Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Prototypical Knowledge Distillation for Noise Robust Keyword Spotting

Authors
Kim, DonghyeonKim, GwantaeLee, BokyeungKo, Hanseok
Issue Date
2022
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Keywords
Keyword spotting; knowledge distillation; prototypical learning. features trained the
Citation
IEEE SIGNAL PROCESSING LETTERS, v.29, pp.2298 - 2302
Indexed
SCIE
SCOPUS
Journal Title
IEEE SIGNAL PROCESSING LETTERS
Volume
29
Start Page
2298
End Page
2302
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/147104
DOI
10.1109/LSP.2022.3219358
ISSN
1070-9908
Abstract
Keyword Spotting (KWS) is an essential component in contemporary audio-based deep learning systems and should be of minimal design when the system is working in streaming and on-device environments. We presented a robust feature extraction with a single-layer dynamic convolution model in our previous work. In this letter, we expand our earlier study into multi-layers of operation and propose a robust Knowledge Distillation (KD) learning method. Based on the distribution between class-centroids and embedding vectors, we compute three distinct distance metrics for the KD training and feature extraction processes. The results indicate that our KD method shows similar KWS performance over state-of-the-art models in terms of KWS but with low computational costs. Furthermore, our proposed method results in a more robust performance in noisy environments than conventional KD methods.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > School of Electrical Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Ko, Han seok photo

Ko, Han seok
공과대학 (전기전자공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE