Tsubasa Ochiai

发表

Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event Localization

Tomohiro Nakatani, Shoko Araki, Marc Delcroix, 2021, 2020 28th European Signal Processing Conference (EUSIPCO).

Does speech enhancement work with end-to-end ASR objectives?: Experimental analysis of multichannel end-to-end ASR

Shigeru Katagiri, Shinji Watanabe, Tsubasa Ochiai, 2017, 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP).

Speech pattern classification using Large Geometric Margin Minimum Classification Error training

Shigeru Katagiri, Hisashi Kawai, Miho Ohsaki, 2015, TENCON 2015 - 2015 IEEE Region 10 Conference.

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

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

Unified Architecture for Multichannel End-to-End Speech Recognition With Neural Beamforming

John R. Hershey, Shinji Watanabe, Takaaki Hori, 2017, IEEE Journal of Selected Topics in Signal Processing.

Speaker adaptive training for deep neural networks embedding linear transformation networks

Shigeru Katagiri, Chiori Hori, Xugang Lu, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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).

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

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

Convolutive Transfer Function Invariant SDR training criteria for Multi-Channel Reverberant Speech Separation pdf

Tomohiro Nakatani, Marc Delcroix, Reinhold Haeb-Umbach, 2020, ArXiv.

A Dynamic Stream Weight Backprop Kalman Filter for Audiovisual Speaker Tracking

Tomohiro Nakatani, Shoko Araki, Marc Delcroix, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Self-Distillation for Improving CTC-Transformer-Based ASR Systems

Marc Delcroix, Ryo Masumura, Tsubasa Ochiai, 2020, INTERSPEECH.

Speaker Adaptation for Multichannel End-to-End Speech Recognition

Shigeru Katagiri, John R. Hershey, Shinji Watanabe, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

SpeakerBeam: Speaker Aware Neural Network for Target Speaker Extraction in Speech Mixtures

Tomohiro Nakatani, Marc Delcroix, Keisuke Kinoshita, 2019, IEEE Journal of Selected Topics in Signal Processing.

Speaker Adaptive Training using Deep Neural Networks

Shigeru Katagiri, Chiori Hori, Xugang Lu, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Listen to What You Want: Neural Network-based Universal Sound Selector

Shoko Araki, Marc Delcroix, Keisuke Kinoshita, 2020, INTERSPEECH.

DNN-supported Mask-based Convolutional Beamforming for Simultaneous Denoising, Dereverberation, and Source Separation

Tomohiro Nakatani, Shoko Araki, Marc Delcroix, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Neural Network-based Virtual Microphone Estimator pdf

Tomohiro Nakatani, Shoko Araki, Marc Delcroix, 2021, ArXiv.

Automatic node selection for Deep Neural Networks using Group Lasso regularization

Shigeru Katagiri, Shigeki Matsuda, Tsubasa Ochiai, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Bottleneck linear transformation network adaptation for speaker adaptive training-based hybrid DNN-HMM speech recognizer

Shigeru Katagiri, Hisashi Kawai, Xugang Lu, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multichannel End-to-end Speech Recognition

John R. Hershey, Shinji Watanabe, Takaaki Hori, 2017, ICML.

Compact Network for Speakerbeam Target Speaker Extraction

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

Improving Speaker Discrimination of Target Speech Extraction With Time-Domain Speakerbeam

Tomohiro Nakatani, Shoko Araki, Marc Delcroix, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speaker Adaptive Training Localizing Speaker Modules in DNN for Hybrid DNN-HMM Speech Recognizers

Shigeru Katagiri, Chiori Hori, Hisashi Kawai, 2016, IEICE Trans. Inf. Syst..

Beam-TasNet: Time-domain Audio Separation Network Meets Frequency-domain Beamformer

Tomohiro Nakatani, Shoko Araki, Marc Delcroix, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Cumulative moving averaged bottleneck speaker vectors for online speaker adaptation of CNN-based acoustic models

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

ESPnet: End-to-End Speech Processing Toolkit pdf

Shinji Watanabe, Takaaki Hori, Tsubasa Ochiai, 2018, INTERSPEECH.

Improving Noise Robust Automatic Speech Recognition with Single-Channel Time-Domain Enhancement Network

Tomohiro Nakatani, Marc Delcroix, Keisuke Kinoshita, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speaker activity driven neural speech extraction pdf

Tomohiro Nakatani, Marc Delcroix, Keisuke Kinoshita, 2021, ArXiv.

Simpleflat: A Simple Whole-Network Pre-Training Approach for RNN Transducer-Based End-to-End Speech Recognition

Yusuke Ijima, Hiroshi Sato, Tsubasa Ochiai, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Convolutive Transfer Function Invariant SDR Training Criteria for Multi-Channel Reverberant Speech Separation

Tomohiro Nakatani, Marc Delcroix, Keisuke Kinoshita, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multimodal Attention Fusion for Target Speaker Extraction

Tomohiro Nakatani, Shoko Araki, Marc Delcroix, 2021, 2021 IEEE Spoken Language Technology Workshop (SLT).

End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend

Shinji Watanabe, Tomohiro Nakatani, Marc Delcroix, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Few-shot learning of new sound classes for target sound extraction pdf

Shoko Araki, Marc Delcroix, Keisuke Kinoshita, 2021, Interspeech.

Streaming End-to-End Speech Recognition for Hybrid RNN-T/Attention Architecture

Marc Delcroix, Hiroshi Sato, Tsubasa Ochiai, 2021, Interspeech.

Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition pdf

Marc Delcroix, Keisuke Kinoshita, Hiroshi Sato, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition pdf

Marc Delcroix, Keisuke Kinoshita, Hiroshi Sato, 2021, Interspeech.

Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model pdf

Marc Delcroix, Lukás Burget, Jan Cernocký, 2021, ArXiv.

PILOT: Introducing Transformers for Probabilistic Sound Event Localization pdf

Dorothea Kolossa, Tomohiro Nakatani, Shoko Araki, 2021, Interspeech.

Data Fusion for Audiovisual Speaker Localization: Extending Dynamic Stream Weights to the Spatial Domain

Dorothea Kolossa, Tomohiro Nakatani, Shoko Araki, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speaker Activity Driven Neural Speech Extraction

Tomohiro Nakatani, Marc Delcroix, Keisuke Kinoshita, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR pdf

Shigeru Katagiri, Shoko Araki, Marc Delcroix, 2022, ArXiv.