AI 中文总结
针对流式目标说话人提取中稳定性与可塑性难以兼得的问题，提出41k参数锚定快速权重记忆，通过元训练状态动态，在严重不匹配下提升3.0 dB，且开销低于5%。
AI 中文摘要
流式目标说话人提取必须维护一个关于提取对象的表征，而目标可能静音、被干扰掩盖或声学上偏离注册。现有系统通常将这种状态作为存储的嵌入，并通过手工设计的规则进行更新。在22种配置中，包括置信门控和神谕活动门控更新，我们表明这类系统位于稳定性-可塑性边界上：即使完美的目标活动信息也无法将目标缺失的鲁棒性与注册-混合不匹配的适应性结合起来。因此，我们通过闭环流式循环元训练说话人状态动态，使更新器暴露于其自身的污染证据。我们提出的41k参数锚定快速权重（AFW）记忆超越了实测的启发式边界，在严重不匹配下比最佳启发式方法获得3.0 dB的提升，同时在30秒缺失后保持在静态注册的0.9 dB以内，且运行时开销低于5%。门控循环单元（GRU）控制实验确认该增益并非AFW特有，而AFW更小且更具可解释性：在严重不匹配下，其写入残差增长并与目标而非干扰者对齐。代码公开于该https URL。
英文摘要
Streaming target speaker extraction must maintain a representation of whom to extract while the target may fall silent, be masked by interference, or drift acoustically away from enrollment. Existing systems typically hold this state as a stored embedding updated by hand-designed rules. Across 22 configurations, including confidence-gated and oracle-activity-gated updates, we show that this family lies on a stability-plasticity frontier: even perfect target-activity information cannot combine robustness to target absence with adaptation to enrollment-mixture mismatch. We therefore meta-train speaker-state dynamics through the closed streaming loop, exposing the updater to its own contaminated evidence. Our proposed 41k-parameter anchored fast-weights (AFW) memory moves beyond the measured heuristic frontier, gaining 3.0 dB over the best heuristic under severe mismatch while staying within 0.9 dB of static enrollment after 30 s of absence, at under 5% runtime overhead. A gated recurrent unit (GRU) control confirms that the gain is not AFW-specific, while AFW is smaller and more interpretable: under severe mismatch, its write residual grows and aligns with the target rather than the interferer. Code is publicly available at https://github.com/ym2976/anchor-fast-weight.
