@inproceedings{guo-etal-2025-effective,
    title = "Effective Speaker Diarization Leveraging Multi-task Logarithmic Loss Objectives",
    author = "Guo, Jhih-Rong  and
      Lo, Tien-Hong  and
      Tsao, Yu-Sheng  and
      Lee, Pei-Ying  and
      Hsu, Yung-Chang  and
      Chen, Berlin",
    editor = "Chang, Kai-Wei  and
      Lu, Ke-Han  and
      Yang, Chih-Kai  and
      Tam, Zhi-Rui  and
      Chang, Wen-Yu  and
      Wang, Chung-Che",
    booktitle = "Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)",
    month = nov,
    year = "2025",
    address = "National Taiwan University, Taipei City, Taiwan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/dashboard/2025.rocling-main.17/",
    pages = "140--145",
    ISBN = "979-8-89176-379-1",
    abstract = "End-to-End Neural Diarization (EEND) has undergone substantial development, particularly with powerset classification methods that enhance performance but can exacerbate speaker confusion. To address this, we propose a novel training strategy that complements the standard cross entropy loss with an auxiliary ordinal log loss, guided by a distance matrix of speaker combinations. Our experiments reveal that while this approach yields significant relative improvements of 15.8{\%} in false alarm rate and 10.0{\%} in confusion error rate, it also uncovers a critical trade-off with an increased missed error rate. The primary contribution of this work is the identification and analysis of this trade-off, which stems from the model adopting a more conservative prediction strategy. This insight is crucial for designing more balanced and effective loss functions in speaker diarization."
}