Discriminatory and Orthogonal Feature Learning for Noise Robust Keyword Spotting

Donghyeon Kim, Kyungdeuk Ko, David K. Han, Hanseok Ko

Research output: Contribution to journalArticlepeer-review

Abstract

Keyword Spotting (KWS) is an essential component in a smart device for alerting the system when a user prompts it with a command. As these devices are typically constrained by computational and energy resources, the KWS model should be designed with a small footprint. In our previous work, we developed lightweight dynamic filters which extract a robust feature map within a noisy environment. The learning variables of the dynamic filter are jointly optimized with KWS weights by using Cross-Entropy (CE) loss. CE loss alone, however, is not sufficient for high performance when the SNR is low. In order to train the network for more robust performance in noisy environments, we introduce the LOw Variant Orthogonal (LOVO) loss. The LOVO loss is composed of a triplet loss applied on the output of the dynamic filter, a spectral norm-based orthogonal loss, and an inner class distance loss applied in the KWS model. These losses are particularly useful in encouraging the network to extract discriminatory features in unseen noise environments.

Original languageEnglish
Pages (from-to)1913-1917
Number of pages5
JournalIEEE Signal Processing Letters
Volume29
DOIs
Publication statusPublished - 2022

Keywords

  • Keyword Spotting
  • metric learning
  • robustness

ASJC Scopus subject areas

  • Signal Processing
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Discriminatory and Orthogonal Feature Learning for Noise Robust Keyword Spotting'. Together they form a unique fingerprint.

Cite this