I am a Ph.D. candidate in the School of Data Science at The Chinese University of Hong Kong, Shenzhen. My chief supervisor is Prof. Satoshi Nakamura, and my co-supervisor is Prof. Haizhou Li. I received my bachelor’s degree in Electronic and Information Engineering from Beihang University, and my master’s degree in Integrated Circuit Engineering from Tsinghua University, supervised by Prof. Shouyi Yin. From 2020 to 2022, I worked as a speech algorithm engineer at Lenovo and Meituan.

My research interests include speech-to-speech translation, speech-to-text translation, machine translation, and speech generation.

Google Scholar View citations ↗

🔥 News

• 2024.08:  🎉🎉 We release training codes with the hope of contributing to the language model-based speech translation community.
• 2024.05:  🎉🎉 Our speech-to-text translation paper is accepted by ACL 2024.
• 2023.12:  🎉🎉 Our accent conversion paper is accepted by ICASSP 2024.

📖 Educations

• 2022.09 - Present, Ph.D. candidate at the School of Data Science, The Chinese University of Hong Kong, Shenzhen.
• 2017.09 - 2020.06, M.E. in Integrated Circuit Engineering, Tsinghua University, Beijing.
• 2013.09 - 2017.06, B.E. in the School Electronic and Information Engineering, Beihang University, Beijing.

💻 Internships

• 2026.07 - Present, Machine Translation team, Apple
• 2025.09 - 2026.06, Multilingual team, Qwen, Alibaba

📝 Publications

• Qwen Team, “Qwen3.5-Omni Technical Report” (arXiv 2026)

• Xi Chen, Songyang Zhang, Satoshi Nakamura, “LLaS2S: LLM-Based Speech-to-Speech Translation With Context-Aware Duration Prediction Units” (IEEE Transactions on Audio, Speech and Language Processing, 2026)

• Zeyu Yang, Lai Wei, Roman Koshkin, Xi Chen, Satoshi Nakamura, “SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation” (AAAI 2026)

• Xi Chen, Yuchen Song, Satoshi Nakamura, “StressTransfer: Stress-Aware Speech-to-Speech Translation with Emphasis Preservation” (arXiv 2025)

• Pei Zhang, Andong Chen, Xi Chen, Baosong Yang, Derek F. Wong, Fei Huang, “PART: Progressive Alignment Representation Training for Multilingual Speech-To-Text with LLMs” (arXiv 2025)

• Xi Chen, Songyang Zhang, Qibing Bai, Kai Chen, Satoshi Nakamura “LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models” (Accepted by ACL 2024)

• Xi Chen, Jiakun Pei, Liumeng Xue, Mingyang Zhang “Transfer the linguistic representations from TTS to accent conversion with non-parallel data” (Accepted by ICASSP 2024)

• Xueyao Zhang, Liumeng Xue, Yicheng Gu, Yuancheng Wang, Jiaqi Li, Haorui He, Chaoren Wang, Songting Liu, Xi Chen, et al. “Amphion: An Open-Source Audio, Music and Speech Generation Toolkit” (Accepted by SLT 2024)

• Huiyu Shi, Xi Chen, Tianlong Kong, Shouyi Yin, Peng Ouyang “GLMSnet: Single Channel Speech Separation Framework in Noisy and Reverberant Environments” (Accepted by ASRU 2021)

• Xi Chen, Songyang Zhang, Dandan Song, Peng Ouyang, Shouyi Yin “Transformer with bidirectional decoder for speech recognition” (Accepted by InterSpeech 2020)

• Xi Chen, Shouyi Yin, Dandan Song, Peng Ouyang, Leibo Liu, Shaojun Wei “Small-footprint keyword spotting with graph convolutional network” (Accepted by ASRU 2019)

• Zeqing Zhao*, Xi Chen*, Hui Liu, Xuyang Wang, Lin Yang, Junjie Wang Sptts: Parallel speech synthesis without extra aligner model (Accepted by APSIPA ASC 2021)

• Ruiqi Guo, Yonggang Liu, Shixuan Zheng, Ssu-Yen Wu, Peng Ouyang, Win-San Khwa, Xi Chen, et al. A 5.1 pJ/neuron 127.3 us/inference RNN-based speech recognition processor using 16 computing-in-memory SRAM macros in 65nm CMOS (Accepted by VLSI 2019)

🎖 Honors and Awards

• Duan Yong Ping Travel Award, 2024
• National Encouragement Scholarship in China, 2016

🧑‍🏫 Teaching

• Leading TA, AIR6001 Advanced Artificial Intelligence, Fall 2024
• TA, CSC3160 Fundamentals of Speech and Language Processing, Spring 2023
• TA, CSC3100 Data Structures, Fall 2022, Fall 2023
• TA, DDA2003 Visual Analytics_L01, Spring 2024