Channel Shuffle Neural Architecture Search for Key Word Spotting

Bokyeung Lee, Donghyeon Kim, Gwantae Kim, Hanseok Ko

Research output: Contribution to journalArticlepeer-review

Abstract

The evolution of Network Architecture (NA) allowed Key-Word Spotting (KWS) to exhibit high performance. Generally, NA for KWS is required to have low parameter and computation complexity maintaining high classification performance. Most of the attempts so far have been based on manual approaches, and often the architectures developed from such efforts dwell in the balance of the performance and the network complexity. Then, several KWS models based on Neural Architecture Search (NAS) technique have been proposed. However, these methods do not consider the number of parameters and FLOPs for NA in the search process and manually adjusted the complexity of NA by reducing the number of cells. It may not produce optimized NA with a balance between network complexity and performance. To develop effective network architecture for KWS, network complexity and performance must be considered. In this letter, we propose Channel Shuffle Neural Architecture Search (CSNAS) with channel weights. CSNAS selects whether each channel of the input feature is reflected in the computation or not in the search process and simultaneously controls the number of parameters, FLOPs, and performance. Experiment results show that CSNAS can generate NA that satisfies complexity and performance conditions, and NAs generated by CSNAS outperform state-of-the-art KWS methods.

Original languageEnglish
Pages (from-to)443-447
Number of pages5
JournalIEEE Signal Processing Letters
Volume30
DOIs
Publication statusPublished - 2023

Bibliographical note

Funding Information:
This work was supported by the National Research Foundation of Korea funded by the KoreaGovernment underGrantNRF-2023R1A2C2005916.

Publisher Copyright:
© 1994-2012 IEEE.

Keywords

  • Keyword spotting
  • neural architecture search

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Channel Shuffle Neural Architecture Search for Key Word Spotting'. Together they form a unique fingerprint.

Cite this