Hirokazu Masataki

44 papers A* 1A 21B 1Misc 9Journal 7Unranked 5

Year	Rank	Type	Title / Venue / Authors
2019	J	`jnl`	Viterbi Approximation of Latent Words Language Models for Automatic Speech Recognition. J. Inf. Process. Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi
2018	J	`jnl`	Domain Adaptation Based on Mixture of Latent Words Language Models for Automatic Speech Recognition. IEICE Trans. Inf. Syst. Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito
2018	B	`conf`	Multi-task and Multi-lingual Joint Learning of Neural Lexical Utterance Classification based on Partially-shared Modeling. COLING Ryo Masumura, Tomohiro Tanaka, Ryuichiro Higashinaka, Hirokazu Masataki, Yushi Aono
2018	Misc	`conf`	Neural Confnet Classification: Fully Neural Network Based Spoken Utterance Classification Using Word Confusion Networks. ICASSP Ryo Masumura, Yusuke Ijima, Taichi Asami, Hirokazu Masataki, Ryuichiro Higashinaka
2018	A	`conf`	Neural Error Corrective Language Models for Automatic Speech Recognition. INTERSPEECH Tomohiro Tanaka, Ryo Masumura, Hirokazu Masataki, Yushi Aono
2018	A	`conf`	Role Play Dialogue Aware Language Models Based on Conditional Hierarchical Recurrent Encoder-Decoder. INTERSPEECH Ryo Masumura, Tomohiro Tanaka, Atsushi Ando, Hirokazu Masataki, Yushi Aono
2017	Misc	`conf`	Domain adaptation of DNN acoustic models using knowledge distillation. ICASSP Taichi Asami, Ryo Masumura, Yoshikazu Yamaguchi, Hirokazu Masataki, Yushi Aono
2017	—	`conf`	Hyperspherical Query Likelihood Models with Word Embeddings. IJCNLP(2) Ryo Masumura, Taichi Asami, Hirokazu Masataki, Kugatsu Sadamitsu, Kyosuke Nishida, Ryuichiro Higashinaka
2017	—	`conf`	Joint unsupervised adaptation of n-gram and RNN language models via LDA-based hybrid mixture modeling. APSIPA Ryo Masumura, Taichi Asami, Hirokazu Masataki, Yushi Aono
2017	A	`conf`	Online End-of-Turn Detection from Speech Based on Stacked Time-Asynchronous Sequential Networks. INTERSPEECH Ryo Masumura, Taichi Asami, Hirokazu Masataki, Ryo Ishii, Ryuichiro Higashinaka
2017	Misc	`conf`	Parallel phonetically aware DNNs and LSTM-RNNS for frame-by-frame discriminative modeling of spoken language identification. ICASSP Ryo Masumura, Taichi Asami, Hirokazu Masataki, Yushi Aono
2016	J	`jnl`	Investigation of Combining Various Major Language Model Technologies including Data Expansion and Adaptation. IEICE Trans. Inf. Syst. Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito
2016	A	`conf`	Language Identification Based on Generative Modeling of Posteriorgram Sequences Extracted from Frame-by-Frame DNNs and LSTM-RNNs. INTERSPEECH Ryo Masumura, Taichi Asami, Hirokazu Masataki, Yushi Aono, Sumitaka Sakauchi
2016	J	`jnl`	N-gram Approximation of Latent Words Language Models for Domain Robust Automatic Speech Recognition. IEICE Trans. Inf. Syst. Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Satoshi Takahashi
2015	A	`conf`	Agreement and disagreement utterance detection in conversational speech by extracting and integrating local features. INTERSPEECH Atsushi Ando, Taichi Asami, Manabu Okamoto, Hirokazu Masataki, Sumitaka Sakauchi
2015	A	`conf`	Combinations of various language model technologies including data expansion and adaptation in spontaneous speech recognition. INTERSPEECH Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito
2015	A*	`conf`	Hierarchical Latent Words Language Models for Robust Modeling to Out-Of Domain Tasks. EMNLP Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito
2015	A	`conf`	Latent words recurrent neural network language models. INTERSPEECH Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi, Akinori Ito
2015	A	`conf`	Training data selection for acoustic modeling via submodular optimization of joint kullback-leibler divergence. INTERSPEECH Taichi Asami, Ryo Masumura, Hirokazu Masataki, Manabu Okamoto, Sumitaka Sakauchi
2014	J	`jnl`	Automatic Vocabulary Adaptation Based on Semantic and Acoustic Similarities. IEICE Trans. Inf. Syst. Shoko Yamahata, Yoshikazu Yamaguchi, Atsunori Ogawa, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi
2014	J	`jnl`	Efficient data selection for speech recognition based on prior confidence estimation using speech and monophone models. Comput. Speech Lang. Satoshi Kobashikawa, Taichi Asami, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi
2014	A	`conf`	Mixture of latent words language models for domain adaptation. INTERSPEECH Ryo Masumura, Taichi Asami, Takanobu Oba, Hirokazu Masataki, Sumitaka Sakauchi
2014	A	`conf`	Read and spontaneous speech classification based on variance of GMM supervectors. INTERSPEECH Taichi Asami, Ryo Masumura, Hirokazu Masataki, Sumitaka Sakauchi
2014	Misc	`conf`	Role play dialogue topic model for language model adaptation in multi-party conversation speech recognition. ICASSP Ryo Masumura, Takanobu Oba, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi
2013	J	`jnl`	Fast unsupervised adaptation based on efficient statistics accumulation using frame independent confidence within monophone states. Comput. Speech Lang. Satoshi Kobashikawa, Atsunori Ogawa, Taichi Asami, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi
2013	A	`conf`	Unsupervised confidence calibration using examples of recognized words and their contexts. INTERSPEECH Taichi Asami, Satoshi Kobashikawa, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi
2013	A	`conf`	Unsupervised discriminative language modeling using error rate estimator. INTERSPEECH Takanobu Oba, Atsunori Ogawa, Takaaki Hori, Hirokazu Masataki, Atsushi Nakamura
2013	Misc	`conf`	Use of latent words language models in ASR: A sampling-based implementation. ICASSP Ryo Masumura, Hirokazu Masataki, Takanobu Oba, Osamu Yoshioka, Satoshi Takahashi
2013	A	`conf`	Viterbi decoding for latent words language models using gibbs sampling. INTERSPEECH Ryo Masumura, Hirokazu Masataki, Takanobu Oba, Osamu Yoshioka, Satoshi Takahashi
2012	A	`conf`	Automatic Vocabulary Adaptation Based on Semantic Similarity and Speech Recognition Confidence Measure. INTERSPEECH Shoko Yamahata, Yoshikazu Yamaguchi, Atsunori Ogawa, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi
2012	A	`conf`	Efficient Beam Width Control to Suppress Excessive Speech Recognition Computation Time Based on Prior Score Range Normalization. INTERSPEECH Satoshi Kobashikawa, Takaaki Hori, Yoshikazu Yamaguchi, Taichi Asami, Hirokazu Masataki, Satoshi Takahashi
2012	—	`conf`	Efficient prior and incremental beam width control to suppress excessive speech recognition time based on score range estimation. SLT Satoshi Kobashikawa, Takaaki Hori, Yoshikazu Yamaguchi, Taichi Asami, Hirokazu Masataki, Satoshi Takahashi
2012	A	`conf`	Speech Data Clustering Based on Phoneme Error Trend for Unsupervised Acoustic Model Adaptation. INTERSPEECH Taichi Asami, Satoshi Kobashikawa, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi
2011	A	`conf`	Anger Recognition in Spoken Dialog Using Linguistic and Para-Linguistic Information. INTERSPEECH Narichika Nomoto, Masafumi Tamoto, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi
2011	Misc	`conf`	Extracting call-reason segments from contact center dialogs by using automatically acquired boundary expressions. ICASSP Takaaki Fukutomi, Satoshi Kobashikawa, Taichi Asami, Tsubasa Shinozaki, Hirokazu Masataki, Satoshi Takahashi
2011	A	`conf`	Morpheme Conversion for Connecting Speech Recognizer and Language Analyzers in Unsegmented Languages. INTERSPEECH Kenji Imamura, Tomoko Izumi, Kugatsu Sadamitsu, Kuniko Saito, Satoshi Kobashikawa, Hirokazu Masataki
2011	A	`conf`	Spoken Document Confidence Estimation Using Contextual Coherence. INTERSPEECH Taichi Asami, Narichika Nomoto, Satoshi Kobashikawa, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi
2010	A	`conf`	Detection of anger emotion in dialog speech using prosody feature and temporal relation of utterances. INTERSPEECH Narichika Nomoto, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi
2010	A	`conf`	Efficient data selection for speech recognition based on prior confidence estimation using speech and context independent models. INTERSPEECH Satoshi Kobashikawa, Taichi Asami, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi
2010	—	`conf`	Efficient data selection for spoken document retrieval based on prior confidence estimation using speech and context independent models. SLT Satoshi Kobashikawa, Taichi Asami, Yoshikazu Yamaguchi, Hirokazu Masataki, Satoshi Takahashi
2010	—	`conf`	Improving hmm-based extractive summarization for multi-domain contact center dialogues. SLT Ryuichiro Higashinaka, Yasuhiro Minami, Hitoshi Nishikawa, Kohji Dohsaka, Toyomi Meguro, Satoshi Kobashikawa, Hirokazu Masataki, Osamu Yoshioka, Satoshi Takahashi, Gen-ichiro Kikui
1997	Misc	`conf`	Task adaptation using MAP estimation in N-gram language modeling. ICASSP Hirokazu Masataki, Yoshinori Sagisaka, Kazuya Hisaki, Tatsuya Kawahara
1996	Misc	`conf`	Spontaneous dialogue speech recognition using cross-word context constrained word graphs. ICASSP Tohru Shimizu, Hirofumi Yamamoto, Hirokazu Masataki, Shoichi Matsunaga, Yoshinori Sagisaka
1996	Misc	`conf`	Variable-order N-gram generation by word-class splitting and consecutive word grouping. ICASSP Hirokazu Masataki, Yoshinori Sagisaka