Keyword : LSTM


Detecting Depression from Speech through an Attentive LSTM Network
Yan ZHAO Yue XIE Ruiyu LIANG Li ZHANG Li ZHAO Chengyu LIU 
Publication:   
Publication Date: 2021/11/01
Vol. E104-D  No. 11 ; pp. 2019-2023
Type of Manuscript:  LETTER
Category: Speech and Hearing
Keyword: 
depression detectionLSTMattention mechanismvocal expression
 Summary | Full Text:PDF

FiC-RNN: A Multi-FPGA Acceleration Framework for Deep Recurrent Neural Networks
Yuxi SUN Hideharu AMANO 
Publication:   
Publication Date: 2020/12/01
Vol. E103-D  No. 12 ; pp. 2457-2462
Type of Manuscript:  Special Section PAPER (Special Section on Parallel, Distributed, and Reconfigurable Computing, and Networking)
Category: Computer System
Keyword: 
multi-FPGArecurrent neural networksLSTM
 Summary | Full Text:PDF

Contextualized Character Embedding with Multi-Sequence LSTM for Automatic Word Segmentation
Hyunyoung LEE Seungshik KANG 
Publication:   
Publication Date: 2020/11/01
Vol. E103-D  No. 11 ; pp. 2371-2378
Type of Manuscript:  PAPER
Category: Natural Language Processing
Keyword: 
contextualized character embeddingLSTMlinear-chain CRFword segmentation
 Summary | Full Text:PDF

Attentive Sequences Recurrent Network for Social Relation Recognition from Video
Jinna LV Bin WU Yunlei ZHANG Yunpeng XIAO 
Publication:   
Publication Date: 2019/12/01
Vol. E102-D  No. 12 ; pp. 2568-2576
Type of Manuscript:  PAPER
Category: Image Recognition, Computer Vision
Keyword: 
social relation recognitionvideo analysisdeep learningLSTMattention mechanism
 Summary | Full Text:PDF

Attention-Based Dense LSTM for Speech Emotion Recognition
Yue XIE Ruiyu LIANG Zhenlin LIANG Li ZHAO 
Publication:   
Publication Date: 2019/07/01
Vol. E102-D  No. 7 ; pp. 1426-1429
Type of Manuscript:  LETTER
Category: Pattern Recognition
Keyword: 
attention mechanismspeech emotion recognitiondense connectionsLSTM
 Summary | Full Text:PDF

Feature Based Domain Adaptation for Neural Network Language Models with Factorised Hidden Layers
Michael HENTSCHEL Marc DELCROIX Atsunori OGAWA Tomoharu IWATA Tomohiro NAKATANI 
Publication:   
Publication Date: 2019/03/01
Vol. E102-D  No. 3 ; pp. 598-608
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
language modelLSTMdomain adaptationunsupervisedlatent Dirichlet allocation
 Summary | Full Text:PDF

Automatic Speech Recognition System with Output-Gate Projected Gated Recurrent Unit
Gaofeng CHENG Pengyuan ZHANG Ji XU 
Publication:   
Publication Date: 2019/02/01
Vol. E102-D  No. 2 ; pp. 355-363
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
GRULSTMneural network language modelspeech recognition
 Summary | Full Text:PDF

Multi-Channels LSTM Networks for Fence Activity Classification
Kelu HU Chunlei ZHENG Wei HE Xinghe BAO Yingguan WANG 
Publication:   
Publication Date: 2018/08/01
Vol. E101-D  No. 8 ; pp. 2173-2177
Type of Manuscript:  LETTER
Category: Biocybernetics, Neurocomputing
Keyword: 
LSTMneural networkfenceinertial sensors
 Summary | Full Text:PDF

A Deep Learning-Based Approach to Non-Intrusive Objective Speech Intelligibility Estimation
Deokgyu YUN Hannah LEE Seung Ho CHOI 
Publication:   
Publication Date: 2018/04/01
Vol. E101-D  No. 4 ; pp. 1207-1208
Type of Manuscript:  LETTER
Category: Speech and Hearing
Keyword: 
non-intrusivespeech intelligibilityLSTMRNNSTOI
 Summary | Full Text:PDF

Next-Activity Set Prediction Based on Sequence Partitioning to Reduce Activity Pattern Complexity in the Multi-User Smart Space
Younggi KIM Younghee LEE 
Publication:   
Publication Date: 2017/10/01
Vol. E100-D  No. 10 ; pp. 2587-2596
Type of Manuscript:  PAPER
Category: Pattern Recognition
Keyword: 
activity predictionsequence partitioningmulti-user smart spaceLSTM
 Summary | Full Text:PDF