Few-shot continual learning for audio classification

Yu Wang, Nicholas J. Bryan, Mark Cartwright, Juan Pablo Bello, Justin Salamon

Research output: Contribution to journalConference articlepeer-review

27 Scopus citations

Abstract

Supervised learning for audio classification typically imposes a fixed class vocabulary, which can be limiting for real-world applications where the target class vocabulary is not known a priori or changes dynamically. In this work, we introduce a few-shot continual learning framework for audio classification, where we can continuously expand a trained base classifier to recognize novel classes based on only few labeled data at inference time. This enables fast and interactive model updates by end-users with minimal human effort. To do so, we leverage the dynamic few-shot learning technique and adapt it to a challenging multi-label audio classification scenario. We incorporate a recent state-of-the-art audio feature extraction model as a backbone and perform a comparative analysis of our approach on two popular audio datasets (ESC-50 and AudioSet). We conduct an in-depth evaluation to illustrate the complexities of the problem and show that, while there is still room for improvement, our method outperforms three baselines on novel class detection while maintaining its performance on base classes.

Original languageEnglish (US)
Pages (from-to)321-325
Number of pages5
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2021-June
DOIs
StatePublished - 2021
Externally publishedYes
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: Jun 6 2021Jun 11 2021

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Keywords

  • Audio classification
  • Continual learning
  • Few-shot learning
  • Supervised learning

Fingerprint

Dive into the research topics of 'Few-shot continual learning for audio classification'. Together they form a unique fingerprint.

Cite this