English

A Separable Temporal Convolution Neural Network with Attention for Small-Footprint Keyword Spotting

Sound 2021-09-02 v1 Audio and Speech Processing

Abstract

Keyword spotting (KWS) on mobile devices generally requires a small memory footprint. However, most current models still maintain a large number of parameters in order to ensure good performance. To solve this problem, this paper proposes a separable temporal convolution neural network with attention, it has a small number of parameters. Through the time convolution combined with attention mechanism, a small number of parameters model (32.2K) is implemented while maintaining high performance. The proposed model achieves 95.7% accuracy on the Google Speech Commands dataset, which is close to the performance of Res15(239K), the state-of-the-art model in KWS at present.

Keywords

Cite

@article{arxiv.2109.00260,
  title  = {A Separable Temporal Convolution Neural Network with Attention for Small-Footprint Keyword Spotting},
  author = {Shenghua Hu and Jing Wang and Yujun Wang and Lidong Yang and Wenjing Yang},
  journal= {arXiv preprint arXiv:2109.00260},
  year   = {2021}
}

Comments

arXiv admin note: text overlap with arXiv:2108.12146

R2 v1 2026-06-24T05:35:22.210Z