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

Add to Chrome

Add to Firefox

Picture for Yu Wu

Yu Wu

SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding

Jul 27, 2022
Mengxue Qu, Yu Wu, Wu Liu, Qiqi Gong, Xiaodan Liang, Olga Russakovsky, Yao Zhao, Yunchao Wei

Figure 1 for SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding

Figure 2 for SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding

Figure 3 for SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding

Figure 4 for SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding

* 21 pages (including Supplementary Materials); Accepted to ECCV 2022

Access Paper or Ask Questions

Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training

Jun 21, 2022
Chengyi Wang, Yiming Wang, Yu Wu, Sanyuan Chen, Jinyu Li, Shujie Liu, Furu Wei

Figure 1 for Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training

Figure 2 for Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training

* To appear in Proc. Interspeech 2022

Access Paper or Ask Questions

Ultra Fast Speech Separation Model with Teacher Student Learning

Apr 27, 2022
Sanyuan Chen, Yu Wu, Zhuo Chen, Jian Wu, Takuya Yoshioka, Shujie Liu, Jinyu Li, Xiangzhan Yu

Figure 1 for Ultra Fast Speech Separation Model with Teacher Student Learning

Figure 2 for Ultra Fast Speech Separation Model with Teacher Student Learning

Figure 3 for Ultra Fast Speech Separation Model with Teacher Student Learning

* Accepted by interspeech 2021

Access Paper or Ask Questions

Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?

Apr 27, 2022
Sanyuan Chen, Yu Wu, Chengyi Wang, Shujie Liu, Zhuo Chen, Peidong Wang, Gang Liu, Jinyu Li, Jian Wu, Xiangzhan Yu, Furu Wei

Figure 1 for Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?

Figure 2 for Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?

Figure 3 for Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?

Figure 4 for Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?

* Submitted to INTERSPEECH 2022

Access Paper or Ask Questions

A collaborative decomposition-based evolutionary algorithm integrating normal and penalty-based boundary intersection for many-objective optimization

Apr 14, 2022
Yu Wu, Jianle Wei, Weiqin Ying, Yanqi Lan, Zhen Cui, Zhenyu Wang

Access Paper or Ask Questions

Speech Pre-training with Acoustic Piece

Apr 07, 2022
Shuo Ren, Shujie Liu, Yu Wu, Long Zhou, Furu Wei

Figure 1 for Speech Pre-training with Acoustic Piece

Figure 2 for Speech Pre-training with Acoustic Piece

Figure 3 for Speech Pre-training with Acoustic Piece

Figure 4 for Speech Pre-training with Acoustic Piece

* 5 pages, 4 figures; submitted to Interspeech 2022

Access Paper or Ask Questions

Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings

Mar 30, 2022
Naoyuki Kanda, Jian Wu, Yu Wu, Xiong Xiao, Zhong Meng, Xiaofei Wang, Yashesh Gaur, Zhuo Chen, Jinyu Li, Takuya Yoshioka

Figure 1 for Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings

Figure 2 for Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings

Figure 3 for Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings

Figure 4 for Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings

* Submitted to Interspeech 2022

Access Paper or Ask Questions