About Me

Hi! I’m Haibin Wu. I am currently a third-year Ph.D. student at the college of Electrical Engineering and Computer Science (EECS) at National Taiwan University (NTU). I am a member of the Speech Processing Lab, working with Prof. Hung-yi Lee and Prof. Lin-shan Lee in the area of machine learning and speech processing. I mainly work on speaker verification and anti-spoofing. By the way. I was fortunate enough to be funded by a Google PhD Fellowship. I’m a main contributor for S3PRL with 1.5k+ github stars. I also like photography very much (please see my homepage).

I am now looking for full-time and internship jobs. If you have openings, please contact me and I really appreciate it.

Publications

  • Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection
    Xuanjun Chen, Haibin Wu, Helen Meng, Hung-yi Lee, Jyh-Shing Roger Jang
    SLT 2023
    [ pdf]

  • SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning
    SLT 2023
    Tzu-hsun Feng, Annie Dong, Ching-Feng Yeh, Shu-wen Yang, Tzu-Quan Lin, Jiatong Shi, Kai-Wei Chang, Zili Huang, Haibin Wu, etc.
    [ pdf]

  • Spoofing-Aware Speaker Verification by Multi-Level Fusion
    Haibin Wu, Lingwei Meng, Jiawen Kang, etc.
    Interspeech 2022
    [ pdf]

  • MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification
    Yang Zhang, Zhiqiang Lv, Haibin Wu, etc.
    Interspeech 2022
    [ pdf]

  • Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion
    Haibin Wu, Jiawen Kang, Lingwei Meng, etc.
    Odyssey 2022
    [ pdf]

  • Partially Fake Audio Detection by Self-Attention-Based Fake Span Discovery
    Haibin Wu, Heng-Cheng Kuo, Naijun Zheng, Kuo-Hsuan Hung, Hung-Yi Lee, Yu Tsao, Hsin-Min Wang, Helen Meng
    ICASSP 2022
    [ pdf | video]

  • Adversarial Sample Detection for Speaker Verification by Neural Vocoders
    Haibin Wu, Po-chun Hsu, Ji Gao, Shanshan Zhang, Shen Huang, Jian Kang, Zhiyong Wu, Helen Meng, Hung-yi Lee
    ICASSP 2022
    [ pdf | Github | video]

  • Characterizing the adversarial vulnerability of speech self-supervised learning
    Haibin Wu, Bo Zheng, Xu Li, Xixin Wu, Hung-yi Lee, Helen Meng
    ICASSP 2022
    [ pdf | video]

  • The CUHK-TENCENT speaker diarization system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge
    Naijun Zheng, Na Li, Xixin Wu, Lingwei Meng, Jiawen Kang, Haibin Wu, Chao Weng, Dan Su, Helen Meng
    ICASSP 2022
    [ pdf]

  • Voting for the right answer: Adversarial defense for speaker verification
    Haibin Wu, Yang Zhang, Zhiyong Wu, Dong Wang, Hung-yi Lee
    Interspeech 2021
    [ pdf | Github]

  • Adversarial defense for automatic speaker verification by cascaded self-supervised learning models
    Haibin Wu, Xu Li, Andy T. Liu, Zhiyong Wu, Helen Meng, Hung-yi Lee
    ICASSP 2021
    [ pdf ]

  • Defense for Black-box Attacks on Anti-spoofing Models by Self-Supervised Learning
    Haibin Wu, AT Liu, H Lee
    Interspeech 2020
    [ pdf | video ]

  • Defense against adversarial attacks on spoofing countermeasures of ASV
    Haibin Wu, Songxiang Liu, Helen Meng, Hung-yi Lee
    ICASSP 2020
    [ pdf ]

  • Simplified Granger causality map for data-driven root cause diagnosis of process disturbances
    Y Liu, HS Chen, Haibin Wu, Y Dai, Y Yao, Z Yan
    Journal of Process Control
    [ pdf]

  • Adversarial attacks on spoofing countermeasures of automatic speaker verification
    S Liu, H Wu, H Lee, H Meng
    ASRU 2019
    [ pdf ]

  • Multiview Learning for Subsurface Defect Detection in Composite Products: A Challenge on Thermographic Data Analysis
    Haibin Wu, K Zheng, S Sfarra, Y Liu, Y Yao
    IEEE Transactions on Industrial Informatics
    [ pdf ]

  • Physically Consistent Soft-Sensor Development Using Sequence-to-Sequence Neural Networks
    Cheng-Hung Chou (co-first), Haibin Wu (co-first), Jia-Lin Kang, David Shan-Hill Wong, Yuan Yao, etc.
    IEEE Transactions on Industrial Informatics
    [ pdf ]

  • Process Monitoring Using a Sequence to Sequence Model
    H Wu, CH Chou, Y Yao, DSH Wong, Y Liu
    DDCLS 2019
    [ pdf ]

  • RIIT: Rethinking the Importance of Implementation Tricks in Multi-Agent Reinforcement Learning
    J Hu, H Wu, SA Harding, S Liao
    Preprint.
    [ pdf ]

  • QR-MIX: Distributional Value Function Factorisation for Cooperative Multi-Agent Reinforcement Learning
    Jian Hu, Seth Austin Harding, Haibin Wu, Siyue Hu, Shih-wei Liao
    Preprint.
    [ pdf ]

Research Experience

  • Applied scientist intern at Amazon Sep 2022 - present

  • Research scientist intern at Meta May 2022 - Aug 2022

  • Visiting Student at the Chinese University of Hong Kong May 2021 - April 2022

  • Visiting Student at SIGS of Tsinghua University Aug. 2020 - May 2021

  • Intern at Tencent Jan. 2021 - May 2021

Challenge

Honers

  • Interspeech travel grant Interspeech 2022

  • Appier Scholarship Appier 2022

  • Google PHD Fellowship Google 2021

  • Advanced Speech Technologies Scholarship NTU EECS 2020

  • Academic Achievement Award NCTU EECS 2019

  • Academic Achievement Award NCTU EECS 2018

  • National Scholarship Chinese Ministry of Education 2014

Teaching