Query-By-Example Keyword Spotting System Using Multi-Head Attention and Soft-triple Loss

Jinmiao Huang; Waseem Gharbieh; Han Suk Shim; Eugene Kim

ICASSP 2021accepted0 citations

Query-By-Example Keyword Spotting System Using Multi-Head Attention and Soft-triple Loss

Jinmiao Huang, Waseem Gharbieh, Han Suk Shim, Eugene Kim

Abstract

This paper proposes a neural network architecture for tackling the query-by-example user-defined keyword spotting task. A multi-head attention module is added on top of a multi-layered GRU for effective feature extraction, and a normalized multi-head attention module is proposed for feature aggregation. We also adopt the softtriple loss - a combination of triplet loss and softmax loss - and showcase its effectiveness. We demonstrate the performance of our model on internal datasets with different languages and the public Hey-Snips dataset. We compare the performance of our model to a baseline system [1] and conduct an ablation study to show the benefit of each component in our architecture. The proposed work shows solid performance while preserving simplicity.

BibTeX

@inproceedings{icassp2021_querybyexampleke,
  title = {Query-By-Example Keyword Spotting System Using Multi-Head Attention and Soft-triple Loss},
  author = {Jinmiao Huang and Waseem Gharbieh and Han Suk Shim and Eugene Kim},
  booktitle = {ICASSP 2021},
  year = {2021}
}