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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM


Sep 08, 2022
Hayato Futami, Hirofumi Inaguma, Sei Ueno, Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara

* Accepted in Interspeech2022 

   Access Paper or Ask Questions

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

Distilling the Knowledge of BERT for CTC-based ASR


Sep 05, 2022
Hayato Futami, Hirofumi Inaguma, Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara


   Access Paper or Ask Questions

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

A Study of Transducer based End-to-End ASR with ESPnet: Architecture, Auxiliary Loss and Decoding Strategies


Jan 14, 2022
Florian Boyer, Yusuke Shinohara, Takaaki Ishii, Hirofumi Inaguma, Shinji Watanabe


   Access Paper or Ask Questions

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

A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation


Oct 11, 2021
Yosuke Higuchi, Nanxin Chen, Yuya Fujita, Hirofumi Inaguma, Tatsuya Komatsu, Jaesong Lee, Jumon Nozaki, Tianzi Wang, Shinji Watanabe

* Accepted to ASRU2021 

   Access Paper or Ask Questions

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

ASR Rescoring and Confidence Estimation with ELECTRA


Oct 05, 2021
Hayato Futami, Hirofumi Inaguma, Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara

* Accepted in ASRU2021 

   Access Paper or Ask Questions

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

Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates


Sep 27, 2021
Hirofumi Inaguma, Siddharth Dalmia, Brian Yan, Shinji Watanabe

* Accepted at IEEE ASRU 2021 

   Access Paper or Ask Questions

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

Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring


Sep 09, 2021
Hirofumi Inaguma, Yosuke Higuchi, Kevin Duh, Tatsuya Kawahara, Shinji Watanabe


   Access Paper or Ask Questions

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

VAD-free Streaming Hybrid CTC/Attention ASR for Unsegmented Recording


Jul 15, 2021
Hirofumi Inaguma, Tatsuya Kawahara

* Accepted at 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

StableEmit: Selection Probability Discount for Reducing Emission Latency of Streaming Monotonic Attention ASR


Jul 15, 2021
Hirofumi Inaguma, Tatsuya Kawahara

* Accepted at 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

ESPnet-ST IWSLT 2021 Offline Speech Translation System


Jul 06, 2021
Hirofumi Inaguma, Brian Yan, Siddharth Dalmia, Pengcheng Guo, Jiatong Shi, Kevin Duh, Shinji Watanabe

* IWSLT 2021 

   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
3
4
>>