Publications

You can also check my Google Scholar

Journal Paper

(Main author)

Kenichi Fujita, Atsushi Ando, and Yusuke Ijima, ``Speech Rhythm-Based Speaker Embeddings Extraction from Phonemes and Phoneme Duration for Multi-Speaker Speech Synthesis," IEICE Trans. on Information and Systems, vol. 107, no. 1, pp. 93-104, Jan. 2024. (https://www.jstage.jst.go.jp/article/transinf/E107.D/1/E107.D_2023EDP7039/_article)
Kenichi Fujita, Syogo Yonekura, Satoshi Nishikawa, Ryuma Niiyama, Yasuo Kuniyoshi, ``Physical Reservoir Computing in Tensegrity with Structural Softness and Ground Collision Dynamics,'' Journal of the Institute of Industrial Applications Engineers, vol. 6, no. 2, pp. 92-99, Apr. 2018.
(https://www2.ia-engineers.org/Journal_E/index.php/jiiae/article/view/160)

(Co-author)

Takumi Matsuda, Kenichi Fujita, Yuya Hamamatsu, Takashi Sakamaki, and Toshihiro Maki, ``Parent–Child‐Based Navigation Method of Multiple Autonomous Underwater Vehicles for an Underwater Self‐Completed Survey, '' Journal of Field Robotics, vol. 39, no. 2, pp. 89-106, Mar. 2022.
(https://onlinelibrary.wiley.com/doi/abs/10.1002/rob.22038)

International Conference

(Main author)

Kenichi Fujita, Shota Horiguchi, and Yusuke Ijima, ``Voice Impression Control in Zero-Shot TTS ,'' Proc. INTERSPEECH 2025, pp. 4363-4367, Sept. 2025. (https://www.isca-archive.org/interspeech_2025/fujita25_interspeech.html)
Hiroki Kanagawa, Kenichi Fujita (Equal Contribution), Aya Watanabe, Yusuke Ijima, ``Multi-interaction TTS toward professional recording reproduction'', Proc. 13th edition of the Speech Synthesis Workshop, pp. 110-116, Sept. 2025. (https://www.isca-archive.org/ssw_2025/kanagawa25_ssw.html)
Kenichi Fujita, Takanori Ashihara, Marc Delcroix, and Yusuke Ijima, ``Lightweight Zero-shot Text-to-Speech with Mixture of Adapters,'' Proc. INTERSPEECH 2024, pp. 692-696, Sept. 2024. (https://www.isca-archive.org/interspeech_2024/fujita24b_interspeech.html#)
Kenichi Fujita, Hiroshi Sato, Takanori Ashihara, Hiroki Kanagawa, Marc Delcroix, Takafumi Moriya, and Yusuke Ijima, ``Noise-Robust Zero-Shot Text-to-Speech Synthesis Conditioned on Self-Supervised Speech-Representation Model with Adapters,'' Proc. IEEE ICASSP 2024, pp. 11471-11475, Apr. 2024.
(https://ieeexplore.ieee.org/document/10447809)
Kenichi Fujita, Takanori Ashihara, Hiroki Kanagawa, Takafumi Moriya, and Yusuke Ijima, ``Zero-Shot Text-to-Speech Synthesis Conditioned Using Self-Supervised Speech Representation Model,'' Proc. IEEE ICASSP 2023 workshop Self-supervision in Audio, Speech and Beyond, June 2023. (Best Paper Award)
(https://ieeexplore.ieee.org/document/10193459)
Kenichi Fujita, Yusuke Ijima, and Hiroaki Sugiyama, ``Direct Speech-Reply Generation from Text-Dialogue Context,'' Proc. APSIPA Annual Summit and Conference 2022, pp. 1655-1660, Nov. 2022.
(https://ieeexplore.ieee.org/abstract/document/9979940)
Kenichi Fujita, Atsushi Ando, and Yusuke Ijima, ``Phoneme Duration Modeling Using Speech Rhythm-Based Speaker Embeddings for Multi-Speaker Speech Synthesis,'' Proc. INTERSPEECH 2021, pp. 3141-3145, Sept. 2021.
(https://www.isca-archive.org/interspeech_2021/fujita21_interspeech.html)
Kenichi Fujita, Takumi Matsuda, and Toshihiro Maki, ``Bearing Only Localization for Multiple AUV with Acoustic Broadcast Communication, '' Proc. 2019 19th International Conference on Control, Automation and Systems (ICCAS), pp. 1371-1376, Oct. 2019.
(https://ieeexplore.ieee.org/abstract/document/8971524)
Kenichi Fujita, and Toshihiro Maki, ``Momonga-like AUV–AUV with a Variable Wing–, '' Proc. 2018 IEEE/OES Autonomous Underwater Vehicle Workshop (AUV) (student poster competition), Nov. 2018.
(https://ieeexplore.ieee.org/abstract/document/8729749)
Kenichi Fujita, Syogo Yonekura, Satoshi Nishikawa, Ryuma Niiyama, and Yasuo Kuniyoshi, ``Environmental and Structural Effects on Physical Reservoir Computing with Tensegrity, '' Proc. the 5th IIAE International Conference on Intelligent Systems and Image Processing 2017, pp. 197-204, Sept. 2017. (Best Presentation Award)
(https://pdfs.semanticscholar.org/aec2/fd10fbfa220460613b9b516d1b35c150d06c.pdf)

(Co-author)

Hikaru Yanagida, Mizuki Nagano, Kenichi Fujita, and Yusuke Ijima, `` Effects of One’s Own Voice on Narrative Transportation via Identification, '' Proc. SPSP Annual Convention, Feb. 2026.
Takumi Matsuda, Yuya Hamamatsu, Kenichi Fujita, Takashi Sakamaki, and Toshihiro Maki, ``Experimental Results of Ship-free Underwater Survey Method of Multiple Autonomous Underwater Vehicles, '' Proc. Oceans 2021, Sept. 2021.
(https://ieeexplore.ieee.org/abstract/document/9705869)

Domestic Conference

(主著)

藤田健一，井島勇祐 ,``発話ペア間の相対的音声印象推定手法の検討 , '' 日本音響学会春季研究発表会, 1-Q-38, Mar. 2026.
藤田健一，堀口翔太，井島勇祐 ,``音声印象を操作可能なZero-shot 音声合成, '' 日本音響学会秋季研究発表会, 3-1-1, Sep. 2025.
藤田健一，芦原孝典，デルクロアマーク，井島勇祐 ,``Mixture of Adapters を用いた軽量なzero-shot 音声合成, '' 日本音響学会春季研究発表会, 1-2-4, Mar. 2025.
藤田健一，佐藤宏，芦原孝典，金川裕紀，デルクロアマーク，森谷崇史，井島勇祐 ,``自己教師あり学習モデルを用いたノイズに頑健な zero-shot 音声合成の検討, '' 日本音響学会春季研究発表会, 3-2-1, Mar. 2024.
藤田健一，芦原孝典，金川裕紀，森谷崇史，井島勇祐, ``自己教師あり学習モデルを用いた zero-shot 音声合成の性能評価, '' 日本音響学会秋季研究発表会, 3-9-1, Sept. 2023.
藤田健一，芦原孝典，金川裕紀，森谷崇史，井島勇祐, ``自己教師あり学習モデルを用いた zero-shot 音声合成の検討, '' 日本音響学会春季研究発表会, 1-3-8, Mar. 2023.
藤田健一，井島勇祐，杉山弘晃, ``応答テキストを介さないテキスト対話系列からの音声応答生成の検討, '' 日本音響学会秋季研究発表会, 2-Q-38, Sept. 2022.
藤田健一，安藤厚志，井島勇祐，``発話リズムに基づく話者埋め込みを用いた音素継続時間長モデリングの検討, '' 日本音響学会秋季研究発表会, 1-3-13, Sept. 2021.
藤田健一，安藤厚志，井島勇祐，``音素継続時間長のモデル化のための発話リズムに基づく話者埋め込みの検討, '' 研究報告音声言語情報処理（SLP）, 2021-SLP-136, pp. 1-6, Feb. 2021.
藤田健一，米倉将吾，西川鋭，新山龍馬，國吉康夫, ``身体構造のダイナミクスを利用した Reservoir Computing に関する研究, '' ロボティクス・メカトロニクス講演会講演概要集 2017, 1P2-N11, May. 2017.

(共著)

柳田耀，長野瑞生，藤田健一，井島勇祐 ``自他の朗読音声が聞き手の没入感に与える影響の分析 , '' 日本音響学会春季研究発表会, 3-8-2, Mar. 2026.
柳田耀，長野瑞生，藤田健一，井島勇祐 ``朗読音声の自分らしさが聞き手の没入感に与える影響の検討 , '' 日本音響学会秋季研究発表会, 3-Q-39, Sep. 2025.
長野瑞生，藤田健一，井島勇祐，廣谷定男 ``感情を考慮した宣伝音声の合成手法および主観的評価 ,'' 日本音響学会秋季研究発表会, 1-2-4, Sep. 2025.