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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

How Information on Acoustic Scenes and Sound Events Mutually Benefits Event Detection and Scene Classification Tasks


Apr 05, 2022
Keisuke Imoto , Yuka Komatsu , Shunsuke Tsubaki , Tatsuya Komatsu

* 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

Better Intermediates Improve CTC Inference


Apr 01, 2022
Tatsuya Komatsu , Yusuke Fujita , Jaesong Lee , Lukas Lee , Shinji Watanabe , Yusuke Kida

* 5 pages, submitted INTERSPEECH2022 

   Access Paper or Ask Questions

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

Multi-sequence Intermediate Conditioning for CTC-based ASR


Apr 01, 2022
Yusuke Fujita , Tatsuya Komatsu , Yusuke Kida

* This paper was 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

InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR


Apr 01, 2022
Yu Nakagome , Tatsuya Komatsu , Yusuke Fujita , Shuta Ichimura , Yusuke Kida

* This paper was submitted to INTERSPEECH2022 

   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 ASR with Self-Conditioned Folded Encoders


Feb 17, 2022
Tatsuya Komatsu

* 5 pages, accepted at ICASSP2022 

   Access Paper or Ask Questions

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

Acoustic Event Detection with Classifier Chains


Feb 17, 2022
Tatsuya Komatsu , Shinji Watanabe , Koichi Miyazaki , Tomoki Hayashi

* 5pages, presented at Interspeech2021 

   Access Paper or Ask Questions

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

MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition


Feb 17, 2022
Jin Sakuma , Tatsuya Komatsu , Robin Scheibler

* 8 pages, 4 figures 

   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

Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers


Apr 21, 2021
Yusuke Kida , Tatsuya Komatsu , Masahito Togami

* 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

Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions


Apr 06, 2021
Jumon Nozaki , Tatsuya Komatsu

* Submitted to INTERSPEECH2021 

   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
>>