Kenji Nagamatsu

发表

Anticipating the Start of User Interaction for Service Robot in the Wild

Shota Horiguchi, Kenji Nagamatsu, Quan Kong, 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

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

Naoyuki Kanda, Shinji Watanabe, Shota Horiguchi, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

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

Shinji Watanabe, Shota Horiguchi, Yusuke Fujita, 2020, INTERSPEECH.

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

Naoyuki Kanda, Shinji Watanabe, Shota Horiguchi, 2019, INTERSPEECH.

Neural Speaker Diarization with Speaker-Wise Chain Rule pdf

Shinji Watanabe, Shota Horiguchi, Yusuke Fujita, 2020, ArXiv.

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

Shinji Watanabe, Shota Horiguchi, Kenji Nagamatsu, 2021, Interspeech.

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

Naoyuki Kanda, Reinhold Häb-Umbach, Shota Horiguchi, 2019, INTERSPEECH.

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

Shinji Watanabe, Shota Horiguchi, Yusuke Fujita, 2020, ArXiv.

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

Shinji Watanabe, Shota Horiguchi, Kenji Nagamatsu, 2021, 2021 IEEE Spoken Language Technology Workshop (SLT).

Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition

Naoyuki Kanda, Shinji Watanabe, Ryoichi Takashima, 2019, INTERSPEECH.

Sequence Distillation for Purely Sequence Trained Acoustic Models

Naoyuki Kanda, Yusuke Fujita, Kenji Nagamatsu, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Face-Voice Matching using Cross-modal Embeddings

Naoyuki Kanda, Shota Horiguchi, Kenji Nagamatsu, 2018, ACM Multimedia.

Addressing Ambiguity of Emotion Labels Through Meta-Learning pdf

Kenji Nagamatsu, Takuya Fujioka, Takeshi Homma, 2019, ArXiv.

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

Shinji Watanabe, Shota Horiguchi, Kenji Nagamatsu, 2021, Interspeech.

End-To-End Speaker Diarization as Post-Processing pdf

Shota Horiguchi, Yusuke Fujita, Kenji Nagamatsu, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Team Hitachi @ AutoMin 2021: Reference-free Automatic Minuting Pipeline with Argument Structure Construction over Topic-based Summarization pdf

Hiroaki Ozaki, Kenji Nagamatsu, Gaku Morio, 2021, First Shared Task on Automatic Minuting at Interspeech 2021.

Investigation of lattice-free maximum mutual information-based acoustic models with sequence-level Kullback-Leibler divergence

Naoyuki Kanda, Yusuke Fujita, Kenji Nagamatsu, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Cycle time based multi-goal path optimization for redundant robotic systems

Kenji Shimada, Kenji Nagamatsu, Iacopo Gentilini, 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

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

Naoyuki Kanda, Shinji Watanabe, Shota Horiguchi, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).