Zhizheng Wu武执政

Associate Professor · CUHK-Shenzhen副教授 · 香港中文大学（深圳）

Zhizheng Wu武执政

I work on speech and audio AI, and build open-source tools, datasets, and community challenges that others can build on. 研究语音与音频人工智能，长期投入开源：做工具、建数据集、办评测，让更多人能在此基础上继续往前走。

Portrait of Zhizheng Wu

Media媒体报道

Interview with Shenzhen Satellite TV深圳卫视专访 Play video · 18 minutes · in Chinese点击播放 · 18 分钟
On voice interaction, emotion recognition, and how we should live with AI, for the programme 科创最前沿, November 2026. Watch on Bilibili做客深圳卫视《科创最前沿》：从语音交互、情绪识别，聊到人该怎样与 AI 相处。2026 年 11 月 · 去 B 站观看

Research研究方向

  • Speech generation语音生成

    Zero-shot text-to-speech, voice imitation, and singing voice generation that can be controlled and scaled.零样本语音合成、声音克隆与歌声生成，追求可控、好用、能规模化。

    MaskGCT · Metis · Vevo and Vevo2 · FlexiVoice · NaturalSpeech 3 · FlexiVoice · SpeechJudge

  • Speech language models语音大模型

    How well speech language models reason and understand, and how to judge generated speech the way people do.让语音大模型真正听得懂、会推理，并探索如何像人一样评判合成语音的好坏。

    FlexiSLM · SD-Eval · TARS · AURAL · ConvexLLM · EvoAudio · Jarvis

  • Speech tokenizers and neural codecs语音表征与神经编解码

    Compact, low-frame-rate representations of speech that language models can read and write.把语音压成紧凑、低帧率的离散表示，让大模型读得懂、写得出。

    FlexiCodec · TaDiCodec · DualCodec · TASLA

  • Trustworthy audio AI音频安全与可信 AI

    Spoofing and deepfake detection, adversarial attacks on speaker verification, spoken misinformation, and privacy.伪造语音检测、声纹系统的对抗攻防、语音虚假信息识别与隐私保护。

    ASVspoof · AdvSV · SpMis · VoxPrivacy · VoxSafeBench

All publications查看全部论文 · Research group了解团队

Representative papers代表论文

  1. FlexiSLM: A Spoken Language Model with Dynamic and Controllable Frame Rates

    Jiaqi Li, Chaoren Wang, Xiaohai Tian, Mingjie Chen, Xinyu Liang, Xu Li, Yufan Lin, Junwen Qiu, Jun Zhang, Lu Lu, Zhizheng Wu

    Conference会议 EMNLP 2026

  2. Vevo2: A Unified and Controllable Framework for Speech and Singing Voice Generation

    Xueyao Zhang, Junan Zhang, Yuancheng Wang, Chaoren Wang, Yuanzhe Chen, Dongya Jia, Zhuo Chen, Zhizheng Wu

    Journal期刊 IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2026

  3. MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer

    Yuancheng Wang, Haoyue Zhan, Liwei Liu, Ruihong Zeng, Haotian Guo, Jiachen Zheng, Qiang Zhang, Xueyao Zhang, Shunsi Zhang, Zhizheng Wu

    Conference会议 ICLR 2025

  4. Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation

    Haorui He, Zengqiang Shang, Chaoren Wang, Xuyuan Li, Yicheng Gu, Hua Hua, Liwei Liu, Chen Yang, Jiaqi Li, Peiyang Shi, Yuancheng Wang, Kai Chen, Pengyuan Zhang, Zhizheng Wu

    Conference会议 IEEE Spoken Language Technology Workshop (SLT) 2024

  5. Spoofing and Countermeasures for Speaker Verification: A Survey

    Zhizheng Wu, Nicholas Evans, Tomi Kinnunen, Junichi Yamagishi, Federico Alegre, Haizhou Li

    Journal期刊 Speech Communication, 66, pp. 130–153, 2015

All publications查看全部论文

About个人简介

Zhizheng Wu is an Associate Professor at The Chinese University of Hong Kong, Shenzhen. He received his Ph.D. from Nanyang Technological University and has held positions at Meta (formerly Facebook), Apple, the University of Edinburgh, and Microsoft Research Asia.

Professor Wu has initiated several open-source projects, including Merlin, Amphion, and Emilia. He also initiated and organized the first ASVspoof Challenge and the first Voice Conversion Challenge, and served as an organizer of the Blizzard Challenge 2019.

He currently serves on the editorial boards of IEEE/ACM Transactions on Audio, Speech, and Language Processing and IEEE Signal Processing Letters. He was the General Chair of the IEEE Spoken Language Technology Workshop 2024 and will serve as the General Chair of the IEEE Conference on Artificial Intelligence 2027.

武执政，香港中文大学（深圳）副教授，博士毕业于新加坡南洋理工大学。加入港中大（深圳）之前，曾在 Meta、苹果、爱丁堡大学和微软亚洲研究院从事研究与研发工作。

他是 Merlin、Amphion、Emilia 等开源项目的发起人，也是首届 ASVspoof 声纹防伪挑战赛和首届语音转换挑战赛（Voice Conversion Challenge）的发起人与组织者，并参与组织了 Blizzard Challenge 2019。

目前担任 IEEE/ACM Transactions on Audio, Speech, and Language Processing 和 IEEE Signal Processing Letters 编委；曾任 IEEE SLT 2024 大会主席，并将出任 IEEE CAI 2027 大会主席。

Open source开源项目

  • Amphion An open-source toolkit for audio, music, and speech generation.音频、音乐与语音生成的一站式开源工具包。
  • Emilia A large-scale multilingual dataset for speech generation.大规模多语种语音生成数据集。
  • Merlin An open-source neural-network speech synthesis toolkit.开源的神经网络语音合成系统。

Challenges国际评测与挑战赛

  • ASVspoof Initiated and organized the first challenge on speaker verification spoofing and countermeasures.发起并组织首届比赛，聚焦声纹识别的伪造攻击与防御。
  • Voice Conversion Challenge语音转换挑战赛（Voice Conversion Challenge） Initiated and organized the first edition.发起并组织首届比赛。
  • Blizzard Challenge 2019 Organizer.担任组织者。

Service学术服务

  • General Chair大会主席 IEEE Conference on Artificial Intelligence 2027 (upcoming)IEEE Conference on Artificial Intelligence 2027（筹办中）
    IEEE Spoken Language Technology Workshop 2024
  • Editorial board编委 IEEE/ACM Transactions on Audio, Speech, and Language Processing
    IEEE Signal Processing Letters

Contact联系方式

Writing about one of these? The buttons start an email with the subject filled in.来信请按需选择，点一下就能发邮件，主题已经帮你填好。

Room 715, Teaching Complex C
The Chinese University of Hong Kong, Shenzhen
Shenzhen, China广东省深圳市龙岗区龙翔大道 2001 号
香港中文大学（深圳）教学楼 C 栋 715 室