Profile

News


Intro

I'm an upcoming PhD student in the MINE-Lab at the University of Notre Dame, working with Prof. Xiangliang Zhang. Prior to joining ND, I received my Master degree from Institute of Automation Chinese Academy of Sciences (CASIA), mentored by Prof. Jianhua Tao and Beijing Jiaotong University (BJTU), advised by Prof. Mangui Liang in 2024, and won the Outstanding M.S. Dissertation Award from the BJTU. During my M.S. study, I worked as a short-term interning student at the UNC Chapel Hill, collaborated with Prof. Huaxiu Yao and Prof. Mohit Bansal.

My research interest includes following topics:
  • Efficient Deep Learning: Continual Learning, Domain Adaptation, Out-of-Distribution
  • Multimodal Learning: Multimodal LLM, Multimodal Information Understanding, and Generation
  • Learning with Real-world Data: Self-supervised Learning and Input Selective Learning

  • For my long-term research goal, I aim to encompass broad research fields to understand humans and impact our real lives through ever-evolving embodied AI systems with multiple agents & modalities. In particular, I've been focusing on tackling practical and real-world challenges in various research domains, including continual learning, multimodal learning (w/ audio, video, language, etc), online/streaming learning, and LLMs.


    Recent Preprints

    (*: equal contribution)


    concept
    [P1] Audio Deepfake Detection: A Survey

    Jiangyan Yi, Chenglong Wang, Jianhua Tao, Xiaohui Zhang, Chuyuan Zhang, and Yan Zhao

    arXiv 2023
    Paper BibTeX


    Publications


    concept
    [C10] RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detection

    Yujie Chen, Jiangyan Yi, Jun Xue, Chenglong Wang, Xiaohui Zhang, Shunbo Dong, Siding Zeng, Jianhua Tao, Lv Zhao, Cunhang Fan

    INTERSPEECH 2024
    Paper BibTeX

    concept
    [C9] Multimodal Representation Learning by Alternating Unimodal Adaptation

    Xiaohui Zhang, Jaehong Yoon, Mohit Bansal, and Huaxiu Yao

    CVPR 2024
    Paper Code BibTeX

    concept
    [J1] The Elastic Orthogonal Weight Modification for Synthetic Audio Detection in Continual Learning

    Xiaohui Zhang, Jiangyan Yi, Jianhua Tao, and Junzuo Zhou

    Journal of Computer Research and Development
    Paper BibTeX

    concept
    [C8] What to remember: Self-adaptive continual learning for audio deepfake detection

    Xiaohui Zhang, Jiangyan Yi, Chenglong Wang, Chuyuan Zhang, Siding Zeng, and Jianhua Tao

    AAAI 2024
    Paper Code BibTeX

    concept
    [C7] Multi-Scale Permutation Entropy for Audio Deepfake Detection

    Chenglong Wang*, Jiayi He*, Jiangyan Yi, Jianhua Tao, Chu Yuan Zhang, Xiaohui Zhang

    ICASSP 2024
    Paper Code BibTeX

    concept
    [C6, W3] Adaptive Fake Audio Detection with Low-Rank Model Squeezing

    Xiaohui Zhang, Jiangyan Yi, Jianhua Tao, Chenlong Wang, Le Xu, Ruibo Fu

    IJCAI 2023 Workshop on Deepfake Audio Detection and Analysis
    IJCAI 2023
    Paper BibTeX

    concept
    [C5, W2] Low-rank Adaptation Method for Wav2vec2-based Fake Audio Detection

    Chenlong Wang, Jiangyan Yi, Xiaohui Zhang Jianhua Tao, Le Xu, Ruibo Fu

    IJCAI 2023 Workshop on Deepfake Audio Detection and Analysis
    IJCAI 2023
    Paper BibTeX

    concept
    [C4, W1] ADD 2023: the Second Audio Deepfake Detection Challenge

    Jiangyan Yi, Jianhua Tao, Ruibo Fu, Xinrui Yan, Chenglong Wang, Tao Wang, Chu Yuan Zhang, Xiaohui Zhang, Yan Zhao, Yong Ren, Le Xu, Junzuo Zhou, Hao Gu, Zhengqi Wen, Shan Liang, Zheng Lian, Shuai Nie, Haizhou Li

    IJCAI 2023 Workshop on Deepfake Audio Detection and Analysis
    IJCAI 2023
    Paper BibTeX

    concept
    [C3] TST: Time-Sparse Transducer for Automatic Speech Recognition

    Xiaohui Zhang, Mangui Liang, Zhengkun Tian, Jiangyan Yi, Jianhua Tao

    CICAI 2023
    Paper BibTeX

    concept
    [C2] Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection

    XiaoHui Zhang, Jiangyan Yi, Chenglong Wang, Chu Yuan Zhang, Jianhua Tao

    ICML 2023
    Paper Code BibTeX

    concept
    [C1] A multilingual framework based on pre-training model for speech emotion recognition

    Zhaohang Zhang, Xiaohui Zhang, Min Guo, Wei-Qiang Zhang, Ke Li, Yukai Huang

    APSIPA 2021
    Paper BibTeX