AI 中文总结
针对低资源声学任务中不完美教师带来的偏差问题，提出边界锚定质量分割蒸馏（BA-MPD），通过校正教师预测并分离蒸馏，提升学生泛化性能，实验验证其优于基线并适应跨预算场景。
AI 中文摘要
知识蒸馏（KD）通过用固定教师网络的软化预测分布丰富独热监督，从而改善低资源声学学习。然而，使用有限或不平衡标注训练的教师可能会产生有偏分布，其组成部分并非均匀可靠。尽管该分布仍可编码有用知识，但直接的全分布匹配也可能传递教师引入的偏差，从而扭曲学生的决策边界并降低其泛化性能。为解决这一局限，我们提出边界锚定质量分割蒸馏（BA-MPD），一种基于logit的蒸馏目标，由边界锚定校正（BAC）和质量分割蒸馏（MPD）组成。BAC通过将真实标签与教师最高预测集合中排名最低的条目交换，解决该集合中缺失真实标签的问题，从而保持集合的质量和不确定性不变。MPD随后通过分离的损失蒸馏这一校正后的分布，这些损失在集合内强制关系一致性，平衡高置信度与低置信度组之间的质量，并对低置信度依赖进行加权。最终，BAC和MPD共同抑制有害的排名错误和嘈杂的低置信度细节，同时保留所有有用的教师信息。在两个声学基准上的多个标签预算实验表明，BA-MPD持续优于监督学习基线和普通KD，同时与强logit-based KD基线保持竞争力。跨预算结果进一步表明，当教师和学生模型使用不匹配的标签预算时，BA-MPD仍然有效，展示了其在监督差距中利用不完美教师的能力。实现可在https://this URL获取。
英文摘要
Knowledge distillation (KD) improves low-resource acoustic learning by enriching one-hot supervision with the softened predictive distribution of a fixed teacher network. However, a teacher trained with limited or imbalanced annotations may produce a biased distribution whose components are not uniformly reliable. Although this distribution can still encode useful knowledge, direct full-distribution matching may also transfer teacher-induced biases, thereby distorting the student's decision boundary and degrading its generalization performance. To address this limitation, we propose Boundary-Anchored Mass-Partitioned Distillation (BA-MPD), a logit-based distillation objective composed of Boundary-Anchored Correction (BAC) and Mass-Partitioned Distillation (MPD). BAC addresses missing ground-truth labels in the set of the teacher's top predictions by swapping the true label for the lowest-ranked entry of the set, thus keeping the mass and uncertainty of the set unchanged. MPD then distills this corrected distribution through separate losses that enforce relational consistency within the set, balance the mass between high- and low-confidence groups, and weight lower-confidence dependencies. Ultimately, BAC and MPD together suppress harmful ranking errors and noisy low-confidence details, while retaining all useful teacher information. Experiments on two acoustic benchmarks under multiple label budgets show that BA-MPD consistently improves over supervised-learning baselines and vanilla KD while remaining competitive with strong logit-based KD baselines. Cross-budget results further show that BA-MPD remains effective when the teacher and student models use mismatched label budgets, demonstrating its ability to exploit imperfect teachers across supervision gaps. Implementation available at https://github.com/ShuanglinLi/BA-MPD.
