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

Add to Chrome

Add to Firefox

Picture for Rongzhi Gu

Rongzhi Gu

Improving Dual-Microphone Speech Enhancement by Learning Cross-Channel Features with Multi-Head Attention

May 03, 2022
Xinmeng Xu, Rongzhi Gu, Yuexian Zou

Figure 1 for Improving Dual-Microphone Speech Enhancement by Learning Cross-Channel Features with Multi-Head Attention

Figure 2 for Improving Dual-Microphone Speech Enhancement by Learning Cross-Channel Features with Multi-Head Attention

Figure 3 for Improving Dual-Microphone Speech Enhancement by Learning Cross-Channel Features with Multi-Head Attention

Figure 4 for Improving Dual-Microphone Speech Enhancement by Learning Cross-Channel Features with Multi-Head Attention

* Accepted by ICASSP 2022

Access Paper or Ask Questions

Speaker-Aware Mixture of Mixtures Training for Weakly Supervised Speaker Extraction

Apr 15, 2022
Zifeng Zhao, Rongzhi Gu, Dongchao Yang, Jinchuan Tian, Yuexian Zou

Figure 1 for Speaker-Aware Mixture of Mixtures Training for Weakly Supervised Speaker Extraction

Figure 2 for Speaker-Aware Mixture of Mixtures Training for Weakly Supervised Speaker Extraction

Figure 3 for Speaker-Aware Mixture of Mixtures Training for Weakly Supervised Speaker Extraction

Figure 4 for Speaker-Aware Mixture of Mixtures Training for Weakly Supervised Speaker Extraction

* 5 pages, 4 tables, 4 figures. Submitted to INTERSPEECH 2022

Access Paper or Ask Questions

Target Confusion in End-to-end Speaker Extraction: Analysis and Approaches

Apr 04, 2022
Zifeng Zhao, Dongchao Yang, Rongzhi Gu, Haoran Zhang, Yuexian Zou

Figure 1 for Target Confusion in End-to-end Speaker Extraction: Analysis and Approaches

Figure 2 for Target Confusion in End-to-end Speaker Extraction: Analysis and Approaches

Figure 3 for Target Confusion in End-to-end Speaker Extraction: Analysis and Approaches

Figure 4 for Target Confusion in End-to-end Speaker Extraction: Analysis and Approaches

* 5 pages, 1 table, 5 figures. Submitted to INTERSPEECH 2022

Access Paper or Ask Questions

Learning Decoupling Features Through Orthogonality Regularization

Mar 31, 2022
Li Wang, Rongzhi Gu, Weiji Zhuang, Peng Gao, Yujun Wang, Yuexian Zou

Figure 1 for Learning Decoupling Features Through Orthogonality Regularization

Figure 2 for Learning Decoupling Features Through Orthogonality Regularization

Figure 3 for Learning Decoupling Features Through Orthogonality Regularization

Figure 4 for Learning Decoupling Features Through Orthogonality Regularization

* Accepted at ICASSP 2022

Access Paper or Ask Questions