解决关键词识别中稀有词与常见噪声的不平衡问题
ImKWS: Test-Time Adaptation for Keyword Spotting with Class Imbalance
- 将熵最小化分为奖励与惩罚分支，分别控制更新强度
- 在谷歌语音命令数据集上实现稳定适配，准确率显著提升
- 适合在无标注测试数据下优化语音助手关键词识别
关键词识别（KWS）用于语音助手中的词语检测，但环境噪声常导致准确率下降。标准适应方法需原始或带标签音频，而测试时自适应（TTA）仅使用无标签测试音频，突破数据限制。然而，现有方法难以应对稀有关键词与高频背景音之间的严重类别不平衡问题，导致标准熵最小化过于自信且严重偏向常见背景类。为此，本文提出名为ImKWS的TTA方法：将熵过程拆分为奖励分支与惩罚分支，分别设置独立更新强度；同时通过多组音频变换的一致性约束，确保模型更新稳定。在谷歌语音命令数据集上的实验表明，ImKWS在真实不平衡场景下实现了可靠的自适应性能。代码已开源。
原文摘要 · Abstract (English)
Keyword spotting (KWS) identifies words for voice assistants, but environmental noise frequently reduces accuracy. Standard adaptation fixes this issue and strictly requires original or labeled audio. Test-time adaptation (TTA) solves this data constraint using only unlabeled test audio. However, current methods fail to handle the severe imbalance between rare keywords and frequent background sounds. Consequently, standard entropy minimization becomes overconfident and heavily biased toward the frequent background class. To overcome this problem, we propose a TTA method named ImKWS. Our approach splits the entropy process into a reward branch and a penalty branch with separate update strengths. Furthermore, we enforce consistency across multiple audio transformations to ensure stable model updates. Experiments on the Google Speech Commands dataset indicate ImKWS achieves reliable adaptation in realistic imbalanced scenarios. The code is available on GitHub.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。