流式日志模型适应中的指标掩盖与 rehearsal 代价
原标题：When Forgetting Looks Like Improvement: Metric Masking in Streaming Diarizer Adaptation and the Price of Rehearsal
AI 摘要
该研究针对流式说话人日志（diarization）模型在少量数据域适应后出现的指标掩盖问题展开诊断。作者将发布的 Streaming Sortformer v2 在 7.5 小时双人对话数据上微调，并在六个语料库上评估，发现域内 DER 显著改善且可迁移到独立语料，但改进并不一致：额外混淆主要来自时间身份一致性受损，而非说话人数目错误。局部重映射诊断显示不同语料库的身份退化模式不同，而 rehearsal 虽能减少退化，却牺牲了跨域迁移性能。
正文节选
When Forgetting Looks Like Improvement: Metric Masking in Streaming Diarizer Adaptation and the Price of Rehearsal Abstract Small-data adaptation can improve speech detection while degrading speaker attribution. We study this discrepancy in a released streaming diarizer adapted on 7.5 h of two-party conversation and evaluated across six corpora. Adaptation substantially improves in-domain diarization performance and transfers to an independent corpus. However, this improvement is not consistent