Hirokazu Masataki

According to our database, Hirokazu Masataki authored at least 44 papers between 1996 and 2019.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2019

Viterbi Approximation of Latent Words Language Models for Automatic Speech Recognition.

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi

J. Inf. Process., 2019

2018

Domain Adaptation Based on Mixture of Latent Words Language Models for Automatic Speech Recognition.

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito

IEICE Trans. Inf. Syst., 2018

Neural Error Corrective Language Models for Automatic Speech Recognition.

Tomohiro Tanaka, Ryo Masumura, Hirokazu Masataki, Yushi Aono

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

Role Play Dialogue Aware Language Models Based on Conditional Hierarchical Recurrent Encoder-Decoder.

Ryo Masumura, Tomohiro Tanaka, Atsushi Ando, Hirokazu Masataki, Yushi Aono

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

Neural Confnet Classification: Fully Neural Network Based Spoken Utterance Classification Using Word Confusion Networks.

Ryo Masumura, Yusuke Ijima, Taichi Asami, Hirokazu Masataki, Ryuichiro Higashinaka

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Multi-task and Multi-lingual Joint Learning of Neural Lexical Utterance Classification based on Partially-shared Modeling.

Ryo Masumura, Tomohiro Tanaka, Ryuichiro Higashinaka, Hirokazu Masataki, Yushi Aono

Proceedings of the 27th International Conference on Computational Linguistics, 2018

2017

Online End-of-Turn Detection from Speech Based on Stacked Time-Asynchronous Sequential Networks.

Ryo Masumura, Taichi Asami, Hirokazu Masataki, Ryo Ishii, Ryuichiro Higashinaka

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Hyperspherical Query Likelihood Models with Word Embeddings.

Ryo Masumura, Taichi Asami, Hirokazu Masataki, Kugatsu Sadamitsu, Kyosuke Nishida, Ryuichiro Higashinaka

Proceedings of the Eighth International Joint Conference on Natural Language Processing, 2017

Parallel phonetically aware DNNs and LSTM-RNNS for frame-by-frame discriminative modeling of spoken language identification.

Ryo Masumura, Taichi Asami, Hirokazu Masataki, Yushi Aono

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Domain adaptation of DNN acoustic models using knowledge distillation.

Taichi Asami, Ryo Masumura, Yoshikazu Yamaguchi, Hirokazu Masataki, Yushi Aono

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Joint unsupervised adaptation of n-gram and RNN language models via LDA-based hybrid mixture modeling.

Ryo Masumura, Taichi Asami, Hirokazu Masataki, Yushi Aono

Proceedings of the 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2017

2016

N-gram Approximation of Latent Words Language Models for Domain Robust Automatic Speech Recognition.

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Satoshi Takahashi

IEICE Trans. Inf. Syst., 2016

Investigation of Combining Various Major Language Model Technologies including Data Expansion and Adaptation.

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito

IEICE Trans. Inf. Syst., 2016

Language Identification Based on Generative Modeling of Posteriorgram Sequences Extracted from Frame-by-Frame DNNs and LSTM-RNNs.

Ryo Masumura, Taichi Asami, Hirokazu Masataki, Yushi Aono, Sumitaka Sakauchi

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

2015

Latent words recurrent neural network language models.

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Combinations of various language model technologies including data expansion and adaptation in spontaneous speech recognition.

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Training data selection for acoustic modeling via submodular optimization of joint kullback-leibler divergence.

Taichi Asami, Ryo Masumura, Hirokazu Masataki, Manabu Okamoto, Sumitaka Sakauchi

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Agreement and disagreement utterance detection in conversational speech by extracting and integrating local features.

Atsushi Ando, Taichi Asami, Manabu Okamoto, Hirokazu Masataki, Sumitaka Sakauchi

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Hierarchical Latent Words Language Models for Robust Modeling to Out-Of Domain Tasks.

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015

2014

Automatic Vocabulary Adaptation Based on Semantic and Acoustic Similarities.

Shoko Yamahata, Yoshikazu Yamaguchi, Atsunori Ogawa, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi

IEICE Trans. Inf. Syst., 2014

Efficient data selection for speech recognition based on prior confidence estimation using speech and monophone models.

Satoshi Kobashikawa, Taichi Asami, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi

Comput. Speech Lang., 2014

Mixture of latent words language models for domain adaptation.

Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Read and spontaneous speech classification based on variance of GMM supervectors.

Taichi Asami, Ryo Masumura, Hirokazu Masataki, Sumitaka Sakauchi

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Role play dialogue topic model for language model adaptation in multi-party conversation speech recognition.

Ryo Masumura, Takanobu Oba, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi

Proceedings of the IEEE International Conference on Acoustics, 2014

2013

Fast unsupervised adaptation based on efficient statistics accumulation using frame independent confidence within monophone states.

Satoshi Kobashikawa, Atsunori Ogawa, Taichi Asami, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi

Comput. Speech Lang., 2013

Unsupervised discriminative language modeling using error rate estimator.

Takanobu Oba, Atsunori Ogawa, Takaaki Hori, Hirokazu Masataki, Atsushi Nakamura

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Viterbi decoding for latent words language models using gibbs sampling.

Ryo Masumura, Hirokazu Masataki, Takanobu Oba, Osamu Yoshioka, Satoshi Takahashi

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Unsupervised confidence calibration using examples of recognized words and their contexts.

Taichi Asami, Satoshi Kobashikawa, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Use of latent words language models in ASR: A sampling-based implementation.

Ryo Masumura, Hirokazu Masataki, Takanobu Oba, Osamu Yoshioka, Satoshi Takahashi

Proceedings of the IEEE International Conference on Acoustics, 2013

2012

Efficient prior and incremental beam width control to suppress excessive speech recognition time based on score range estimation.

Satoshi Kobashikawa, Takaaki Hori, Yoshikazu Yamaguchi, Taichi Asami, Hirokazu Masataki, Satoshi Takahashi

Proceedings of the 2012 IEEE Spoken Language Technology Workshop (SLT), 2012

Automatic Vocabulary Adaptation Based on Semantic Similarity and Speech Recognition Confidence Measure.

Shoko Yamahata, Yoshikazu Yamaguchi, Atsunori Ogawa, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Efficient Beam Width Control to Suppress Excessive Speech Recognition Computation Time Based on Prior Score Range Normalization.

Satoshi Kobashikawa, Takaaki Hori, Yoshikazu Yamaguchi, Taichi Asami, Hirokazu Masataki, Satoshi Takahashi

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Speech Data Clustering Based on Phoneme Error Trend for Unsupervised Acoustic Model Adaptation.

Taichi Asami, Satoshi Kobashikawa, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

2011

Anger Recognition in Spoken Dialog Using Linguistic and Para-Linguistic Information.

Narichika Nomoto, Masafumi Tamoto, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Morpheme Conversion for Connecting Speech Recognizer and Language Analyzers in Unsegmented Languages.

Kenji Imamura, Tomoko Izumi, Kugatsu Sadamitsu, Kuniko Saito, Satoshi Kobashikawa, Hirokazu Masataki

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Spoken Document Confidence Estimation Using Contextual Coherence.

Taichi Asami, Narichika Nomoto, Satoshi Kobashikawa, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Extracting call-reason segments from contact center dialogs by using automatically acquired boundary expressions.

Takaaki Fukutomi, Satoshi Kobashikawa, Taichi Asami, Tsubasa Shinozaki, Hirokazu Masataki, Satoshi Takahashi

Proceedings of the IEEE International Conference on Acoustics, 2011

2010

Efficient data selection for spoken document retrieval based on prior confidence estimation using speech and context independent models.

Satoshi Kobashikawa, Taichi Asami, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi

Proceedings of the 2010 IEEE Spoken Language Technology Workshop, 2010

Improving hmm-based extractive summarization for multi-domain contact center dialogues.

Ryuichiro Higashinaka, Yasuhiro Minami, Hitoshi Nishikawa, Kohji Dohsaka, Toyomi Meguro, Satoshi Kobashikawa, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi, Gen-ichiro Kikui

Proceedings of the 2010 IEEE Spoken Language Technology Workshop, 2010

Detection of anger emotion in dialog speech using prosody feature and temporal relation of utterances.

Narichika Nomoto, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Efficient data selection for speech recognition based on prior confidence estimation using speech and context independent models.

Satoshi Kobashikawa, Taichi Asami, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

1997

Task adaptation using MAP estimation in N-gram language modeling.

Hirokazu Masataki, Yoshinori Sagisaka, Kazuya Hisaki, Tatsuya Kawahara

Proceedings of the 1997 IEEE International Conference on Acoustics, 1997

1996

Spontaneous dialogue speech recognition using cross-word context constrained word graphs.

Tohru Shimizu, Hirofumi Yamamoto, Hirokazu Masataki, Shoichi Matsunaga, Yoshinori Sagisaka

Proceedings of the 1996 IEEE International Conference on Acoustics, 1996

Variable-order N-gram generation by word-class splitting and consecutive word grouping.

Hirokazu Masataki, Yoshinori Sagisaka

Proceedings of the 1996 IEEE International Conference on Acoustics, 1996