Ryo Masumura
Ryo Masumura
Distinguished Research Scientist, NTT Computer and Data Science Laboratories, NTT Corporation
Verified email at lab.ntt.co.jp - Homepage
Title
Cited by
Cited by
Year
Domain adaptation of dnn acoustic models using knowledge distillation
T Asami, R Masumura, Y Yamaguchi, H Masataki, Y Aono
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
592017
Online End-of-Turn Detection from Speech Based on Stacked Time-Asynchronous Sequential Networks.
R Masumura, T Asami, H Masataki, R Ishii, R Higashinaka
Interspeech 2017, 1661-1665, 2017
312017
Soft-target training with ambiguous emotional utterances for dnn-based speech emotion classification
A Ando, S Kobashikawa, H Kamiyama, R Masumura, Y Ijima, Y Aono
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
242018
Neural confnet classification: Fully neural network based spoken utterance classification using word confusion networks
R Masumura, Y Ijima, T Asami, H Masataki, R Higashinaka
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
232018
Large context end-to-end automatic speech recognition via extension of hierarchical recurrent encoder-decoder models
R Masumura, T Tanaka, T Moriya, Y Shinohara, T Oba, Y Aono
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
202019
Neural Dialogue Context Online End-of-Turn Detection
R Masumura, T Tanaka, A Ando, R Ishii, R Higashinaka, Y Aono
Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue …, 2018
172018
Improving neural text normalization with data augmentation at character-and morphological levels
I Saito, J Suzuki, K Nishida, K Sadamitsu, S Kobashikawa, R Masumura, ...
Proceedings of the Eighth International Joint Conference on Natural Language …, 2017
172017
Parallel phonetically aware DNNs and LSTM-RNNs for frame-by-frame discriminative modeling of spoken language identification
R Masumura, T Asami, H Masataki, Y Aono
Acoustics, Speech and Signal Processing (ICASSP), 2017 IEEE International …, 2017
162017
A transformer-based audio captioning model with keyword estimation
Y Koizumi, R Masumura, K Nishida, M Yasuda, S Saito
arXiv preprint arXiv:2007.00222, 2020
152020
Neural Error Corrective Language Models for Automatic Speech Recognition.
T Tanaka, R Masumura, H Masataki, Y Aono
INTERSPEECH, 401-405, 2018
152018
Hierarchical LSTMs with Joint Learning for Estimating Customer Satisfaction from Contact Center Calls.
A Ando, R Masumura, H Kamiyama, S Kobashikawa, Y Aono
INTERSPEECH, 1716-1720, 2017
152017
Adversarial training for multi-task and multi-lingual joint modeling of utterance intent classification
R Masumura, Y Shinohara, R Higashinaka, Y Aono
Proceedings of the 2018 Conference on Empirical Methods in Natural Language …, 2018
142018
Training a language model using webdata for large vocabulary Japanese spontaneous speech recognition
R Masumura, S Hahm, A Ito
Twelfth Annual Conference of the International Speech Communication Association, 2011
142011
Use of latent words language models in ASR: a sampling-based implementation
R Masumura, H Masataki, T Oba, O Yoshioka, S Takahashi
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
132013
Language model expansion using webdata for spoken document retrieval
R Masumura, S Hahm, A Ito
Twelfth Annual Conference of the International Speech Communication Association, 2011
122011
Sequence-level consistency training for semi-supervised end-to-end automatic speech recognition
R Masumura, M Ihori, A Takashima, T Moriya, A Ando, Y Shinohara
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
112020
Customer satisfaction estimation in contact center calls based on a hierarchical multi-task model
A Ando, R Masumura, H Kamiyama, S Kobashikawa, Y Aono, T Toda
IEEE/ACM Transactions on Audio, Speech, and Language Processing 28, 715-728, 2020
82020
Speech Emotion Recognition Based on Multi-Label Emotion Existence Model.
A Ando, R Masumura, H Kamiyama, S Kobashikawa, Y Aono
INTERSPEECH, 2818-2822, 2019
82019
Multi-task and multi-lingual joint learning of neural lexical utterance classification based on partially-shared modeling
R Masumura, T Tanaka, R Higashinaka, H Masataki, Y Aono
Proceedings of the 27th International Conference on Computational …, 2018
82018
Role Play Dialogue Aware Language Models Based on Conditional Hierarchical Recurrent Encoder-Decoder.
R Masumura, T Tanaka, A Ando, H Masataki, Y Aono
INTERSPEECH, 1259-1263, 2018
82018
The system can't perform the operation now. Try again later.
Articles 1–20