTC) att ent ion speech recognition

Long Short-Term Memory Recurrent Neural Network-Based Acoustic Model Using Connectionist Temporal Classification on a Large-Scale Training Corpus被引量：9: 《China Communications》2017年第9期23-31,共9页Donghyun Lee Minkyu Lim Hosung Park Yoseb Kang Jeong-Sik Park Gil-Jin Jang Ji-Hwan Kim; supported by the Ministry of Trade,Industry & Energy(MOTIE,Korea) under Industrial Technology Innovation Program (No.10063424,'development of distant speech recognition and multi-task dialog processing technologies for in-door conversational robots'); A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a force...; 关键词：acoustic model connectionisttemporal classification LARGE-SCALE trainingcorpus LONG SHORT-TERM memory recurrentneural network

Recent Progresses in Deep Learning Based Acoustic Models被引量：10: 《IEEE/CAA Journal of Automatica Sinica》2017年第3期396-409,共14页Dong Yu Jinyu Li; In this paper,we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques.We first discuss models such as recurrent neural networks(RNNs) a...; 关键词：Attention model convolutional neural network(CNN) connectionist temporal classification(CTC) deep learning(DL) long short-term memory(LSTM) permutation invariant training speech adaptation speech processing speech recognition speech separation

Brain as an Emergent Finite Automaton: A Theory and Three Theorems: 《International Journal of Intelligence Science》2015年第2期112-131,共20页Juyang Weng; This paper models a biological brain—excluding motivation (e.g., emotions)—as a Finite Automaton in Developmental Network (FA-in-DN), but such an FA emerges incrementally in DN. In artificial intelligence (AI), ther...; 关键词：BRAIN Mind CONNECTIONIST AUTOMATA THEORY Finite AUTOMATON Symbolic Artificial Intelligence

Intrusion Detection Approach Using Connectionist Expert System: 《Journal of Beijing Institute of Technology》2005年第4期467-470,共4页马锐刘玉树杜彦辉; SponsoredbytheMinisterialLevelFoundation(9181201); In order to improve the detection efficiency of rule-based expert systems, an intrusion detection approach using connectionist expert system is proposed. The approach converts the AND/OR nodes into the corresponding n...; 关键词：intrusion detection neural networks expert system

CONNECTIONIST