This tab includes all my academic activities and events.

Presentations & Talks

• 2026

  • 04.10 - Visiting talk @ Duke-Kunshan University, China
    • Audio Security - Where have we been, where are we, and where are we going?
    • (Slides coming soon)

• 2025

  • 09.10 - IJCB 2025 @ Osaka, Japan
    • LENS-DF: Deepfake Detection and Temporal Localization for Long-Form Noisy Speech
  • 06.20 - NII Openhouse 2025 @ Tokyo, Japan
    • 汎用性と頑健性を備えた 音声ディープフェイク検出 (Japanese poster narration only)
  • 04.09 - ICASSP 2025 @ Hyderabad, India
    • Explaining Speaker and Spoof Embeddings via Probing
    • The onsite oral presentation was done by Dr. Md Sahidullah

• 2024

  • 09.25 - BIOSIG 2024 @ Darmstadt, Germany
    • A Preliminary Case Study on Long-Form In-the-Wild Audio Spoofing Detection)
    • The onsite oral presentation was done by Prof. Junichi Yamagishi

• 2023

  • 11.24 - Research briefing @ NII
    • Linking Speaker and Textual Information via Contrastive Learning
  • 10.18 - PhD defense lectio @ UEF
    • Advances in Deep Speaker Verification
  • 06.19 - Self-introduction @ NII
    • Advances in Deep Speaker Verification (mock lectio)
  • 03.30 - Special course in speech security and privacy @ UEF
    • Deep Speaker Verification
  • 02.24 - Weekly Reading Club, Computational Speech Group @ UEF
    • PLDA and Cosine Scoring

• 2022

  • 04.21 - Machine Learning for Speech @ UEF
    • A Short Introduction of Speech Recognition
  • (Yearly) Weekly Reading Club, Computational Speech Group @ UEF
    • 09.16 - Transmission Neural Networks
    • 03.18 - Neuron Shapley
    • 01.28 - Neural Tangent Kernel

• 2021

  • 05.24 - IEEE ISCAS @ Online
    • Learnable MFCCs for Speaker Verification
  • 09.02 - Weekly Seminar, MULTISPEECH @ Inria Nancy
    • Frontend Optimization Methods for Robust Speaker Verification
  • (Yearly) Weekly Reading Club, Computational Speech Group @ UEF
    • 10.29 - A Metric Learning Reality Check
    • 06.04 - VoxCeleb Summary and Updates (ICASSP 2021)
    • 04.09 - Unified Acoustic and Language Modeling
    • 01.15 - Collaborative Learning

• 2019

  • 03.02 - Future of Work @ the Melting Pot, Edinburgh, United Kingdom
    • Artificial Intelligence: Where we will take it to?
    • (Slides cannot be found)

Events

Organizer/Supporter

• 2026
  • RADAR, APSIPA 2026 Grand Challange
• 2023
  • ASVSpoof5
  • Joint Workshop of VoicePersonae and ASVspoof 2023
• 2022
  • Spoofing-aware speaker verification (SaSV) Challenge
• 2021
  • ASVSpoof
  • Spring Weekly Reading Club, Computational Speech Group @ UEF

Participant

• 2022
  • VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22)
• 2021
  • Short-duration Speaker Verification Challenge (SdSVC-21)
• 2020
  • NIST SRE
    • System description
  • Short-duration Speaker Verification Challenge (SdSVC-20)
    • System description

Teaching & Reviewing

Teaching (including TA & guest lecturing)

XJTLU

• Deep Learning: 2026
• Data Structure & Algorithms: 2026
• Computer Architecture and Operating Systems: 2026

UEF

• Special Course in Speech Security and Privacy: 2023
• Artificial Intelligence: 2021, 2022
• Machine Learning for Speech: 2020, 2022

Journal Paper Reviewing

• IEEE Signal Processing Letters
• IEEE (formerly IEEE/ACM) Transactions on Audio, Speech and Language Processing
• IEEE Transactions on Information Forensics and Security
• Neural Networks
• Speech Communication
• ACM Transactions on Intelligent Systems and Technology
• Computer Speech and Language

Conference Paper Reviewing

• AAAI: 2026
• ACL ARR: 2026
• ICLR: 2022, 2023, 2024, 2026
• IEEE ICME: 2026
• ISCA Interspeech: 2024, 2025, 2026
• ISCA SPSC: 2026
• ICML: 2023, 2024, 2025
• IEEE ASRU: 2023, 2025
• IEEE ICASSP: 2023, 2024
• IEEE SLT: 2024