Naoyuki Kanda

Best Publications

• WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing

  Sanyuan Chen;Chengyi Wang;Zhengyang Chen;Yu Wu

  1378
  Citations

• CHiME-6 Challenge: Tackling multispeaker speech recognition for unsegmented recordings

  Shinji Watanabe;Michael Mandel;Jon Barker;Emmanuel Vincent

  316
  Citations

• End-to-end neural speaker diarization with permutation-free objectives

  Yusuke Fujita;Yusuke Fujita;Naoyuki Kanda;Shota Horiguchi;Kenji Nagamatsu

  227
  Citations

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

  Yusuke Fujita;Naoyuki Kanda;Shota Horiguchi;Yawen Xue

  222
  Citations

• Elastic spectral distortion for low resource speech recognition with deep neural networks

  Unknown

  138
  Citations

• CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings

  Shinji Watanabe;Michael Mandel;Jon Barker;Emmanuel Vincent

  104
  Citations

• Serialized Output Training for End-to-End Overlapped Speech Recognition.

  Naoyuki Kanda;Yashesh Gaur;Xiaofei Wang;Zhong Meng

  102
  Citations

• Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition

  Zhong Meng;Sarangarajan Parthasarathy;Eric Sun;Yashesh Gaur

  90
  Citations

• Integration of Speech Separation, Diarization, and Recognition for Multi-Speaker Meetings: System Description, Comparison, and Analysis

  Desh Raj;Pavel Denisov;Zhuo Chen;Hakan Erdogan

  78
  Citations

• A two-layer model for behavior and dialogue planning in conversational service robots

  M. Nakano;Y. Hasegawa;K. Nakadai;T. Nakamura

  75
  Citations

• Microsoft Speaker Diarization System for the Voxceleb Speaker Recognition Challenge 2020

  Xiong Xiao;Naoyuki Kanda;Zhuo Chen;Tianyan Zhou

  73
  Citations

• Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of any Number of Speakers.

  Naoyuki Kanda;Yashesh Gaur;Xiaofei Wang;Zhong Meng

  71
  Citations

• Multi-Domain Spoken Dialogue System with Extensibility and Robustness against Speech Recognition Errors

  Kazunori Komatani;Naoyuki Kanda;Mikio Nakano;Kazuhiro Nakadai

  69
  Citations

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

  Naoyuki Kanda;Christoph Böddeker;Jens Heitkaemper;Yusuke Fujita

  68
  Citations

• The Hitachi/JHU CHiME-5 system: Advances in speech recognition for everyday home environments using multiple microphone arrays

  Unknown

  58
  Citations

• Serialized Output Training for End-to-End Overlapped Speech Recognition

  Naoyuki Kanda;Yashesh Gaur;Xiaofei Wang;Zhong Meng

  49
  Citations

• A Review of Speaker Diarization: Recent Advances with Deep Learning

  Tae Jin Park;Naoyuki Kanda;Dimitrios Dimitriadis;Kyu J. Han

  48
  Citations

• Acoustic Modeling for Distant Multi-talker Speech Recognition with Single- and Multi-channel Branches

  Naoyuki Kanda;Yusuke Fujita;Shota Horiguchi;Rintaro Ikeshita

  47
  Citations

• Face-Voice Matching using Cross-modal Embeddings

  Unknown

  47
  Citations

• Maximum a posteriori Based Decoding for CTC Acoustic Models.

  Unknown

  47
  Citations