A. Ogawa

发表

Balancing acoustic and linguistic probabilities

F. Itakura, A. Ogawa, K. Takeda, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices

Chengzhu Yu, Masakiyo Fujimoto, Tomohiro Nakatani, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Low-Latency Real-Time Meeting Recognition and Understanding Using Distant Microphones and Omni-Directional Camera

Masakiyo Fujimoto, Shinji Watanabe, Tomohiro Nakatani, 2012, IEEE Transactions on Audio, Speech, and Language Processing.

NORMALIZATION AND ADAPTATION BY CONSISTENTLY EMPLOYING MAP ESTIMATION

A. Ogawa, A. Nakamura, Takaaki Hori, 2012 .

BALANCING STOCHASTIC KNOWLEDGE ON ACOUSTICS AND LINGUISTICS

Atsunori Ogawa, Kazuya Takeda, Fumitada Itakura, 1998 .

Effective data screening technique for crowdsourced speech intelligibility experiments: Evaluation with IRM-based speech enhancement

T. Irino, A. Ogawa, T. Nakatani, 2022, 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

End-to-End Spontaneous Speech Recognition Using Hesitation Labeling

A. Ogawa, N. Kitaoka, Ryota Nishimura, 2021, 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Speech Intelligibility Prediction through Direct Estimation of Word Accuracy Using Conformer

T. Irino, A. Ogawa, T. Nakatani, 2022, 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Improving Speaker-Attribute Estimation by Voting Based on Speaker Cluster Information

Atsunori Ogawa, Naohiro Tawara, Hosana Kamiyama, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Non-native English speech recognition using bilingual English lexicon and acoustic models

Atsunori Ogawa, Akihiro Imamura, Yoshikazu Yamaguchi, 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

Estimating Speech Recognition Accuracy Based on Error Type Classification

Atsunori Ogawa, Atsushi Nakamura, Takaaki Hori, 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

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

Satoshi Takahashi, Atsunori Ogawa, Taichi Asami, 2013, Comput. Speech Lang..

Multimodal SpeakerBeam: Single Channel Target Speech Extraction with Audio-Visual Speaker Clues

Tomohiro Nakatani, Marc Delcroix, Atsunori Ogawa, 2019, INTERSPEECH.

End-to-End SpeakerBeam for Single Channel Target Speech Recognition

Shinji Watanabe, Tomohiro Nakatani, Marc Delcroix, 2019, INTERSPEECH.

Single Channel Target Speaker Extraction and Recognition with Speaker Beam

Tomohiro Nakatani, Marc Delcroix, Atsunori Ogawa, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Learning speaker representation for neural network based multichannel speaker extraction

Tomohiro Nakatani, Marc Delcroix, Atsunori Ogawa, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Speaker-Aware Neural Network Based Beamformer for Speaker Extraction in Speech Mixtures

Tomohiro Nakatani, Marc Delcroix, Atsunori Ogawa, 2017, INTERSPEECH.

Leveraging Large Text Corpora for End-to-End Speech Summarization

A. Ogawa, Ryo Masumura, Tomohiro Tanaka, 2023, 2303.00978.

Improved Deep Duel Model for Rescoring N-Best Speech Recognition List Using Backward LSTMLM and Ensemble Encoders

Tomohiro Nakatani, Marc Delcroix, Atsunori Ogawa, 2019, INTERSPEECH.

Improved Example-Based Speech Enhancement by Using Deep Neural Network Acoustic Model for Noise Robust Example Search

Tomohiro Nakatani, Marc Delcroix, Atsunori Ogawa, 2017, INTERSPEECH.

Zero-resource spoken term detection using hierarchical graph-based similarity search

Atsunori Ogawa, Atsushi Nakamura, Takaaki Hori, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Text-informed speech enhancement with deep neural networks

Tomohiro Nakatani, Marc Delcroix, Atsunori Ogawa, 2015, INTERSPEECH.

Estimating entropy of a language from optimal word insertion penalty

Atsunori Ogawa, Kazuya Takeda, Fumitada Itakura, 1998, ICSLP.

Error detection and accuracy estimation in automatic speech recognition using deep bidirectional recurrent neural networks

Atsunori Ogawa, Takaaki Hori, A. Ogawa, 2017, Speech Commun..

Semi-supervised End-to-end Speech Recognition Using Text-to-speech and Autoencoders

Tomoharu Iwata, Shinji Watanabe, Tomohiro Nakatani, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving Transformer-Based End-to-End Speech Recognition with Connectionist Temporal Classification and Language Model Integration

Shinji Watanabe, Tomohiro Nakatani, Marc Delcroix, 2019, INTERSPEECH.

Feature-Based Learning Hidden Unit Contributions for Domain Adaptation of RNN-LMs

Tomohiro Nakatani, Marc Delcroix, Atsunori Ogawa, 2018, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

A Unified Framework for Neural Speech Separation and Extraction

Tomohiro Nakatani, Marc Delcroix, Atsunori Ogawa, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Context adaptive deep neural networks for fast acoustic model adaptation in noisy conditions

Chengzhu Yu, Tomohiro Nakatani, Takuya Yoshioka, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

SEQUENCE TRAINING OF ENCODER-DECODER MODEL USING POLICY GRADIENT FOR END- TO-END SPEECH RECOGNITION

Tomohiro Nakatani, Marc Delcroix, Atsunori Ogawa, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

LINEAR PREDICTION-BASED DEREVERBERATION WITH ADVANCED SPEECH ENHANCEMENT AND RECOGNITION TECHNOLOGIES FOR THE REVERB CHALLENGE

Masakiyo Fujimoto, Tomohiro Nakatani, Takuya Yoshioka, 2014 .

Intelligibility prediction of enhanced speech using recognition accuracy of end-to-end ASR systems

T. Irino, A. Ogawa, T. Nakatani, 2022, 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Children's speech recognition using elementary-school-student speech database

Atsunori Ogawa, Yoshikazu Yamaguchi, Shoichi Matsunaga, 2005, Systems and Computers in Japan.

Predicting Intelligibility of Enhanced Speech Using Posteriors Derived from DNN-Based ASR System

Tomohiro Nakatani, Shoko Araki, Toshio Irino, 2020, INTERSPEECH.

Predicting Speech Intelligibility of Enhanced Speech Using Phone Accuracy of DNN-Based ASR System

Tomohiro Nakatani, Shoko Araki, Toshio Irino, 2019, INTERSPEECH.

Speech Summarization of Long Spoken Document: Improving Memory Efficiency of Speech/Text Encoders

A. Ogawa, Shinji Watanabe, Kohei Matsuura, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Spatial correlation model based observation vector clustering and MVDR beamforming for meeting recognition

Tomohiro Nakatani, Shoko Araki, Masahiro Okada, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Frame-Level Phoneme-Invariant Speaker Embedding for Text-Independent Speaker Recognition on Extremely Short Utterances

Tetsuji Ogawa, Marc Delcroix, Atsunori Ogawa, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multi-Stream Extension of Variational Bayesian HMM Clustering (MS-VBx) for Combined End-to-End and Vector Clustering-based Diarization

L. Burget, A. Ogawa, T. Nakatani, 2023, ArXiv.

Deep mixture density network for statistical model-based feature enhancement

Tomohiro Nakatani, Marc Delcroix, Atsunori Ogawa, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Attention-Based Multi-Hypothesis Fusion for Speech Summarization pdf

Shinji Watanabe, Marc Delcroix, Atsunori Ogawa, 2021, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Joint estimation of confidence and error causes in speech recognition

Atsunori Ogawa, Atsushi Nakamura, A. Ogawa, 2012, Speech Commun..

Efficient Combination of Likelihood Recycling and Batch Calculation for Fast Acoustic Likelihood Calculation

Satoshi Takahashi, Atsunori Ogawa, Atsushi Nakamura, 2011, IEICE Trans. Inf. Syst..

Discriminative confidence and error cause estimation for extended speech recognition function

Atsunori Ogawa, Atsushi Nakamura, A. Ogawa, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

A novel confidence measure based on marginalization of jointly estimated error cause probabilities

Atsunori Ogawa, Atsushi Nakamura, A. Ogawa, 2010, INTERSPEECH.

Robust Example Search Using Bottleneck Features for Example-Based Speech Enhancement

Tomohiro Nakatani, Takuya Yoshioka, Marc Delcroix, 2016, INTERSPEECH.

Fast segment search for corpus-based speech enhancement based on speech recognition technology

Tomohiro Nakatani, Atsunori Ogawa, Atsushi Nakamura, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Iterative Shallow Fusion of Backward Language Model for End-To-End Speech Recognition

A. Ogawa, Naohiro Tawara, Naoyuki Kamo, 2023, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Real-time meeting recognition and understanding using distant microphones and omni-directional camera

Masakiyo Fujimoto, Shinji Watanabe, Tomohiro Nakatani, 2010, 2010 IEEE Spoken Language Technology Workshop.

Age-VOX-Celeb: Multi-Modal Corpus for Facial and Speech Estimation

Atsunori Ogawa, Naohiro Tawara, Hosana Kamiyama, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech recognition in the presence of highly non-stationary noise based on spatial, spectral and temporal speech/noise modeling combined with dynamic variance adaptation

Masakiyo Fujimoto, Shinji Watanabe, Tomohiro Nakatani, 2011 .

Language Model Domain Adaptation Via Recurrent Neural Networks with Domain-Shared and Domain-Specific Representations

Tetsuji Ogawa, Tetsunori Kobayashi, Tomoharu Iwata, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Unified Framework for Feature-based Domain Adaptation of Neural Network Language Models

Tomoharu Iwata, Tomohiro Nakatani, Marc Delcroix, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Semi-Supervised End-to-End Speech Recognition

Tomoharu Iwata, Shinji Watanabe, Marc Delcroix, 2018, INTERSPEECH.

Coupling beamforming with spatial and spectral feature based spectral enhancement and its application to meeting recognition

Tomohiro Nakatani, Shoko Araki, Takuya Yoshioka, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Advanced language model fusion method for encoder-decoder model in Japanese speech recognition

A. Ogawa, N. Kitaoka, Ryota Nishimura, 2021, 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Double-layer neighborhood graph based similarity search for fast query-by-example spoken term detection

Atsunori Ogawa, Takaaki Hori, Takashi Hattori, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Online meeting recognition in noisy environments with time-frequency mask based MVDR beamforming

Tomohiro Nakatani, Shoko Araki, Takuya Yoshioka, 2017, 2017 Hands-free Speech Communications and Microphone Arrays (HSCMA).

Rescoring N-Best Speech Recognition List Based on One-on-One Hypothesis Comparison Using Encoder-Classifier Model

Tomohiro Nakatani, Marc Delcroix, Atsunori Ogawa, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization

A. Ogawa, Tomohiro Tanaka, Kohei Matsuura, 2023, INTERSPEECH.