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

Add to Chrome

Add to Firefox

Picture for Shulin He

Shulin He

TEA-PSE 3.0: Tencent-Ethereal-Audio-Lab Personalized Speech Enhancement System For ICASSP 2023 DNS Challenge

Mar 14, 2023
Yukai Ju, Jun Chen, Shimin Zhang, Shulin He, Wei Rao, Weixin Zhu, Yannan Wang, Tao Yu, Shidong Shang

Figure 1 for TEA-PSE 3.0: Tencent-Ethereal-Audio-Lab Personalized Speech Enhancement System For ICASSP 2023 DNS Challenge

Figure 2 for TEA-PSE 3.0: Tencent-Ethereal-Audio-Lab Personalized Speech Enhancement System For ICASSP 2023 DNS Challenge

Figure 3 for TEA-PSE 3.0: Tencent-Ethereal-Audio-Lab Personalized Speech Enhancement System For ICASSP 2023 DNS Challenge

* Accepted by ICASSP 2023

Access Paper or Ask Questions

ExARN: self-attending RNN for target speaker extraction

Dec 02, 2022
Pengjie Shen, Shulin He, Xueliang Zhang

Figure 1 for ExARN: self-attending RNN for target speaker extraction

Figure 2 for ExARN: self-attending RNN for target speaker extraction

Figure 3 for ExARN: self-attending RNN for target speaker extraction

Figure 4 for ExARN: self-attending RNN for target speaker extraction

* Submitted to ICASSP 2023, 5 pages with 3 figures

Access Paper or Ask Questions

Speech Enhancement with Intelligent Neural Homomorphic Synthesis

Oct 28, 2022
Shulin He, Wei Rao, Jinjiang Liu, Jun Chen, Yukai Ju, Xueliang Zhang, Yannan Wang, Shidong Shang

Figure 1 for Speech Enhancement with Intelligent Neural Homomorphic Synthesis

Figure 2 for Speech Enhancement with Intelligent Neural Homomorphic Synthesis

Figure 3 for Speech Enhancement with Intelligent Neural Homomorphic Synthesis

Figure 4 for Speech Enhancement with Intelligent Neural Homomorphic Synthesis

* Submitted to ICASSP 2023

Access Paper or Ask Questions

Local-global speaker representation for target speaker extraction

Oct 28, 2022
Shulin He, Wei Rao, Kanghao Zhang, Yukai Ju, Yang Yang, Xueliang Zhang, Yannan Wang, Shidong Shang

Figure 1 for Local-global speaker representation for target speaker extraction

Figure 2 for Local-global speaker representation for target speaker extraction

Figure 3 for Local-global speaker representation for target speaker extraction

Figure 4 for Local-global speaker representation for target speaker extraction

* Submitted to ICASSP 2023

Access Paper or Ask Questions

Speakerfilter-Pro: an improved target speaker extractor combines the time domain and frequency domain

Oct 25, 2020
Shulin He, Hao Li, Xueliang Zhang

Figure 1 for Speakerfilter-Pro: an improved target speaker extractor combines the time domain and frequency domain

Figure 2 for Speakerfilter-Pro: an improved target speaker extractor combines the time domain and frequency domain

Figure 3 for Speakerfilter-Pro: an improved target speaker extractor combines the time domain and frequency domain

Figure 4 for Speakerfilter-Pro: an improved target speaker extractor combines the time domain and frequency domain

* Preprint, submitted to ICASSP 2021

Access Paper or Ask Questions