publications

2025

  1. Interspeech
    Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations
    T. Aleksandra Ma, Sile Yin, Li-Chia Yang, and 1 more author
    In Interspeech 2025
  2. WASPAA
    Real-Time System for Audio-Visual Target Speech Enhancement
    T. Aleksandra Ma, Sile Yin, Li-Chia Yang, and 1 more author
    In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) Demonstrations 2025
  3. ECIR
    Uncertainty Estimation in the Real World: A Study on Music Emotion Recognition
    Karn N Watcharasupat, Yiwei Ding, T Aleksandra Ma, and 2 more authors
    In European Conference on Information Retrieval 2025
  4. arXiv
    Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction
    Yusong Wu, Stephen Brade, T. Aleksandra Ma, and 6 more authors
    2025

2024

  1. AES
    Music auto-tagging in the long tail: A few-shot approach
    T. Aleksandra Ma, and Alexander Lerch
    In Audio Engineering Society Convention NY 2024 2024

2026

  1. IUI
    Work Under Review about Agents in Concerts
    Stephen Brade, T. Aleksandra Ma, Lancelot Blanchard, and 3 more authors
    2026