Biography

Xu Li is currently a senior researcher at Tencent ARC Lab, working on speech processing and machine learning.
He obtained the Ph.D. degree in Department of Systems Engineering & Engineering Management at The Chinese University of Hong Kong (CUHK), advised by Prof. Helen Meng.
Before that, he obtained the B.E. degree in Information Science and Technology at University of Science and Technology of China in 2017.

  • The Chinese University of Hong Kong, August 2017 - July 2021
    Ph.D. in Dept. of Systems Engineering and Engineering Management
  • University of Science and Technology of China, July 2013 - June 2017
    B.E. in Dept. of Information Science and Technology

    • Research Interests

  • Speech Synthesis and Voice Conversion
  • Speaker Recognition and Voiceprint Anti-Spoofing Countermeasures
  • Mispronunciation Detection and Diagnosis
  • Machine Learning Algorithms

    • Selected Publications [Google Scholar]

    Journal Papers

  • Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning
    Xu Li*, Haibin Wu*, Andy T. Liu, Zhiyong Wu, Helen Meng and Hung-yi Lee
    in IEEE/ACM Transactions on Audio Speech and Language Processing, 2021
  • Automatic Lexical Stress and Pitch Accent Detection for L2 English Speech using Multi-distribution Deep Neural Networks
    Kun Li, Shaoguang Mao, Xu Li, Zhiyong Wu, Helen Meng
    in Speech Communication, 2018

    • Conference Papers

  • A Hierarchical Speaker Representation Framework for One-shot Singing Voice Conversion
    Xu Li, Shansong Liu and Ying Shan
    in the Proceedings of Interspeech, 2022
  • Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks
    Xu Li, Xixin Wu, Hui Lu, Xunying Liu and Helen Meng
    in the Proceedings of Interspeech, 2021
    [Code]
  • Replay and Synthetic Speech Detection with Res2Net Architecture
    Xu Li, Na Li, Chao Weng, Xunying Liu, Dan Su, Dong Yu and Helen Meng
    in IEEE ICASSP, 2021
    [Code]
  • Adversarial Defense for Automatic Speaker Verification by Cascaded Self-supervised Learning Models
    Xu Li*, Haibin Wu*, Andy T. Liu, Zhiyong Wu, Helen Meng and Hung-yi Lee
    in IEEE ICASSP, 2021
  • Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification
    Xu Li, Na Li, Jinghua Zhong, Xixin Wu, Xunying Liu, Dan Su, Dong Yu and Helen Meng
    in the Proceedings of Interspeech, 2020
  • Adversarial Attacks on GMM i-vector based Speaker Verification Systems
    Xu Li, Jinghua Zhong, Xixin Wu, Jianwei Yu, Xunying Liu and Helen Meng
    in IEEE ICASSP, 2020
    [Code], [Demo]
  • Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification
    Xu Li, Jinghua Zhong, Jianwei Yu, Shoukang Hu, Xixin Wu, Xunying Liu and Helen Meng
    in Speaker Odyssey, 2020
  • Unsupervised Discovery of Non-native Phonetic Patterns in L2 English Speech for Mispronunciation Detection and Diagnosis
    Xu Li, Shaoguang Mao, Xixin Wu, Kun Li, Xunying Liu and Helen Meng
    in the Proceedings of Interspeech, 2018

    • Preprints

  • Deep Segmental Phonetic Posterior-grams based Discovery of Non-categories in L2 English Speech
    Xu Li, Xixin Wu, Xunying Liu and Helen Meng
    arXiv preprint arXiv:2002.00205 (2020)
    [Demo]

    • Professional Activities

  • Journal Reviewer of Transactions on Audio, Speech, and Language Processing; IEEE Transactions on Human-Machine Systems; Journal of Intelligent & Fuzzy Systems
  • Conference Reviewer of ICME 2019; Interspeech 2020; APSIPA ASC 2019, 2020 and 2021; ICASSP 2022

    • Concat Info: xuliustc1306 [at] gmail.com
    Last Updated: Aug. 2nd, 2022