CV

A pdf version can be downloaded from here.

Research Interests

• Automatic Speech Recognition (ASR)
• Speech Translation (ST)

Education

• 2013.10 - now: Ph.D student in Graduate School of Informatics, Kyoto University, supervised by Prof. Tatsuya Kawahara
• 2021.10 - 2023.09: M.S. in Graduate School of Advanced Science and Technology, Japan Advanced Institue of Science and Technology, supervised by Prof. Nguyen Minh Le
• 2013.09 - 2017.07: B.S. in School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University

Internship / Work experience

• 2026.10 - now: Research Assistant
  • Speech and Audio Processing Lab, Kyoto University, Kyoto, Japan
• 2025.08 - 2025.11: Research Intern
  • A*STAR Institute for Infocomm Research (I2R), Singapore
• 2023.10 - 2024.04: Research Assistant
  • Speech and Audio Processing Lab, Kyoto University, Kyoto, Japan
• 2017.07 - 2020.11: Java Developer / Senior Java Developer
  • Shanghai Huaxin Securities, Shanghai, China

Hornors

• 2024.04 - 2026.10: Fellowship of DoGS Next AI Program, awarded by Japan Science and Technology Agency (JST)
• 2022.10 - 2023.09: JAIST Scholarship, awarded by JAIST

Skills

• Natural Languages: Mandarin Chinese (native), English (fluent), Japanese (fluent), Korean (only a little)
• Programming Languages: Python, Java, C, C++

Publications

Language-Aware Routing in Mixtures of Experts for Low-Resource Automatic Speech Recognition

Loasr-bench: Evaluating large speech language models on low-resource automatic speech recognition across language families

Chen, J., Gao, X., Tatsuya, K., & Chen, N. F. (2026). Loasr-bench: Evaluating large speech language models on low-resource automatic speech recognition across language families. IEEE Signal Processing Letters.

Data Selection using Spoken Language Identification for Low-Resource and Zero-Resource Speech Recognition

J. Chen, C. Chu, S. Li and T. Kawahara, "Data Selection using Spoken Language Identification for Low-Resource and Zero-Resource Speech Recognition," 2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Macau, Macao, 2024, pp. 1-6, doi: 10.1109/APSIPAASC63619.2025.10848811.

An Isotropy Analysis for Self-Supervised Acoustic Unit Embeddings on the Zero Resource Speech Challenge 2021 Framework

J. Chen and S. Sakti, "An Isotropy Analysis for Self-Supervised Acoustic Unit Embeddings on the Zero Resource Speech Challenge 2021 Framework," ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5, doi: 10.1109/ICASSP49357.2023.10095119.

WeExt: A Framework of Extending Deterministic Knowledge Graph Embedding Models for Embedding Weighted Knowledge Graphs

K. W. Kun et al., "WeExt: A Framework of Extending Deterministic Knowledge Graph Embedding Models for Embedding Weighted Knowledge Graphs," in IEEE Access, vol. 11, pp. 48901-48911, 2023, doi: 10.1109/ACCESS.2023.3276319.

Workshop / Seminar Prensentations

• 2026.9: JST NEXUS symposium on Multimodal LLM for Enhancing Human Activities, @Kyotu University
• 2026.6: 2nd ASEAN-NEXUS Early Career Researchers Conclave, @Singapore
• 2026.2: 第20回ICTイノベーション, @Kyoto University
• 2025.12: 京都大学卓越ワークショップ2025, @Kyoto University
• 2024.11: 第60回関西合同音声ゼミ, @龍谷大学