Rchr
J-GLOBAL ID:201501090163048030   Update date: Feb. 08, 2021

Ochiai Tsubasa

オチアイ ツバサ | Ochiai Tsubasa
Affiliation and department:
Other affiliations (2):
Research field  (1): Perceptual information processing
Research keywords  (5): Automatic Speech Recognition ,  Speech Enhancement/Source Separation ,  Deep Learning ,  Array Signal Processing ,  Machine Learning
Papers (5):
  • Tatsuya MATSUHIRO, Tetsuya HASHIMOTO, Mikiyo KITAOKA, David HA, Tsubasa OCHIAI, Hideyuki WATANABE, Shigeru KATAGIRI, Miho OHSAKI. Develpment and Experimental Evaluation of Large Geometric Margin Minimum Classification Error Training for Classification of Variable-length Time Series Patterns. Transaction of Information Processing Society of Japan (IPSJ). 2018. 59. 4. 1295-1308
  • Tsubasa Ochiai, Shinji Watanabe, Takaaki Hori, John R. Hershey, Xiong Xiao. Unified Architecture for Multichannel End-to-End Speech Recognition With Neural Beamforming. IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING. 2017. 11. 8. 1274-1288
  • Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Shigeru Katagiri. AUTOMATIC NODE SELECTION FOR DEEP NEURAL NETWORKS USING GROUP LASSO REGULARIZATION. 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP). 2017. 5485-5489
  • Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Chiori Hori, Hisashi Kawai, Shigeru Katagiri. Speaker Adaptive Training Localizing Speaker Modules in DNN for Hybrid DNN-HMM Speech Recognizers. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS. 2016. E99D. 10. 2431-2443
  • Tsubasa Ochiai, Shigeki Matsuda, Xugang Lu, Chiori Hori, Shigeru Katagiri. SPEAKER ADAPTIVE TRAINING USING DEEP NEURAL NETWORKS. 2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP). 2014
MISC (1):
  • Tsubasa Ochiai, Tatsuya Mitsuhiro, Shigeki Matsuda, Shigeru Katagiri. Introduction to Deep Learning Toolkit for Speech and Language Processing. Proc. ASJ. 2017. 73. 1. 63-72
Lectures and oral presentations  (13):
  • 話者正規化学習された DNN における行列のランクに基づく動作分析
    (日本音響学会 春季研究発表会 2015)
  • 国際会議ICASSP2015参加報告
    (情報処理学会 音声言語情報処理研究会 2015)
  • 線形変換ネットワークを用いて話者正規化学習された DNN における ネットワークサイズが与える影響の実験的評価
    (電子情報通信学会 音声研究会 2015)
  • Speaker adaptive training using deep neural networks embedding linear transformation networks
    (International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015)
  • 線形変換ネットワークを用いて話者正規化学習された DNN のためのボトルネック話者適応法の提案
    (日本音響学会 春季研究発表会 2015)
more...
Education (3):
  • 2015 - 2018 Doshisha University Knowledge Engineering and Computer Sciences
  • 2013 - 2015 Doshisha University Knowledge Engineering and Computer Sciences
  • 2009 - 2013 Doshisha University Department of Information Systems Design
Work history (4):
  • 2018/04 - 現在 NTT Communication Science Laboratory
  • 2015/04 - 2018/03 National Institute of Information and Communications Technology
  • 2015/04 - 2018/03 独立行政法人 日本学術振興会 特別研究員 (DC1)
  • 2013/08 - 2015/03 独立行政法人 情報通信研究機構 協力研究員
Awards (2):
  • 2016/02 - IEEE 関西支部 学生研究奨励賞
  • 2014/09 - 日本音響学会 学生優秀発表賞
Association Membership(s) (3):
IEICE ,  ACOUSTICAL SOCIETY OF JAPAN ,  IEEE
※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page