English

Low-complexity CNNs for Acoustic Scene Classification

Audio and Speech Processing 2022-08-03 v1 Machine Learning Sound

Abstract

This technical report describes the SurreyAudioTeam22s submission for DCASE 2022 ASC Task 1, Low-Complexity Acoustic Scene Classification (ASC). The task has two rules, (a) the ASC framework should have maximum 128K parameters, and (b) there should be a maximum of 30 millions multiply-accumulate operations (MACs) per inference. In this report, we present low-complexity systems for ASC that follow the rules intended for the task.

Cite

@article{arxiv.2208.01555,
  title  = {Low-complexity CNNs for Acoustic Scene Classification},
  author = {Arshdeep Singh and James A King and Xubo Liu and Wenwu Wang and Mark D. Plumbley},
  journal= {arXiv preprint arXiv:2208.01555},
  year   = {2022}
}

Comments

Technical Report DCASE 2022 TASK 1. arXiv admin note: substantial text overlap with arXiv:2207.11529

R2 v1 2026-06-25T01:25:10.543Z