Research Interests

• Streaming and end-to-end speech recognition
• Speech synthesis and audio language models
• Efficient multimodal training and inference

Selected Publications

For the complete list, please visit my Google Scholar profile.

2026

• Semantic Refinement of Universal Audio Representations through Audio-Description Alignment

  Lejun Min, Junyu Dai, Ruichen Zheng, Xinyue Fan, Yang Xiang, Huaichen Zhang, Xingchen Song, Yufei Shi, Han Zhao, Xiangang Li

  arXiv preprint · 2026 Paper arXiv PDF

• Qwen-Audio-3.0-Gen-Preview Technical Report

  Junyu Dai, Xiaoyue Duan, Xinyue Fan, Yihan Feng, Jingbei Li, Xiangang Li, Yunjia Li, Lejun Min, Yufei Shi, Xingchen Song, Yiran Wang, Cheng Wen, Menglin Wu, Bajian Xiang, Huaicheng Zhang, Han Zhao, Ruichen Zheng

  Technical report · 2026 Paper arXiv PDF

• Harness TTS: Towards Context-Aware Expressive Speech Synthesis with Harness Layer

  Shengfan Shen, Di Wu, Xingchen Song, Dinghao Zhou, Pengyu Cheng, Sixiang Lyu, Jian Luan, Shuai Wang

  arXiv preprint · 2026 Paper arXiv PDF

• F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation

  Dinghao Zhou, Xingchen Song, Di Wu, Pengyu Cheng, Shengfan Shen, Sixiang Lv

  Technical report · 2026 Paper arXiv PDF

• Any2Speech: Borderless Long Speech Synthesis

  Xingchen Song, Di Wu, Dinghao Zhou, Pengyu Cheng, Hongwu Ding, Yunchao He, Jie Wang, Shengfan Shen, Sixiang Lv, Lichun Fan, Hang Su, Yifeng Wang, Shuai Wang, Meng Meng, Jian Luan

  arXiv preprint · 2026 Paper arXiv PDF

• ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching

  Han Zhu, Wei Kang, Liyong Guo, Zengwei Yao, Fangjun Kuang, Weiji Zhuang, Zhaoqing Li, Zhifeng Han, Dong Zhang, Xin Zhang, Xingchen Song, Lingxuan Ye, Long Lin, Daniel Povey

  Findings of ACL · 2026 Paper arXiv PDF

2025

• MiMo-Audio: Audio Language Models are Few-Shot Learners

  Xiaomi LLM-Core Team (including Xingchen Song)

  Full author list

  Xiaomi LLM-Core Team, Dong Zhang, Gang Wang, Jinlong Xue, Kai Fang, Liang Zhao, Rui Ma, Shuhuai Ren, Shuo Liu, Tao Guo, Weiji Zhuang, Xin Zhang, Xingchen Song, Yihan Yan, Yongzhe He, Cici, Bowen Shen, Chengxuan Zhu, Chong Ma, Chun Chen, Heyu Chen, Jiawei Li, Lei Li, Menghang Zhu, Peidian Li, Qiying Wang, Sirui Deng, Weimin Xiong, Wenshan Huang, Wenyu Yang, Yilin Jiang, Yixin Yang, Yuanyuan Tian, Yue Ma, Yue Yu, Zihan Zhang, Zihao Yue, Bangjun Xiao, Bingquan Xia, Bofei Gao, Bowen Ye, Can Cai, Chang Liu, Chenhong He, Chunan Li, Dawei Zhu, Duo Zhang, Fengyuan Shi, Guoan Wang, Hailin Zhang, Hanglong Lv, Hanyu Li, Hao Tian, Heng Qu, Hongshen Xu, Houbin Zhang, Huaqiu Liu, Jiangshan Duo, Jianguang Zuo, Jianyu Wei, Jiebao Xiao, Jinhao Dong, Jun Shi, Junhao Hu, Kainan Bao, Kang Zhou, Linghao Zhang, Meng Chen, Nuo Chen, Peng Zhang, Qianli Chen, Qiantong Wang, Rang Li, Shaohui Liu, Shengfan Wang, Shicheng Li, Shihua Yu, Shijie Cao, Shimao Chen, Shuhao Gu, Weikun Wang, Wenhan Ma, Xiangwei Deng, Xing Yong, Xing Zhang, Xu Wang, Yifan Song, Yihao Zhao, Yingbo Zhao, Yizhao Gao, Yu Cheng, Yu Tu, Yudong Wang, Zhaojun Huang, Zhengju Tang, Zhenru Lin, Zhichao Song, Zhipeng Xu, Zhixian Zheng, Zihan Jiang

  Technical report · 2025 Paper arXiv PDF

• Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding

  Haoran Zhou, Xingchen Song, Brendan Fahy, Qiaochu Song, Binbin Zhang, Zhendong Peng, Anshul Wadhawan, Denglin Jiang, Apurv Verma, Vinay Ramesh, Srivas Prasad, Michele M. Franceschini

  Interspeech · 2025 Paper arXiv PDF

2024

• TouchASP: Elastic Automatic Speech Perception that Everyone Can Touch

  Xingchen Song, Chengdong Liang, Binbin Zhang, Pengshen Zhang, ZiYu Wang, Youcheng Ma, Menglong Xu, Lin Wang, Di Wu, Fuping Pan, Dinghao Zhou, Zhendong Peng

  Technical report · 2024 Paper arXiv PDF

• TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch

  Xingchen Song, Mengtao Xing, Changwei Ma, Shengqiang Li, Di Wu, Binbin Zhang, Fuping Pan, Dinghao Zhou, Yuekai Zhang, Shun Lei, Zhendong Peng, Zhiyong Wu

  Technical report · 2024 Paper arXiv PDF

• U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF

  Xingchen Song, Di Wu, Binbin Zhang, Dinghao Zhou, Zhendong Peng, Bo Dang, Fuping Pan, Chao Yang

  arXiv preprint · 2024 Paper arXiv PDF

2023

• ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs

  Xingchen Song, Di Wu, Binbin Zhang, Zhendong Peng, Bo Dang, Fuping Pan, Zhiyong Wu

  Interspeech · 2023 Paper arXiv PDF

• TrimTail: Low-Latency Streaming ASR with Simple But Effective Spectrogram-Level Length Penalty

  Xingchen Song, Di Wu, Zhiyong Wu, Binbin Zhang, Yuekai Zhang, Zhendong Peng, Wenpeng Li, Fuping Pan, Changbao Zhu

  ICASSP · 2023 Paper arXiv PDF

2022

• WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit

  Binbin Zhang, Di Wu, Zhendong Peng, Xingchen Song, Zhuoyuan Yao, Hang Lv, Lei Xie, Chao Yang, Fuping Pan, Jianwei Niu

  Interspeech · 2022 Paper arXiv PDF

2021

• Non-Autoregressive Transformer ASR with CTC-Enhanced Decoder Input

  Xingchen Song, Zhiyong Wu, Yiheng Huang, Chao Weng, Dan Su, Helen Meng

  ICASSP · 2021 Paper arXiv PDF

2020

• Speech-XLNet: Unsupervised Acoustic Model Pretraining for Self-Attention Networks

  Xingchen Song, Guangsen Wang, Yiheng Huang, Zhiyong Wu, Dan Su, Helen Meng

  Interspeech · 2020 Paper arXiv PDF

Open-Source Projects

• TouchNet

  Personal project · In development

  A native PyTorch library for large-scale text and audio language model training, with multimodal data pipelines, sequence packing, distributed checkpointing, and N-dimensional parallelism.

• FlashCosyVoice

  Personal project

  A lightweight inference engine for CosyVoice, built for distributed offline speech generation. It supports prefix caching, torch compilation, and CUDA graphs in a compact Python implementation.

• S3Tokenizer

  Personal project

  A PyTorch implementation of the supervised semantic speech tokenizer used in CosyVoice, supporting batch and distributed inference, online speech token extraction, and long audio processing.

• WeNet

  Contributor

  A production-oriented toolkit for streaming and non-streaming end-to-end speech recognition. My related publications include WeNet 2.0, TrimTail, ZeroPrompt, and U2++ MoE.

• QwenAudio Toolkits

  Contributor

  A desktop workspace for audio AI models, covering speech recognition, audio enhancement, text normalization, and speech synthesis, with local model runtimes and optional cloud models.

More projects on GitHub

Education

• M.S. in Computer Science and Technology

  Tsinghua University · 2019–2022

  Advisor: Zhiyong Wu

• B.E. in Computer Science and Technology

  Dalian University of Technology · 2015–2019

Experience

• Research Intern @ Microsoft Research Asia (MSRA)

  Speech Group · Dec. 2020–Mar. 2021

  Mispronunciation detection and diagnosis.

  Mentors: Frank K. Soong

• Research Intern @ Tencent AI Lab

  Speech Group · Jun. 2019–Dec. 2020

  Acoustic modeling and end-to-end speech recognition.

  Mentors: Guangsen Wang, Yiheng Huang