End-to-end Keyword Spotting using Neural Architecture Search and Quantization

David Peter, Wolfgang Roth, Franz Pernkopf

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

This paper introduces neural architecture search (NAS) for the automatic discovery of end-to-end keyword spotting (KWS) models for limited resource environments. We employ a differentiable NAS approach to optimize the structure of convolutional neural networks (CNNs) operating on raw audio waveforms. After a suitable KWS model is found with NAS, we conduct quantization of weights and activations to reduce the memory footprint. We conduct extensive experiments on the Google speech commands dataset. In particular, we compare our end-to-end models to mel-frequency cepstral coefficient (MFCC) based CNNs. For quantization, we compare fixed bit-width quantization and trained bit-width quantization. Using NAS only, we were able to obtain a highly efficient model with an accuracy of 95.55% using 75.7k parameters and 13.6M operations. Using trained bit-width quantization, the same model achieves a test accuracy of 93.76% while using on average only 2.91 bits per activation and 2.51 bits per weight
Original languageEnglish
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers
Pages3423-3427
Number of pages5
ISBN (Electronic)9781665405409
DOIs
Publication statusPublished - 2022
Event47th IEEE International Conference on Acoustics, Speech and Signal Processing: ICASSP 2022 - Virtual, Online, Singapore
Duration: 22 May 202227 May 2022

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference47th IEEE International Conference on Acoustics, Speech and Signal Processing
Abbreviated titleICASSP 2022
Country/TerritorySingapore
CityVirtual, Online
Period22/05/2227/05/22

Keywords

  • keyword spotting
  • neural architecture search
  • quantization

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fields of Expertise

  • Information, Communication & Computing
  • Intelligent Systems

    Pernkopf, F.

    1/01/02 → …

    Project: Research area

Cite this