Polyphonic training set synthesis improves self-supervised urban sound classification - Archive ouverte HAL Access content directly
Journal Articles Journal of the Acoustical Society of America Year : 2021

Polyphonic training set synthesis improves self-supervised urban sound classification

Abstract

Machine listening systems for environmental acoustic monitoring face a shortage of expert annotations to be used as training data. To circumvent this issue, the emerging paradigm of self-supervised learning proposes to pre-train audio classifiers on a task whose ground truth is trivially available. Alternatively, training set synthesis consists in annotating a small corpus of acoustic events of interest which are then automatically mixed at random to form a larger corpus of polyphonic scenes. Prior studies have considered these two paradigms in isolation, but rarely ever in conjunction. Furthermore, the impact of data curation in training set synthesis remains unclear. To fill this gap in research, this article proposes a two-stage approach. In the self-supervised stage, we formulate a pretext task (Audio2Vec skip-gram inpainting) on unlabeled spectrograms from an acoustic sensor network. Then, in the supervised stage, we formulate a downstream task of multilabel urban sound classification on synthetic scenes. We find that training set synthesis benefits more to overall performance than self-supervised learning. Interestingly, the geographical origin of the acoustic events in training set synthesis appears to have a decisive impact.
Fichier principal
Vignette du fichier
gontier2021jasa (2).pdf (1.61 Mo) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

hal-03262863 , version 1 (23-07-2021)

Identifiers

  • HAL Id : hal-03262863 , version 1

Cite

Félix Gontier, Vincent Lostanlen, Nicolas Fortin, Mathieu Lagrange, Catherine Lavandier, et al.. Polyphonic training set synthesis improves self-supervised urban sound classification. Journal of the Acoustical Society of America, 2021. ⟨hal-03262863⟩
98 View
94 Download

Share

Gmail Facebook Twitter LinkedIn More