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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition


Apr 14, 2022
Zhao You, Shulin Feng, Dan Su, Dong Yu

* 5 pages, 1 figure. Submitted to 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

SpeechMoE2: Mixture-of-Experts Model with Improved Routing


Nov 23, 2021
Zhao You, Shulin Feng, Dan Su, Dong Yu

* 5 pages, 1 figure. Submitted to 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

Latency-Controlled Neural Architecture Search for Streaming Speech Recognition


May 08, 2021
Liqiang He, Shulin Feng, Dan Su, Dong Yu

* Submitted to INTERSPEECH 2021 

   Access Paper or Ask Questions

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

SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts


May 07, 2021
Zhao You, Shulin Feng, Dan Su, Dong Yu

* 5 pages, 2 figures. Submitted to Interspeech 2021 

   Access Paper or Ask Questions

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

Learning discriminative features in sequence training without requiring framewise labelled data


May 16, 2019
Jun Wang, Dan Su, Jie Chen, Shulin Feng, Dongpeng Ma, Na Li, Dong Yu

* Accepted in ICASSP 2019 lecture session 

   Access Paper or Ask Questions

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