Cross-Domain Few-Shot Open-Set Keyword Spotting Using Keyword Adaptation and Prototype Reprojection

Mingru Yang; Qianhua He; Jinxin Huang; Yongqiang Chen; Zunxian Liu; Yanxiong Li

ICASSP 2025accepted0 citations

Cross-Domain Few-Shot Open-Set Keyword Spotting Using Keyword Adaptation and Prototype Reprojection

Mingru Yang, Qianhua He, Jinxin Huang, Yongqiang Chen, Zunxian Liu, Yanxiong Li

Abstract

Personalized keyword spotting (KWS) with few enrollment utterances remains an important problem over years. KWS remains a challenging task due to the following factors, including the scarcity of enrollment samples, speech variation in the open-set scenarios, and distributional gap between source and target domains. In this paper, we formulate a KWS task of Cross-Domain Few-Shot Open-Set (CD-FSOS) and propose a dedicated framework Adapt-KWS to bridge the distribution gap between the source domain and target open-set domain with quite limited enrollment data. The proposed Adapt-KWS consists of a set of Custom-Keyword Adapters (CKAs) and a Prototype Reprojection Module (PRM). CKAs enable the efficient adaptation to new target tasks with limited training samples, aiming to improve cross-domain generalization. PRM reprojects the support prototypes into the query embedding space to enhance their alignment, mitigating the potential covariate shift between open-set queries and enrollments. Experimental results demonstrate the effectiveness of our framework and proposed modules on multiple datasets. Code will be available at: https://github.com/Raynaming/CD-FSOS-KWS.

BibTeX

@inproceedings{icassp2025_crossdomainfewsh,
  title = {Cross-Domain Few-Shot Open-Set Keyword Spotting Using Keyword Adaptation and Prototype Reprojection},
  author = {Mingru Yang and Qianhua He and Jinxin Huang and Yongqiang Chen and Zunxian Liu and Yanxiong Li},
  booktitle = {ICASSP 2025},
  year = {2025}
}