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 Haizhou Li

Haizhou Li

Emotion Intensity and its Control for Emotional Voice Conversion


Jan 10, 2022
Kun Zhou, Berrak Sisman, Rajib Rana, Björn W. Schuller, Haizhou Li

Figure 1 for Emotion Intensity and its Control for Emotional Voice Conversion
Figure 2 for Emotion Intensity and its Control for Emotional Voice Conversion
Figure 3 for Emotion Intensity and its Control for Emotional Voice Conversion
Figure 4 for Emotion Intensity and its Control for Emotional Voice Conversion
* Submitted to IEEE Transactions on Affective Computing 
  Access Paper or Ask Questions

MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation


Dec 14, 2021
Chen Zhang, Luis Fernando D'Haro, Thomas Friedrichs, Haizhou Li

Figure 1 for MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation
Figure 2 for MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation
Figure 3 for MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation
Figure 4 for MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation
* Accepted to AAAI2022 (10 pages, 3 figures, Preprint version) 
  Access Paper or Ask Questions

Time-Frequency Attention for Monaural Speech Enhancement


Nov 17, 2021
Qiquan Zhang, Qi Song, Zhaoheng Ni, Aaron Nicolson, Haizhou Li

Figure 1 for Time-Frequency Attention for Monaural Speech Enhancement
Figure 2 for Time-Frequency Attention for Monaural Speech Enhancement
Figure 3 for Time-Frequency Attention for Monaural Speech Enhancement
Figure 4 for Time-Frequency Attention for Monaural Speech Enhancement
* 5 pages, 4 figures, Submitted to ICASSP2022 
  Access Paper or Ask Questions

HLT-NUS SUBMISSION FOR 2020 NIST Conversational Telephone Speech SRE


Nov 12, 2021
Rohan Kumar Das, Ruijie Tao, Haizhou Li

Figure 1 for HLT-NUS SUBMISSION FOR 2020 NIST Conversational Telephone Speech SRE
Figure 2 for HLT-NUS SUBMISSION FOR 2020 NIST Conversational Telephone Speech SRE
* 3 pages 
  Access Paper or Ask Questions

MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition


Oct 27, 2021
Jinming Zhao, Ruichen Li, Qin Jin, Xinchao Wang, Haizhou Li

Figure 1 for MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition
Figure 2 for MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition
Figure 3 for MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition
Figure 4 for MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition
* 4 papges, 2 figures 
  Access Paper or Ask Questions

Identity Conversion for Emotional Speakers: A Study for Disentanglement of Emotion Style and Speaker Identity


Oct 20, 2021
Zongyang Du, Berrak Sisman, Kun Zhou, Haizhou Li

Figure 1 for Identity Conversion for Emotional Speakers: A Study for Disentanglement of Emotion Style and Speaker Identity
Figure 2 for Identity Conversion for Emotional Speakers: A Study for Disentanglement of Emotion Style and Speaker Identity
Figure 3 for Identity Conversion for Emotional Speakers: A Study for Disentanglement of Emotion Style and Speaker Identity
Figure 4 for Identity Conversion for Emotional Speakers: A Study for Disentanglement of Emotion Style and Speaker Identity
* Submitted to ICASSP2022 
  Access Paper or Ask Questions

Ego4D: Around the World in 3,000 Hours of Egocentric Video


Oct 13, 2021
Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan, Ilija Radosavovic, Santhosh Kumar Ramakrishnan, Fiona Ryan, Jayant Sharma, Michael Wray, Mengmeng Xu, Eric Zhongcong Xu, Chen Zhao, Siddhant Bansal, Dhruv Batra, Vincent Cartillier, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Christian Fuegen, Abrham Gebreselasie, Cristina Gonzalez, James Hillis, Xuhua Huang, Yifei Huang, Wenqi Jia, Weslie Khoo, Jachym Kolar, Satwik Kottur, Anurag Kumar, Federico Landini, Chao Li, Yanghao Li, Zhenqiang Li, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Yuchen Wang, Xindi Wu, Takuma Yagi, Yunyi Zhu, Pablo Arbelaez, David Crandall, Dima Damen, Giovanni Maria Farinella, Bernard Ghanem, Vamsi Krishna Ithapu, C. V. Jawahar, Hanbyul Joo, Kris Kitani, Haizhou Li, Richard Newcombe, Aude Oliva, Hyun Soo Park, James M. Rehg, Yoichi Sato, Jianbo Shi, Mike Zheng Shou, Antonio Torralba, Lorenzo Torresani, Mingfei Yan, Jitendra Malik

Figure 1 for Ego4D: Around the World in 3,000 Hours of Egocentric Video
Figure 2 for Ego4D: Around the World in 3,000 Hours of Egocentric Video
Figure 3 for Ego4D: Around the World in 3,000 Hours of Egocentric Video
Figure 4 for Ego4D: Around the World in 3,000 Hours of Egocentric Video

  Access Paper or Ask Questions

DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding


Oct 13, 2021
Sergey Nikonorov, Berrak Sisman, Mingyang Zhang, Haizhou Li

Figure 1 for DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding
Figure 2 for DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding
Figure 3 for DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding
Figure 4 for DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding
* Accepted to ASRU 2021 
  Access Paper or Ask Questions

VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over


Oct 09, 2021
Junchen Lu, Berrak Sisman, Rui Liu, Mingyang Zhang, Haizhou Li

Figure 1 for VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over
Figure 2 for VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over
Figure 3 for VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over
* Submitted to ICASSP 2022 
  Access Paper or Ask Questions

StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis


Oct 08, 2021
Rui Liu, Berrak Sisman, Haizhou Li

Figure 1 for StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis
Figure 2 for StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis
Figure 3 for StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis
Figure 4 for StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis
* Submitted to ICASSP 2022. 5 pages, 3 figures, 1 table. Our codes are available at: https://github.com/ttslr/StrengthNet 
  Access Paper or Ask Questions

Self-supervised Speaker Recognition with Loss-gated Learning


Oct 08, 2021
Ruijie Tao, Kong Aik Lee, Rohan Kumar Das, Ville Hautamäki, Haizhou Li

Figure 1 for Self-supervised Speaker Recognition with Loss-gated Learning
Figure 2 for Self-supervised Speaker Recognition with Loss-gated Learning
Figure 3 for Self-supervised Speaker Recognition with Loss-gated Learning
Figure 4 for Self-supervised Speaker Recognition with Loss-gated Learning
* 5 pages, 3 figures 
  Access Paper or Ask Questions

Investigating the Impact of Pre-trained Language Models on Dialog Evaluation


Oct 05, 2021
Chen Zhang, Luis Fernando D'Haro, Yiming Chen, Thomas Friedrichs, Haizhou Li

Figure 1 for Investigating the Impact of Pre-trained Language Models on Dialog Evaluation
Figure 2 for Investigating the Impact of Pre-trained Language Models on Dialog Evaluation
Figure 3 for Investigating the Impact of Pre-trained Language Models on Dialog Evaluation
Figure 4 for Investigating the Impact of Pre-trained Language Models on Dialog Evaluation
* Accepted by IWSDS2021 (Long Paper) 
  Access Paper or Ask Questions

Revisiting Self-Training for Few-Shot Learning of Language Model


Oct 04, 2021
Yiming Chen, Yan Zhang, Chen Zhang, Grandee Lee, Ran Cheng, Haizhou Li

Figure 1 for Revisiting Self-Training for Few-Shot Learning of Language Model
Figure 2 for Revisiting Self-Training for Few-Shot Learning of Language Model
Figure 3 for Revisiting Self-Training for Few-Shot Learning of Language Model
Figure 4 for Revisiting Self-Training for Few-Shot Learning of Language Model
* Accepted to EMNLP 2021 
  Access Paper or Ask Questions

PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction


Oct 03, 2021
Yi Ma, Kong Aik Lee, Ville Hautamaki, Haizhou Li

Figure 1 for PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction
Figure 2 for PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction
Figure 3 for PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction
Figure 4 for PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction

  Access Paper or Ask Questions

USEV: Universal Speaker Extraction with Visual Cue


Sep 30, 2021
Zexu Pan, Meng Ge, Haizhou Li

Figure 1 for USEV: Universal Speaker Extraction with Visual Cue
Figure 2 for USEV: Universal Speaker Extraction with Visual Cue
Figure 3 for USEV: Universal Speaker Extraction with Visual Cue
Figure 4 for USEV: Universal Speaker Extraction with Visual Cue

  Access Paper or Ask Questions

Exploring Teacher-Student Learning Approach for Multi-lingual Speech-to-Intent Classification


Sep 28, 2021
Bidisha Sharma, Maulik Madhavi, Xuehao Zhou, Haizhou Li

Figure 1 for Exploring Teacher-Student Learning Approach for Multi-lingual Speech-to-Intent Classification
Figure 2 for Exploring Teacher-Student Learning Approach for Multi-lingual Speech-to-Intent Classification
Figure 3 for Exploring Teacher-Student Learning Approach for Multi-lingual Speech-to-Intent Classification
Figure 4 for Exploring Teacher-Student Learning Approach for Multi-lingual Speech-to-Intent Classification

  Access Paper or Ask Questions

Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification


Aug 05, 2021
Yidi Jiang, Bidisha Sharma, Maulik Madhavi, Haizhou Li

Figure 1 for Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification
Figure 2 for Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification
Figure 3 for Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification
Figure 4 for Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification
* Interspeech 2021 
  Access Paper or Ask Questions

SLoClas: A Database for Joint Sound Localization and Classification


Aug 05, 2021
Xinyuan Qian, Bidisha Sharma, Amine El Abridi, Haizhou Li

Figure 1 for SLoClas: A Database for Joint Sound Localization and Classification
Figure 2 for SLoClas: A Database for Joint Sound Localization and Classification
Figure 3 for SLoClas: A Database for Joint Sound Localization and Classification
Figure 4 for SLoClas: A Database for Joint Sound Localization and Classification
* Submitted to O-COCOSDA 2021 
  Access Paper or Ask Questions

Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection


Jul 25, 2021
Ruijie Tao, Zexu Pan, Rohan Kumar Das, Xinyuan Qian, Mike Zheng Shou, Haizhou Li

Figure 1 for Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection
Figure 2 for Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection
Figure 3 for Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection
Figure 4 for Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection
* ACM Multimedia 2021 
  Access Paper or Ask Questions

Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding


Jul 14, 2021
Hongning Zhu, Kong Aik Lee, Haizhou Li

Figure 1 for Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding
Figure 2 for Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding
Figure 3 for Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding
Figure 4 for Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding
* Accepted by Interspeech 2021 
  Access Paper or Ask Questions

Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer


Jul 08, 2021
Zongyang Du, Berrak Sisman, Kun Zhou, Haizhou Li

Figure 1 for Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer
Figure 2 for Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer
Figure 3 for Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer
Figure 4 for Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer
* Submitted to ASRU 2021 
  Access Paper or Ask Questions

Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification


Jun 17, 2021
Li Zhang, Qing Wang, Kong Aik Lee, Lei Xie, Haizhou Li

Figure 1 for Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification
Figure 2 for Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification
Figure 3 for Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification
Figure 4 for Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification

  Access Paper or Ask Questions

Selective Hearing through Lip-reading


Jun 14, 2021
Zexu Pan, Ruijie Tao, Chenglin Xu, Haizhou Li

Figure 1 for Selective Hearing through Lip-reading
Figure 2 for Selective Hearing through Lip-reading
Figure 3 for Selective Hearing through Lip-reading
Figure 4 for Selective Hearing through Lip-reading

  Access Paper or Ask Questions

DynaEval: Unifying Turn and Dialogue Level Evaluation


Jun 06, 2021
Chen Zhang, Yiming Chen, Luis Fernando D'Haro, Yan Zhang, Thomas Friedrichs, Grandee Lee, Haizhou Li

Figure 1 for DynaEval: Unifying Turn and Dialogue Level Evaluation
Figure 2 for DynaEval: Unifying Turn and Dialogue Level Evaluation
Figure 3 for DynaEval: Unifying Turn and Dialogue Level Evaluation
Figure 4 for DynaEval: Unifying Turn and Dialogue Level Evaluation
* ACL-IJCNLP 2021 (Main conference, Long paper) 
  Access Paper or Ask Questions

Emotional Voice Conversion: Theory, Databases and ESD


May 31, 2021
Kun Zhou, Berrak Sisman, Rui Liu, Haizhou Li

Figure 1 for Emotional Voice Conversion: Theory, Databases and ESD
Figure 2 for Emotional Voice Conversion: Theory, Databases and ESD
Figure 3 for Emotional Voice Conversion: Theory, Databases and ESD
Figure 4 for Emotional Voice Conversion: Theory, Databases and ESD
* Submitted to Speech Communication 
  Access Paper or Ask Questions

Multi-target DoA Estimation with an Audio-visual Fusion Mechanism


May 13, 2021
Xinyuan Qian, Maulik Madhavi, Zexu Pan, Jiadong Wang, Haizhou Li

Figure 1 for Multi-target DoA Estimation with an Audio-visual Fusion Mechanism
Figure 2 for Multi-target DoA Estimation with an Audio-visual Fusion Mechanism
Figure 3 for Multi-target DoA Estimation with an Audio-visual Fusion Mechanism
Figure 4 for Multi-target DoA Estimation with an Audio-visual Fusion Mechanism
* ICASSP 2021 accepted 
  Access Paper or Ask Questions

The Multi-speaker Multi-style Voice Cloning Challenge 2021


Apr 05, 2021
Qicong Xie, Xiaohai Tian, Guanghou Liu, Kun Song, Lei Xie, Zhiyong Wu, Hai Li, Song Shi, Haizhou Li, Fen Hong, Hui Bu, Xin Xu

Figure 1 for The Multi-speaker Multi-style Voice Cloning Challenge 2021
Figure 2 for The Multi-speaker Multi-style Voice Cloning Challenge 2021
* has been accepted to ICASSP 2021 
  Access Paper or Ask Questions

Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability


Apr 03, 2021
Rui Liu, Berrak Sisman, Haizhou Li

Figure 1 for Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability
Figure 2 for Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability
Figure 3 for Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability
Figure 4 for Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability
* 5 pages, 4 figures, Submitted to Interspeech 2021, Speech Samples: https://ttslr.github.io/i-ETTS 
  Access Paper or Ask Questions