In small-footprint end-to-end keyword spotting, it is often expensive and time-consuming to acquire sufficient labels in various speech scenarios. To overcome this problem, transfer learning leverages the rich knowledge of the auxiliary domain to annotate the unlabeled target data. However, most existing transfer learning methods typically learn a domain-invariant feature representation while ignoring the negative transfer problem. In this paper, we propose a new and general cross-domain keyword spotting framework called selective transfer subspace learning (STSL) that avoid negative transfer and dramatically improve the accuracy for cross-domain keyword spotting by actively selecting appropriate source samples. Specifically, STSL first aligns geometrical relationship and weighted distribution discrepancy to learn a domain-invariant projection subspace. Then, it actively selects appropriate source samples that are similar to the target domain for transfer learning to avoid negative transfer. Finally, we formulate a minimization problem that alternately optimizes the projection subspace and source active selection, giving an effective optimization. Experimental results on 10 groups of cross-domain keyword spotting tasks show that our STSL outperforms some state-of-the-art transfer learning methods and no transfer learning methods.

在小规模端到端关键词识别中，在各种语音场景中获取足够的标签通常既昂贵又耗时。为了克服这个问题，迁移学习利用辅助域的丰富知识来注释未标记的目标数据。然而，大多数现有的迁移学习方法通​​常学习域不变的特征表示，同时忽略负迁移问题。在本文中，我们提出了一种新的通用跨域关键词识别框架，称为选择性迁移子空间学习（STSL），它可以避免负迁移，并通过主动选择适当的源样本来显着提高跨域关键词识别的准确性。具体来说，STSL首先对齐几何关系和加权分布差异来学习域不变的投影子空间。然后，它主动选择与目标域相似的合适源样本进行迁移学习，以避免负迁移。最后，我们制定了一个最小化问题，交替优化投影子空间和源主动选择，给出了有效的优化。10 组跨域关键词识别任务的实验结果表明，我们的 STSL 优于一些最先进的迁移学习方法和无迁移学习方法。