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 Keisuke Kinoshita

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

Dual-Path Modeling for Long Recording Speech Separation in Meetings


Feb 23, 2021
Chenda Li, Zhuo Chen, Yi Luo, Cong Han, Tianyan Zhou, Keisuke Kinoshita, Marc Delcroix, Shinji Watanabe, Yanmin Qian

* Accepted by 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

Integrating end-to-end neural and clustering-based diarization: Getting the best of both worlds


Oct 26, 2020
Keisuke Kinoshita, Marc Delcroix, Naohiro Tawara

* 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

Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR


Jun 04, 2020
Thilo von Neumann, Christoph Boeddeker, Lukas Drude, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach

* 5 pages, 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

Tackling real noisy reverberant meetings with all-neural source separation, counting, and diarization system


Mar 09, 2020
Keisuke Kinoshita, Marc Delcroix, Shoko Araki, Tomohiro Nakatani

* 8 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

End-to-end training of time domain audio separation and recognition


Dec 25, 2019
Thilo von Neumann, Keisuke Kinoshita, Lukas Drude, Christoph Boeddeker, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach

* 5 pages, 1 figure, to appear in ICASSP 2020 

  Access Paper or Ask Questions

Ene-to-end training of time domain audio separation and recognition


Dec 18, 2019
Thilo von Neumann, Keisuke Kinoshita, Lukas Drude, Christoph Boeddeker, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach

* 5 pages, 1 figure, to appear in ICASSP 2020 

  Access Paper or Ask Questions

Jointly optimal dereverberation and beamforming


Oct 30, 2019
Christoph Boeddeker, Tomohiro Nakatani, Keisuke Kinoshita, Reinhold Haeb-Umbach

* Submitted to ICASSP 2020 

  Access Paper or Ask Questions

All-neural online source separation, counting, and diarization for meeting analysis


Feb 21, 2019
Thilo von Neumann, Keisuke Kinoshita, Marc Delcroix, Shoko Araki, Tomohiro Nakatani, Reinhold Haeb-Umbach

* 5 pages, to appear in ICASSP2019 

  Access Paper or Ask Questions