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 Yu Wu

Yu Wu

UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset


Jul 12, 2021
Chengyi Wang, Yu Wu, Shujie Liu, Jinyu Li, Yao Qian, Kenichi Kumatani, Furu Wei

Figure 1 for UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset
Figure 2 for UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset
Figure 3 for UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset
Figure 4 for UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset

  Access Paper or Ask Questions

Investigation of Practical Aspects of Single Channel Speech Separation for ASR


Jul 05, 2021
Jian Wu, Zhuo Chen, Sanyuan Chen, Yu Wu, Takuya Yoshioka, Naoyuki Kanda, Shujie Liu, Jinyu Li

Figure 1 for Investigation of Practical Aspects of Single Channel Speech Separation for ASR
Figure 2 for Investigation of Practical Aspects of Single Channel Speech Separation for ASR
Figure 3 for Investigation of Practical Aspects of Single Channel Speech Separation for ASR
* Accepted by Interspeech 2021 
  Access Paper or Ask Questions

Saying the Unseen: Video Descriptions via Dialog Agents


Jun 26, 2021
Ye Zhu, Yu Wu, Yi Yang, Yan Yan

Figure 1 for Saying the Unseen: Video Descriptions via Dialog Agents
Figure 2 for Saying the Unseen: Video Descriptions via Dialog Agents
Figure 3 for Saying the Unseen: Video Descriptions via Dialog Agents
Figure 4 for Saying the Unseen: Video Descriptions via Dialog Agents
* Accepted as a regular paper at TPAMI 2021 
  Access Paper or Ask Questions

Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition


Jun 04, 2021
Zhong Meng, Yu Wu, Naoyuki Kanda, Liang Lu, Xie Chen, Guoli Ye, Eric Sun, Jinyu Li, Yifan Gong

Figure 1 for Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition
Figure 2 for Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition
Figure 3 for Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition
* Interspeech 2021, Brno, Czech Republic 
 * 5 pages, Interspeech 2021 
  Access Paper or Ask Questions

Template-Based Named Entity Recognition Using BART


Jun 03, 2021
Leyang Cui, Yu Wu, Jian Liu, Sen Yang, Yue Zhang

Figure 1 for Template-Based Named Entity Recognition Using BART
Figure 2 for Template-Based Named Entity Recognition Using BART
Figure 3 for Template-Based Named Entity Recognition Using BART
Figure 4 for Template-Based Named Entity Recognition Using BART

  Access Paper or Ask Questions

Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation


Jun 02, 2021
Chen Liang, Yu Wu, Tianfei Zhou, Wenguan Wang, Zongxin Yang, Yunchao Wei, Yi Yang

Figure 1 for Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation
Figure 2 for Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation
Figure 3 for Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation
Figure 4 for Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation

  Access Paper or Ask Questions

Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone


Apr 12, 2021
Naoyuki Kanda, Guoli Ye, Yu Wu, Yashesh Gaur, Xiaofei Wang, Zhong Meng, Zhuo Chen, Takuya Yoshioka

Figure 1 for Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone
Figure 2 for Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone
Figure 3 for Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone
* Submitted to INTERSPEECH 2021 
  Access Paper or Ask Questions

ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation


Mar 19, 2021
Chen Liang, Yu Wu, Yawei Luo, Yi Yang

Figure 1 for ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation
Figure 2 for ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation
Figure 3 for ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation
Figure 4 for ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation

  Access Paper or Ask Questions

Learning Audio-Visual Correlations from Variational Cross-Modal Generation


Feb 14, 2021
Ye Zhu, Yu Wu, Hugo Latapie, Yi Yang, Yan Yan

Figure 1 for Learning Audio-Visual Correlations from Variational Cross-Modal Generation
Figure 2 for Learning Audio-Visual Correlations from Variational Cross-Modal Generation
Figure 3 for Learning Audio-Visual Correlations from Variational Cross-Modal Generation
Figure 4 for Learning Audio-Visual Correlations from Variational Cross-Modal Generation
* Accepted to ICASSP 2021 
  Access Paper or Ask Questions

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data


Jan 19, 2021
Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang

Figure 1 for UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
Figure 2 for UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
Figure 3 for UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
Figure 4 for UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

  Access Paper or Ask Questions

Learning to Anticipate Egocentric Actions by Imagination


Jan 19, 2021
Yu Wu, Linchao Zhu, Xiaohan Wang, Yi Yang, Fei Wu

Figure 1 for Learning to Anticipate Egocentric Actions by Imagination
Figure 2 for Learning to Anticipate Egocentric Actions by Imagination
Figure 3 for Learning to Anticipate Egocentric Actions by Imagination
Figure 4 for Learning to Anticipate Egocentric Actions by Imagination
* IEEE Transactions on Image Processing, vol. 30, pp. 1143-1152, 2021 
 * Accepted to IEEE Transactions on Image Processing (TIP) 
  Access Paper or Ask Questions

Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer


Oct 23, 2020
Sanyuan Chen, Yu Wu, Zhuo Chen, Takuya Yoshioka, Shujie Liu, Jinyu Li

Figure 1 for Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer
Figure 2 for Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer
Figure 3 for Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer

  Access Paper or Ask Questions

Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset


Oct 22, 2020
Xie Chen, Yu Wu, Zhenghao Wang, Shujie Liu, Jinyu Li

Figure 1 for Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset
Figure 2 for Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset
Figure 3 for Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset
Figure 4 for Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset
* 5 pages 
  Access Paper or Ask Questions

Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents


Aug 22, 2020
Ye Zhu, Yu Wu, Yi Yang, Yan Yan

Figure 1 for Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents
Figure 2 for Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents
Figure 3 for Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents
Figure 4 for Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents
* ECCV2020 
  Access Paper or Ask Questions

Describing Unseen Videos via Multi-ModalCooperative Dialog Agents


Aug 18, 2020
Ye Zhu, Yu Wu, Yi Yang, Yan Yan

Figure 1 for Describing Unseen Videos via Multi-ModalCooperative Dialog Agents
Figure 2 for Describing Unseen Videos via Multi-ModalCooperative Dialog Agents
Figure 3 for Describing Unseen Videos via Multi-ModalCooperative Dialog Agents
Figure 4 for Describing Unseen Videos via Multi-ModalCooperative Dialog Agents
* ECCV2020 
  Access Paper or Ask Questions

Continuous Speech Separation with Conformer


Aug 13, 2020
Sanyuan Chen, Yu Wu, Zhuo Chen, Jinyu Li, Chengyi Wang, Shujie Liu, Ming Zhou

Figure 1 for Continuous Speech Separation with Conformer
Figure 2 for Continuous Speech Separation with Conformer
Figure 3 for Continuous Speech Separation with Conformer
Figure 4 for Continuous Speech Separation with Conformer

  Access Paper or Ask Questions

Does BERT Solve Commonsense Task via Commonsense Knowledge?


Aug 10, 2020
Leyang Cui, Sijie Cheng, Yu Wu, Yue Zhang

Figure 1 for Does BERT Solve Commonsense Task via Commonsense Knowledge?
Figure 2 for Does BERT Solve Commonsense Task via Commonsense Knowledge?
Figure 3 for Does BERT Solve Commonsense Task via Commonsense Knowledge?
Figure 4 for Does BERT Solve Commonsense Task via Commonsense Knowledge?

  Access Paper or Ask Questions

Abnormal activity capture from passenger flow of elevator based on unsupervised learning and fine-grained multi-label recognition


Jun 29, 2020
Chunhua Jia, Wenhai Yi, Yu Wu, Hui Huang, Lei Zhang, Leilei Wu

Figure 1 for Abnormal activity capture from passenger flow of elevator based on unsupervised learning and fine-grained multi-label recognition
Figure 2 for Abnormal activity capture from passenger flow of elevator based on unsupervised learning and fine-grained multi-label recognition
Figure 3 for Abnormal activity capture from passenger flow of elevator based on unsupervised learning and fine-grained multi-label recognition
Figure 4 for Abnormal activity capture from passenger flow of elevator based on unsupervised learning and fine-grained multi-label recognition
* 9 pages, 8 figures, submitted to 34th Conference on Neural Information Processing System(NeurIPS 2020) 
  Access Paper or Ask Questions

On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition


May 28, 2020
Jinyu Li, Yu Wu, Yashesh Gaur, Chengyi Wang, Rui Zhao, Shujie Liu

Figure 1 for On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition
Figure 2 for On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition
* submitted to Interspeech 2020 
  Access Paper or Ask Questions

Curriculum Pre-training for End-to-End Speech Translation


Apr 21, 2020
Chengyi Wang, Yu Wu, Shujie Liu, Ming Zhou, Zhenglu Yang

Figure 1 for Curriculum Pre-training for End-to-End Speech Translation
Figure 2 for Curriculum Pre-training for End-to-End Speech Translation
Figure 3 for Curriculum Pre-training for End-to-End Speech Translation
Figure 4 for Curriculum Pre-training for End-to-End Speech Translation
* accepted by ACL2020 
  Access Paper or Ask Questions

MuTual: A Dataset for Multi-Turn Dialogue Reasoning


Apr 09, 2020
Leyang Cui, Yu Wu, Shujie Liu, Yue Zhang, Ming Zhou

Figure 1 for MuTual: A Dataset for Multi-Turn Dialogue Reasoning
Figure 2 for MuTual: A Dataset for Multi-Turn Dialogue Reasoning
Figure 3 for MuTual: A Dataset for Multi-Turn Dialogue Reasoning
Figure 4 for MuTual: A Dataset for Multi-Turn Dialogue Reasoning
* ACL 2020 
  Access Paper or Ask Questions

Signature features with the visibility transformation


Apr 08, 2020
Yu Wu, Hao Ni, Terrence J. Lyons, Robin L. Hudson

Figure 1 for Signature features with the visibility transformation
Figure 2 for Signature features with the visibility transformation
Figure 3 for Signature features with the visibility transformation
Figure 4 for Signature features with the visibility transformation

  Access Paper or Ask Questions

Unsupervised Person Re-identification via Softened Similarity Learning


Apr 07, 2020
Yutian Lin, Lingxi Xie, Yu Wu, Chenggang Yan, Qi Tian

Figure 1 for Unsupervised Person Re-identification via Softened Similarity Learning
Figure 2 for Unsupervised Person Re-identification via Softened Similarity Learning
Figure 3 for Unsupervised Person Re-identification via Softened Similarity Learning
Figure 4 for Unsupervised Person Re-identification via Softened Similarity Learning
* Accepted to CVPR 2020 
  Access Paper or Ask Questions

Symbiotic Attention with Privileged Information for Egocentric Action Recognition


Feb 08, 2020
Xiaohan Wang, Yu Wu, Linchao Zhu, Yi Yang

Figure 1 for Symbiotic Attention with Privileged Information for Egocentric Action Recognition
Figure 2 for Symbiotic Attention with Privileged Information for Egocentric Action Recognition
Figure 3 for Symbiotic Attention with Privileged Information for Egocentric Action Recognition
Figure 4 for Symbiotic Attention with Privileged Information for Egocentric Action Recognition
* AAAI-2020(Oral) 
  Access Paper or Ask Questions

Semantic Mask for Transformer based End-to-End Speech Recognition


Dec 06, 2019
Chengyi Wang, Yu Wu, Yujiao Du, Jinyu Li, Shujie Liu, Liang Lu, Shuo Ren, Guoli Ye, Sheng Zhao, Ming Zhou

Figure 1 for Semantic Mask for Transformer based End-to-End Speech Recognition
Figure 2 for Semantic Mask for Transformer based End-to-End Speech Recognition
Figure 3 for Semantic Mask for Transformer based End-to-End Speech Recognition
Figure 4 for Semantic Mask for Transformer based End-to-End Speech Recognition

  Access Paper or Ask Questions

Unsupervised Context Rewriting for Open Domain Conversation


Oct 30, 2019
Kun Zhou, Kai Zhang, Yu Wu, Shujie Liu, Jingsong Yu

Figure 1 for Unsupervised Context Rewriting for Open Domain Conversation
Figure 2 for Unsupervised Context Rewriting for Open Domain Conversation
Figure 3 for Unsupervised Context Rewriting for Open Domain Conversation
Figure 4 for Unsupervised Context Rewriting for Open Domain Conversation

  Access Paper or Ask Questions