Kenji Nagamatsu

53 papers A* 2A 12C 4Misc 4Journal 20Unranked 11
YearRankTypeTitle / Venue / Authors
2021 A conf
Audio-Visual Speech Emotion Recognition by Disentangling Emotion and Identity Attributes.
Interspeech
Koichiro Ito, Takuya Fujioka, Qinghua Sun, Kenji Nagamatsu
2021 Misc conf
Audio-Visual Speech Enhancement Method Conditioned in the Lip Motion and Speaker-Discriminative Embeddings.
ICASSP
Koichiro Ito, Masaaki Yamamoto, Kenji Nagamatsu
2021 — conf
Block-Online Guided Source Separation.
SLT
Shota Horiguchi, Yusuke Fujita, Kenji Nagamatsu
2021 J jnl
Emotional Speech Synthesis for Companion Robot to Imitate Professional Caregiver Speech.
CoRR
Takeshi Homma, Qinghua Sun, Takuya Fujioka, Ryuta Takawaki, Eriko Ankyu, Kenji Nagamatsu, Daichi Sugawara, Etsuko T. Harada
2021 Misc conf
End-To-End Speaker Diarization as Post-Processing.
ICASSP
Shota Horiguchi, Paola García, Yusuke Fujita, Shinji Watanabe, Kenji Nagamatsu
2021 — conf
End-to-End Speaker Diarization Conditioned on Speech Activity and Overlap Detection.
SLT
Yuki Takashima, Yusuke Fujita, Shinji Watanabe, Shota Horiguchi, Paola García, Kenji Nagamatsu
2021 J jnl
End-to-End Speaker Diarization Conditioned on Speech Activity and Overlap Detection.
CoRR
Yuki Takashima, Yusuke Fujita, Shinji Watanabe, Shota Horiguchi, Paola García, Kenji Nagamatsu
2021 — conf
Online End-To-End Neural Diarization with Speaker-Tracing Buffer.
SLT
Yawen Xue, Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, Paola García, Kenji Nagamatsu
2021 J jnl
Online End-to-End Neural Diarization Handling Overlapping Speech and Flexible Numbers of Speakers.
CoRR
Yawen Xue, Shota Horiguchi, Yusuke Fujita, Yuki Takashima, Shinji Watanabe, Paola García, Kenji Nagamatsu
2021 A conf
Online Streaming End-to-End Neural Diarization Handling Overlapping Speech and Flexible Numbers of Speakers.
Interspeech
Yawen Xue, Shota Horiguchi, Yusuke Fujita, Yuki Takashima, Shinji Watanabe, Leibny Paola García-Perera, Kenji Nagamatsu
2021 A conf
Semi-Supervised Training with Pseudo-Labeling for End-To-End Neural Diarization.
Interspeech
Yuki Takashima, Yusuke Fujita, Shota Horiguchi, Shinji Watanabe, Leibny Paola García-Perera, Kenji Nagamatsu
2021 J jnl
Semi-Supervised Training with Pseudo-Labeling for End-to-End Neural Diarization.
CoRR
Yuki Takashima, Yusuke Fujita, Shota Horiguchi, Shinji Watanabe, Paola García, Kenji Nagamatsu
2021 J jnl
Team Hitachi @ AutoMin 2021: Reference-free Automatic Minuting Pipeline with Argument Structure Construction over Topic-based Summarization.
CoRR
Atsuki Yamaguchi, Gaku Morio, Hiroaki Ozaki, Ken-Ichi Yokote, Kenji Nagamatsu
2020 A* conf
Anticipating the Start of User Interaction for Service Robot in the Wild.
ICRA
Koichiro Ito, Quan Kong, Shota Horiguchi, Takashi Sumiyoshi, Kenji Nagamatsu
2020 J jnl
Block-Online Guided Source Separation.
CoRR
Shota Horiguchi, Yusuke Fujita, Kenji Nagamatsu
2020 J jnl
Building Multi lingual TTS using Cross Lingual Voice Conversion.
CoRR
Qinghua Sun, Kenji Nagamatsu
2020 — conf
Delay Mitigation for Backchannel Prediction in Spoken Dialog System.
IWSDS
Amalia Istiqlali Adiba, Takeshi Homma, Dario Bertero, Takashi Sumiyoshi, Kenji Nagamatsu
2020 J jnl
End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classification.
CoRR
Yusuke Fujita, Shinji Watanabe, Shota Horiguchi, Yawen Xue, Kenji Nagamatsu
2020 J jnl
End-to-End Speaker Diarization as Post-Processing.
CoRR
Shota Horiguchi, Paola García, Yusuke Fujita, Shinji Watanabe, Kenji Nagamatsu
2020 A conf
End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors.
INTERSPEECH
Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, Yawen Xue, Kenji Nagamatsu
2020 J jnl
End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors.
CoRR
Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, Yawen Xue, Kenji Nagamatsu
2020 A conf
Meta-Learning for Speech Emotion Recognition Considering Ambiguity of Emotion Labels.
INTERSPEECH
Takuya Fujioka, Takeshi Homma, Kenji Nagamatsu
2020 J jnl
Neural Speaker Diarization with Speaker-Wise Chain Rule.
CoRR
Yusuke Fujita, Shinji Watanabe, Shota Horiguchi, Yawen Xue, Jing Shi, Kenji Nagamatsu
2020 J jnl
Online End-to-End Neural Diarization with Speaker-Tracing Buffer.
CoRR
Yawen Xue, Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, Kenji Nagamatsu
2020 A conf
Utterance-Wise Meeting Transcription System Using Asynchronous Distributed Microphones.
INTERSPEECH
Shota Horiguchi, Yusuke Fujita, Kenji Nagamatsu
2020 J jnl
Utterance-Wise Meeting Transcription System Using Asynchronous Distributed Microphones.
CoRR
Shota Horiguchi, Yusuke Fujita, Kenji Nagamatsu
2019 Misc conf
Acoustic Modeling for Distant Multi-talker Speech Recognition with Single- and Multi-channel Branches.
ICASSP
Naoyuki Kanda, Yusuke Fujita, Shota Horiguchi, Rintaro Ikeshita, Kenji Nagamatsu, Shinji Watanabe
2019 J jnl
Addressing Ambiguity of Emotion Labels Through Meta-Learning.
CoRR
Takuya Fujioka, Dario Bertero, Takeshi Homma, Kenji Nagamatsu
2019 A conf
Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition.
INTERSPEECH
Naoyuki Kanda, Shota Horiguchi, Ryoichi Takashima, Yusuke Fujita, Kenji Nagamatsu, Shinji Watanabe
2019 J jnl
Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition.
CoRR
Naoyuki Kanda, Shota Horiguchi, Ryoichi Takashima, Yusuke Fujita, Kenji Nagamatsu, Shinji Watanabe
2019 A conf
End-to-End Neural Speaker Diarization with Permutation-Free Objectives.
INTERSPEECH
Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi, Kenji Nagamatsu, Shinji Watanabe
2019 J jnl
End-to-End Neural Speaker Diarization with Permutation-Free Objectives.
CoRR
Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi, Kenji Nagamatsu, Shinji Watanabe
2019 C conf
End-to-End Neural Speaker Diarization with Self-Attention.
ASRU
Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi, Yawen Xue, Kenji Nagamatsu, Shinji Watanabe
2019 J jnl
End-to-End Neural Speaker Diarization with Self-attention.
CoRR
Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi, Yawen Xue, Kenji Nagamatsu, Shinji Watanabe
2019 A conf
Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR.
INTERSPEECH
Naoyuki Kanda, Christoph Böddeker, Jens Heitkaemper, Yusuke Fujita, Shota Horiguchi, Kenji Nagamatsu, Reinhold Haeb-Umbach
2019 J jnl
Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR.
CoRR
Naoyuki Kanda, Christoph Böddeker, Jens Heitkaemper, Yusuke Fujita, Shota Horiguchi, Kenji Nagamatsu, Reinhold Haeb-Umbach
2019 A conf
Multimodal Response Obligation Detection with Unsupervised Online Domain Adaptation.
INTERSPEECH
Shota Horiguchi, Naoyuki Kanda, Kenji Nagamatsu
2019 C conf
Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models.
ASRU
Naoyuki Kanda, Shota Horiguchi, Yusuke Fujita, Yawen Xue, Kenji Nagamatsu, Shinji Watanabe
2019 J jnl
Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models.
CoRR
Naoyuki Kanda, Shota Horiguchi, Yusuke Fujita, Yawen Xue, Kenji Nagamatsu, Shinji Watanabe
2018 A* conf
Face-Voice Matching using Cross-modal Embeddings.
ACM Multimedia
Shota Horiguchi, Naoyuki Kanda, Kenji Nagamatsu
2018 — conf
Fast Multichannel Nonnegative Matrix Factorization with Constraints on Active Source Candidates.
IWAENC
Rintaro Ikeshita, Yohei Kawaguchi, Kenji Nagamatsu
2018 A conf
Lattice-free State-level Minimum Bayes Risk Training of Acoustic Models.
INTERSPEECH
Naoyuki Kanda, Yusuke Fujita, Kenji Nagamatsu
2018 Misc conf
Sequence Distillation for Purely Sequence Trained Acoustic Models.
ICASSP
Naoyuki Kanda, Yusuke Fujita, Kenji Nagamatsu
2017 — conf
Independent vector analysis with frequency range division and prior switching.
EUSIPCO
Rintaro Ikeshita, Yohei Kawaguchi, Masahito Togami, Yusuke Fujita, Kenji Nagamatsu
2017 C conf
Investigation of lattice-free maximum mutual information-based acoustic models with sequence-level Kullback-Leibler divergence.
ASRU
Naoyuki Kanda, Yusuke Fujita, Kenji Nagamatsu
2017 — conf
Local Gaussian model with source-set constraints in audio source separation.
MLSP
Rintaro Ikeshita, Masahito Togami, Yohei Kawaguchi, Yusuke Fujita, Kenji Nagamatsu
2013 A conf
Cycle time based multi-goal path optimization for redundant robotic systems.
IROS
Iacopo Gentilini, Kenji Nagamatsu, Kenji Shimada
2010 J jnl
A Pre-Identification Method for Chinese Named Entity Recognition.
J. Softw.
Hongjian Liu, Defeng Guo, Quan Zhou, Kenji Nagamatsu, Qinghua Sun
2009 — conf
A Hybrid Method of Chinese Prosodic Word Tagging Based on Keyword Anchor and Hidden Markov Model.
IALP
Quan Zhou, Pan Deng, Hongjian Liu, Defeng Guo, Kenji Nagamatsu
2009 — conf
Cascade Chinese Potential Name Recognition.
IFITA (3)
Hongjian Liu, Defeng Guo, Quan Zhou, Kenji Nagamatsu, Qinghua Sun
2006 — conf
Scalable Implementation Of Unit Selection Based Text-To-Speech System For Embedded Solutions.
ICASSP (1)
Nobuo Nukaga, Ryota Kamoshida, Kenji Nagamatsu, Yoshinori Kitahara
2004 — conf
Unit selection using pitch synchronous cross correlation for Japanese concatenative speech synthesis.
SSW
Nobuo Nukaga, Ryota Kamoshida, Kenji Nagamatsu
1996 C conf
Estimating Point-of-View-based Similarity Using POV Reinforcement and Similarity Propagation.
PACLIC
Kenji Nagamatsu, Hidehiko Tanaka