Speech and Audio Models | Field

Senior Algorithm Expert in Alibaba Tongyi Lab's Language Technology Lab and Qwen Team member whose work focuses on multilingual large language models and machine translation.

Research scientist at Tongyi Lab, Alibaba Group, working on multimodal large language models, machine reasoning, and efficient learning.

Junyang Lin (Justin Lin) is a researcher and open-source maintainer known for the Qwen family of models. His public profiles list interests in LLMs, AI agents, multimodal learning, long-horizon reasoning, world models, and reinforcement learning; multiple March 2026 news reports said he stepped down from the Qwen tech lead role.

Jin Xu's homepage says he leads the audio group at Qwen Team, Alibaba, working on audio understanding, real-time multimodal interaction, speech synthesis, general audio synthesis, and audio-centered chat models. He previously completed a Ph.D. at IIIS, Tsinghua University and received a BSc in 2018 from Beijing University of Posts and Telecommunications.

Jingren Zhou is Chief Technology Officer of Alibaba Cloud. Public speaker biographies describe him as a computer scientist and entrepreneur whose work includes large-scale AI and cloud systems.

Furu Wei is a Distinguished Scientist and Chief Scientist of Microsoft Research Asia, listed on Microsoft Research and connected in LLMpeople to Microsoft technical reports including Kosmos, VALL-E, BitNet, and Multilingual E5.

Alibaba Qwen report author whose DBLP profile identifies an Alibaba Group affiliation and Qwen technical report authorship.

Jinyu Li is a report-backed author in the LLMpeople atlas, connected through 3 technical reports.

Long Zhou is a report-backed author in the LLMpeople atlas, connected through 3 technical reports.

Sanyuan Chen is a report-backed author in the LLMpeople atlas, connected through 3 technical reports.

Sheng Zhao is a report-backed author in the LLMpeople atlas, connected through 3 technical reports.

Shujie Liu is a report-backed author in the LLMpeople atlas, connected through 3 technical reports.

Yanqing Liu is a report-backed author in the LLMpeople atlas, connected through 3 technical reports.

Chengyi Wang is a report-backed author in the LLMpeople atlas, connected through 2 technical reports.

Hongkun Hao is a report-backed author in the LLMpeople atlas, connected through 2 technical reports.

Huaming Wang is a report-backed author in the LLMpeople atlas, connected through 2 technical reports.

Lei He is a report-backed author in the LLMpeople atlas, connected through 2 technical reports.

Researcher at Kyutai and coauthor of the Moshi: a speech-text foundation model for real-time dialogue.

Xiong Wang is a report-backed author in the LLMpeople atlas, connected through 2 technical reports.

Yu Wu is a report-backed author in the LLMpeople atlas, connected through 2 technical reports.

Zhifang Guo is a report-backed author in the LLMpeople atlas, connected through 2 technical reports.

Zhuo Chen is a report-backed author in the LLMpeople atlas, connected through 2 technical reports.

Ziqiang Zhang is a report-backed author in the LLMpeople atlas, connected through 2 technical reports.

Zishan Guo is a report-backed author in the LLMpeople atlas, connected through 2 technical reports.

Research scientist in Tongyi Lab whose public profile highlights work on speech processing, machine learning, and multimodal large language models.

Alexandre Défossez is a report-backed author in the LLMpeople atlas, connected through Continuous Audio Language Models.

Axel Roebel is a report-backed author in the LLMpeople atlas, connected through Continuous Audio Language Models.

Bin Zhang is a report-backed author in the LLMpeople atlas, connected through Qwen3-TTS Technical Report.

Boyong Wu is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Chao Yan is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Dake Guo is a report-backed author in the LLMpeople atlas, connected through Qwen3-TTS Technical Report.

Daxin Jiang is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Fei Tian is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Gang Yu is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Guoqiang Hu is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Hangrui Hu is a report-backed author in the LLMpeople atlas, connected through Qwen3-TTS Technical Report.

Li Xie is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Neil Zeghidour is a report-backed author in the LLMpeople atlas, connected through Continuous Audio Language Models.

Pengfei Tan is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Peng Yang is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Shuchang Zhou is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Simon Rouard is a report-backed author in the LLMpeople atlas, connected through Continuous Audio Language Models.

Ting He is a report-backed author in the LLMpeople atlas, connected through Qwen3-TTS Technical Report.

Xiangyu (Tony) Zhang is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Xiangyu Zhang is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Xian Shi is a report-backed author in the LLMpeople atlas, connected through Qwen3-ASR Technical Report.

Xinfa Zhu is a report-backed author in the LLMpeople atlas, connected through Qwen3-TTS Technical Report.

Xuerui Yang is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Xu Tan is a report-backed author in the LLMpeople atlas, connected through VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers.

Yao Qian is a report-backed author in the LLMpeople atlas, connected through VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers.

Yu Xi is a report-backed author in the LLMpeople atlas, connected through Qwen3-ASR Technical Report.

Yuxin Zhang is a report-backed author in the LLMpeople atlas, connected through Step-Audio-EditX Technical Report.

Ziyue Jiang is a report-backed author in the LLMpeople atlas, connected through Qwen3-TTS Technical Report.

Baosong Yang

Xinyu Zhang

Junyang Lin

Jin Xu

Jingren Zhou

Furu Wei

Pei Zhang

Jinyu Li

Long Zhou

Sanyuan Chen

Sheng Zhao

Shujie Liu

Yanqing Liu

Chengyi Wang

Hongkun Hao

Huaming Wang

Lei He

Manu Orsini

Xiong Wang

Yu Wu

Zhifang Guo

Zhuo Chen

Ziqiang Zhang

Zishan Guo

Yongqi Wang

Alexandre Défossez

Axel Roebel

Bin Zhang

Boyong Wu

Chao Yan

Dake Guo

Daxin Jiang

Fei Tian

Gang Yu

Guoqiang Hu

Hangrui Hu

Li Xie

Neil Zeghidour

Pengfei Tan

Peng Yang

Shuchang Zhou

Simon Rouard

Ting He

Xiangyu (Tony) Zhang

Xiangyu Zhang

Xian Shi

Xinfa Zhu

Xuerui Yang

Xu Tan

Yao Qian

Yu Xi

Yuxin Zhang

Ziyue Jiang