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 Zheng-Hua Tan

Zheng-Hua Tan

Senior Member, IEEE

Improvement of Noise-Robust Single-Channel Voice Activity Detection with Spatial Pre-processing


Apr 12, 2021
Max Væhrens, Andreas Jonas Fuglsig, Anders Post Jacobsen, Nicolai Almskou Rasmussen, Victor Mølbach Nissen, Joachim Roland Hejslet, Zheng-Hua Tan

Figure 1 for Improvement of Noise-Robust Single-Channel Voice Activity Detection with Spatial Pre-processing
Figure 2 for Improvement of Noise-Robust Single-Channel Voice Activity Detection with Spatial Pre-processing
Figure 3 for Improvement of Noise-Robust Single-Channel Voice Activity Detection with Spatial Pre-processing
Figure 4 for Improvement of Noise-Robust Single-Channel Voice Activity Detection with Spatial Pre-processing
* Submitted to Interspeech 2021 
  Access Paper or Ask Questions

INTERSPEECH 2021 ConferencingSpeech Challenge: Towards Far-field Multi-Channel Speech Enhancement for Video Conferencing


Apr 02, 2021
Wei Rao, Yihui Fu, Yanxin Hu, Xin Xu, Yvkai Jv, Jiangyu Han, Zhongjie Jiang, Lei Xie, Yannan Wang, Shinji Watanabe, Zheng-Hua Tan, Hui Bu, Tao Yu, Shidong Shang

Figure 1 for INTERSPEECH 2021 ConferencingSpeech Challenge: Towards Far-field Multi-Channel Speech Enhancement for Video Conferencing
Figure 2 for INTERSPEECH 2021 ConferencingSpeech Challenge: Towards Far-field Multi-Channel Speech Enhancement for Video Conferencing
Figure 3 for INTERSPEECH 2021 ConferencingSpeech Challenge: Towards Far-field Multi-Channel Speech Enhancement for Video Conferencing
* 5 pages, submitted to INTERSPEECH 2021 
  Access Paper or Ask Questions

On TasNet for Low-Latency Single-Speaker Speech Enhancement


Mar 27, 2021
Morten Kolbæk, Zheng-Hua Tan, Søren Holdt Jensen, Jesper Jensen

Figure 1 for On TasNet for Low-Latency Single-Speaker Speech Enhancement
Figure 2 for On TasNet for Low-Latency Single-Speaker Speech Enhancement
Figure 3 for On TasNet for Low-Latency Single-Speaker Speech Enhancement
Figure 4 for On TasNet for Low-Latency Single-Speaker Speech Enhancement

  Access Paper or Ask Questions

PAC-Bayesian theory for stochastic LTI systems


Mar 25, 2021
Deividas Eringis, John Leth, Zheng-Hua Tan, Rafal Wisniewski, Alireza Fakhrizadeh Esfahani, Mihaly Petreczky

Figure 1 for PAC-Bayesian theory for stochastic LTI systems
Figure 2 for PAC-Bayesian theory for stochastic LTI systems
Figure 3 for PAC-Bayesian theory for stochastic LTI systems

  Access Paper or Ask Questions

Data Generation Using Pass-phrase-dependent Deep Auto-encoders for Text-Dependent Speaker Verification


Feb 03, 2021
Achintya Kumar Sarkar, Md Sahidullah, Zheng-Hua Tan

Figure 1 for Data Generation Using Pass-phrase-dependent Deep Auto-encoders for Text-Dependent Speaker Verification
Figure 2 for Data Generation Using Pass-phrase-dependent Deep Auto-encoders for Text-Dependent Speaker Verification
Figure 3 for Data Generation Using Pass-phrase-dependent Deep Auto-encoders for Text-Dependent Speaker Verification
Figure 4 for Data Generation Using Pass-phrase-dependent Deep Auto-encoders for Text-Dependent Speaker Verification

  Access Paper or Ask Questions

Vocal Tract Length Perturbation for Text-Dependent Speaker Verification with Autoregressive Prediction Coding


Nov 25, 2020
Achintya kr. Sarkar, Zheng-Hua Tan

Figure 1 for Vocal Tract Length Perturbation for Text-Dependent Speaker Verification with Autoregressive Prediction Coding
Figure 2 for Vocal Tract Length Perturbation for Text-Dependent Speaker Verification with Autoregressive Prediction Coding
Figure 3 for Vocal Tract Length Perturbation for Text-Dependent Speaker Verification with Autoregressive Prediction Coding
Figure 4 for Vocal Tract Length Perturbation for Text-Dependent Speaker Verification with Autoregressive Prediction Coding

  Access Paper or Ask Questions

Assessing Wireless Sensing Potential with Large Intelligent Surfaces


Nov 16, 2020
Cristian J. Vaca-Rubio, Pablo Ramirez-Espinosa, Kimmo Kansanen, Zheng-Hua Tan, Elisabeth de Carvalho, Petar Popovski

Figure 1 for Assessing Wireless Sensing Potential with Large Intelligent Surfaces
Figure 2 for Assessing Wireless Sensing Potential with Large Intelligent Surfaces
Figure 3 for Assessing Wireless Sensing Potential with Large Intelligent Surfaces
Figure 4 for Assessing Wireless Sensing Potential with Large Intelligent Surfaces
* arXiv admin note: text overlap with arXiv:2006.06563 
  Access Paper or Ask Questions

CC-Loss: Channel Correlation Loss For Image Classification


Oct 12, 2020
Zeyu Song, Dongliang Chang, Zhanyu Ma, Xiaoxu Li, Zheng-Hua Tan

Figure 1 for CC-Loss: Channel Correlation Loss For Image Classification
Figure 2 for CC-Loss: Channel Correlation Loss For Image Classification
Figure 3 for CC-Loss: Channel Correlation Loss For Image Classification
Figure 4 for CC-Loss: Channel Correlation Loss For Image Classification
* accepted by ICPR2020 
  Access Paper or Ask Questions

Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization


Oct 11, 2020
Jiyang Xie, Zhanyu Ma, Guoqiang Zhang, Jing-Hao Xue, Zheng-Hua Tan, Jun Guo

Figure 1 for Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization
Figure 2 for Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization
Figure 3 for Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization
Figure 4 for Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization

  Access Paper or Ask Questions

Audio-Visual Speech Inpainting with Deep Learning


Oct 09, 2020
Giovanni Morrone, Daniel Michelsanti, Zheng-Hua Tan, Jesper Jensen

Figure 1 for Audio-Visual Speech Inpainting with Deep Learning
Figure 2 for Audio-Visual Speech Inpainting with Deep Learning
Figure 3 for Audio-Visual Speech Inpainting with Deep Learning

  Access Paper or Ask Questions

An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation


Aug 21, 2020
Daniel Michelsanti, Zheng-Hua Tan, Shi-Xiong Zhang, Yong Xu, Meng Yu, Dong Yu, Jesper Jensen

Figure 1 for An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation
Figure 2 for An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation
Figure 3 for An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation
Figure 4 for An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation

  Access Paper or Ask Questions

UIAI System for Short-Duration Speaker Verification Challenge 2020


Jul 26, 2020
Md Sahidullah, Achintya Kumar Sarkar, Ville Vestman, Xuechen Liu, Romain Serizel, Tomi Kinnunen, Zheng-Hua Tan, Emmanuel Vincent

Figure 1 for UIAI System for Short-Duration Speaker Verification Challenge 2020
Figure 2 for UIAI System for Short-Duration Speaker Verification Challenge 2020
Figure 3 for UIAI System for Short-Duration Speaker Verification Challenge 2020
Figure 4 for UIAI System for Short-Duration Speaker Verification Challenge 2020

  Access Paper or Ask Questions

A Primer on Large Intelligent Surface (LIS) for Wireless Sensing in an Industrial Setting


Jun 11, 2020
Cristian J. Vaca-Rubio, Pablo Ramirez-Espinosa, Robin Jess Williams, Kimmo Kansanen, Zheng-Hua Tan, Elisabeth de Carvalho, Petar Popovski

Figure 1 for A Primer on Large Intelligent Surface (LIS) for Wireless Sensing in an Industrial Setting
Figure 2 for A Primer on Large Intelligent Surface (LIS) for Wireless Sensing in an Industrial Setting
Figure 3 for A Primer on Large Intelligent Surface (LIS) for Wireless Sensing in an Industrial Setting
Figure 4 for A Primer on Large Intelligent Surface (LIS) for Wireless Sensing in an Industrial Setting

  Access Paper or Ask Questions

Exploring Filterbank Learning for Keyword Spotting


May 30, 2020
Iván López-Espejo, Zheng-Hua Tan, Jesper Jensen

Figure 1 for Exploring Filterbank Learning for Keyword Spotting
Figure 2 for Exploring Filterbank Learning for Keyword Spotting
Figure 3 for Exploring Filterbank Learning for Keyword Spotting
Figure 4 for Exploring Filterbank Learning for Keyword Spotting

  Access Paper or Ask Questions

On Bottleneck Features for Text-Dependent Speaker Verification Using X-vectors


May 15, 2020
Achintya Kumar Sarkar, Zheng-Hua Tan

Figure 1 for On Bottleneck Features for Text-Dependent Speaker Verification Using X-vectors
Figure 2 for On Bottleneck Features for Text-Dependent Speaker Verification Using X-vectors
Figure 3 for On Bottleneck Features for Text-Dependent Speaker Verification Using X-vectors

  Access Paper or Ask Questions

OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer


Apr 20, 2020
Xiaoxu Li, Dongliang Chang, Zhanyu Ma, Zheng-Hua Tan, Jing-Hao Xue, Jie Cao, Jingyi Yu, Jun Guo

Figure 1 for OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
Figure 2 for OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
Figure 3 for OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
Figure 4 for OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
* TIP 2020. Code available at https://github.com/dongliangchang/OSLNet 
  Access Paper or Ask Questions

Vocoder-Based Speech Synthesis from Silent Videos


Apr 06, 2020
Daniel Michelsanti, Olga Slizovskaia, Gloria Haro, Emilia Gómez, Zheng-Hua Tan, Jesper Jensen

Figure 1 for Vocoder-Based Speech Synthesis from Silent Videos
Figure 2 for Vocoder-Based Speech Synthesis from Silent Videos
Figure 3 for Vocoder-Based Speech Synthesis from Silent Videos
Figure 4 for Vocoder-Based Speech Synthesis from Silent Videos

  Access Paper or Ask Questions

Adversarial Example Detection by Classification for Deep Speech Recognition


Oct 22, 2019
Saeid Samizade, Zheng-Hua Tan, Chao Shen, Xiaohong Guan

Figure 1 for Adversarial Example Detection by Classification for Deep Speech Recognition
Figure 2 for Adversarial Example Detection by Classification for Deep Speech Recognition
Figure 3 for Adversarial Example Detection by Classification for Deep Speech Recognition
Figure 4 for Adversarial Example Detection by Classification for Deep Speech Recognition

  Access Paper or Ask Questions

On Loss Functions for Supervised Monaural Time-Domain Speech Enhancement


Sep 03, 2019
Morten Kolbæk, Zheng-Hua Tan, Søren Holdt Jensen, Jesper Jensen

Figure 1 for On Loss Functions for Supervised Monaural Time-Domain Speech Enhancement
Figure 2 for On Loss Functions for Supervised Monaural Time-Domain Speech Enhancement
Figure 3 for On Loss Functions for Supervised Monaural Time-Domain Speech Enhancement
Figure 4 for On Loss Functions for Supervised Monaural Time-Domain Speech Enhancement

  Access Paper or Ask Questions

Keyword Spotting for Hearing Assistive Devices Robust to External Speakers


Jun 26, 2019
Iván López-Espejo, Zheng-Hua Tan, Jesper Jensen

Figure 1 for Keyword Spotting for Hearing Assistive Devices Robust to External Speakers
Figure 2 for Keyword Spotting for Hearing Assistive Devices Robust to External Speakers
Figure 3 for Keyword Spotting for Hearing Assistive Devices Robust to External Speakers
Figure 4 for Keyword Spotting for Hearing Assistive Devices Robust to External Speakers

  Access Paper or Ask Questions

rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method


Jun 09, 2019
Zheng-Hua Tan, Achintya kr. Sarkar, Najim Dehak

Figure 1 for rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method
Figure 2 for rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method
Figure 3 for rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method
Figure 4 for rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method
* Computer Speech & Language, 2019 
 * Paper is to appear in CSL 
  Access Paper or Ask Questions

Deep-Learning-Based Audio-Visual Speech Enhancement in Presence of Lombard Effect


May 29, 2019
Daniel Michelsanti, Zheng-Hua Tan, Sigurdur Sigurdsson, Jesper Jensen

Figure 1 for Deep-Learning-Based Audio-Visual Speech Enhancement in Presence of Lombard Effect
Figure 2 for Deep-Learning-Based Audio-Visual Speech Enhancement in Presence of Lombard Effect
Figure 3 for Deep-Learning-Based Audio-Visual Speech Enhancement in Presence of Lombard Effect
Figure 4 for Deep-Learning-Based Audio-Visual Speech Enhancement in Presence of Lombard Effect

  Access Paper or Ask Questions

Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification


May 11, 2019
Achintya kr. Sarkar, Zheng-Hua Tan, Hao Tang, Suwon Shon, James Glass

Figure 1 for Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
Figure 2 for Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
Figure 3 for Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
Figure 4 for Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
* IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019 
 * Copyright (c) 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works 
  Access Paper or Ask Questions

Subjective Annotations for Vision-Based Attention Level Estimation


Dec 12, 2018
Andrea Coifman, Péter Rohoska, Miklas S. Kristoffersen, Sven E. Shepstone, Zheng-Hua Tan

Figure 1 for Subjective Annotations for Vision-Based Attention Level Estimation
Figure 2 for Subjective Annotations for Vision-Based Attention Level Estimation
Figure 3 for Subjective Annotations for Vision-Based Attention Level Estimation
Figure 4 for Subjective Annotations for Vision-Based Attention Level Estimation
* 14th International Conference on Computer Vision Theory and Applications (VISAPP) 
  Access Paper or Ask Questions

Effects of Lombard Reflex on the Performance of Deep-Learning-Based Audio-Visual Speech Enhancement Systems


Nov 15, 2018
Daniel Michelsanti, Zheng-Hua Tan, Sigurdur Sigurdsson, Jesper Jensen

Figure 1 for Effects of Lombard Reflex on the Performance of Deep-Learning-Based Audio-Visual Speech Enhancement Systems
Figure 2 for Effects of Lombard Reflex on the Performance of Deep-Learning-Based Audio-Visual Speech Enhancement Systems
Figure 3 for Effects of Lombard Reflex on the Performance of Deep-Learning-Based Audio-Visual Speech Enhancement Systems
Figure 4 for Effects of Lombard Reflex on the Performance of Deep-Learning-Based Audio-Visual Speech Enhancement Systems

  Access Paper or Ask Questions

On Training Targets and Objective Functions for Deep-Learning-Based Audio-Visual Speech Enhancement


Nov 15, 2018
Daniel Michelsanti, Zheng-Hua Tan, Sigurdur Sigurdsson, Jesper Jensen

Figure 1 for On Training Targets and Objective Functions for Deep-Learning-Based Audio-Visual Speech Enhancement
Figure 2 for On Training Targets and Objective Functions for Deep-Learning-Based Audio-Visual Speech Enhancement

  Access Paper or Ask Questions

The Importance of Context When Recommending TV Content: Dataset and Algorithms


Jul 30, 2018
Miklas S. Kristoffersen, Sven E. Shepstone, Zheng-Hua Tan

Figure 1 for The Importance of Context When Recommending TV Content: Dataset and Algorithms
Figure 2 for The Importance of Context When Recommending TV Content: Dataset and Algorithms
Figure 3 for The Importance of Context When Recommending TV Content: Dataset and Algorithms
Figure 4 for The Importance of Context When Recommending TV Content: Dataset and Algorithms

  Access Paper or Ask Questions

A Parallel/Distributed Algorithmic Framework for Mining All Quantitative Association Rules


Apr 18, 2018
Ioannis T. Christou, Emmanouil Amolochitis, Zheng-Hua Tan

Figure 1 for A Parallel/Distributed Algorithmic Framework for Mining All Quantitative Association Rules
Figure 2 for A Parallel/Distributed Algorithmic Framework for Mining All Quantitative Association Rules
Figure 3 for A Parallel/Distributed Algorithmic Framework for Mining All Quantitative Association Rules
Figure 4 for A Parallel/Distributed Algorithmic Framework for Mining All Quantitative Association Rules
* 14 pages, 2 figures 
  Access Paper or Ask Questions

Time-Contrastive Learning Based DNN Bottleneck Features for Text-Dependent Speaker Verification


Nov 27, 2017
Achintya Kr. Sarkar, Zheng-Hua Tan

Figure 1 for Time-Contrastive Learning Based DNN Bottleneck Features for Text-Dependent Speaker Verification
Figure 2 for Time-Contrastive Learning Based DNN Bottleneck Features for Text-Dependent Speaker Verification
Figure 3 for Time-Contrastive Learning Based DNN Bottleneck Features for Text-Dependent Speaker Verification
Figure 4 for Time-Contrastive Learning Based DNN Bottleneck Features for Text-Dependent Speaker Verification

  Access Paper or Ask Questions

Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification


Sep 07, 2017
Daniel Michelsanti, Zheng-Hua Tan

Figure 1 for Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification
Figure 2 for Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification
Figure 3 for Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification
Figure 4 for Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification
* INTERSPEECH 2017 August 20-24, 2017, Stockholm, Sweden 
  Access Paper or Ask Questions