Large-Scale Weakly Labeled Semi-Supervised Sound Event Detection in Domestic Environments

Abstract : This paper presents DCASE 2018 task 4. The task evaluates systems for the large-scale detection of sound events using weakly labeled data (without time boundaries). The target of the systems is to provide not only the event class but also the event time boundaries given that multiple events can be present in an audio recording. Another challenge of the task is to explore the possibility to exploit a large amount of unbalanced and unlabeled training data together with a small weakly labeled training set to improve system performance. The data are Youtube video excerpts from domestic context which have many applications such as ambient assisted living. The domain was chosen due to the scientific challenges (wide variety of sounds, time-localized events.. .) and potential industrial applications .
Type de document :
Pré-publication, Document de travail
Submitted to DCASE2018 Workshop. 2018
Liste complète des métadonnées
Contributeur : Romain Serizel <>
Soumis le : vendredi 27 juillet 2018 - 11:12:17
Dernière modification le : jeudi 2 août 2018 - 11:00:33


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01850270, version 1
  • ARXIV : 1807.10501



Romain Serizel, Nicolas Turpault, Hamid Eghbal-Zadeh, Ankit Parag Shah. Large-Scale Weakly Labeled Semi-Supervised Sound Event Detection in Domestic Environments. Submitted to DCASE2018 Workshop. 2018. 〈hal-01850270〉



Consultations de la notice


Téléchargements de fichiers