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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Tsubasa Ochiai

Few-shot learning of new sound classes for target sound extraction


Jun 14, 2021
Marc Delcroix, Jorge Bennasar Vázquez, Tsubasa Ochiai, Keisuke Kinoshita, Shoko Araki

* To appear in Interspeech 2021 

  Access Paper or Ask Questions

PILOT: Introducing Transformers for Probabilistic Sound Event Localization


Jun 07, 2021
Christopher Schymura, Benedikt Bönninghoff, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki, Dorothea Kolossa

* Accepted at INTERSPEECH 2021 

  Access Paper or Ask Questions

Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition


Jun 02, 2021
Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Takafumi Moriya, Naoyuki Kamo

* 5 pages, 1 figure 

  Access Paper or Ask Questions

Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event Localization


Feb 28, 2021
Christopher Schymura, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki, Dorothea Kolossa

* Published in Proceedings of the 28th European Signal Processing Conference (EUSIPCO), 2020 

  Access Paper or Ask Questions

Data Fusion for Audiovisual Speaker Localization: Extending Dynamic Stream Weights to the Spatial Domain


Feb 24, 2021
Julio Wissing, Benedikt Boenninghoff, Dorothea Kolossa, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki, Christopher Schymura

* 4 pages, 6 figures, ICASSP 2021 

  Access Paper or Ask Questions

End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend


Feb 23, 2021
Wangyou Zhang, Christoph Boeddeker, Shinji Watanabe, Tomohiro Nakatani, Marc Delcroix, Keisuke Kinoshita, Tsubasa Ochiai, Naoyuki Kamo, Reinhold Haeb-Umbach, Yanmin Qian

* 5 pages, 1 figure, accepted by ICASSP 2021 

  Access Paper or Ask Questions

Speaker activity driven neural speech extraction


Feb 09, 2021
Marc Delcroix, Katerina Zmolikova, Tsubasa Ochiai, Keisuke Kinoshita, Tomohiro Nakatani

* To appear in ICASSP 2021 

  Access Paper or Ask Questions

Multimodal Attention Fusion for Target Speaker Extraction


Feb 02, 2021
Hiroshi Sato, Tsubasa Ochiai, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, Shoko Araki

* in IEEE Spoken Language Technology Workshop (SLT), 2021, pp. 778-784 
* 7 pages, 5 figures 

  Access Paper or Ask Questions

Neural Network-based Virtual Microphone Estimator


Jan 12, 2021
Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, Shoko Araki

* 5 pages, 2 figures, submitted to ICASSP 2021 

  Access Paper or Ask Questions

Listen to What You Want: Neural Network-based Universal Sound Selector


Jun 10, 2020
Tsubasa Ochiai, Marc Delcroix, Yuma Koizumi, Hiroaki Ito, Keisuke Kinoshita, Shoko Araki

* 5 pages, 2 figures, submitted to INTERSPEECH 2020 

  Access Paper or Ask Questions

Improving noise robust automatic speech recognition with single-channel time-domain enhancement network


Mar 09, 2020
Keisuke Kinoshita, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani

* 5 pages, to appear in ICASSP2020 

  Access Paper or Ask Questions

Improving speaker discrimination of target speech extraction with time-domain SpeakerBeam


Jan 23, 2020
Marc Delcroix, Tsubasa Ochiai, Katerina Zmolikova, Keisuke Kinoshita, Naohiro Tawara, Tomohiro Nakatani, Shoko Araki

* 5 pages, 3 figures. Submitted to ICASSP 2020 

  Access Paper or Ask Questions

ESPnet: End-to-End Speech Processing Toolkit


Mar 30, 2018
Shinji Watanabe, Takaaki Hori, Shigeki Karita, Tomoki Hayashi, Jiro Nishitoba, Yuya Unno, Nelson Enrique Yalta Soplin, Jahn Heymann, Matthew Wiesner, Nanxin Chen, Adithya Renduchintala, Tsubasa Ochiai


  Access Paper or Ask Questions

Multichannel End-to-end Speech Recognition


Mar 14, 2017
Tsubasa Ochiai, Shinji Watanabe, Takaaki Hori, John R. Hershey


  Access Paper or Ask Questions

Automatic Node Selection for Deep Neural Networks using Group Lasso Regularization


Nov 17, 2016
Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Shigeru Katagiri

* Submitted to ICASSP 2017 

  Access Paper or Ask Questions