Sparse Binarization for Fast Keyword Spotting

Jonathan Svirsky, Uri Shaham, Ofir Lindenbaum

Research output: Contribution to journalConference articlepeer-review

Abstract

With the increasing prevalence of voice-activated devices and applications, keyword spotting (KWS) models enable users to interact with technology hands-free, enhancing convenience and accessibility in various contexts. Deploying KWS models on edge devices, such as smartphones and embedded systems, offers significant benefits for real-time applications, privacy, and bandwidth efficiency. However, these devices often possess limited computational power and memory. This necessitates optimizing neural network models for efficiency without significantly compromising their accuracy. To address these challenges, we propose a novel keyword-spotting model based on sparse input representation followed by a linear classifier. The model is four times faster than the previous state-of-the-art edge device-compatible model with better accuracy. We show that our method is also more robust in noisy environments while being fast. Our code is available at: https://github.com/jsvir/sparknet.

Original languageEnglish
Pages (from-to)3010-3014
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
DOIs
StatePublished - 2024
Event25th Interspeech Conferece 2024 - Kos Island, Greece
Duration: 1 Sep 20245 Sep 2024

Bibliographical note

Publisher Copyright:
© 2024 International Speech Communication Association. All rights reserved.

Keywords

  • keyword spotting
  • low-resource model
  • sparse learning

Fingerprint

Dive into the research topics of 'Sparse Binarization for Fast Keyword Spotting'. Together they form a unique fingerprint.

Cite this