Learning Representations for New Sound Classes With Continual Self-Supervised Learning

Zhepei Wang, Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, Paris Smaragdis

Research output: Contribution to journalArticlepeer-review


In this article, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose adopting representation learning, where an encoder is trained using unlabeled data. This learning framework enables the study and implementation of a practically relevant use case where only a small amount of the labels is available in a continual learning context. We also make the empirical observation that a similarity-based representation learning method within this framework is robust to forgetting even if no explicit mechanism against forgetting is employed. We show that this approach obtains similar performance compared to several distillation-based continual learning methods when employed on self-supervised representation learning methods.

Original languageEnglish (US)
Pages (from-to)2607-2611
Number of pages5
JournalIEEE Signal Processing Letters
StatePublished - 2022
Externally publishedYes


  • Continual learning
  • representation learning
  • self-supervised learning
  • sound classification

ASJC Scopus subject areas

  • Signal Processing
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Learning Representations for New Sound Classes With Continual Self-Supervised Learning'. Together they form a unique fingerprint.

Cite this