Education
Apr. 2025 - current
Nara Institute of Science and Technology (NAIST)
Postdoctoral Researcher
Human-AI Interaction Lab.
Apr. 2022 - Mar. 2025
Nara Institute of Science and Technology (NAIST)
Doctor of Engineering
Augmented Human Communication Lab. (2022.4-2024.3)Human-AI Interaction Lab. (2024.4-2025.03)
Apr. 2020 - Mar. 2022
Nara Institute of Science and Technology (NAIST)
Master of Engineering
Augmented Human
Communication Lab.
Apr. 2016 - Mar. 2020
Osaka Prefecture University
Bachelor of Engineering
Electricity Engineering, Information Engineering.
Apr. 2013 - Mar. 2016
Kyoto Prefectual Nanyo High School
Journal Paper
End-to-end Simultaneous Speech Translation with Style Tags using Human Simultaneous Interpretation Data.
Yuka Ko, Ryo Fukuda, Yuta Nishikawa, Yasumasa Kano, Katsuhito Sudoh, Sakriani Sakti and Satoshi Nakamura.
Journal of Natural Language Processing, Vol.32, No.2, To appear. June. 2025.
Neural End-to-end Speech Translation Leveraged by ASR Posterior Distribution.
Yuka Ko, Katsuhito Sudoh, Sakriani Sakti, Satoshi Nakamura.
IEICE TRANSACTIONS on Information and Systems, Vol.E107-D, No.10, pp. 1322-1331. Oct. 2024.
International Conference (Peer-reviewed)
LLM as decoder: Investigating Lattice-based Speech Recognition Hypotheses Rescoring Using LLM.
Sheng Li, Yuka Ko, Akinori Ito.
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2024 (APSIPA ASC 2024), To appear, Macau, China, December 2024.
Word Order in English-Japanese Simultaneous Interpretation: Analyses and Evaluation using Chunk-wise Monotonic Translation.
Kosuke Doi, Yuka Ko, Mana Makinae, Katsuhito Sudoh and
Satoshi Nakamura.
In Proceedings of the 21th International Conference on Spoken Language Translation (IWSLT), pp. 254-264, Bangkok, Thailand, Aug. 2024.
NAIST-SIC-Aligned: Automatically-Aligned English-Japanese Simultaneous
Interpretation Corpus.
Jinming Zhao*, Yuka Ko*, Kosuke Doi, Ryo Fukuda, Katsuhito Sudoh and
Satoshi Nakamura.
In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING), pp. 12046-12052, Torino, Italia, May 2024. (*: Equal Contribution)
Tagged End-to-End Simultaneous Speech Translation Training using
Simultaneous Interpretation Data.
Yuka Ko, Ryo Fukuda, Yuta Nishikawa, Yasumasa Kano, Katsuhito Sudoh and
Satoshi Nakamura.
In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT), pp. 363-375, Toronto, Canada,
July 2023. (Best Student Paper Award)
Simultaneous Speech-to-speech Translation System with
Transformer-based Incremental ASR, MT, and TTS.
Ryo Fukuda, Sashi Novitasari, Yui Oka, Yasumasa Kano, Yuki Yano, Yuka Ko,
Hirotaka Tokuyama, Kosuke Doi, Tomoya Yanagita, Sakriani Sakti, Katsuhito Sudoh and Satoshi
Nakamura.
In Proceedings of the 24th Conference of the Oriental COCOSDA (O-COCOSDA), pp. 186-192, Singapore, Nov. 2021. (Best
Student Paper Award)
ASR Posterior-based Loss for Multi-task End-to-end Speech Translation.
Yuka Ko, Katsuhito Sudoh, Sakriani Sakti, Satoshi Nakamura.
In Proceedings of the 22nd Annual Conference of the International Speech Communication
Association (INTERSPEECH), pp. 2272-2276, Brno, Czechia, Aug. 2021. (acceptance rate: 963/1990=48.4%)
International Conference (Non peer-reviewed)
NAIST Simultaneous Speech Translation System for IWSLT 2024.
Yuka Ko, Ryo Fukuda, Yuta Nishikawa, Yasumasa Kano, Tomoya Yanagita, Kosuke
Doi, Mana Makinae, Haotian Tan, Makoto Sakai, Sakriani Sakti, Katsuhito Sudoh and Satoshi Nakamura.
In Proceedings of the 21th International Conference on Spoken Language Translation (IWSLT), pp. 170-182, Bangkok, Thailand, Aug. 2024.
NAIST Simultaneous Speech-to-speech Translation System for IWSLT 2023.
Ryo Fukuda, Yuta Nishikawa, Yasumasa Kano, Yuka Ko, Tomoya Yanagita, Kosuke
Doi, Mana Makinae, Sakriani Sakti, Katsuhito Sudoh and Satoshi Nakamura.
In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT), pp. 330-340, Toronto, Canada,
July 2023.
NAIST Simultaneous Speech-to-Text Translation System for IWSLT 2022.
Ryo Fukuda, Yuka Ko, Yasumasa Kano, Kosuke Doi, Hirotaka Tokuyama, Sakriani
Sakti, Katsuhito Sudoh, Satoshi Nakamura.
In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT), pp. 286-292, Dublin, Ireland,
May 2022.
NAIST English-to-Japanese Simultaneous Translation System for IWSLT
2021 Simultaneous Text-to-text Task.
Ryo Fukuda, Yui Oka, Yasumasa Kano, Yuki Yano, Yuka Ko, Hirotaka Tokuyama,
Kosuke Doi, Sakriani Sakti, Katsuhito Sudoh, Satoshi Nakamura.
In Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT), pp. 39-45, Bangkok, Thailand, Aug. 2021.
Preprint
Benchmarking Japanese Speech Recognition on ASR-LLM Setups with Multi-Pass Augmented Generative Error Correction.
Yuka Ko, Sheng Li, Chao-Han Huck Yang, Tatsuya Kawahara.
arXiv preprint arXiv:2408.16180.
Domestic Conference (Non Peer-reviewed)
音声認識出力の曖昧性を考慮したMulti-task End-to-end音声翻訳と曖昧性の高い音声入力に対する頑健性の分析
胡 尤佳, 須藤 克仁, 中村 哲, Sakriani Sakti. 言語処理学会第31回年次大会 (NLP), pp. 2013-2018, 長崎, 2025年3月.
[PDF]
タグ付き混合データ学習と自己教師あり学習による
同時通訳データを用いた End-to-End 同時音声翻訳胡 尤佳, 福田 りょう, 西川 勇太, 加納 保昌, 須藤 克仁, 中村 哲. 言語処理学会第30回年次大会 (NLP), pp. 2324-2329, 神戸, 2024年3月.
[PDF]
非流暢性タグを用いた目的言語テキストによる自由発話の音声翻訳胡 尤佳, 須藤 克仁, 中村
哲言語処理学会第29回年次大会 (NLP 2023), pp. 1423-1427, 沖縄, 2023年3月.
[PDF]
機械翻訳の前処理のための言い換え辞書自動作成手法の提案胡 尤佳，岡田 真，森
直樹情報処理学会第241回自然言語処理研究会 (IPSJ-NL 2019), Vol.2019-NL-241 No.17, 小樽, 2019年8月. [PDF]
Award and Activity
Jan 2024 - Feb 2024
NTT Communication Science Laboratories, Internship
Tagged End-to-End Simultaneous Speech Translation Training using
Simultaneous Interpretation Data.
Yuka Ko, Ryo Fukuda, Yuta Nishikawa, Yasumasa Kano, Katsuhito Sudoh and
Satoshi Nakamura.
In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT), pp. 363-375, Toronto, Canada,
July 2023. (Best Student Paper Award)
日本学生支援機構 第一種奨学金 博士前期課程 返済全額免除
Fully exempt from repayment of JASSO student loan
令和4年度 奈良先端科学技術大学院大学 優秀学生奨学制度対象者
The NAIST Top Scholarship Program 2022.
(Tuition exemption in 1st year of Ph.D. course)
Simultaneous Speech-to-speech Translation System with
Transformer-based Incremental ASR, MT, and TTS.
Ryo Fukuda, Sashi Novitasari, Yui Oka, Yasumasa Kano, Yuki Yano, Yuka Ko,
Hirotaka Tokuyama, Kosuke Doi, Tomoya Yanagita, Sakriani Sakti, Katsuhito Sudoh and Satoshi
Nakamura.
In Proceedings of the 24th Conference of the Oriental COCOSDA (O-COCOSDA), pp. 186-192, Singapore, Nov. 2021. (Best
Student Paper Award)
Research Grant
Apr 2025 - Mar 2026
JSPS 日本学術振興会特別研究員 PD
JSPS Research Fellowship for Young Scientist PD
Apr 2024 - Mar 2025
JSPS 日本学術振興会特別研究員 DC2
JSPS Research Fellowship for Young Scientist DC2
Apr 2022 - Mar 2024
JST 次世代研究者研究プログラム 先端科学技術融合分野におけるイノベーティブ博士人材支援プロジェクト (NAIST Touch
Stone)
2022 Support Project for Innovative Doctoral Students in the Field of Multi-disciplinary
Research in Advanced Science and Technology (NAIST Touch Stone), JST SPRING: Support for
Pioneering Research Initiated by the Next Generation.
Certification
June 2020
PAST Algorithm TestAdvanced Beginner Class
Oct 2018
TOEIC Listening & Reading 835