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 Kenji Nagamatsu

Semi-Supervised Training with Pseudo-Labeling for End-to-End Neural Diarization


Jun 09, 2021
Yuki Takashima, Yusuke Fujita, Shota Horiguchi, Shinji Watanabe, Paola García, Kenji Nagamatsu

* Accepted for Interspeech 2021 

  Access Paper or Ask Questions

End-to-End Speaker Diarization Conditioned on Speech Activity and Overlap Detection


Jun 08, 2021
Yuki Takashima, Yusuke Fujita, Shinji Watanabe, Shota Horiguchi, Paola García, Kenji Nagamatsu

* IEEE Spoken Language Technology Workshop (SLT), 2021, pp. 849-856 
* Accepted for SLT 2021 

  Access Paper or Ask Questions

Online End-to-End Neural Diarization Handling Overlapping Speech and Flexible Numbers of Speakers


Jan 21, 2021
Yawen Xue, Shota Horiguchi, Yusuke Fujita, Yuki Takashima, Shinji Watanabe, Paola Garcia, Kenji Nagamatsu


  Access Paper or Ask Questions

Building Multi lingual TTS using Cross Lingual Voice Conversion


Dec 28, 2020
Qinghua Sun, Kenji Nagamatsu


  Access Paper or Ask Questions

End-to-End Speaker Diarization as Post-Processing


Dec 23, 2020
Shota Horiguchi, Paola Garcia, Yusuke Fujita, Shinji Watanabe, Kenji Nagamatsu


  Access Paper or Ask Questions

Utterance-Wise Meeting Transcription System Using Asynchronous Distributed Microphones


Jul 31, 2020
Shota Horiguchi, Yusuke Fujita, Kenji Nagamatsu

* Accepted to INTERSPEECH 2020 

  Access Paper or Ask Questions

Neural Speaker Diarization with Speaker-Wise Chain Rule


Jun 02, 2020
Yusuke Fujita, Shinji Watanabe, Shota Horiguchi, Yawen Xue, Jing Shi, Kenji Nagamatsu

* Submitted to Interspeech 2020 

  Access Paper or Ask Questions

End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors


May 20, 2020
Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, Yawen Xue, Kenji Nagamatsu


  Access Paper or Ask Questions

End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classification


Feb 24, 2020
Yusuke Fujita, Shinji Watanabe, Shota Horiguchi, Yawen Xue, Kenji Nagamatsu

* Submission to IEEE TASLP. This article draws from our previous conference papers: arxiv:1909.06247 and arxiv:1909.05952 

  Access Paper or Ask Questions

Addressing Ambiguity of Emotion Labels Through Meta-Learning


Nov 07, 2019
Takuya Fujioka, Dario Bertero, Takeshi Homma, Kenji Nagamatsu

* Submitted to ICASSP 2020 

  Access Paper or Ask Questions

Addressing Ambiguity of Emotion Labels Through Meta-learning


Nov 06, 2019
Takuya Fujioka, Dario Bertero, Takeshi Homma, Kenji Nagamatsu

* Submitted to ICASSP 2020 

  Access Paper or Ask Questions

Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models


Sep 17, 2019
Naoyuki Kanda, Shota Horiguchi, Yusuke Fujita, Yawen Xue, Kenji Nagamatsu, Shinji Watanabe

* Accepted to ASRU 2019 

  Access Paper or Ask Questions

End-to-End Neural Speaker Diarization with Self-attention


Sep 13, 2019
Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi, Yawen Xue, Kenji Nagamatsu, Shinji Watanabe

* Accepted for ASRU 2019 

  Access Paper or Ask Questions

End-to-End Neural Speaker Diarization with Permutation-Free Objectives


Sep 12, 2019
Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi, Kenji Nagamatsu, Shinji Watanabe

* Accepted to INTERSPEECH 2019 

  Access Paper or Ask Questions

Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition


Jun 26, 2019
Naoyuki Kanda, Shota Horiguchi, Ryoichi Takashima, Yusuke Fujita, Kenji Nagamatsu, Shinji Watanabe

* Accepted to INTERSPEECH 2019 

  Access Paper or Ask Questions

Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR


May 29, 2019
Naoyuki Kanda, Christoph Boeddeker, Jens Heitkaemper, Yusuke Fujita, Shota Horiguchi, Kenji Nagamatsu, Reinhold Haeb-Umbach

* Submitted to INTERSPEECH 2019 

  Access Paper or Ask Questions