English

Speech Augmentation Based Unsupervised Learning for Keyword Spotting

Sound 2022-05-31 v1 Computation and Language Audio and Speech Processing

Abstract

In this paper, we investigated a speech augmentation based unsupervised learning approach for keyword spotting (KWS) task. KWS is a useful speech application, yet also heavily depends on the labeled data. We designed a CNN-Attention architecture to conduct the KWS task. CNN layers focus on the local acoustic features, and attention layers model the long-time dependency. To improve the robustness of KWS model, we also proposed an unsupervised learning method. The unsupervised loss is based on the similarity between the original and augmented speech features, as well as the audio reconstructing information. Two speech augmentation methods are explored in the unsupervised learning: speed and intensity. The experiments on Google Speech Commands V2 Dataset demonstrated that our CNN-Attention model has competitive results. Moreover, the augmentation based unsupervised learning could further improve the classification accuracy of KWS task. In our experiments, with augmentation based unsupervised learning, our KWS model achieves better performance than other unsupervised methods, such as CPC, APC, and MPC.

Keywords

Cite

@article{arxiv.2205.14329,
  title  = {Speech Augmentation Based Unsupervised Learning for Keyword Spotting},
  author = {Jian Luo and Jianzong Wang and Ning Cheng and Haobin Tang and Jing Xiao},
  journal= {arXiv preprint arXiv:2205.14329},
  year   = {2022}
}

Comments

accepted by WCCI 2022

R2 v1 2026-06-24T11:31:39.801Z