Logo image
Back
Discriminatory and orthogonal feature learning for noise robust keyword spotting
Journal article   Open access   Peer reviewed

Discriminatory and orthogonal feature learning for noise robust keyword spotting

Donghyeon Kim, Kyungdeuk Ko, David K. Han, Hanseok Ko and Dong Ho Kim
IEEE signal processing letters, v 29, pp 1-5
2022
DOI: https://doi.org/10.1109/LSP.2022.3203911
url
http://arxiv.org/abs/2210.11519View
SubmittedOpen Access (License Unspecified),  Open

Abstract

Computational modeling Convolution Euclidean distance Feature extraction keyword Spotting Mathematical models Measurement metric learning robustness Training
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.

Metrics

12 Record Views
4 citations in Web of Science
3 citations in Scopus

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Domestic collaboration
International collaboration
Web of Science research areas
Engineering, Electrical & Electronic
Logo image