Research theme for competitive and other funds (10):
2021 - 2025 プライバシー保護を考慮した深層学習のための学習可能な画像暗号化法の構築
2020 - 2024 Innovation of speech / acoustic scene recognition based on distributed acoustic sensing and asynchronous sequence modeling
2019 - 2022 A study on secure biometric authentication systems for voice control devices
2016 - 2019 Corpus development considering pop-noise balance for robust speaker verification systems
2014 - 2017 Investigation on secure speaker verification based on vocal liveness detection
2013 - 2015 Constructing noise robust speaker verification system based on kernel method
2013 - 2015 カーネル法に基づいた歪みに頑健な話者照合システムの構築
2013 - 2014 音声認識に基づく人間中心対話式ロボット操作システムの確立
2013 - 2014 話者照合における合成音声による詐称に関する研究
2011 - 2012 複数の共有構造を用いたアニーリングに基づく音響モデリング
Show all
Papers (75):
Yuki Shiroma, Yuma Kinoshita, Keisuke Imoto, Sayaka Shiota, Nobutaka Ono, Hitoshi Kiya. Missing Data Completion of Multi-Channel Signals Using Autoencoder for Acoustic Scene Classification. APSIPA Transactions on Signal and Information Processing. 2023. 12. 3. 1-22
Yuki Shiroma, Yuma Kinoshita, Keisuke Imoto, Sayaka Shiota, Nobutaka Ono, Hitoshi Kiya. Missing data recovery using autoencoder for multi-channel acoustic scene classification. 30th European Signal Processing Conference(EUSIPCO). 2022. 767-771
Imaizumi, R., Masumura, R., Shiota, S., Kiya, H. End-to-end Japanese Multi-dialect Speech Recognition and Dialect Identification with Multi-task Learning. APSIPA Transactions on Signal and Information Processing. 2022. 11. 1
Hiroto Kai, Shinnosuke Takamichi, Sayaka Shiota, Hitoshi Kiya. Lightweight and irreversible speech pseudonymization based on data-driven optimization of cascaded voice modification modules. Comput. Speech Lang. 2022. 72. 101315-101315
Hitoshi Kiya, AprilPyone MaungMaung, Yuma Kinoshita, Imaizumi Shoko, Sayaka Shiota. An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications. CoRR. 2022. abs/2201.11006. 1
Shinnosuke Takamichi, Ludwig Kürzinger, Takaaki Saeki, Sayaka Shiota, Shinji Watanabe. JTubeSpeech: corpus of Japanese speech collected from YouTube for speech recognition and speaker verification. CoRR. 2021. abs/2112.09323
Miki Tanaka, Sayaka Shiota, Hitoshi Kiya. A universal detector of CNN-generated images using properties of checkerboard artifacts in the frequency domain. GCCE. 2021. abs/2108.01892. 103-106
2014/04 - 2018/03 Tokyo Metropolitan University the Department of Information and Communication Systems, Graduate School of System Design Assistant Professor
2013/02 - 2014/03 The Institute of Statistical Mathematics Reserch Center for Statistical Machine Learning Project Assistant Professor
Committee career (6):
2022/04 - 現在 IEICE SIP
2021/01 - 現在 APSIPA SLTC APSIPA SLTC member
2020/10 - 現在 APSIPA Japan Chapter Treasurer
2020/04 - 現在 IEICE SP
2019/04 - 現在 一般社団法人日本音響学会 広報・電子化委員会
2018/04 - 現在 情報処理学会 音声言語情報処理学会
Show all
Awards (2):
2023/03 - 一般社団法人日本音響学会 学会活動貢献賞
2018/09 - The Acoustic Society of Japan Awaya Kiyoshi Research Award
Association Membership(s) (5):
APSIPA
, IEEE SPS
, THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS
, INFORMATION PROCESSING SOCIETY OF JAPAN
, ACOUSTICAL SOCIETY OF JAPAN