Nelson Yalta
Nelson Yalta
Hitachi LTD.
Verified email at - Homepage
Cited by
Cited by
Espnet: End-to-end speech processing toolkit
S Watanabe, T Hori, S Karita, T Hayashi, J Nishitoba, Y Unno, NEY Soplin, ...
arXiv preprint arXiv:1804.00015, 2018
A comparative study on transformer vs rnn in speech applications
S Karita, N Chen, T Hayashi, T Hori, H Inaguma, Z Jiang, M Someki, ...
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2019
Improving transformer-based end-to-end speech recognition with connectionist temporal classification and language model integration
T Nakatani
Proc. Interspeech 2019, 2019
ESPnet-ST: All-in-one speech translation toolkit
H Inaguma, S Kiyono, K Duh, S Karita, NEY Soplin, T Hayashi, ...
arXiv preprint arXiv:2004.10234, 2020
Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling
J Cho, MK Baskar, R Li, M Wiesner, SH Mallidi, N Yalta, M Karafiat, ...
2018 IEEE Spoken Language Technology Workshop (SLT), 521-527, 2018
Sound source localization using deep learning models
N Yalta, K Nakadai, T Ogata
Journal of Robotics and Mechatronics 29 (1), 37-48, 2017
The Hitachi/JHU CHiME-5 system: Advances in speech recognition for everyday home environments using multiple microphone arrays
N Kanda, R Ikeshita, S Horiguchi, Y Fujita, K Nagamatsu, X Wang, ...
Proc. CHiME-5, 6-10, 2018
Weakly-supervised deep recurrent neural networks for basic dance step generation
N Yalta, S Watanabe, K Nakadai, T Ogata
2019 International Joint Conference on Neural Networks (IJCNN), 1-8, 2019
The Hitachi-JHU DIHARD III system: Competitive end-to-end neural diarization and x-vector clustering systems combined by DOVER-Lap
S Horiguchi, N Yalta, P Garcia, Y Takashima, Y Xue, D Raj, Z Huang, ...
arXiv preprint arXiv:2102.01363, 2021
CNN-based Multichannel End-to-End Speech Recognition for Everyday Home Environments*
N Yalta, S Watanabe, T Hori, K Nakadai, T Ogata
2019 27th European Signal Processing Conference (EUSIPCO), 1-5, 2019
HATSUKI: An anime character like robot figure platform with anime-style expressions and imitation learning based action generation
PC Yang, M Al-Sada, CC Chiu, K Kuo, TP Tomo, K Suzuki, N Yalta, ...
2020 29th IEEE International Conference on Robot and Human Interactive …, 2020
Sequential deep learning for dancing motion generation
N Yalta, T Ogata, K Nakadai
Proc. the 46th AI Challenge Study Group, 43-49, 2016
The Hitachi DCASE 2021 Task 3 system: Handling directive interference with self attention layers
N Yalta, T Sumiyoshi, Y Kawaguchi
Delayed skip connections for music content driven motion generation
N Yalta, K Nakadai, T Ogata
The system can't perform the operation now. Try again later.
Articles 1–14