Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Junjie Wang

Junjie Wang

Sparsely Overlapped Speech Training in the Time Domain: Joint Learning of Target Speech Separation and Personal VAD Benefits

Jun 28, 2021
Qingjian Lin, Lin Yang, Xuyang Wang, Luyuan Xie, Chen Jia, Junjie Wang

Figure 1 for Sparsely Overlapped Speech Training in the Time Domain: Joint Learning of Target Speech Separation and Personal VAD Benefits

Figure 2 for Sparsely Overlapped Speech Training in the Time Domain: Joint Learning of Target Speech Separation and Personal VAD Benefits

Figure 3 for Sparsely Overlapped Speech Training in the Time Domain: Joint Learning of Target Speech Separation and Personal VAD Benefits

Figure 4 for Sparsely Overlapped Speech Training in the Time Domain: Joint Learning of Target Speech Separation and Personal VAD Benefits

* Rejected by Interspeech 2021. Plan to commit to ICASSP 2022

Access Paper or Ask Questions

Change Detection from SAR Images Based on Deformable Residual Convolutional Neural Networks

Apr 06, 2021
Junjie Wang, Feng Gao, Junyu Dong

Figure 1 for Change Detection from SAR Images Based on Deformable Residual Convolutional Neural Networks

Figure 2 for Change Detection from SAR Images Based on Deformable Residual Convolutional Neural Networks

Figure 3 for Change Detection from SAR Images Based on Deformable Residual Convolutional Neural Networks

Figure 4 for Change Detection from SAR Images Based on Deformable Residual Convolutional Neural Networks

* Accepted by ACM Multimedia Asia 2020

Access Paper or Ask Questions

TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling

Apr 04, 2021
Tze Yuang Chong, Xuyang Wang, Lin Yang, Junjie Wang

Figure 1 for TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling

Figure 2 for TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling

Figure 3 for TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling

Figure 4 for TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling

* INTERSPEECH 2021 (under reviewed)

Access Paper or Ask Questions

Training Wake Word Detection with Synthesized Speech Data on Confusion Words

Nov 03, 2020
Yan Jia, Zexin Cai, Murong Ma, Zeqing Zhao, Xuyang Wang, Junjie Wang, Ming Li

Figure 1 for Training Wake Word Detection with Synthesized Speech Data on Confusion Words

Figure 2 for Training Wake Word Detection with Synthesized Speech Data on Confusion Words

Figure 3 for Training Wake Word Detection with Synthesized Speech Data on Confusion Words

Figure 4 for Training Wake Word Detection with Synthesized Speech Data on Confusion Words

* Submitted to ICASSP 2021

Access Paper or Ask Questions

Dynamic Horizon Value Estimation for Model-based Reinforcement Learning

Sep 21, 2020
Junjie Wang, Qichao Zhang, Dongbin Zhao, Mengchen Zhao, Jianye Hao

Figure 1 for Dynamic Horizon Value Estimation for Model-based Reinforcement Learning

Figure 2 for Dynamic Horizon Value Estimation for Model-based Reinforcement Learning

Figure 3 for Dynamic Horizon Value Estimation for Model-based Reinforcement Learning

Figure 4 for Dynamic Horizon Value Estimation for Model-based Reinforcement Learning

* 9 pages, 6 figures

Access Paper or Ask Questions

DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team

Feb 23, 2020
Qingjian Lin, Weicheng Cai, Lin Yang, Junjie Wang, Jun Zhang, Ming Li

Figure 1 for DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team

Figure 2 for DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team

Figure 3 for DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team

Figure 4 for DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team

* Submitted to Odyssesy 2020

Access Paper or Ask Questions