Journal Paper

• Longfei Yang, Jiyi Li, Sheng Li, Takahiro Shinozaki. Multi-Domain Dialogue State Tracking with Large Language Model Rationale and Disentangled Domain-Slot Attention, IEEE Trans. Audio, Speech \& Language Process. (TASLP), Dec. 2025.

International Conference (Reviewed)

• Jianing Yang, Sheng Li, Takahiro Shinozaki, Yuki Saito, Hiroshi Saruwatari. Emotional Text-To-Speech Based on Mutual-Information-Guided Emotion-Timbre Disentanglement, APSIPA ASC, Dec. 2025.
• Pengcheng Wang, Sheng Li, Takahiro Shinozaki. RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition,, Interspeech2025 MLC-SLM Challenge workshop, Aug. 2025.
• Tingyuan Zhu, Shudong Liu, Yidong Wang, Derek F. Wong, Han Yu, Takahiro Shinozaki, Jindong Wang. Learning from "Silly" Questions Improves Large Language Models, But Only Slightly, AAAI Workshop, Feb. 2025.

Domestic Conference (Not reviewed / Unknown)

• Jianing Yang, 李 勝, Takahiro Shinozaki, 齋藤 佑樹, 猿渡 洋. 相互情報量最小化による感情・音色の分離に基づく感情的音声合成, ASJ2025 autumn, Dec. 2025.
• Pengcheng Wang, Sheng Li, Takahiro Shinozaki. RAG-Boost: Retrieval-Augmented Generation Enhanced Speech Recognition in LLM-based Spoken Dialogue Systems, 日本音響学会研究発表会講演論文集, 秋季, Sept. 2025.
• Takahiro Shinozaki, 佐藤秋太朗, 李勝. 大規模言語モデルを用いた英語学習者発話のCEFR-Jレベル推定, Mar. 2025.
• Renon Toyosaki, Koki Mikuriya, Taisei Awashima, Kota Kawakita, Takahiro Shinozaki. Spolacq-GDS: 有限状態オートマトンと大規模生成モデルを用いた生成的対話シミュレータ, 日本音響学会2025年春季研究発表会, 日本音響学会2025年春季研究発表会講演論文集, 2-2-7, Mar. 2025.
• Taisei Awashima, Renon Toyosaki, Koki Mikuriya, Kota Kawakita, Takahiro Shinozaki. Spolacq-GDS を用いた音声言語獲得に関する予備実験, 日本音響学会2025年春季研究発表会, 日本音響学会2025年春季研究発表会講演論文集, 2-2-8, Mar. 2025.
• Kota Kawakita, Ryota Komatsu, 岡本 拓磨, Takahiro Shinozaki. Speaker-Disentangled HuBERT を用いた教師なし音節発見法の分析評価, 日本音響学会2025年春季研究発表会, 日本音響学会2025年春季研究発表会講演論文集, 2-2-9, Mar. 2025.

[ Save as BibTeX ]    [ Paper, Presentations, Books, Others, Degrees: Save as CSV ]    [ Patents: Save as CSV ]