Sound event detection in domestic environments with weakly labeled data and soundscape synthesis

Abstract : This paper presents Task 4 of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 challenge and provides a first analysis of the challenge results. The task is a followup to Task 4 of DCASE 2018, and involves training systems for large-scale detection of sound events using a combination of weakly labeled data, i.e. training labels without time boundaries, and strongly-labeled synthesized data. The paper introduces Domestic Environment Sound Event Detection (DESED) dataset mixing a part of last year dataset and an additional synthetic, strongly labeled, dataset provided this year that we’ll describe more in detail. We also report the performance of the submitted systems on the official evaluation (test) and development sets as well as several additional datasets. The best systems from this year outperform last year’s winning system by about 10% points in terms of F-measure.
Complete list of metadatas

Cited literature [30 references]  Display  Hide  Download

https://hal.inria.fr/hal-02160855
Contributor : Romain Serizel <>
Submitted on : Tuesday, July 16, 2019 - 11:59:04 AM
Last modification on : Wednesday, July 17, 2019 - 1:27:43 AM

File

Sound_event_detection_in_domes...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02160855, version 2

Collections

Citation

Nicolas Turpault, Romain Serizel, Ankit Parag Shah, Justin Salamon. Sound event detection in domestic environments with weakly labeled data and soundscape synthesis. 2019. ⟨hal-02160855v2⟩

Share

Metrics

Record views

125

Files downloads

378