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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks


Dec 14, 2022
Darius Petermann, Gordon Wichern, Aswin Shanmugam Subramanian, Zhong-Qiu Wang, Jonathan Le Roux

Add code

* Submitted to IEEE TASLP (In review), 13 pages, 6 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation


Nov 22, 2022
Zhong-Qiu Wang, Samuele Cornell, Shukjae Choi, Younglo Lee, Byeong-Yeol Kim, Shinji Watanabe

Add code

* In submission. A sound demo is available at https://zqwang7.github.io/demos/TF-GridNet-demo/index.html 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation


Sep 08, 2022
Zhong-Qiu Wang, Samuele Cornell, Shukjae Choi, Younglo Lee, Byeong-Yeol Kim, Shinji Watanabe

Add code

* in submission 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding


Jul 19, 2022
Yen-Ju Lu, Xuankai Chang, Chenda Li, Wangyou Zhang, Samuele Cornell, Zhaoheng Ni, Yoshiki Masuyama, Brian Yan, Robin Scheibler, Zhong-Qiu Wang, Yu Tsao, Yanmin Qian, Shinji Watanabe

Add code

* To appear in Interspeech 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

STFT-Domain Neural Speech Enhancement with Very Low Algorithmic Latency


Apr 21, 2022
Zhong-Qiu Wang, Gordon Wichern, Shinji Watanabe, Jonathan Le Roux

Add code

* in submission 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Improving Frame-Online Neural Speech Enhancement with Overlapped-Frame Prediction


Apr 15, 2022
Zhong-Qiu Wang, Shinji Watanabe

Add code

* in submission 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Locate This, Not That: Class-Conditioned Sound Event DOA Estimation


Mar 08, 2022
Olga Slizovskaia, Gordon Wichern, Zhong-Qiu Wang, Jonathan Le Roux

Add code

* Accepted for publication at ICASSP 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge


Feb 24, 2022
Yen-Ju Lu, Samuele Cornell, Xuankai Chang, Wangyou Zhang, Chenda Li, Zhaoheng Ni, Zhong-Qiu Wang, Shinji Watanabe

Add code

* to be published in IEEE ICASSP 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Conditional Diffusion Probabilistic Model for Speech Enhancement


Feb 10, 2022
Yen-Ju Lu, Zhong-Qiu Wang, Shinji Watanabe, Alexander Richard, Cheng Yu, Yu Tsao

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks


Oct 19, 2021
Darius Petermann, Gordon Wichern, Zhong-Qiu Wang, Jonathan Le Roux

Add code

* Submitted to ICASSP2022. For resources and examples, see https://cocktail-fork.github.io 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>