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

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Jun Du

Jun Du

Target-speaker Voice Activity Detection with Improved I-Vector Estimation for Unknown Number of Speaker


Aug 07, 2021
Maokui He, Desh Raj, Zili Huang, Jun Du, Zhuo Chen, Shinji Watanabe

Figure 1 for Target-speaker Voice Activity Detection with Improved I-Vector Estimation for Unknown Number of Speaker
Figure 2 for Target-speaker Voice Activity Detection with Improved I-Vector Estimation for Unknown Number of Speaker
Figure 3 for Target-speaker Voice Activity Detection with Improved I-Vector Estimation for Unknown Number of Speaker
Figure 4 for Target-speaker Voice Activity Detection with Improved I-Vector Estimation for Unknown Number of Speaker

  Access Paper or Ask Questions

Split, embed and merge: An accurate table structure recognizer


Jul 20, 2021
Zhenrong Zhang, Jianshu Zhang, Jun Du

Figure 1 for Split, embed and merge: An accurate table structure recognizer
Figure 2 for Split, embed and merge: An accurate table structure recognizer
Figure 3 for Split, embed and merge: An accurate table structure recognizer
Figure 4 for Split, embed and merge: An accurate table structure recognizer

  Access Paper or Ask Questions

Separation Guided Speaker Diarization in Realistic Mismatched Conditions


Jul 06, 2021
Shu-Tong Niu, Jun Du, Lei Sun, Chin-Hui Lee

Figure 1 for Separation Guided Speaker Diarization in Realistic Mismatched Conditions
Figure 2 for Separation Guided Speaker Diarization in Realistic Mismatched Conditions
Figure 3 for Separation Guided Speaker Diarization in Realistic Mismatched Conditions
Figure 4 for Separation Guided Speaker Diarization in Realistic Mismatched Conditions

  Access Paper or Ask Questions

A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification


Jul 03, 2021
Chao-Han Huck Yang, Hu Hu, Sabato Marco Siniscalchi, Qing Wang, Yuyang Wang, Xianjun Xia, Yuanjun Zhao, Yuzhong Wu, Yannan Wang, Jun Du, Chin-Hui Lee

Figure 1 for A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification
Figure 2 for A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification
Figure 3 for A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification
Figure 4 for A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification
* Detection and Classification of Acoustic Scenes and Events (DCASE), 2021 
 * 5 figures. DCASE 2021. The project started in November 2020 
  Access Paper or Ask Questions

AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario


Apr 08, 2021
Yihui Fu, Luyao Cheng, Shubo Lv, Yukai Jv, Yuxiang Kong, Zhuo Chen, Yanxin Hu, Lei Xie, Jian Wu, Hui Bu, Xin Xu, Jun Du, Jingdong Chen

Figure 1 for AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario
Figure 2 for AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario
Figure 3 for AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario
Figure 4 for AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario
* Submitted to Interspeech 2021 
  Access Paper or Ask Questions

USTC-NELSLIP System Description for DIHARD-III Challenge


Mar 19, 2021
Yuxuan Wang, Maokui He, Shutong Niu, Lei Sun, Tian Gao, Xin Fang, Jia Pan, Jun Du, Chin-Hui Lee

Figure 1 for USTC-NELSLIP System Description for DIHARD-III Challenge
Figure 2 for USTC-NELSLIP System Description for DIHARD-III Challenge
Figure 3 for USTC-NELSLIP System Description for DIHARD-III Challenge
Figure 4 for USTC-NELSLIP System Description for DIHARD-III Challenge

  Access Paper or Ask Questions

A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection


Jan 08, 2021
Qing Wang, Jun Du, Hua-Xin Wu, Jia Pan, Feng Ma, Chin-Hui Lee

Figure 1 for A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection
Figure 2 for A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection
Figure 3 for A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection
Figure 4 for A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection
* 12 pages, 8 figures 
  Access Paper or Ask Questions

Lip-reading with Hierarchical Pyramidal Convolution and Self-Attention


Dec 28, 2020
Hang Chen, Jun Du, Yu Hu, Li-Rong Dai, Chin-Hui Lee, Bao-Cai Yin

Figure 1 for Lip-reading with Hierarchical Pyramidal Convolution and Self-Attention
Figure 2 for Lip-reading with Hierarchical Pyramidal Convolution and Self-Attention
Figure 3 for Lip-reading with Hierarchical Pyramidal Convolution and Self-Attention
Figure 4 for Lip-reading with Hierarchical Pyramidal Convolution and Self-Attention
* 5 pages, 7 figures 
  Access Paper or Ask Questions

Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition


Dec 27, 2020
Hengshun Zhou, Debin Meng, Yuanyuan Zhang, Xiaojiang Peng, Jun Du, Kai Wang, Yu Qiao

Figure 1 for Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition
Figure 2 for Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition
Figure 3 for Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition
Figure 4 for Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition
* Accepted by ACM ICMI'19 (2019 International Conference on Multimodal Interaction) 
  Access Paper or Ask Questions

Frequency Gating: Improved Convolutional Neural Networks for Speech Enhancement in the Time-Frequency Domain


Nov 08, 2020
Koen Oostermeijer, Qing Wang, Jun Du

Figure 1 for Frequency Gating: Improved Convolutional Neural Networks for Speech Enhancement in the Time-Frequency Domain
Figure 2 for Frequency Gating: Improved Convolutional Neural Networks for Speech Enhancement in the Time-Frequency Domain
Figure 3 for Frequency Gating: Improved Convolutional Neural Networks for Speech Enhancement in the Time-Frequency Domain
Figure 4 for Frequency Gating: Improved Convolutional Neural Networks for Speech Enhancement in the Time-Frequency Domain

  Access Paper or Ask Questions

A Two-Stage Approach to Device-Robust Acoustic Scene Classification


Nov 03, 2020
Hu Hu, Chao-Han Huck Yang, Xianjun Xia, Xue Bai, Xin Tang, Yajian Wang, Shutong Niu, Li Chai, Juanjuan Li, Hongning Zhu, Feng Bao, Yuanjun Zhao, Sabato Marco Siniscalchi, Yannan Wang, Jun Du, Chin-Hui Lee

Figure 1 for A Two-Stage Approach to Device-Robust Acoustic Scene Classification
Figure 2 for A Two-Stage Approach to Device-Robust Acoustic Scene Classification
Figure 3 for A Two-Stage Approach to Device-Robust Acoustic Scene Classification
Figure 4 for A Two-Stage Approach to Device-Robust Acoustic Scene Classification
* Submitted to ICASSP 2021. Code available: https://github.com/MihawkHu/DCASE2020_task1 
  Access Paper or Ask Questions

Correlating Subword Articulation with Lip Shapes for Embedding Aware Audio-Visual Speech Enhancement


Sep 21, 2020
Hang Chen, Jun Du, Yu Hu, Li-Rong Dai, Bao-Cai Yin, Chin-Hui Lee

Figure 1 for Correlating Subword Articulation with Lip Shapes for Embedding Aware Audio-Visual Speech Enhancement
Figure 2 for Correlating Subword Articulation with Lip Shapes for Embedding Aware Audio-Visual Speech Enhancement
Figure 3 for Correlating Subword Articulation with Lip Shapes for Embedding Aware Audio-Visual Speech Enhancement
Figure 4 for Correlating Subword Articulation with Lip Shapes for Embedding Aware Audio-Visual Speech Enhancement
* 34 pages, 8 figures 
  Access Paper or Ask Questions

Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation


Aug 27, 2020
Hu Hu, Chao-Han Huck Yang, Xianjun Xia, Xue Bai, Xin Tang, Yajian Wang, Shutong Niu, Li Chai, Juanjuan Li, Hongning Zhu, Feng Bao, Yuanjun Zhao, Sabato Marco Siniscalchi, Yannan Wang, Jun Du, Chin-Hui Lee

Figure 1 for Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation
Figure 2 for Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation
Figure 3 for Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation
* Revised Technical Report. Proposed systems attain 2nds in both Task-1a and Task-1b in the official DCASE challenge 2020 
  Access Paper or Ask Questions

On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression


Aug 12, 2020
Jun Qi, Jun Du, Sabato Marco Siniscalchi, Xiaoli Ma, Chin-Hui Lee

Figure 1 for On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression
Figure 2 for On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression
* IEEE Signal Processing Letters, 2020 
  Access Paper or Ask Questions

Analyzing Upper Bounds on Mean Absolute Errors for Deep Neural Network Based Vector-to-Vector Regression


Aug 04, 2020
Jun Qi, Jun Du, Sabato Marco Siniscalchi, Xiaoli Ma, Chin-Hui Lee

Figure 1 for Analyzing Upper Bounds on Mean Absolute Errors for Deep Neural Network Based Vector-to-Vector Regression
Figure 2 for Analyzing Upper Bounds on Mean Absolute Errors for Deep Neural Network Based Vector-to-Vector Regression
Figure 3 for Analyzing Upper Bounds on Mean Absolute Errors for Deep Neural Network Based Vector-to-Vector Regression
Figure 4 for Analyzing Upper Bounds on Mean Absolute Errors for Deep Neural Network Based Vector-to-Vector Regression
* IEEE Transactions on Signal Processing, Vol 68, pp. 3411-3422, 2020 
  Access Paper or Ask Questions

An Acoustic Segment Model Based Segment Unit Selection Approach to Acoustic Scene Classification with Partial Utterances


Jul 31, 2020
Hu Hu, Sabato Marco Siniscalchi, Yannan Wang, Xue Bai, Jun Du, Chin-Hui Lee

Figure 1 for An Acoustic Segment Model Based Segment Unit Selection Approach to Acoustic Scene Classification with Partial Utterances
Figure 2 for An Acoustic Segment Model Based Segment Unit Selection Approach to Acoustic Scene Classification with Partial Utterances
Figure 3 for An Acoustic Segment Model Based Segment Unit Selection Approach to Acoustic Scene Classification with Partial Utterances
Figure 4 for An Acoustic Segment Model Based Segment Unit Selection Approach to Acoustic Scene Classification with Partial Utterances
* Accepted by Interspeech 2020 
  Access Paper or Ask Questions

Stroke Constrained Attention Network for Online Handwritten Mathematical Expression Recognition


Feb 20, 2020
Jiaming Wang, Jun Du, Jianshu Zhang

Figure 1 for Stroke Constrained Attention Network for Online Handwritten Mathematical Expression Recognition
Figure 2 for Stroke Constrained Attention Network for Online Handwritten Mathematical Expression Recognition
Figure 3 for Stroke Constrained Attention Network for Online Handwritten Mathematical Expression Recognition
Figure 4 for Stroke Constrained Attention Network for Online Handwritten Mathematical Expression Recognition

  Access Paper or Ask Questions

Joint Architecture and Knowledge Distillation in Convolutional Neural Network for Offline Handwritten Chinese Text Recognition


Dec 17, 2019
Zi-Rui Wang, Jun Du

Figure 1 for Joint Architecture and Knowledge Distillation in Convolutional Neural Network for Offline Handwritten Chinese Text Recognition
Figure 2 for Joint Architecture and Knowledge Distillation in Convolutional Neural Network for Offline Handwritten Chinese Text Recognition
Figure 3 for Joint Architecture and Knowledge Distillation in Convolutional Neural Network for Offline Handwritten Chinese Text Recognition
Figure 4 for Joint Architecture and Knowledge Distillation in Convolutional Neural Network for Offline Handwritten Chinese Text Recognition

  Access Paper or Ask Questions

Challenge of Spatial Cognition for Deep Learning


Jul 30, 2019
Xiaolin Wu, Xi Zhang, Jun Du

Figure 1 for Challenge of Spatial Cognition for Deep Learning
Figure 2 for Challenge of Spatial Cognition for Deep Learning
Figure 3 for Challenge of Spatial Cognition for Deep Learning
Figure 4 for Challenge of Spatial Cognition for Deep Learning

  Access Paper or Ask Questions

Adaptive Period Embedding for Representing Oriented Objects in Aerial Images


Jun 22, 2019
Yixing Zhu, Xueqing Wu, Jun Du

Figure 1 for Adaptive Period Embedding for Representing Oriented Objects in Aerial Images
Figure 2 for Adaptive Period Embedding for Representing Oriented Objects in Aerial Images
Figure 3 for Adaptive Period Embedding for Representing Oriented Objects in Aerial Images
Figure 4 for Adaptive Period Embedding for Representing Oriented Objects in Aerial Images

  Access Paper or Ask Questions

The Second DIHARD Diarization Challenge: Dataset, task, and baselines


Jun 18, 2019
Neville Ryant, Kenneth Church, Christopher Cieri, Alejandrina Cristia, Jun Du, Sriram Ganapathy, Mark Liberman

Figure 1 for The Second DIHARD Diarization Challenge: Dataset, task, and baselines
Figure 2 for The Second DIHARD Diarization Challenge: Dataset, task, and baselines
* Accepted by Interspeech 2019 
  Access Paper or Ask Questions

Deep Neural Network Embeddings with Gating Mechanisms for Text-Independent Speaker Verification


Apr 04, 2019
Lanhua You, Wu Guo, Lirong Dai, Jun Du

Figure 1 for Deep Neural Network Embeddings with Gating Mechanisms for Text-Independent Speaker Verification
Figure 2 for Deep Neural Network Embeddings with Gating Mechanisms for Text-Independent Speaker Verification
Figure 3 for Deep Neural Network Embeddings with Gating Mechanisms for Text-Independent Speaker Verification
Figure 4 for Deep Neural Network Embeddings with Gating Mechanisms for Text-Independent Speaker Verification
* 5 pages, 3 figures, submitted to INTERSPEECH 2019 
  Access Paper or Ask Questions

Deep Fusion: An Attention Guided Factorized Bilinear Pooling for Audio-video Emotion Recognition


Jan 15, 2019
Yuanyuan Zhang, Zi-Rui Wang, Jun Du

Figure 1 for Deep Fusion: An Attention Guided Factorized Bilinear Pooling for Audio-video Emotion Recognition
Figure 2 for Deep Fusion: An Attention Guided Factorized Bilinear Pooling for Audio-video Emotion Recognition
Figure 3 for Deep Fusion: An Attention Guided Factorized Bilinear Pooling for Audio-video Emotion Recognition
Figure 4 for Deep Fusion: An Attention Guided Factorized Bilinear Pooling for Audio-video Emotion Recognition

  Access Paper or Ask Questions

Writer-Aware CNN for Parsimonious HMM-Based Offline Handwritten Chinese Text Recognition


Dec 24, 2018
Zi-Rui Wang, Jun Du, Jia-Ming Wang

Figure 1 for Writer-Aware CNN for Parsimonious HMM-Based Offline Handwritten Chinese Text Recognition
Figure 2 for Writer-Aware CNN for Parsimonious HMM-Based Offline Handwritten Chinese Text Recognition
Figure 3 for Writer-Aware CNN for Parsimonious HMM-Based Offline Handwritten Chinese Text Recognition
Figure 4 for Writer-Aware CNN for Parsimonious HMM-Based Offline Handwritten Chinese Text Recognition

  Access Paper or Ask Questions

TextMountain: Accurate Scene Text Detection via Instance Segmentation


Nov 30, 2018
Yixing Zhu, Jun Du

Figure 1 for TextMountain: Accurate Scene Text Detection via Instance Segmentation
Figure 2 for TextMountain: Accurate Scene Text Detection via Instance Segmentation
Figure 3 for TextMountain: Accurate Scene Text Detection via Instance Segmentation
Figure 4 for TextMountain: Accurate Scene Text Detection via Instance Segmentation

  Access Paper or Ask Questions

Parsimonious HMMs for Offline Handwritten Chinese Text Recognition


Aug 13, 2018
Wenchao Wang, Jun Du, Zi-Rui Wang

Figure 1 for Parsimonious HMMs for Offline Handwritten Chinese Text Recognition
Figure 2 for Parsimonious HMMs for Offline Handwritten Chinese Text Recognition
Figure 3 for Parsimonious HMMs for Offline Handwritten Chinese Text Recognition
Figure 4 for Parsimonious HMMs for Offline Handwritten Chinese Text Recognition
* Accepted by ICFHR2018 
  Access Paper or Ask Questions

DenseRAN for Offline Handwritten Chinese Character Recognition


Aug 13, 2018
Wenchao Wang, Jianshu Zhang, Jun Du, Zi-Rui Wang, Yixing Zhu

Figure 1 for DenseRAN for Offline Handwritten Chinese Character Recognition
Figure 2 for DenseRAN for Offline Handwritten Chinese Character Recognition
Figure 3 for DenseRAN for Offline Handwritten Chinese Character Recognition
Figure 4 for DenseRAN for Offline Handwritten Chinese Character Recognition
* Accepted by ICFHR2018 
  Access Paper or Ask Questions

Attention Based Fully Convolutional Network for Speech Emotion Recognition


Jun 05, 2018
Yuanyuan Zhang, Jun Du, Zirui Wang, Jianshu Zhang

Figure 1 for Attention Based Fully Convolutional Network for Speech Emotion Recognition
Figure 2 for Attention Based Fully Convolutional Network for Speech Emotion Recognition
Figure 3 for Attention Based Fully Convolutional Network for Speech Emotion Recognition
Figure 4 for Attention Based Fully Convolutional Network for Speech Emotion Recognition

  Access Paper or Ask Questions