English

The DKU System Description for The Interspeech 2021 Auto-KWS Challenge

Audio and Speech Processing 2021-04-13 v1

Abstract

This paper introduces the system submitted by the DKU-SMIIP team for the Auto-KWS 2021 Challenge. Our implementation consists of a two-stage keyword spotting system based on query-by-example spoken term detection and a speaker verification system. We employ two different detection algorithms in our proposed keyword spotting system. The first stage adopts subsequence dynamic time warping for template matching based on frame-level language-independent bottleneck feature and phoneme posterior probability. We use a sliding window template matching algorithm based on acoustic word embeddings to further verify the detection from the first stage. As a result, our KWS system achieves an average score of 0.61 on the feedback dataset, which outperforms the baseline1 system by 0.25.

Keywords

Cite

@article{arxiv.2104.04993,
  title  = {The DKU System Description for The Interspeech 2021 Auto-KWS Challenge},
  author = {Yechen Wang and Yan Jia and Murong Ma and Zexin Cai and Ming Li},
  journal= {arXiv preprint arXiv:2104.04993},
  year   = {2021}
}

Comments

5 pages, 1 figures, submitted to INTERSPEECH

R2 v1 2026-06-24T01:03:07.635Z