Satoshi Nakamura

Satoshi Nakamura (中村 哲, Nakamura Satoshi; born 1958) is a Japanese computer scientist specialising in speech and language processing. He is a Presidential Chair Professor in the School of Data Science at the Chinese University of Hong Kong, Shenzhen; Professor Emeritus at the Nara Institute of Science and Technology (NAIST); and Honorary professor of Karlsruhe Institute of Technology, Germany. He is widely recognised for pioneering work in speech-to-speech translation, having led international initiatives such as C-Star, A-Star and the International Workshop on Spoken Language Translation (IWSLT), and currently chairs the ISCA Special Interest Group on Spoken Language Translation (SIG-SLT).

His research covers speech recognition and synthesis, spoken-dialog systems, simultaneous translation, natural-language processing and data-science applications. Earlier in his career he directed the ATR Spoken Language Communication Laboratories (2000–2008), headed Keihanna Research Laboratories at the National Institute of Information and Communications Technology (NICT) (2009–2010), and founded the Data Science Center at NAIST (2017–2021). He is a Fellow of IEEE, ISCA, IPSJ and ATR, and received the Antonio Zampolli Prize in 2012.

Education He received his B.S. in Electrical Engineering from Kyoto Institute of Technology in 1981 and his Ph.D. in Information Science from Kyoto University in 1992. 2009 – Executive Researcher, National Institute of Information and Communications Technology (NICT), Japan 2010 – Director General, Keihanna Research Laboratories, NICT, Japan 2011 – Full Professor, Graduate School of Information Science, NAIST, Japan 2017–2021 – Director, Data Science Center, NAIST, Japan 2017–2021 – Councilor, NAIST, Japan 2017–2021 – Principal Investigator, Tourism Information Analysis Team, AIP Center, RIKEN, Japan Nov 2023–Mar 2024 – Visiting Professor, School of Data Science, CUHK Shenzhen, China Apr 2024 – Full Professor, School of Data Science, CUHK Shenzhen, China Jan 2025 – Presidential Chair Professor, School of Data Science, CUHK Shenzhen, China

Research His research spans fundamental speech technology, multimodal interaction, and applied data science. Key areas include: Speech-to-speech and simultaneous translation – Principal investigator of international programs such as C-Star, A-Star and ATR-MATRIX; his group introduced latency-aware metrics (e.g., Average Token Delay) and built simultaneous speech-translation systems for IWSLT 2023–2024. Spoken dialog and conversational AI – Developed reinforcement-learning and knowledge-integrated dialog models and released large corpora for persuasion and healthcare conversations published at SIGDIAL and IWSDS. Embodied conversational agents for behavioural health – Created automated social-skills-training and CBT agents for autism spectrum and mood disorders, validated with EEG and eye-tracking studies. Neural ASR/TTS and speech generation – Proposed the Machine Speech Chain, code-switch ASR/TTS, incremental TTS, expressive voice conversion and other models that have shaped ZeroSpeech, Blizzard and Voice Conversion Challenge tracks. Multimodal analytics and data science – Led tourism information analytics at RIKEN AIP and healthcare/biometrics projects at NAIST Data Science Center, applying speech and language technologies to large-scale behavioural data. Standardisation and community leadership – Contributed to ITU-T standards on network-based speech translation, chairs the ISCA SIG-SLT, and has authored 600+ peer-reviewed papers across venues such as IEEE Access, IJHCS, and Computational Visual Media (2024). 2014 – IEEE Spoken Language Technology Workshop Poster Award 2015 – IEICE Best Paper Award 2016 – IEEE Fellow 2016 – EMNLP Best Short Paper Award 2017 – Itakura Award, Acoustical Society of Japan 2017 – IBM Faculty Award 2017 – IPSJ Fellow 2018 – Yahoo! JAPAN Award, Information Processing Society of Japan 2019 – ANLP Best Paper Award 2019 – Best Paper Award, Workshop on NLP for Conversational AI 2019 – Google AI Focused Research Award 2020 – ISCA Fellow 2020 – IWSDS Best Paper Award 2020 – 1st Place, MOTS Challenge 2020 (ReMOTS) at CVPR 2020 2021 – Best Research Award, Japanese Society for Artificial Intelligence 2021 – Special Award, Association for Natural Language Processing (Japan) 2022 – Google AI Focused Research Award

Selected publications Nakamura, S. et al. “ATR-MATRIX: Speech-to-speech translation system.” In: *Proceedings of ICSLP*, 2000. Kano, Y.; Sudoh, K.; & Nakamura, S. “Average Token Delay: A Latency Metric for Simultaneous Translation.” *Interspeech*, 2023. Koshkin, R.; Sudoh, K.; & Nakamura, S. “LLMs Are Zero-Shot Context-Aware Simultaneous Translators.” *EMNLP*, 2024. Ishibashi, Y.; Yokoi, S.; Sudoh, K.; & Nakamura, S. “Subspace Representations for Soft Set Operations and Sentence Similarities.” *NAACL*, 2024.