Nelson Yalta

CNN-based Multichannel End-to-End Speech Recognition for Everyday Home Environments*

Shinji Watanabe, Tetsuya Ogata, Takaaki Hori, 2019, 2019 27th European Signal Processing Conference (EUSIPCO).

HATSUKI : An anime character like robot figure platform with anime-style expressions and imitation learning based action generation

Tetsuya Ogata, Tito Pradhono Tomo, Kanata Suzuki, 2020, 2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN).

Multilingual Sequence-to-Sequence Speech Recognition: Architecture, Transfer Learning, and Language Modeling

Shinji Watanabe, Sri Harish Reddy Mallidi, Takaaki Hori, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Weakly-Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation

Shinji Watanabe, Tetsuya Ogata, Kazuhiro Nakadai, 2018, 2019 International Joint Conference on Neural Networks (IJCNN).

DELAYED SKIP CONNECTIONS FOR MUSIC CONTENT DRIVEN MOTION GENERATION

Tetsuya Ogata, Kazuhiro Nakadai, Nelson Yalta, 2018 .

Sound Source Localization Using Deep Learning Models

Tetsuya Ogata, Kazuhiro Nakadai, Nelson Yalta, 2017, J. Robotics Mechatronics.

Effective Imitation Learning Robot Platform using Game Engine: Autonomous Humanoid Figure ”Hatsuki” Mk.I

Tetsuya Ogata, Tito Pradhono Tomo, Kanata Suzuki, 2020 .

The Hitachi-JHU DIHARD III System: Competitive End-to-End Neural Diarization and X-Vector Clustering Systems Combined by DOVER-Lap pdf

Shinji Watanabe, Sanjeev Khudanpur, Shota Horiguchi, 2021, arXiv.org.

Sequential Deep Learning for Dancing Motion Generation

Tetsuya Ogata, Kazuhiro Nakadai, Nelson Yalta, 2016 .