Hui Lu is now a 4th-year Ph.D. student at the Chinese University of Hong Kong, supervised by Prof. Helen Meng.

Hui Lu received his M.Eng degree in Computer Technology from Tsinghua University in 2020, supervised by Prof. Zhiyong Wu. Before that, he obtained his B.Eng. degree in Communication Engineering from Tongji University in 2017.

His research interests lie in unsupervised learning of disentangled speech representation and personalized speech generation.

[Google Scholar][Github]

Selected Publications

Journal Papers

  • Hiformer: Sequence Modeling Networks with Hierarchical Attention Mechanisms
    Xixin Wu, Hui Lu, Kun Li, Zhiyong Wu, Xunying Liu, Helen Meng
    In IEEE/ACM Transactions on Audio Speech and Language Processing, 2023
  • Exemplar-Based Emotive Speech Synthesis
    Xixin Wu, Yuewen Cao, Hui Lu, Songxiang Liu, Shiyin Kang, Zhiyong Wu, Xunying Liu, Helen Meng
    In IEEE/ACM Transactions on Audio Speech and Language Processing, 2021
  • Speech Emotion Recognition using Sequential Capsule Networks
    Xixin Wu, Yuewen Cao, Hui Lu, Songxiang Liu, Disong Wang, Zhiyong Wu, Xunying Liu, Helen Meng
    In IEEE/ACM Transactions on Audio Speech and Language Processing, 2021

    • Conference Papers

  • SpeechTripleNet: End-to-End Disentangled Speech Representation Learning for Content, Timbre and Prosody, [demo][code]
    Hui Lu, Xixin Wu, Zhiyong Wu, and Helen Meng.
    In ACMMM 2023
  • Disentangled Speech Representation Learning for One-Shot Cross-Lingual Voice Conversion Using ß-VAE, [demo][code]
    Hui Lu, Disong Wang, Xixin Wu, Zhiyong Wu, Xunying Liu, Helen Meng.
    In SLT 2022
  • VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis, [demo][code]
    Hui Lu, Zhiyong Wu, Xixin Wu, Xu Li, Shiyin Kang, Xunying Liu, Helen Meng
    In Interspeech 2021
  • One-Shot Voice Conversion with Global Speaker Embeddings, [demo]
    Hui Lu, Zhiyong Wu, Dongyang Dai, Runnan Li, Shiyin Kang, Jia Jia, Helen Meng
    In Interspeech 2019.
  • A Compact Framework for Voice Conversion Using Wavenet Conditioned on Phonetic Posteriorgrams, [demo]
    Hui Lu, Zhiyong Wu, Runnan Li, Shiyin Kang, Jia Jia, Helen Meng
    In ICASSP 2019


    • Contact info

    E-mail: luhui@se.cuhk.edu.hk